From 00857218d228506d5bc3c9b849a74625d9d553ca Mon Sep 17 00:00:00 2001 From: manumachu Date: Mon, 29 May 2017 10:14:18 +0100 Subject: [PATCH] IEEE MOP TC: Adding results for dgemm DVFS... --- tests/dgemmenergies2GHz.h | 800 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- tests/dgemmenergies2GHzSD.h | 416 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ tests/dgemmetimes2GHz.h | 800 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- tests/dgemmresultsdvfs/dgemmse1.txt | 122 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ tests/dgemmresultsdvfs/dgemmse_2.00GHz.txt | 3600 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ tests/dgemmresultsdvfs/dgemmse_nxn_2.00GHz.txt | 3601 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ tests/dgemmresultsdvfs3/dgemmse.txt | 96 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 7 files changed, 8635 insertions(+), 800 deletions(-) create mode 100644 tests/dgemmenergies2GHzSD.h create mode 100644 tests/dgemmresultsdvfs/dgemmse1.txt create mode 100644 tests/dgemmresultsdvfs/dgemmse_2.00GHz.txt create mode 100644 tests/dgemmresultsdvfs/dgemmse_nxn_2.00GHz.txt create mode 100644 tests/dgemmresultsdvfs3/dgemmse.txt diff --git a/tests/dgemmenergies2GHz.h b/tests/dgemmenergies2GHz.h index b402289..56a9172 100644 --- a/tests/dgemmenergies2GHz.h +++ b/tests/dgemmenergies2GHz.h @@ -7,406 +7,406 @@ /*--------------------------------------------------------*/ double energies[] = { -316.500000, -221.466667, -221.266667, -261.866667, -257.183333, -220.100000, -253.500000, -219.366667, -255.383333, -260.383333, -254.933333, -327.950000, -447.766667, -562.416667, -555.666667, -667.816667, -448.400000, -448.016667, -561.983333, -559.466667, -448.650000, -449.716667, -448.533333, -449.366667, -668.233333, -630.616667, -928.650000, -996.583333, -892.433333, -1004.750000, -1116.383333, -895.266667, -891.583333, -1005.333333, -893.083333, -1004.150000, -892.133333, -892.216667, -896.766667, -1388.750000, -1333.366667, -1329.116667, -1438.033333, -1325.533333, -1321.550000, -1541.066667, -1324.050000, -1436.800000, -1549.216667, -1328.883333, -1323.283333, -1326.833333, -1436.816667, -1555.483333, -1779.866667, -1887.700000, -1882.850000, -1876.783333, -1872.816667, -1759.966667, -1756.683333, -1765.483333, -1758.433333, -1871.416667, -1860.233333, -1866.516667, -2385.366667, -2366.166667, -2237.366667, -2349.900000, -2371.500000, -2228.033333, -2210.433333, -2303.883333, -2202.450000, -2185.016667, -2180.850000, -2297.066667, -2473.733333, -2767.416667, -2763.183333, -2754.383333, -2807.150000, -2712.650000, -2799.066667, -2806.166667, -2683.816667, -2760.033333, -2672.833333, -3552.783333, -3079.433333, -2895.300000, -3404.300000, -3306.450000, -3429.816667, -3337.366667, -3229.300000, -3457.483333, -3195.883333, -3164.100000, -3332.466667, -3270.866667, -3480.033333, -3224.866667, -3954.433333, -3826.300000, -3902.200000, -3915.133333, -3774.500000, -3847.366667, -3835.083333, -3719.383333, -3748.900000, -3673.233333, -3689.150000, -3645.350000, -4479.783333, -4480.416667, -4361.350000, -4331.516667, -4409.350000, -4289.266667, -4377.500000, -4480.216667, -4234.666667, -4233.566667, -4246.433333, -4197.500000, -4550.133333, -4953.966667, -4937.983333, -4887.850000, -5003.983333, -4835.650000, -4954.766667, -4945.733333, -4776.916667, -4917.783333, -4838.883333, -4851.866667, -5479.216667, -5570.850000, -5513.966667, -5491.066667, -5531.333333, -5494.900000, -5350.450000, -5504.400000, -5409.250000, -5345.833333, -5852.833333, -6066.800000, -5639.616667, -6014.200000, -5968.716667, -6052.866667, -6039.033333, -6064.666667, -6123.433333, -5867.366667, -5984.733333, -5836.583333, -5845.733333, -6573.800000, -6572.366667, -6656.850000, -6528.183333, -6705.533333, -6551.516667, -6564.350000, -6516.150000, -6454.733333, -6396.733333, -6433.883333, -7140.500000, -7157.933333, -7115.750000, -7097.333333, -7155.016667, -7199.283333, -7023.816667, -7033.566667, -7019.533333, -6994.183333, -7158.733333, -7638.933333, -7684.900000, -7702.933333, -7802.766667, -7825.150000, -7589.950000, -7576.016667, -7777.683333, -7558.116667, -7658.550000, -8317.566667, -8304.783333, -8320.283333, -8189.466667, -8236.800000, -8191.733333, -8161.350000, -8179.116667, -8142.683333, -8181.183333, -8115.833333, -8690.466667, -8793.466667, -8949.500000, -8807.850000, -8773.483333, -8864.366667, -8695.050000, -8732.000000, -8727.566667, -8705.583333, -8655.600000, -8836.700000, -9393.033333, -9387.666667, -9351.816667, -9334.216667, -9407.333333, -9328.400000, -9239.966667, -9439.516667, -9322.183333, -9214.300000, -9949.816667, -9953.183333, -9955.583333, -9890.416667, -9922.066667, -9857.483333, -9849.650000, -10158.266667, -9772.216667, -9786.233333, -9786.933333, -10539.933333, -10470.900000, -10486.166667, -10448.233333, -10491.416667, -10552.950000, -10473.983333, -10368.400000, -10435.900000, -10342.950000, -10431.466667, -11166.316667, -11083.816667, -11024.766667, -11065.116667, -11054.466667, -11915.683333, -11201.600000, -10974.866667, -11014.616667, -11079.783333, -10904.783333, -11814.983333, -11651.683333, -11716.300000, -11735.816667, -11558.716667, -11711.216667, -11496.150000, -11641.233333, -12170.900000, -12253.750000, -13326.533333, -12288.783333, -12354.116667, -12297.550000, -12181.250000, -12155.183333, -12160.583333, -12104.150000, -12084.216667, -13091.716667, -12801.066667, -13049.966667, -12881.033333, -12869.616667, -13002.450000, -12769.100000, -12736.450000, -13479.783333, -12767.300000, -12658.283333, -13096.200000, -13475.950000, -13393.650000, -13495.883333, -13325.383333, -13382.983333, -13425.500000, -13392.600000, -13276.016667, -13352.316667, -14000.900000, -14128.833333, -13962.400000, -14051.600000, -14021.083333, -14015.316667, -13863.083333, -14096.766667, -13970.816667, -13835.783333, -14290.850000, -14543.200000, -14525.966667, -14502.783333, -14519.183333, -14582.283333, -14440.583333, -14423.633333, -14602.083333, -15032.816667, -15126.116667, -15158.933333, -15060.950000, -15146.566667, -15238.583333, -15076.300000, -16417.216667, -15120.766667, -15175.750000, -15252.833333, -15621.966667, -16000.433333, -15713.300000, -15817.550000, -15723.750000, -15691.183333, -15713.783333, -15628.183333, -15659.450000, -16581.716667, -16361.116667, -16423.400000, -16245.250000, -16262.300000, -16294.883333, -16352.083333, -16266.466667, -16731.716667, -17094.116667, -18092.716667, -16946.250000, -16881.983333, -16952.566667, -16885.283333, -17221.466667, -16814.500000, -17197.850000, -16738.633333, -17159.683333, -17398.166667, -17551.350000, -17482.783333, -17432.850000, -17466.750000, -17703.866667, -17588.233333, -17457.166667, -17411.633333, -17685.266667, -18167.183333, -18169.350000, -18073.850000, -18117.450000, -18036.366667, -18292.233333, -17975.250000, -18291.466667, -18115.066667, -18030.966667, -18676.216667, -18598.566667, -18728.216667, -18740.800000, -18756.300000, -18933.383333, -18954.133333, -18638.166667, -19415.300000, -19370.983333, -19259.883333, -19419.050000, -19230.750000, -19323.750000, -19284.116667, -19367.950000, -19152.850000, -19284.100000, -19759.533333, -20796.166667 +21558.966667, +19019.683333, +17049.516667, +17546.100000, +17714.166667, +17436.866667, +17478.266667, +18020.666667, +18078.516667, +18877.316667, +18128.083333, +17437.783333, +18159.550000, +18209.550000, +19020.516667, +18918.933333, +18771.616667, +18843.600000, +18917.900000, +19736.100000, +19329.916667, +20130.633333, +19866.666667, +18813.016667, +19423.583333, +19425.933333, +20197.583333, +20631.450000, +20128.516667, +20320.233333, +20744.483333, +21161.583333, +21349.833333, +21469.600000, +20910.933333, +20064.650000, +20128.883333, +20871.083333, +20705.116667, +21498.583333, +21469.700000, +20956.833333, +21447.000000, +21679.600000, +21957.700000, +22237.016667, +22142.550000, +21463.600000, +21363.200000, +22171.266667, +22204.216667, +22715.283333, +22756.183333, +22449.633333, +22721.066667, +23325.600000, +23324.466667, +24203.950000, +23419.200000, +22911.483333, +23378.433333, +23365.666667, +23874.166667, +24296.366667, +24042.583333, +24045.100000, +24080.583333, +24961.400000, +24661.916667, +25433.516667, +24915.650000, +23181.683333, +24238.316667, +24199.650000, +24543.716667, +24756.366667, +24709.166667, +24821.266667, +25073.816667, +25426.383333, +25682.583333, +26057.133333, +26199.650000, +24529.500000, +25461.950000, +29026.733333, +25858.116667, +26261.283333, +26650.083333, +25888.500000, +26625.350000, +26625.166667, +27233.850000, +27272.200000, +27267.433333, +26607.250000, +26689.466667, +27317.683333, +27553.616667, +28279.583333, +27859.583333, +27338.616667, +28043.533333, +28270.750000, +28431.783333, +28673.016667, +28722.750000, +27277.950000, +28114.916667, +27829.683333, +28365.316667, +28559.783333, +28485.166667, +28510.233333, +28538.283333, +29078.983333, +29215.966667, +29961.216667, +29520.283333, +28558.750000, +29283.533333, +29338.033333, +29717.733333, +30126.733333, +29860.983333, +29790.466667, +29777.400000, +30388.900000, +30723.966667, +31107.750000, +31196.516667, +30335.250000, +30532.216667, +30815.716667, +31110.600000, +31273.700000, +31537.100000, +31096.966667, +31986.616667, +32183.416667, +32654.400000, +32583.216667, +31969.350000, +31286.600000, +31305.283333, +32118.516667, +32121.916667, +32619.900000, +32614.800000, +31610.683333, +32371.583333, +32484.566667, +33004.916667, +33594.083333, +32993.316667, +32457.033333, +32524.050000, +33009.100000, +32904.750000, +33672.516667, +33759.633333, +33925.516667, +33831.200000, +34433.900000, +34420.500000, +35426.516667, +34227.516667, +33881.950000, +34543.566667, +34383.766667, +35285.616667, +35127.800000, +35602.600000, +35291.916667, +34976.233333, +35648.533333, +35861.383333, +36413.400000, +35863.833333, +34421.383333, +35253.150000, +35347.900000, +35805.566667, +35663.566667, +36169.533333, +36119.700000, +36415.333333, +37064.866667, +37136.950000, +37170.850000, +36947.983333, +36472.166667, +37015.633333, +37500.033333, +37050.016667, +37694.683333, +37694.116667, +37013.783333, +37627.883333, +37831.583333, +38856.133333, +38273.400000, +38454.350000, +37659.100000, +37932.066667, +38198.866667, +38241.083333, +39233.116667, +39107.000000, +38560.200000, +38812.916667, +39764.716667, +39419.316667, +40165.750000, +39632.316667, +38547.400000, +39193.650000, +39210.750000, +39862.966667, +40224.883333, +39580.900000, +39791.100000, +39818.816667, +40181.316667, +40061.050000, +41219.466667, +40972.450000, +39698.500000, +40303.316667, +40918.633333, +41046.416667, +41032.816667, +41361.333333, +40825.466667, +41496.433333, +41548.583333, +42222.666667, +42383.633333, +42543.383333, +41369.200000, +41583.516667, +42219.033333, +42022.366667, +42783.850000, +42722.033333, +42139.566667, +43103.150000, +42752.800000, +43399.150000, +43606.233333, +43418.450000, +42073.316667, +42143.100000, +42811.816667, +42663.833333, +43410.150000, +43369.916667, +43382.483333, +43598.450000, +44180.366667, +44623.850000, +44870.483333, +44090.150000, +43653.633333, +44284.516667, +44156.516667, +44756.816667, +48663.716667, +44678.000000, +44691.416667, +44933.583333, +46037.850000, +45655.316667, +46037.766667, +45718.433333, +44805.433333, +45215.150000, +45440.066667, +46027.566667, +45957.433333, +46145.216667, +46282.450000, +46569.016667, +46699.983333, +46707.166667, +47368.600000, +47007.333333, +45860.550000, +46225.016667, +46939.266667, +46591.383333, +47585.600000, +47341.983333, +46555.366667, +47593.016667, +47341.583333, +47976.433333, +48075.416667, +48246.766667, +47231.316667, +47535.133333, +48141.250000, +47770.866667, +48601.800000, +48598.000000, +48223.383333, +48979.566667, +49188.450000, +49101.450000, +50101.850000, +49178.450000, +48651.783333, +49272.966667, +49452.583333, +49345.983333, +49889.383333, +50102.316667, +49966.383333, +49842.316667, +50542.233333, +50445.516667, +50996.416667, +50504.733333, +49170.783333, +50025.500000, +50203.416667, +50508.033333, +50766.400000, +50484.416667, +50389.316667, +50890.200000, +51183.150000, +51571.416667, +51920.533333, +51964.000000, +50912.333333, +51300.083333, +51960.800000, +51692.933333, +52537.616667, +52545.900000, +52063.000000, +52616.383333, +52516.533333, +53047.883333, +53076.816667, +53326.766667, +52517.550000, +52637.300000, +54350.716667, +53055.483333, +54116.916667, +58248.166667, +53090.466667, +53862.350000, +54427.883333, +54380.150000, +54965.883333, +54445.133333, +53213.800000, +53891.533333, +53853.250000, +54537.666667, +58996.983333, +54981.550000, +54716.533333, +54492.850000, +55222.950000, +54993.350000, +55815.766667, +55402.366667, +54660.383333, +55464.783333, +55397.866667, +55842.483333, +56144.866667, +55787.383333, +55822.500000, +56120.433333, +56544.233333, +56571.316667, +57216.883333, +57364.333333, +55931.750000, +56566.050000, +56739.750000, +57160.666667, +57562.650000, +57894.200000, +57593.600000, +57853.450000, +57784.900000, +58588.233333, +58734.483333, +58730.833333, +57038.316667, +57130.016667, +57989.216667, +57682.100000, +58708.683333 }; /*--------------------------------------------------------*/ diff --git a/tests/dgemmenergies2GHzSD.h b/tests/dgemmenergies2GHzSD.h new file mode 100644 index 0000000..176a5c7 --- /dev/null +++ b/tests/dgemmenergies2GHzSD.h @@ -0,0 +1,416 @@ + +/*--------------------------------------------------------*/ + +#ifndef _DGEMM_ENERGIESSD_HH +#define _DGEMM_ENERGIESSD_HH + +/*--------------------------------------------------------*/ + +double energiesSD[] = { +4815.37, +396.865, +167.146, +33.4636, +270.116, +43.1725, +26.3023, +102.218, +27.7018, +69.2467, +41.6195, +50.1218, +23.3733, +62.4731, +366.627, +276.523, +15.4507, +167.597, +278.091, +528.287, +26.8827, +5.19719, +132.878, +269.385, +46.5231, +56.5396, +259.487, +244.773, +50.1437, +109.271, +137.202, +204.674, +487.362, +12.7318, +115.168, +331.112, +37.4593, +195.072, +220.194, +163.119, +13.3848, +114.365, +37.2811, +484.411, +65.7872, +240.6, +140.241, +195.86, +42.6655, +111.515, +414.464, +20.4108, +50.2284, +179.931, +13.7372, +325.265, +21.9423, +269.283, +20.1042, +245.146, +34.9852, +33.3085, +241.823, +265.442, +41.9575, +94.881, +160.776, +386.768, +166.294, +100.811, +213.755, +28.6195, +516.758, +267.717, +55.1818, +263.014, +231.295, +253.42, +276.519, +292.2, +391.403, +260.329, +208.684, +29.3757, +280.853, +5849.31, +58.528, +399.27, +79.5708, +117.179, +73.5245, +41.457, +39.0679, +25.1921, +61.4684, +130.355, +43.845, +27.4573, +621.831, +282.178, +112.768, +251.494, +245.656, +524.476, +27.8243, +247.487, +454.931, +328.992, +483.224, +172.122, +314.605, +289.528, +141.77, +89.4586, +148.599, +37.2705, +230.592, +299.855, +575.461, +182.225, +180.519, +450.852, +35.9085, +756.46, +320.888, +25.7609, +138.837, +93.2, +292.649, +77.5193, +133.189, +83.4671, +143.126, +379.162, +108.731, +179.029, +239.823, +26.9052, +106.397, +242.17, +85.9505, +320.646, +246.755, +363.219, +146.029, +308.331, +68.3222, +499.999, +216.503, +40.7166, +105.541, +314.256, +28.6112, +814.583, +40.1226, +100.865, +190.521, +33.9423, +5.74195, +31.0726, +134.104, +352.975, +170.373, +72.5588, +230.818, +467.391, +22.5789, +214.372, +299.281, +52.1935, +307.584, +250.863, +1038.48, +503.248, +72.8935, +69.6711, +350.794, +145.265, +37.8862, +315.38, +223.658, +314.736, +302.268, +113.808, +174.617, +706.292, +36.946, +990.265, +290.653, +252.348, +11.3018, +91.7731, +301.863, +687.578, +195.433, +72.401, +24.7561, +59.9956, +51.029, +248.233, +1079.04, +61.143, +286.92, +33.8687, +580.309, +39.4319, +148.371, +197.199, +60.7363, +144.409, +76.5329, +267.885, +41.5217, +77.6736, +280.104, +575.208, +484.388, +71.6409, +665.832, +314.709, +234.85, +268.324, +460.613, +2.77053, +33.0603, +447.755, +286.55, +297.321, +189.756, +1463.54, +86.8707, +283.133, +682.844, +86.0461, +39.4495, +244.111, +181.908, +369.242, +243.702, +212.352, +85.541, +73.5188, +57.4154, +71.3876, +29.4531, +244.601, +440.202, +46.7357, +112.173, +116.415, +58.9169, +48.8014, +181.667, +0.94384, +104.791, +77.2384, +22.8683, +413.208, +273.248, +71.9933, +659.412, +91.9873, +2.66646, +263.14, +206.633, +191.6, +68.7517, +6953.69, +33.2568, +31.6093, +211.033, +615.009, +731.605, +169.534, +190.077, +184.873, +138.342, +171.572, +177.745, +65.8034, +347.796, +101.029, +143.99, +17.3757, +154.438, +41.9504, +418.439, +273.389, +97.5046, +145.536, +93.8424, +370.738, +17.1205, +41.7069, +345.113, +47.925, +167.111, +153.974, +707.554, +146.595, +50.8962, +45.0842, +180.844, +182.465, +188.002, +696.437, +877.767, +278.329, +104.549, +154.712, +68.4824, +155.247, +500.822, +346.788, +214.845, +61.1552, +420.513, +36.6113, +34.8717, +121.666, +32.6719, +196.097, +147.877, +102.443, +94.7955, +881.186, +195.906, +565.883, +161.157, +90.9427, +135.538, +166.929, +179.89, +459.468, +170.62, +126.241, +173.619, +98.7304, +116.773, +95.3451, +58.4308, +32.1505, +122.317, +207.487, +14.4659, +89.7311, +139.545, +30.4104, +284.258, +2056.32, +50.3243, +462.346, +3935.56, +53.474, +9.888, +285.168, +41.7981, +425.437, +100.151, +149.212, +421.321, +157.979, +563.549, +6938.26, +779.194, +465.879, +38.1674, +78.7838, +100.672, +119.056, +136.197, +135.323, +666.022, +620.572, +126.282, +749.63, +109.303, +44.167, +243.61, +34.2993, +129.399, +64.6816, +112.608, +72.6001, +70.2987, +133.448, +163.787, +304.382, +393.215, +454.622, +12.1344, +149.594, +136.596, +601.956, +13.1215, +75.9796, +198.263, +182.118, +105.582, +238.896 +}; + +/*--------------------------------------------------------*/ + +#endif + +/*--------------------------------------------------------*/ diff --git a/tests/dgemmetimes2GHz.h b/tests/dgemmetimes2GHz.h index ca412bc..ac82e47 100644 --- a/tests/dgemmetimes2GHz.h +++ b/tests/dgemmetimes2GHz.h @@ -7,406 +7,406 @@ /*--------------------------------------------------------*/ double etimes[] = { -0.006497, -0.015869, -0.026399, -0.040679, -0.048223, -0.060820, -0.072858, -0.094013, -0.104408, -0.134624, -0.166423, -0.161211, -0.186886, -0.198145, -0.235753, -0.273816, -0.258227, -0.304743, -0.326146, -0.348895, -0.358891, -0.375451, -0.430730, -0.425523, -0.492021, -0.500323, -0.559310, -0.549159, -0.654000, -0.623540, -0.686409, -0.637035, -0.703071, -0.710754, -0.777316, -0.759839, -0.908370, -0.875669, -0.956150, -1.003371, -0.956753, -1.032921, -1.049587, -1.110785, -1.170100, -1.105062, -1.170795, -1.202734, -1.301371, -1.359755, -1.277897, -1.368454, -1.417805, -1.452979, -1.530069, -1.526453, -1.556327, -1.634158, -1.648642, -1.727064, -1.835505, -1.682176, -1.791684, -2.061604, -1.833650, -1.931073, -2.041967, -1.957965, -2.033428, -2.108474, -2.140971, -2.206699, -2.285651, -2.302193, -2.313490, -2.376334, -2.473350, -2.481290, -2.579901, -2.666228, -2.539492, -2.564959, -2.657267, -2.718299, -2.748123, -2.863964, -2.968750, -2.827863, -2.925664, -3.035859, -3.066944, -3.098751, -3.210570, -3.339417, -3.168416, -3.280255, -3.378969, -3.479261, -3.453296, -3.687520, -3.671279, -3.603179, -3.532479, -3.660560, -3.761187, -3.781027, -3.850730, -3.964171, -4.053678, -3.988726, -3.997109, -4.099612, -4.217077, -4.216095, -4.287290, -4.407580, -4.551149, -4.414795, -4.459568, -4.573008, -4.842146, -4.747198, -4.778966, -4.892112, -5.006820, -4.864211, -4.813306, -4.915626, -4.998638, -5.111251, -5.111993, -5.249160, -5.349379, -5.448308, -5.247152, -5.441367, -5.514891, -5.639534, -5.660850, -5.728272, -5.819644, -5.935860, -6.015431, -6.391942, -6.000140, -6.151879, -6.290125, -6.324563, -6.352945, -6.472370, -6.584477, -6.751596, -6.343831, -6.503450, -6.605598, -6.707206, -6.794113, -6.771522, -6.922151, -7.031104, -7.194714, -7.099200, -6.997282, -7.209231, -7.333220, -7.456177, -7.444670, -7.503690, -7.891013, -7.752615, -7.881287, -7.680944, -7.768817, -7.864095, -8.043861, -8.164941, -8.114081, -8.255041, -8.384512, -8.508655, -8.635517, -8.325023, -8.356956, -8.398075, -8.598758, -8.695296, -8.730080, -8.761934, -8.945295, -9.046183, -9.227441, -9.070918, -9.017620, -9.161797, -9.273007, -9.785883, -9.478031, -9.514213, -9.617779, -9.831074, -9.865013, -10.012994, -9.706567, -9.904198, -9.993945, -10.151140, -10.290924, -10.338390, -10.346966, -10.522859, -10.629702, -10.883638, -10.704763, -10.470763, -10.597773, -10.747610, -10.870508, -10.998648, -11.024085, -11.085978, -11.185421, -11.354306, -11.526987, -11.518296, -11.612085, -11.496881, -11.570084, -11.739868, -11.942307, -11.892463, -11.896475, -12.009946, -12.256394, -12.415826, -12.486032, -12.267470, -12.291974, -12.430376, -12.590611, -12.784259, -12.873522, -12.758163, -12.942030, -13.088775, -13.237752, -13.450923, -13.368739, -12.894198, -13.148035, -13.233019, -13.412063, -13.615732, -13.665911, -13.548257, -13.782443, -15.433223, -14.088431, -14.284904, -14.216808, -13.920205, -14.100699, -14.268185, -14.338684, -14.677607, -14.689870, -14.577444, -14.889893, -14.961315, -15.085043, -15.337162, -15.334976, -15.146310, -15.140921, -15.303497, -15.495436, -15.630294, -15.792332, -15.846183, -15.790865, -15.938218, -16.205093, -16.360001, -16.398936, -16.175472, -15.848042, -16.040841, -16.215647, -16.369305, -17.155028, -16.583437, -16.569017, -16.766873, -16.947101, -17.027738, -17.283122, -17.306559, -17.154199, -17.072606, -17.199706, -17.409734, -17.482526, -17.833890, -17.800742, -17.667505, -17.958220, -18.160980, -18.394130, -18.496633, -18.722537, -18.415447, -18.259471, -18.545704, -18.637488, -18.786021, -19.006626, -19.977273, -19.107053, -19.205344, -19.347228, -19.585382, -19.532664, -19.894865, -19.692537, -19.801112, -19.663543, -19.703311, -19.868150, -20.097988, -20.111255, -20.340411, -20.176367, -20.458880, -20.586697, -20.650110, -20.910639, -21.354086, -20.907070, -20.679373, -20.832022, -20.991492, -21.232986, -21.568385, -21.672171, -21.655791, -21.678483, -21.808433, -22.004375, -21.999447, -22.333414, -22.458170, -22.142922, -22.222390, -22.276219, -22.319216, -22.511834, -22.933340, -23.133755, -22.991445, -22.859562, -23.156325, -24.175032, -23.505939, -23.608739, -23.948564, -23.480802, -23.194106, -23.367484, -23.614934, -23.571472, -23.931133, -24.264772, -23.986793, -24.071555, -24.320530, -24.278166, -24.735298, -24.691260, -25.072340, -24.929435, -24.575958, -24.853121, -25.046083, -25.179036, -25.449494, -25.708880, -25.613654, -25.774796, -25.533747, -25.993835, -25.961162, -26.245572, -26.290138, -26.721330, -26.225966, -26.057865, -26.463745, -26.504866, -26.764358, -26.742425, -30.024564 +9.584576, +11.770225, +3.628126, +4.479741, +4.457185, +3.556223, +4.514076, +5.421872, +6.353368, +7.276733, +6.509677, +3.856453, +4.859662, +5.805028, +6.688800, +7.690893, +7.668245, +6.686347, +7.642862, +8.584815, +9.531481, +10.435310, +9.603162, +7.010850, +8.032390, +8.913355, +9.827283, +10.827553, +10.828904, +9.814950, +10.772770, +11.699030, +12.600158, +13.592625, +12.159117, +8.360430, +9.328835, +10.264528, +11.220008, +12.205259, +12.127943, +11.159820, +11.989700, +12.907539, +13.970733, +14.864205, +14.099549, +11.494560, +12.451369, +13.402243, +15.266000, +15.069142, +15.186072, +14.297925, +15.144913, +16.041943, +17.087856, +17.837180, +17.083043, +14.631282, +15.620990, +16.496677, +17.477516, +18.343351, +18.330406, +17.400149, +18.369852, +19.190959, +20.200731, +21.189167, +19.761351, +15.872128, +16.898839, +17.888112, +19.352347, +19.750446, +19.654773, +18.703130, +19.665321, +20.680094, +21.528277, +22.370090, +21.574791, +19.062781, +20.034767, +20.915157, +21.812682, +22.894212, +22.883357, +21.798485, +22.811895, +23.683106, +24.579252, +25.657216, +24.730133, +22.175628, +23.180182, +24.065347, +24.957856, +26.021850, +25.913506, +24.975488, +25.949832, +26.839747, +27.641886, +28.664494, +27.285110, +23.466542, +24.534339, +25.439340, +26.260201, +27.235411, +27.618108, +26.291122, +27.313763, +28.236557, +29.066060, +30.053329, +29.229891, +26.648109, +27.672768, +28.598625, +29.464214, +30.391727, +30.421011, +29.443750, +30.466051, +31.344382, +32.187953, +33.188330, +32.573951, +29.798856, +30.837476, +31.741217, +32.584811, +33.547925, +33.572300, +32.594442, +33.883116, +34.517340, +35.334435, +36.394565, +34.948800, +31.136386, +32.186494, +33.080425, +33.902483, +34.899315, +34.909075, +33.927628, +35.168923, +35.906958, +36.667195, +37.655128, +36.908955, +34.273707, +35.306874, +36.222956, +37.026194, +38.084535, +38.041672, +39.096892, +38.095195, +39.020342, +39.813169, +40.803945, +40.033335, +37.418683, +38.524358, +39.401020, +40.179778, +41.165624, +41.196317, +40.201696, +41.257345, +42.123051, +42.959878, +43.968238, +42.567992, +38.733371, +39.787280, +40.723820, +41.565945, +42.508938, +42.562932, +41.564811, +42.586713, +43.545165, +44.363546, +45.290409, +44.645600, +41.920655, +44.485839, +43.844192, +44.693659, +45.649598, +45.704305, +44.722131, +45.724138, +46.680633, +47.459462, +48.458863, +47.687135, +45.058454, +46.051130, +47.038221, +47.832105, +48.863454, +48.887766, +47.878390, +48.944473, +49.839009, +50.590208, +51.670996, +50.396248, +46.498798, +47.401353, +48.521513, +49.270267, +50.200275, +50.306461, +49.201627, +50.274627, +51.197745, +52.016552, +53.012283, +52.208982, +49.548943, +50.600588, +51.559992, +52.483388, +53.314984, +53.483133, +52.747688, +53.453206, +54.306242, +55.143973, +56.164111, +55.395308, +52.728408, +53.781881, +55.232710, +55.938891, +56.522564, +56.507040, +55.666585, +56.642118, +57.433505, +58.286326, +59.335448, +57.956221, +54.139685, +55.116499, +56.004427, +56.886831, +57.877360, +57.890379, +56.902087, +57.985879, +58.833381, +59.669884, +60.709786, +59.911308, +57.194994, +58.270022, +59.083583, +60.166437, +61.005928, +61.115877, +60.028952, +61.123247, +62.075665, +62.799498, +63.825147, +63.022476, +60.407090, +61.455535, +62.352757, +63.188691, +64.117749, +64.209624, +63.214588, +64.213260, +65.134576, +65.965846, +66.964744, +65.615180, +61.763890, +62.701460, +63.658860, +64.579023, +65.510768, +65.594117, +64.522563, +65.549210, +66.484702, +67.368154, +68.339482, +67.455093, +65.040256, +65.913484, +66.919791, +67.710260, +68.710419, +68.749794, +70.686021, +71.832392, +69.676628, +70.493490, +71.512708, +70.677556, +67.977591, +69.064741, +69.976405, +70.844261, +71.919348, +73.540041, +70.842057, +71.937194, +72.818311, +73.670614, +74.597264, +73.325229, +69.419083, +70.453585, +71.297958, +72.268627, +73.129687, +73.260988, +72.351749, +73.284642, +74.184804, +75.106675, +76.065288, +75.224260, +72.665496, +73.640734, +74.543467, +75.353180, +76.352263, +76.383556, +75.421937, +76.457340, +77.378150, +78.192265, +79.463796, +78.490603, +75.728274, +76.722274, +88.163690, +78.536875, +79.553595, +79.488791, +78.547197, +79.556574, +80.566460, +81.385330, +82.356598, +80.903676, +77.157580, +78.048964, +78.939452, +79.938873, +80.903389, +80.916494, +80.276300, +80.919062, +81.812804, +82.765016, +83.870061, +82.959415, +80.250415, +81.384490, +82.179447, +83.020358, +84.000071, +84.041777, +83.280739, +84.081159, +84.999628, +85.891305, +86.883819, +86.062260, +83.441499, +84.954720, +85.409447, +86.150589, +87.226159, +87.247158, +86.200007, +87.301642, +88.287577, +89.233142, +90.109109, +88.632719, +84.836324, +85.772384, +86.727764, +87.507837, +88.575462 }; /*--------------------------------------------------------*/ diff --git a/tests/dgemmresultsdvfs/dgemmse1.txt b/tests/dgemmresultsdvfs/dgemmse1.txt new file mode 100644 index 0000000..3df6881 --- /dev/null +++ b/tests/dgemmresultsdvfs/dgemmse1.txt @@ -0,0 +1,122 @@ +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=47.304372, speed(mflops)=709330.459958 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=47.240372, speed(mflops)=710291.443954 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=47.270657, speed(mflops)=709836.378107 +Max repetitions 3, Elasped time 348.838, Relative error 0.00940976, Mean 33775.6, Standard Deviation 188.522 +Total Energy 33775.566667 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=49.421568, speed(mflops)=678943.089310 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=49.450020, speed(mflops)=678552.444452 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=49.365251, speed(mflops)=679717.640984 +Max repetitions 3, Elasped time 365.454, Relative error 0.0150787, Mean 34034.9, Standard Deviation 304.416 +Total Energy 34034.850000 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=51.757411, speed(mflops)=648301.979363 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=51.697827, speed(mflops)=649049.174438 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=51.773770, speed(mflops)=648097.136709 +Max repetitions 3, Elasped time 379.546, Relative error 0.00409076, Mean 34678.2, Standard Deviation 84.1473 +Total Energy 34678.183333 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=54.246166, speed(mflops)=618558.590955 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=54.179177, speed(mflops)=619323.397467 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=54.298910, speed(mflops)=617957.743772 +Max repetitions 3, Elasped time 396.996, Relative error 0.00696614, Mean 35658.8, Standard Deviation 147.346 +Total Energy 35658.800000 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=57.940127, speed(mflops)=579122.514873 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=57.137714, speed(mflops)=587255.416857 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=57.067799, speed(mflops)=587974.876804 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=57.106478, speed(mflops)=587576.629644 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=57.022444, speed(mflops)=588442.543681 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=57.232492, speed(mflops)=586282.911070 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=57.116888, speed(mflops)=587469.540932 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=57.126456, speed(mflops)=587371.147038 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=56.997696, speed(mflops)=588698.039743 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=57.068792, speed(mflops)=587964.645872 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=57.068838, speed(mflops)=587964.171794 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=57.047264, speed(mflops)=588186.524453 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=58.601939, speed(mflops)=572582.283006 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=57.057002, speed(mflops)=588086.138144 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=57.146482, speed(mflops)=587165.313263 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=57.135554, speed(mflops)=587277.616242 +Max repetitions 16, Elasped time 2268.29, Relative error 0.0249856, Mean 36955.3, Standard Deviation 2106.84 +Total Energy 36955.271875 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=60.312353, speed(mflops)=556344.268733 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=60.296503, speed(mflops)=556490.516463 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=60.825225, speed(mflops)=551653.233805 +Max repetitions 3, Elasped time 438.976, Relative error 0.00244235, Mean 37450.1, Standard Deviation 54.2551 +Total Energy 37450.116667 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=63.819154, speed(mflops)=525773.688371 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=63.979086, speed(mflops)=524459.384130 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=63.862074, speed(mflops)=525420.330906 +Max repetitions 3, Elasped time 464.814, Relative error 0.0106562, Mean 38679.2, Standard Deviation 244.489 +Total Energy 38679.150000 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=67.679364, speed(mflops)=495785.273881 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=67.740378, speed(mflops)=495338.717035 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=67.727658, speed(mflops)=495431.747890 +Max repetitions 3, Elasped time 489.956, Relative error 0.00305235, Mean 39673.8, Standard Deviation 71.8321 +Total Energy 39673.833333 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=72.193508, speed(mflops)=464784.618056 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=72.199834, speed(mflops)=464743.893312 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=72.240426, speed(mflops)=464482.754867 +Max repetitions 3, Elasped time 523.073, Relative error 0.0025602, Mean 42043.9, Standard Deviation 63.8494 +Total Energy 42043.883333 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=77.334066, speed(mflops)=433889.406995 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=77.357690, speed(mflops)=433756.901976 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=77.281578, speed(mflops)=434184.094588 +Max repetitions 3, Elasped time 558.296, Relative error 0.00826106, Mean 43713, Standard Deviation 214.204 +Total Energy 43713.033333 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=83.142341, speed(mflops)=403578.148479 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=83.115701, speed(mflops)=403707.501860 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=83.186064, speed(mflops)=403366.025324 +Max repetitions 3, Elasped time 598.64, Relative error 0.00516742, Mean 46450.1, Standard Deviation 142.377 +Total Energy 46450.066667 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=89.984911, speed(mflops)=372889.539370 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=89.953345, speed(mflops)=373020.391598 +Executable: ./dgemmoptimized 25600 25600 25600 1 0 +m=25600, n=25600, k=25600, time(sec)=89.920064, speed(mflops)=373158.453382 +Max repetitions 3, Elasped time 644.371, Relative error 0.00890861, Mean 49571.4, Standard Deviation 261.952 +Total Energy 49571.400000 diff --git a/tests/dgemmresultsdvfs/dgemmse_2.00GHz.txt b/tests/dgemmresultsdvfs/dgemmse_2.00GHz.txt new file mode 100644 index 0000000..00cd8e2 --- /dev/null +++ b/tests/dgemmresultsdvfs/dgemmse_2.00GHz.txt @@ -0,0 +1,3600 @@ +1 +Executable: ./dgemmoptimized 32 46080 46080 1 0 +m=32, n=46080, k=46080, time(sec)=9.584576, speed(mflops)=14178.556374 +Executable: ./dgemmoptimized 32 46080 46080 1 0 +m=32, n=46080, k=46080, time(sec)=9.568621, speed(mflops)=14202.197720 +Executable: ./dgemmoptimized 32 46080 46080 1 0 +m=32, n=46080, k=46080, time(sec)=9.549268, speed(mflops)=14230.980793 +Max repetitions 3, Elasped time 323.459, Relative error 0.376549, Mean 21559, Standard Deviation 4815.37 +Total Energy 21558.966667 +2 +Executable: ./dgemmoptimized 64 46080 46080 1 0 +m=64, n=46080, k=46080, time(sec)=11.770225, speed(mflops)=23091.393588 +Executable: ./dgemmoptimized 64 46080 46080 1 0 +m=64, n=46080, k=46080, time(sec)=11.727389, speed(mflops)=23175.738647 +Executable: ./dgemmoptimized 64 46080 46080 1 0 +m=64, n=46080, k=46080, time(sec)=11.718436, speed(mflops)=23193.444854 +Max repetitions 3, Elasped time 288.684, Relative error 0.0351771, Mean 19019.7, Standard Deviation 396.865 +Total Energy 19019.683333 +3 +Executable: ./dgemmoptimized 96 46080 46080 1 0 +m=96, n=46080, k=46080, time(sec)=3.628126, speed(mflops)=112368.302359 +Executable: ./dgemmoptimized 96 46080 46080 1 0 +m=96, n=46080, k=46080, time(sec)=3.570786, speed(mflops)=114172.719642 +Executable: ./dgemmoptimized 96 46080 46080 1 0 +m=96, n=46080, k=46080, time(sec)=3.629951, speed(mflops)=112311.804974 +Max repetitions 3, Elasped time 262.4, Relative error 0.0165274, Mean 17049.5, Standard Deviation 167.146 +Total Energy 17049.516667 +4 +Executable: ./dgemmoptimized 128 46080 46080 1 0 +m=128, n=46080, k=46080, time(sec)=4.479741, speed(mflops)=121342.241799 +Executable: ./dgemmoptimized 128 46080 46080 1 0 +m=128, n=46080, k=46080, time(sec)=4.500178, speed(mflops)=120791.174589 +Executable: ./dgemmoptimized 128 46080 46080 1 0 +m=128, n=46080, k=46080, time(sec)=4.523373, speed(mflops)=120171.779586 +Max repetitions 3, Elasped time 265.348, Relative error 0.00321523, Mean 17546.1, Standard Deviation 33.4636 +Total Energy 17546.100000 +5 +Executable: ./dgemmoptimized 160 46080 46080 1 0 +m=160, n=46080, k=46080, time(sec)=4.457185, speed(mflops)=152445.376045 +Executable: ./dgemmoptimized 160 46080 46080 1 0 +m=160, n=46080, k=46080, time(sec)=4.505918, speed(mflops)=150796.628808 +Executable: ./dgemmoptimized 160 46080 46080 1 0 +m=160, n=46080, k=46080, time(sec)=4.519067, speed(mflops)=150357.859405 +Max repetitions 3, Elasped time 267.013, Relative error 0.0257069, Mean 17714.2, Standard Deviation 270.116 +Total Energy 17714.166667 +6 +Executable: ./dgemmoptimized 192 46080 46080 1 0 +m=192, n=46080, k=46080, time(sec)=3.556223, speed(mflops)=229280.536384 +Executable: ./dgemmoptimized 192 46080 46080 1 0 +m=192, n=46080, k=46080, time(sec)=3.556216, speed(mflops)=229280.982160 +Executable: ./dgemmoptimized 192 46080 46080 1 0 +m=192, n=46080, k=46080, time(sec)=3.581379, speed(mflops)=227670.043298 +Max repetitions 3, Elasped time 263.174, Relative error 0.00417406, Mean 17436.9, Standard Deviation 43.1725 +Total Energy 17436.866667 +7 +Executable: ./dgemmoptimized 224 46080 46080 1 0 +m=224, n=46080, k=46080, time(sec)=4.514076, speed(mflops)=210733.746698 +Executable: ./dgemmoptimized 224 46080 46080 1 0 +m=224, n=46080, k=46080, time(sec)=4.473014, speed(mflops)=212668.264054 +Executable: ./dgemmoptimized 224 46080 46080 1 0 +m=224, n=46080, k=46080, time(sec)=4.488030, speed(mflops)=211956.728532 +Max repetitions 3, Elasped time 266.282, Relative error 0.00253697, Mean 17478.3, Standard Deviation 26.3023 +Total Energy 17478.266667 +8 +Executable: ./dgemmoptimized 256 46080 46080 1 0 +m=256, n=46080, k=46080, time(sec)=5.421872, speed(mflops)=200514.429137 +Executable: ./dgemmoptimized 256 46080 46080 1 0 +m=256, n=46080, k=46080, time(sec)=5.444603, speed(mflops)=199677.295760 +Executable: ./dgemmoptimized 256 46080 46080 1 0 +m=256, n=46080, k=46080, time(sec)=5.444438, speed(mflops)=199683.346686 +Max repetitions 3, Elasped time 272.068, Relative error 0.00956262, Mean 18020.7, Standard Deviation 102.218 +Total Energy 18020.666667 +9 +Executable: ./dgemmoptimized 288 46080 46080 1 0 +m=288, n=46080, k=46080, time(sec)=6.353368, speed(mflops)=192505.618744 +Executable: ./dgemmoptimized 288 46080 46080 1 0 +m=288, n=46080, k=46080, time(sec)=6.398414, speed(mflops)=191150.348535 +Executable: ./dgemmoptimized 288 46080 46080 1 0 +m=288, n=46080, k=46080, time(sec)=6.373716, speed(mflops)=191891.052237 +Max repetitions 3, Elasped time 272.581, Relative error 0.00258324, Mean 18078.5, Standard Deviation 27.7018 +Total Energy 18078.516667 +10 +Executable: ./dgemmoptimized 320 46080 46080 1 0 +m=320, n=46080, k=46080, time(sec)=7.276733, speed(mflops)=186753.383784 +Executable: ./dgemmoptimized 320 46080 46080 1 0 +m=320, n=46080, k=46080, time(sec)=7.002039, speed(mflops)=194079.825120 +Executable: ./dgemmoptimized 320 46080 46080 1 0 +m=320, n=46080, k=46080, time(sec)=7.278914, speed(mflops)=186697.425016 +Max repetitions 3, Elasped time 275.258, Relative error 0.00618413, Mean 18877.3, Standard Deviation 69.2467 +Total Energy 18877.316667 +11 +Executable: ./dgemmoptimized 352 46080 46080 1 0 +m=352, n=46080, k=46080, time(sec)=6.509677, speed(mflops)=229635.043477 +Executable: ./dgemmoptimized 352 46080 46080 1 0 +m=352, n=46080, k=46080, time(sec)=6.502560, speed(mflops)=229886.369940 +Executable: ./dgemmoptimized 352 46080 46080 1 0 +m=352, n=46080, k=46080, time(sec)=6.499083, speed(mflops)=230009.362229 +Max repetitions 3, Elasped time 273.579, Relative error 0.00387049, Mean 18128.1, Standard Deviation 41.6195 +Total Energy 18128.083333 +12 +Executable: ./dgemmoptimized 384 46080 46080 1 0 +m=384, n=46080, k=46080, time(sec)=3.856453, speed(mflops)=422861.479129 +Executable: ./dgemmoptimized 384 46080 46080 1 0 +m=384, n=46080, k=46080, time(sec)=3.921882, speed(mflops)=415806.857754 +Executable: ./dgemmoptimized 384 46080 46080 1 0 +m=384, n=46080, k=46080, time(sec)=3.926707, speed(mflops)=415295.916658 +Max repetitions 3, Elasped time 266.006, Relative error 0.00484568, Mean 17437.8, Standard Deviation 50.1218 +Total Energy 17437.783333 +13 +Executable: ./dgemmoptimized 416 46080 46080 1 0 +m=416, n=46080, k=46080, time(sec)=4.859662, speed(mflops)=363531.625132 +Executable: ./dgemmoptimized 416 46080 46080 1 0 +m=416, n=46080, k=46080, time(sec)=4.862147, speed(mflops)=363345.824607 +Executable: ./dgemmoptimized 416 46080 46080 1 0 +m=416, n=46080, k=46080, time(sec)=4.877130, speed(mflops)=362229.596783 +Max repetitions 3, Elasped time 269.335, Relative error 0.00216987, Mean 18159.5, Standard Deviation 23.3733 +Total Energy 18159.550000 +14 +Executable: ./dgemmoptimized 448 46080 46080 1 0 +m=448, n=46080, k=46080, time(sec)=5.805028, speed(mflops)=327739.385054 +Executable: ./dgemmoptimized 448 46080 46080 1 0 +m=448, n=46080, k=46080, time(sec)=5.802432, speed(mflops)=327886.009633 +Executable: ./dgemmoptimized 448 46080 46080 1 0 +m=448, n=46080, k=46080, time(sec)=5.811618, speed(mflops)=327367.742519 +Max repetitions 3, Elasped time 272.45, Relative error 0.00578381, Mean 18209.5, Standard Deviation 62.4731 +Total Energy 18209.550000 +15 +Executable: ./dgemmoptimized 480 46080 46080 1 0 +m=480, n=46080, k=46080, time(sec)=6.688800, speed(mflops)=304752.988166 +Executable: ./dgemmoptimized 480 46080 46080 1 0 +m=480, n=46080, k=46080, time(sec)=6.613249, speed(mflops)=308234.534104 +Executable: ./dgemmoptimized 480 46080 46080 1 0 +m=480, n=46080, k=46080, time(sec)=6.762935, speed(mflops)=301412.296164 +Max repetitions 3, Elasped time 280.645, Relative error 0.0324954, Mean 19020.5, Standard Deviation 366.627 +Total Energy 19020.516667 +16 +Executable: ./dgemmoptimized 512 46080 46080 1 0 +m=512, n=46080, k=46080, time(sec)=7.690893, speed(mflops)=282714.531594 +Executable: ./dgemmoptimized 512 46080 46080 1 0 +m=512, n=46080, k=46080, time(sec)=7.679712, speed(mflops)=283126.135125 +Executable: ./dgemmoptimized 512 46080 46080 1 0 +m=512, n=46080, k=46080, time(sec)=7.670674, speed(mflops)=283459.737295 +Max repetitions 3, Elasped time 280.754, Relative error 0.0246408, Mean 18918.9, Standard Deviation 276.523 +Total Energy 18918.933333 +17 +Executable: ./dgemmoptimized 544 46080 46080 1 0 +m=544, n=46080, k=46080, time(sec)=7.668245, speed(mflops)=301271.362608 +Executable: ./dgemmoptimized 544 46080 46080 1 0 +m=544, n=46080, k=46080, time(sec)=7.658925, speed(mflops)=301637.984193 +Executable: ./dgemmoptimized 544 46080 46080 1 0 +m=544, n=46080, k=46080, time(sec)=7.674886, speed(mflops)=301010.679083 +Max repetitions 3, Elasped time 278.993, Relative error 0.0013876, Mean 18771.6, Standard Deviation 15.4507 +Total Energy 18771.616667 +18 +Executable: ./dgemmoptimized 576 46080 46080 1 0 +m=576, n=46080, k=46080, time(sec)=6.686347, speed(mflops)=365837.742188 +Executable: ./dgemmoptimized 576 46080 46080 1 0 +m=576, n=46080, k=46080, time(sec)=6.537521, speed(mflops)=374165.994487 +Executable: ./dgemmoptimized 576 46080 46080 1 0 +m=576, n=46080, k=46080, time(sec)=6.696520, speed(mflops)=365281.976293 +Max repetitions 3, Elasped time 278.21, Relative error 0.0149942, Mean 18843.6, Standard Deviation 167.597 +Total Energy 18843.600000 +19 +Executable: ./dgemmoptimized 608 46080 46080 1 0 +m=608, n=46080, k=46080, time(sec)=7.642862, speed(mflops)=337833.339841 +Executable: ./dgemmoptimized 608 46080 46080 1 0 +m=608, n=46080, k=46080, time(sec)=7.647830, speed(mflops)=337613.877297 +Executable: ./dgemmoptimized 608 46080 46080 1 0 +m=608, n=46080, k=46080, time(sec)=7.661127, speed(mflops)=337027.895754 +Max repetitions 3, Elasped time 281.448, Relative error 0.0247819, Mean 18917.9, Standard Deviation 278.091 +Total Energy 18917.900000 +20 +Executable: ./dgemmoptimized 640 46080 46080 1 0 +m=640, n=46080, k=46080, time(sec)=8.584815, speed(mflops)=316594.939318 +Executable: ./dgemmoptimized 640 46080 46080 1 0 +m=640, n=46080, k=46080, time(sec)=8.592241, speed(mflops)=316321.315540 +Executable: ./dgemmoptimized 640 46080 46080 1 0 +m=640, n=46080, k=46080, time(sec)=8.595673, speed(mflops)=316195.016418 +Max repetitions 3, Elasped time 286.965, Relative error 0.0451262, Mean 19736.1, Standard Deviation 528.287 +Total Energy 19736.100000 +21 +Executable: ./dgemmoptimized 672 46080 46080 1 0 +m=672, n=46080, k=46080, time(sec)=9.531481, speed(mflops)=299408.290625 +Executable: ./dgemmoptimized 672 46080 46080 1 0 +m=672, n=46080, k=46080, time(sec)=9.550568, speed(mflops)=298809.914822 +Executable: ./dgemmoptimized 672 46080 46080 1 0 +m=672, n=46080, k=46080, time(sec)=9.542002, speed(mflops)=299078.157965 +Max repetitions 3, Elasped time 285.899, Relative error 0.00234457, Mean 19329.9, Standard Deviation 26.8827 +Total Energy 19329.916667 +22 +Executable: ./dgemmoptimized 704 46080 46080 1 0 +m=704, n=46080, k=46080, time(sec)=10.435310, speed(mflops)=286498.429236 +Executable: ./dgemmoptimized 704 46080 46080 1 0 +m=704, n=46080, k=46080, time(sec)=10.314490, speed(mflops)=289854.363827 +Executable: ./dgemmoptimized 704 46080 46080 1 0 +m=704, n=46080, k=46080, time(sec)=10.437398, speed(mflops)=286441.113346 +Max repetitions 3, Elasped time 288.732, Relative error 0.000435243, Mean 20130.6, Standard Deviation 5.19719 +Total Energy 20130.633333 +23 +Executable: ./dgemmoptimized 736 46080 46080 1 0 +m=736, n=46080, k=46080, time(sec)=9.603162, speed(mflops)=325475.642757 +Executable: ./dgemmoptimized 736 46080 46080 1 0 +m=736, n=46080, k=46080, time(sec)=9.611786, speed(mflops)=325183.621130 +Executable: ./dgemmoptimized 736 46080 46080 1 0 +m=736, n=46080, k=46080, time(sec)=9.601765, speed(mflops)=325522.993959 +Max repetitions 3, Elasped time 288.663, Relative error 0.0112758, Mean 19866.7, Standard Deviation 132.878 +Total Energy 19866.666667 +24 +Executable: ./dgemmoptimized 768 46080 46080 1 0 +m=768, n=46080, k=46080, time(sec)=7.010850, speed(mflops)=465206.173501 +Executable: ./dgemmoptimized 768 46080 46080 1 0 +m=768, n=46080, k=46080, time(sec)=7.068490, speed(mflops)=461412.676161 +Executable: ./dgemmoptimized 768 46080 46080 1 0 +m=768, n=46080, k=46080, time(sec)=7.062229, speed(mflops)=461821.716363 +Max repetitions 3, Elasped time 281.315, Relative error 0.0241399, Mean 18813, Standard Deviation 269.385 +Total Energy 18813.016667 +25 +Executable: ./dgemmoptimized 800 46080 46080 1 0 +m=800, n=46080, k=46080, time(sec)=8.032390, speed(mflops)=422960.811196 +Executable: ./dgemmoptimized 800 46080 46080 1 0 +m=800, n=46080, k=46080, time(sec)=7.999828, speed(mflops)=424682.418009 +Executable: ./dgemmoptimized 800 46080 46080 1 0 +m=800, n=46080, k=46080, time(sec)=7.980787, speed(mflops)=425695.639225 +Max repetitions 3, Elasped time 282.9, Relative error 0.00403794, Mean 19423.6, Standard Deviation 46.5231 +Total Energy 19423.583333 +26 +Executable: ./dgemmoptimized 832 46080 46080 1 0 +m=832, n=46080, k=46080, time(sec)=8.913355, speed(mflops)=396403.120899 +Executable: ./dgemmoptimized 832 46080 46080 1 0 +m=832, n=46080, k=46080, time(sec)=8.954016, speed(mflops)=394603.003531 +Executable: ./dgemmoptimized 832 46080 46080 1 0 +m=832, n=46080, k=46080, time(sec)=8.922754, speed(mflops)=395985.552227 +Max repetitions 3, Elasped time 285.588, Relative error 0.00490672, Mean 19425.9, Standard Deviation 56.5396 +Total Energy 19425.933333 +27 +Executable: ./dgemmoptimized 864 46080 46080 1 0 +m=864, n=46080, k=46080, time(sec)=9.827283, speed(mflops)=373366.389719 +Executable: ./dgemmoptimized 864 46080 46080 1 0 +m=864, n=46080, k=46080, time(sec)=10.267253, speed(mflops)=357366.977034 +Executable: ./dgemmoptimized 864 46080 46080 1 0 +m=864, n=46080, k=46080, time(sec)=9.828810, speed(mflops)=373308.380968 +Max repetitions 3, Elasped time 291.002, Relative error 0.0216589, Mean 20197.6, Standard Deviation 259.487 +Total Energy 20197.583333 +28 +Executable: ./dgemmoptimized 896 46080 46080 1 0 +m=896, n=46080, k=46080, time(sec)=10.827553, speed(mflops)=351424.978193 +Executable: ./dgemmoptimized 896 46080 46080 1 0 +m=896, n=46080, k=46080, time(sec)=10.764510, speed(mflops)=353483.123559 +Executable: ./dgemmoptimized 896 46080 46080 1 0 +m=896, n=46080, k=46080, time(sec)=11.135786, speed(mflops)=341697.709483 +Max repetitions 3, Elasped time 295.939, Relative error 0.0200011, Mean 20631.5, Standard Deviation 244.773 +Total Energy 20631.450000 +29 +Executable: ./dgemmoptimized 928 46080 46080 1 0 +m=928, n=46080, k=46080, time(sec)=10.828904, speed(mflops)=363930.457146 +Executable: ./dgemmoptimized 928 46080 46080 1 0 +m=928, n=46080, k=46080, time(sec)=10.819413, speed(mflops)=364249.710942 +Executable: ./dgemmoptimized 928 46080 46080 1 0 +m=928, n=46080, k=46080, time(sec)=10.772703, speed(mflops)=365829.083299 +Max repetitions 3, Elasped time 292.239, Relative error 0.00419976, Mean 20128.5, Standard Deviation 50.1437 +Total Energy 20128.516667 +30 +Executable: ./dgemmoptimized 960 46080 46080 1 0 +m=960, n=46080, k=46080, time(sec)=9.814950, speed(mflops)=415372.823340 +Executable: ./dgemmoptimized 960 46080 46080 1 0 +m=960, n=46080, k=46080, time(sec)=9.802500, speed(mflops)=415900.380927 +Executable: ./dgemmoptimized 960 46080 46080 1 0 +m=960, n=46080, k=46080, time(sec)=9.821961, speed(mflops)=415076.329329 +Max repetitions 3, Elasped time 291.504, Relative error 0.00906561, Mean 20320.2, Standard Deviation 109.271 +Total Energy 20320.233333 +31 +Executable: ./dgemmoptimized 992 46080 46080 1 0 +m=992, n=46080, k=46080, time(sec)=10.772770, speed(mflops)=391056.243266 +Executable: ./dgemmoptimized 992 46080 46080 1 0 +m=992, n=46080, k=46080, time(sec)=10.767185, speed(mflops)=391259.084734 +Executable: ./dgemmoptimized 992 46080 46080 1 0 +m=992, n=46080, k=46080, time(sec)=10.752845, speed(mflops)=391780.873978 +Max repetitions 3, Elasped time 295.964, Relative error 0.0111501, Mean 20744.5, Standard Deviation 137.202 +Total Energy 20744.483333 +32 +Executable: ./dgemmoptimized 1024 46080 46080 1 0 +m=1024, n=46080, k=46080, time(sec)=11.699030, speed(mflops)=371710.674081 +Executable: ./dgemmoptimized 1024 46080 46080 1 0 +m=1024, n=46080, k=46080, time(sec)=11.723827, speed(mflops)=370924.479675 +Executable: ./dgemmoptimized 1024 46080 46080 1 0 +m=1024, n=46080, k=46080, time(sec)=11.702979, speed(mflops)=371585.255614 +Max repetitions 3, Elasped time 299.587, Relative error 0.0163055, Mean 21161.6, Standard Deviation 204.674 +Total Energy 21161.583333 +33 +Executable: ./dgemmoptimized 1056 46080 46080 1 0 +m=1056, n=46080, k=46080, time(sec)=12.600158, speed(mflops)=355912.191362 +Executable: ./dgemmoptimized 1056 46080 46080 1 0 +m=1056, n=46080, k=46080, time(sec)=12.590366, speed(mflops)=356189.000158 +Executable: ./dgemmoptimized 1056 46080 46080 1 0 +m=1056, n=46080, k=46080, time(sec)=12.350626, speed(mflops)=363103.039455 +Max repetitions 3, Elasped time 301.829, Relative error 0.0384838, Mean 21349.8, Standard Deviation 487.362 +Total Energy 21349.833333 +34 +Executable: ./dgemmoptimized 1088 46080 46080 1 0 +m=1088, n=46080, k=46080, time(sec)=13.592625, speed(mflops)=339922.959654 +Executable: ./dgemmoptimized 1088 46080 46080 1 0 +m=1088, n=46080, k=46080, time(sec)=13.485817, speed(mflops)=342615.150416 +Executable: ./dgemmoptimized 1088 46080 46080 1 0 +m=1088, n=46080, k=46080, time(sec)=13.563306, speed(mflops)=340657.752311 +Max repetitions 3, Elasped time 301.999, Relative error 0.000999734, Mean 21469.6, Standard Deviation 12.7318 +Total Energy 21469.600000 +35 +Executable: ./dgemmoptimized 1120 46080 46080 1 0 +m=1120, n=46080, k=46080, time(sec)=12.159117, speed(mflops)=391174.847852 +Executable: ./dgemmoptimized 1120 46080 46080 1 0 +m=1120, n=46080, k=46080, time(sec)=12.168947, speed(mflops)=390858.859296 +Executable: ./dgemmoptimized 1120 46080 46080 1 0 +m=1120, n=46080, k=46080, time(sec)=12.168143, speed(mflops)=390884.683285 +Max repetitions 3, Elasped time 300.256, Relative error 0.00928494, Mean 20910.9, Standard Deviation 115.168 +Total Energy 20910.933333 +36 +Executable: ./dgemmoptimized 1152 46080 46080 1 0 +m=1152, n=46080, k=46080, time(sec)=8.360430, speed(mflops)=585165.617594 +Executable: ./dgemmoptimized 1152 46080 46080 1 0 +m=1152, n=46080, k=46080, time(sec)=8.223525, speed(mflops)=594907.451403 +Executable: ./dgemmoptimized 1152 46080 46080 1 0 +m=1152, n=46080, k=46080, time(sec)=8.360709, speed(mflops)=585146.093916 +Max repetitions 3, Elasped time 288.845, Relative error 0.0278204, Mean 20064.7, Standard Deviation 331.112 +Total Energy 20064.650000 +37 +Executable: ./dgemmoptimized 1184 46080 46080 1 0 +m=1184, n=46080, k=46080, time(sec)=9.328835, speed(mflops)=538988.161922 +Executable: ./dgemmoptimized 1184 46080 46080 1 0 +m=1184, n=46080, k=46080, time(sec)=9.321892, speed(mflops)=539389.602749 +Executable: ./dgemmoptimized 1184 46080 46080 1 0 +m=1184, n=46080, k=46080, time(sec)=9.327212, speed(mflops)=539081.944728 +Max repetitions 3, Elasped time 290.275, Relative error 0.00313733, Mean 20128.9, Standard Deviation 37.4593 +Total Energy 20128.883333 +38 +Executable: ./dgemmoptimized 1216 46080 46080 1 0 +m=1216, n=46080, k=46080, time(sec)=10.264528, speed(mflops)=503094.449801 +Executable: ./dgemmoptimized 1216 46080 46080 1 0 +m=1216, n=46080, k=46080, time(sec)=10.284398, speed(mflops)=502122.454313 +Executable: ./dgemmoptimized 1216 46080 46080 1 0 +m=1216, n=46080, k=46080, time(sec)=10.190234, speed(mflops)=506762.356136 +Max repetitions 3, Elasped time 295.316, Relative error 0.0157569, Mean 20871.1, Standard Deviation 195.072 +Total Energy 20871.083333 +39 +Executable: ./dgemmoptimized 1248 46080 46080 1 0 +m=1248, n=46080, k=46080, time(sec)=11.220008, speed(mflops)=472363.529805 +Executable: ./dgemmoptimized 1248 46080 46080 1 0 +m=1248, n=46080, k=46080, time(sec)=10.949971, speed(mflops)=484012.473956 +Executable: ./dgemmoptimized 1248 46080 46080 1 0 +m=1248, n=46080, k=46080, time(sec)=11.235842, speed(mflops)=471697.852225 +Max repetitions 3, Elasped time 298.357, Relative error 0.0179286, Mean 20705.1, Standard Deviation 220.194 +Total Energy 20705.116667 +40 +Executable: ./dgemmoptimized 1280 46080 46080 1 0 +m=1280, n=46080, k=46080, time(sec)=12.205259, speed(mflops)=445366.865732 +Executable: ./dgemmoptimized 1280 46080 46080 1 0 +m=1280, n=46080, k=46080, time(sec)=12.137581, speed(mflops)=447850.188167 +Executable: ./dgemmoptimized 1280 46080 46080 1 0 +m=1280, n=46080, k=46080, time(sec)=12.158313, speed(mflops)=447086.529843 +Max repetitions 3, Elasped time 301.755, Relative error 0.0127913, Mean 21498.6, Standard Deviation 163.119 +Total Energy 21498.583333 +41 +Executable: ./dgemmoptimized 1312 46080 46080 1 0 +m=1312, n=46080, k=46080, time(sec)=12.127943, speed(mflops)=459411.246879 +Executable: ./dgemmoptimized 1312 46080 46080 1 0 +m=1312, n=46080, k=46080, time(sec)=12.152892, speed(mflops)=458468.115344 +Executable: ./dgemmoptimized 1312 46080 46080 1 0 +m=1312, n=46080, k=46080, time(sec)=12.158955, speed(mflops)=458239.503174 +Max repetitions 3, Elasped time 300.015, Relative error 0.00105101, Mean 21469.7, Standard Deviation 13.3848 +Total Energy 21469.700000 +42 +Executable: ./dgemmoptimized 1344 46080 46080 1 0 +m=1344, n=46080, k=46080, time(sec)=11.159820, speed(mflops)=511442.733161 +Executable: ./dgemmoptimized 1344 46080 46080 1 0 +m=1344, n=46080, k=46080, time(sec)=11.148323, speed(mflops)=511970.172819 +Executable: ./dgemmoptimized 1344 46080 46080 1 0 +m=1344, n=46080, k=46080, time(sec)=11.062127, speed(mflops)=515959.448643 +Max repetitions 3, Elasped time 301.053, Relative error 0.00919998, Mean 20956.8, Standard Deviation 114.365 +Total Energy 20956.833333 +43 +Executable: ./dgemmoptimized 1376 46080 46080 1 0 +m=1376, n=46080, k=46080, time(sec)=11.989700, speed(mflops)=487377.032829 +Executable: ./dgemmoptimized 1376 46080 46080 1 0 +m=1376, n=46080, k=46080, time(sec)=12.128865, speed(mflops)=481784.926378 +Executable: ./dgemmoptimized 1376 46080 46080 1 0 +m=1376, n=46080, k=46080, time(sec)=12.123174, speed(mflops)=482011.093455 +Max repetitions 3, Elasped time 300.426, Relative error 0.0029305, Mean 21447, Standard Deviation 37.2811 +Total Energy 21447.000000 +44 +Executable: ./dgemmoptimized 1408 46080 46080 1 0 +m=1408, n=46080, k=46080, time(sec)=12.907539, speed(mflops)=463248.627219 +Executable: ./dgemmoptimized 1408 46080 46080 1 0 +m=1408, n=46080, k=46080, time(sec)=13.080821, speed(mflops)=457111.963030 +Executable: ./dgemmoptimized 1408 46080 46080 1 0 +m=1408, n=46080, k=46080, time(sec)=13.085198, speed(mflops)=456959.062936 +Max repetitions 3, Elasped time 305.893, Relative error 0.0376689, Mean 21679.6, Standard Deviation 484.411 +Total Energy 21679.600000 +45 +Executable: ./dgemmoptimized 1440 46080 46080 1 0 +m=1440, n=46080, k=46080, time(sec)=13.970733, speed(mflops)=437721.862111 +Executable: ./dgemmoptimized 1440 46080 46080 1 0 +m=1440, n=46080, k=46080, time(sec)=13.928215, speed(mflops)=439058.071706 +Executable: ./dgemmoptimized 1440 46080 46080 1 0 +m=1440, n=46080, k=46080, time(sec)=13.721971, speed(mflops)=445657.203065 +Max repetitions 3, Elasped time 306.413, Relative error 0.00505097, Mean 21957.7, Standard Deviation 65.7872 +Total Energy 21957.700000 +46 +Executable: ./dgemmoptimized 1472 46080 46080 1 0 +m=1472, n=46080, k=46080, time(sec)=14.864205, speed(mflops)=420553.311145 +Executable: ./dgemmoptimized 1472 46080 46080 1 0 +m=1472, n=46080, k=46080, time(sec)=14.699573, speed(mflops)=425263.418508 +Executable: ./dgemmoptimized 1472 46080 46080 1 0 +m=1472, n=46080, k=46080, time(sec)=14.920610, speed(mflops)=418963.480858 +Max repetitions 3, Elasped time 313.447, Relative error 0.0182406, Mean 22237, Standard Deviation 240.6 +Total Energy 22237.016667 +47 +Executable: ./dgemmoptimized 1504 46080 46080 1 0 +m=1504, n=46080, k=46080, time(sec)=14.099549, speed(mflops)=452999.319782 +Executable: ./dgemmoptimized 1504 46080 46080 1 0 +m=1504, n=46080, k=46080, time(sec)=14.074109, speed(mflops)=453818.149060 +Executable: ./dgemmoptimized 1504 46080 46080 1 0 +m=1504, n=46080, k=46080, time(sec)=14.075873, speed(mflops)=453761.281978 +Max repetitions 3, Elasped time 309.709, Relative error 0.0106774, Mean 22142.6, Standard Deviation 140.241 +Total Energy 22142.550000 +48 +Executable: ./dgemmoptimized 1536 46080 46080 1 0 +m=1536, n=46080, k=46080, time(sec)=11.494560, speed(mflops)=567484.234189 +Executable: ./dgemmoptimized 1536 46080 46080 1 0 +m=1536, n=46080, k=46080, time(sec)=11.377476, speed(mflops)=573324.123674 +Executable: ./dgemmoptimized 1536 46080 46080 1 0 +m=1536, n=46080, k=46080, time(sec)=11.356791, speed(mflops)=574368.373041 +Max repetitions 3, Elasped time 302.002, Relative error 0.0153838, Mean 21463.6, Standard Deviation 195.86 +Total Energy 21463.600000 +49 +Executable: ./dgemmoptimized 1568 46080 46080 1 0 +m=1568, n=46080, k=46080, time(sec)=12.451369, speed(mflops)=534790.753143 +Executable: ./dgemmoptimized 1568 46080 46080 1 0 +m=1568, n=46080, k=46080, time(sec)=12.458260, speed(mflops)=534494.945416 +Executable: ./dgemmoptimized 1568 46080 46080 1 0 +m=1568, n=46080, k=46080, time(sec)=12.400330, speed(mflops)=536991.918327 +Max repetitions 3, Elasped time 303.811, Relative error 0.00336691, Mean 21363.2, Standard Deviation 42.6655 +Total Energy 21363.200000 +50 +Executable: ./dgemmoptimized 1600 46080 46080 1 0 +m=1600, n=46080, k=46080, time(sec)=13.402243, speed(mflops)=506987.713268 +Executable: ./dgemmoptimized 1600 46080 46080 1 0 +m=1600, n=46080, k=46080, time(sec)=13.439769, speed(mflops)=505572.116978 +Executable: ./dgemmoptimized 1600 46080 46080 1 0 +m=1600, n=46080, k=46080, time(sec)=13.426914, speed(mflops)=506056.156449 +Max repetitions 3, Elasped time 306.705, Relative error 0.00847935, Mean 22171.3, Standard Deviation 111.515 +Total Energy 22171.266667 +51 +Executable: ./dgemmoptimized 1632 46080 46080 1 0 +m=1632, n=46080, k=46080, time(sec)=15.266000, speed(mflops)=453993.705940 +Executable: ./dgemmoptimized 1632 46080 46080 1 0 +m=1632, n=46080, k=46080, time(sec)=14.300365, speed(mflops)=484649.723526 +Executable: ./dgemmoptimized 1632 46080 46080 1 0 +m=1632, n=46080, k=46080, time(sec)=14.118656, speed(mflops)=490887.232386 +Max repetitions 3, Elasped time 310.405, Relative error 0.0314682, Mean 22204.2, Standard Deviation 414.464 +Total Energy 22204.216667 +52 +Executable: ./dgemmoptimized 1664 46080 46080 1 0 +m=1664, n=46080, k=46080, time(sec)=15.069142, speed(mflops)=468942.653975 +Executable: ./dgemmoptimized 1664 46080 46080 1 0 +m=1664, n=46080, k=46080, time(sec)=15.333857, speed(mflops)=460847.088361 +Executable: ./dgemmoptimized 1664 46080 46080 1 0 +m=1664, n=46080, k=46080, time(sec)=15.309433, speed(mflops)=461582.305946 +Max repetitions 3, Elasped time 312.788, Relative error 0.00151482, Mean 22715.3, Standard Deviation 20.4108 +Total Energy 22715.283333 +53 +Executable: ./dgemmoptimized 1696 46080 46080 1 0 +m=1696, n=46080, k=46080, time(sec)=15.186072, speed(mflops)=474280.562880 +Executable: ./dgemmoptimized 1696 46080 46080 1 0 +m=1696, n=46080, k=46080, time(sec)=15.092515, speed(mflops)=477220.584689 +Executable: ./dgemmoptimized 1696 46080 46080 1 0 +m=1696, n=46080, k=46080, time(sec)=15.298587, speed(mflops)=470792.419544 +Max repetitions 3, Elasped time 312.945, Relative error 0.00372109, Mean 22756.2, Standard Deviation 50.2284 +Total Energy 22756.183333 +54 +Executable: ./dgemmoptimized 1728 46080 46080 1 0 +m=1728, n=46080, k=46080, time(sec)=14.297925, speed(mflops)=513246.102546 +Executable: ./dgemmoptimized 1728 46080 46080 1 0 +m=1728, n=46080, k=46080, time(sec)=14.295258, speed(mflops)=513341.863266 +Executable: ./dgemmoptimized 1728 46080 46080 1 0 +m=1728, n=46080, k=46080, time(sec)=14.167461, speed(mflops)=517972.438439 +Max repetitions 3, Elasped time 311.737, Relative error 0.0135119, Mean 22449.6, Standard Deviation 179.931 +Total Energy 22449.633333 +55 +Executable: ./dgemmoptimized 1760 46080 46080 1 0 +m=1760, n=46080, k=46080, time(sec)=15.144913, speed(mflops)=493515.528855 +Executable: ./dgemmoptimized 1760 46080 46080 1 0 +m=1760, n=46080, k=46080, time(sec)=15.211170, speed(mflops)=491365.867884 +Executable: ./dgemmoptimized 1760 46080 46080 1 0 +m=1760, n=46080, k=46080, time(sec)=15.151170, speed(mflops)=493311.719190 +Max repetitions 3, Elasped time 313.5, Relative error 0.00101927, Mean 22721.1, Standard Deviation 13.7372 +Total Energy 22721.066667 +56 +Executable: ./dgemmoptimized 1792 46080 46080 1 0 +m=1792, n=46080, k=46080, time(sec)=16.041943, speed(mflops)=474390.486417 +Executable: ./dgemmoptimized 1792 46080 46080 1 0 +m=1792, n=46080, k=46080, time(sec)=16.199935, speed(mflops)=469763.927119 +Executable: ./dgemmoptimized 1792 46080 46080 1 0 +m=1792, n=46080, k=46080, time(sec)=16.170507, speed(mflops)=470618.837069 +Max repetitions 3, Elasped time 320.585, Relative error 0.0235085, Mean 23325.6, Standard Deviation 325.265 +Total Energy 23325.600000 +57 +Executable: ./dgemmoptimized 1824 46080 46080 1 0 +m=1824, n=46080, k=46080, time(sec)=17.087856, speed(mflops)=453306.757886 +Executable: ./dgemmoptimized 1824 46080 46080 1 0 +m=1824, n=46080, k=46080, time(sec)=17.081753, speed(mflops)=453468.717184 +Executable: ./dgemmoptimized 1824 46080 46080 1 0 +m=1824, n=46080, k=46080, time(sec)=16.889979, speed(mflops)=458617.543553 +Max repetitions 3, Elasped time 319.671, Relative error 0.00158596, Mean 23324.5, Standard Deviation 21.9423 +Total Energy 23324.466667 +58 +Executable: ./dgemmoptimized 1856 46080 46080 1 0 +m=1856, n=46080, k=46080, time(sec)=17.837180, speed(mflops)=441882.406074 +Executable: ./dgemmoptimized 1856 46080 46080 1 0 +m=1856, n=46080, k=46080, time(sec)=18.080310, speed(mflops)=435940.320404 +Executable: ./dgemmoptimized 1856 46080 46080 1 0 +m=1856, n=46080, k=46080, time(sec)=17.974921, speed(mflops)=438496.285020 +Max repetitions 3, Elasped time 326.883, Relative error 0.0187561, Mean 24204, Standard Deviation 269.283 +Total Energy 24203.950000 +59 +Executable: ./dgemmoptimized 1888 46080 46080 1 0 +m=1888, n=46080, k=46080, time(sec)=17.083043, speed(mflops)=469344.453456 +Executable: ./dgemmoptimized 1888 46080 46080 1 0 +m=1888, n=46080, k=46080, time(sec)=17.083427, speed(mflops)=469333.901029 +Executable: ./dgemmoptimized 1888 46080 46080 1 0 +m=1888, n=46080, k=46080, time(sec)=17.228427, speed(mflops)=465383.842497 +Max repetitions 3, Elasped time 320.668, Relative error 0.00144722, Mean 23419.2, Standard Deviation 20.1042 +Total Energy 23419.200000 +60 +Executable: ./dgemmoptimized 1920 46080 46080 1 0 +m=1920, n=46080, k=46080, time(sec)=14.631282, speed(mflops)=557280.416385 +Executable: ./dgemmoptimized 1920 46080 46080 1 0 +m=1920, n=46080, k=46080, time(sec)=14.604915, speed(mflops)=558286.501270 +Executable: ./dgemmoptimized 1920 46080 46080 1 0 +m=1920, n=46080, k=46080, time(sec)=14.591258, speed(mflops)=558809.054150 +Max repetitions 3, Elasped time 317.223, Relative error 0.0180381, Mean 22911.5, Standard Deviation 245.146 +Total Energy 22911.483333 +61 +Executable: ./dgemmoptimized 1952 46080 46080 1 0 +m=1952, n=46080, k=46080, time(sec)=15.620990, speed(mflops)=530672.025619 +Executable: ./dgemmoptimized 1952 46080 46080 1 0 +m=1952, n=46080, k=46080, time(sec)=15.623026, speed(mflops)=530602.864980 +Executable: ./dgemmoptimized 1952 46080 46080 1 0 +m=1952, n=46080, k=46080, time(sec)=15.633220, speed(mflops)=530256.879147 +Max repetitions 3, Elasped time 318.687, Relative error 0.00252284, Mean 23378.4, Standard Deviation 34.9852 +Total Energy 23378.433333 +62 +Executable: ./dgemmoptimized 1984 46080 46080 1 0 +m=1984, n=46080, k=46080, time(sec)=16.496677, speed(mflops)=510740.309404 +Executable: ./dgemmoptimized 1984 46080 46080 1 0 +m=1984, n=46080, k=46080, time(sec)=16.468672, speed(mflops)=511608.820444 +Executable: ./dgemmoptimized 1984 46080 46080 1 0 +m=1984, n=46080, k=46080, time(sec)=16.415574, speed(mflops)=513263.674930 +Max repetitions 3, Elasped time 319.588, Relative error 0.00240324, Mean 23365.7, Standard Deviation 33.3085 +Total Energy 23365.666667 +63 +Executable: ./dgemmoptimized 2016 46080 46080 1 0 +m=2016, n=46080, k=46080, time(sec)=17.477516, speed(mflops)=489852.976785 +Executable: ./dgemmoptimized 2016 46080 46080 1 0 +m=2016, n=46080, k=46080, time(sec)=17.465708, speed(mflops)=490184.154934 +Executable: ./dgemmoptimized 2016 46080 46080 1 0 +m=2016, n=46080, k=46080, time(sec)=17.384921, speed(mflops)=492462.018573 +Max repetitions 3, Elasped time 322.839, Relative error 0.0170761, Mean 23874.2, Standard Deviation 241.823 +Total Energy 23874.166667 +64 +Executable: ./dgemmoptimized 2048 46080 46080 1 0 +m=2048, n=46080, k=46080, time(sec)=18.343351, speed(mflops)=474139.584847 +Executable: ./dgemmoptimized 2048 46080 46080 1 0 +m=2048, n=46080, k=46080, time(sec)=18.360351, speed(mflops)=473700.576136 +Executable: ./dgemmoptimized 2048 46080 46080 1 0 +m=2048, n=46080, k=46080, time(sec)=18.398178, speed(mflops)=472726.638451 +Max repetitions 3, Elasped time 329.126, Relative error 0.0184182, Mean 24296.4, Standard Deviation 265.442 +Total Energy 24296.366667 +65 +Executable: ./dgemmoptimized 2080 46080 46080 1 0 +m=2080, n=46080, k=46080, time(sec)=18.330406, speed(mflops)=481888.085176 +Executable: ./dgemmoptimized 2080 46080 46080 1 0 +m=2080, n=46080, k=46080, time(sec)=18.289770, speed(mflops)=482958.733925 +Executable: ./dgemmoptimized 2080 46080 46080 1 0 +m=2080, n=46080, k=46080, time(sec)=18.425865, speed(mflops)=479391.558600 +Max repetitions 3, Elasped time 326.298, Relative error 0.00294204, Mean 24042.6, Standard Deviation 41.9575 +Total Energy 24042.583333 +66 +Executable: ./dgemmoptimized 2112 46080 46080 1 0 +m=2112, n=46080, k=46080, time(sec)=17.400149, speed(mflops)=515461.081308 +Executable: ./dgemmoptimized 2112 46080 46080 1 0 +m=2112, n=46080, k=46080, time(sec)=17.399401, speed(mflops)=515483.245638 +Executable: ./dgemmoptimized 2112 46080 46080 1 0 +m=2112, n=46080, k=46080, time(sec)=17.368019, speed(mflops)=516414.666694 +Max repetitions 3, Elasped time 323.67, Relative error 0.00665231, Mean 24045.1, Standard Deviation 94.881 +Total Energy 24045.100000 +67 +Executable: ./dgemmoptimized 2144 46080 46080 1 0 +m=2144, n=46080, k=46080, time(sec)=18.369852, speed(mflops)=495648.799482 +Executable: ./dgemmoptimized 2144 46080 46080 1 0 +m=2144, n=46080, k=46080, time(sec)=18.351187, speed(mflops)=496152.926118 +Executable: ./dgemmoptimized 2144 46080 46080 1 0 +m=2144, n=46080, k=46080, time(sec)=18.314423, speed(mflops)=497148.897338 +Max repetitions 3, Elasped time 328.805, Relative error 0.0112557, Mean 24080.6, Standard Deviation 160.776 +Total Energy 24080.583333 +68 +Executable: ./dgemmoptimized 2176 46080 46080 1 0 +m=2176, n=46080, k=46080, time(sec)=19.190959, speed(mflops)=481523.126801 +Executable: ./dgemmoptimized 2176 46080 46080 1 0 +m=2176, n=46080, k=46080, time(sec)=19.199099, speed(mflops)=481318.969294 +Executable: ./dgemmoptimized 2176 46080 46080 1 0 +m=2176, n=46080, k=46080, time(sec)=19.293130, speed(mflops)=478973.116890 +Max repetitions 3, Elasped time 331.608, Relative error 0.0261217, Mean 24961.4, Standard Deviation 386.768 +Total Energy 24961.400000 +69 +Executable: ./dgemmoptimized 2208 46080 46080 1 0 +m=2208, n=46080, k=46080, time(sec)=20.200731, speed(mflops)=464180.529124 +Executable: ./dgemmoptimized 2208 46080 46080 1 0 +m=2208, n=46080, k=46080, time(sec)=20.020206, speed(mflops)=468366.111433 +Executable: ./dgemmoptimized 2208 46080 46080 1 0 +m=2208, n=46080, k=46080, time(sec)=20.187109, speed(mflops)=464493.753187 +Max repetitions 3, Elasped time 334.819, Relative error 0.0113676, Mean 24661.9, Standard Deviation 166.294 +Total Energy 24661.916667 +70 +Executable: ./dgemmoptimized 2240 46080 46080 1 0 +m=2240, n=46080, k=46080, time(sec)=21.189167, speed(mflops)=448940.794218 +Executable: ./dgemmoptimized 2240 46080 46080 1 0 +m=2240, n=46080, k=46080, time(sec)=21.118961, speed(mflops)=450433.216683 +Executable: ./dgemmoptimized 2240 46080 46080 1 0 +m=2240, n=46080, k=46080, time(sec)=21.134854, speed(mflops)=450094.500017 +Max repetitions 3, Elasped time 336.143, Relative error 0.00668226, Mean 25433.5, Standard Deviation 100.811 +Total Energy 25433.516667 +71 +Executable: ./dgemmoptimized 2272 46080 46080 1 0 +m=2272, n=46080, k=46080, time(sec)=19.761351, speed(mflops)=488254.926751 +Executable: ./dgemmoptimized 2272 46080 46080 1 0 +m=2272, n=46080, k=46080, time(sec)=19.761757, speed(mflops)=488244.895021 +Executable: ./dgemmoptimized 2272 46080 46080 1 0 +m=2272, n=46080, k=46080, time(sec)=19.705753, speed(mflops)=489632.488467 +Max repetitions 3, Elasped time 336.181, Relative error 0.0144632, Mean 24915.6, Standard Deviation 213.755 +Total Energy 24915.650000 +72 +Executable: ./dgemmoptimized 2304 46080 46080 1 0 +m=2304, n=46080, k=46080, time(sec)=15.872128, speed(mflops)=616456.241101 +Executable: ./dgemmoptimized 2304 46080 46080 1 0 +m=2304, n=46080, k=46080, time(sec)=15.896802, speed(mflops)=615499.410266 +Executable: ./dgemmoptimized 2304 46080 46080 1 0 +m=2304, n=46080, k=46080, time(sec)=15.882682, speed(mflops)=616046.613896 +Max repetitions 3, Elasped time 321.082, Relative error 0.00208131, Mean 23181.7, Standard Deviation 28.6195 +Total Energy 23181.683333 +73 +Executable: ./dgemmoptimized 2336 46080 46080 1 0 +m=2336, n=46080, k=46080, time(sec)=16.898839, speed(mflops)=587044.342077 +Executable: ./dgemmoptimized 2336 46080 46080 1 0 +m=2336, n=46080, k=46080, time(sec)=16.864414, speed(mflops)=588242.664970 +Executable: ./dgemmoptimized 2336 46080 46080 1 0 +m=2336, n=46080, k=46080, time(sec)=16.872075, speed(mflops)=587975.561586 +Max repetitions 3, Elasped time 328.731, Relative error 0.0359422, Mean 24238.3, Standard Deviation 516.758 +Total Energy 24238.316667 +74 +Executable: ./dgemmoptimized 2368 46080 46080 1 0 +m=2368, n=46080, k=46080, time(sec)=17.888112, speed(mflops)=562175.775290 +Executable: ./dgemmoptimized 2368 46080 46080 1 0 +m=2368, n=46080, k=46080, time(sec)=17.861798, speed(mflops)=563003.973249 +Executable: ./dgemmoptimized 2368 46080 46080 1 0 +m=2368, n=46080, k=46080, time(sec)=17.869033, speed(mflops)=562776.016762 +Max repetitions 3, Elasped time 331.479, Relative error 0.0186503, Mean 24199.6, Standard Deviation 267.717 +Total Energy 24199.650000 +75 +Executable: ./dgemmoptimized 2400 46080 46080 1 0 +m=2400, n=46080, k=46080, time(sec)=19.352347, speed(mflops)=526662.665185 +Executable: ./dgemmoptimized 2400 46080 46080 1 0 +m=2400, n=46080, k=46080, time(sec)=18.720124, speed(mflops)=544449.316499 +Executable: ./dgemmoptimized 2400 46080 46080 1 0 +m=2400, n=46080, k=46080, time(sec)=18.789264, speed(mflops)=542445.867510 +Max repetitions 3, Elasped time 331.157, Relative error 0.00379032, Mean 24543.7, Standard Deviation 55.1818 +Total Energy 24543.716667 +76 +Executable: ./dgemmoptimized 2432 46080 46080 1 0 +m=2432, n=46080, k=46080, time(sec)=19.750446, speed(mflops)=522927.640579 +Executable: ./dgemmoptimized 2432 46080 46080 1 0 +m=2432, n=46080, k=46080, time(sec)=19.756443, speed(mflops)=522768.909222 +Executable: ./dgemmoptimized 2432 46080 46080 1 0 +m=2432, n=46080, k=46080, time(sec)=19.759584, speed(mflops)=522685.811387 +Max repetitions 3, Elasped time 335.818, Relative error 0.0179107, Mean 24756.4, Standard Deviation 263.014 +Total Energy 24756.366667 +77 +Executable: ./dgemmoptimized 2464 46080 46080 1 0 +m=2464, n=46080, k=46080, time(sec)=19.654773, speed(mflops)=532387.202887 +Executable: ./dgemmoptimized 2464 46080 46080 1 0 +m=2464, n=46080, k=46080, time(sec)=19.681250, speed(mflops)=531670.991185 +Executable: ./dgemmoptimized 2464 46080 46080 1 0 +m=2464, n=46080, k=46080, time(sec)=19.607502, speed(mflops)=533670.715828 +Max repetitions 3, Elasped time 335.871, Relative error 0.0157808, Mean 24709.2, Standard Deviation 231.295 +Total Energy 24709.166667 +78 +Executable: ./dgemmoptimized 2496 46080 46080 1 0 +m=2496, n=46080, k=46080, time(sec)=18.703130, speed(mflops)=566741.773433 +Executable: ./dgemmoptimized 2496 46080 46080 1 0 +m=2496, n=46080, k=46080, time(sec)=18.690493, speed(mflops)=567124.955356 +Executable: ./dgemmoptimized 2496 46080 46080 1 0 +m=2496, n=46080, k=46080, time(sec)=18.688200, speed(mflops)=567194.543644 +Max repetitions 3, Elasped time 335.212, Relative error 0.0172122, Mean 24821.3, Standard Deviation 253.42 +Total Energy 24821.266667 +79 +Executable: ./dgemmoptimized 2528 46080 46080 1 0 +m=2528, n=46080, k=46080, time(sec)=19.665321, speed(mflops)=545922.468674 +Executable: ./dgemmoptimized 2528 46080 46080 1 0 +m=2528, n=46080, k=46080, time(sec)=19.645156, speed(mflops)=546482.836247 +Executable: ./dgemmoptimized 2528 46080 46080 1 0 +m=2528, n=46080, k=46080, time(sec)=20.987717, speed(mflops)=511524.934455 +Max repetitions 3, Elasped time 335.886, Relative error 0.0185919, Mean 25073.8, Standard Deviation 276.519 +Total Energy 25073.816667 +80 +Executable: ./dgemmoptimized 2560 46080 46080 1 0 +m=2560, n=46080, k=46080, time(sec)=20.680094, speed(mflops)=525705.345733 +Executable: ./dgemmoptimized 2560 46080 46080 1 0 +m=2560, n=46080, k=46080, time(sec)=20.553062, speed(mflops)=528954.565895 +Executable: ./dgemmoptimized 2560 46080 46080 1 0 +m=2560, n=46080, k=46080, time(sec)=20.540061, speed(mflops)=529289.371126 +Max repetitions 3, Elasped time 339.641, Relative error 0.0193739, Mean 25426.4, Standard Deviation 292.2 +Total Energy 25426.383333 +81 +Executable: ./dgemmoptimized 2592 46080 46080 1 0 +m=2592, n=46080, k=46080, time(sec)=21.528277, speed(mflops)=511305.733308 +Executable: ./dgemmoptimized 2592 46080 46080 1 0 +m=2592, n=46080, k=46080, time(sec)=21.585215, speed(mflops)=509957.000309 +Executable: ./dgemmoptimized 2592 46080 46080 1 0 +m=2592, n=46080, k=46080, time(sec)=21.353638, speed(mflops)=515487.405554 +Max repetitions 3, Elasped time 340.657, Relative error 0.0256925, Mean 25682.6, Standard Deviation 391.403 +Total Energy 25682.583333 +82 +Executable: ./dgemmoptimized 2624 46080 46080 1 0 +m=2624, n=46080, k=46080, time(sec)=22.370090, speed(mflops)=498139.563288 +Executable: ./dgemmoptimized 2624 46080 46080 1 0 +m=2624, n=46080, k=46080, time(sec)=22.582705, speed(mflops)=493449.604770 +Executable: ./dgemmoptimized 2624 46080 46080 1 0 +m=2624, n=46080, k=46080, time(sec)=22.584305, speed(mflops)=493414.645415 +Max repetitions 3, Elasped time 345.906, Relative error 0.0168429, Mean 26057.1, Standard Deviation 260.329 +Total Energy 26057.133333 +83 +Executable: ./dgemmoptimized 2656 46080 46080 1 0 +m=2656, n=46080, k=46080, time(sec)=21.574791, speed(mflops)=522801.001435 +Executable: ./dgemmoptimized 2656 46080 46080 1 0 +m=2656, n=46080, k=46080, time(sec)=21.695777, speed(mflops)=519885.614067 +Executable: ./dgemmoptimized 2656 46080 46080 1 0 +m=2656, n=46080, k=46080, time(sec)=21.571639, speed(mflops)=522877.389378 +Max repetitions 3, Elasped time 346.235, Relative error 0.0134281, Mean 26199.7, Standard Deviation 208.684 +Total Energy 26199.650000 +84 +Executable: ./dgemmoptimized 2688 46080 46080 1 0 +m=2688, n=46080, k=46080, time(sec)=19.062781, speed(mflops)=598822.273202 +Executable: ./dgemmoptimized 2688 46080 46080 1 0 +m=2688, n=46080, k=46080, time(sec)=19.033826, speed(mflops)=599733.216999 +Executable: ./dgemmoptimized 2688 46080 46080 1 0 +m=2688, n=46080, k=46080, time(sec)=19.018770, speed(mflops)=600207.993404 +Max repetitions 3, Elasped time 334.219, Relative error 0.00201892, Mean 24529.5, Standard Deviation 29.3757 +Total Energy 24529.500000 +85 +Executable: ./dgemmoptimized 2720 46080 46080 1 0 +m=2720, n=46080, k=46080, time(sec)=20.034767, speed(mflops)=576553.411700 +Executable: ./dgemmoptimized 2720 46080 46080 1 0 +m=2720, n=46080, k=46080, time(sec)=20.047378, speed(mflops)=576190.720781 +Executable: ./dgemmoptimized 2720 46080 46080 1 0 +m=2720, n=46080, k=46080, time(sec)=20.038154, speed(mflops)=576455.959030 +Max repetitions 3, Elasped time 339.491, Relative error 0.0185955, Mean 25461.9, Standard Deviation 280.853 +Total Energy 25461.950000 +86 +Executable: ./dgemmoptimized 2752 46080 46080 1 0 +m=2752, n=46080, k=46080, time(sec)=20.915157, speed(mflops)=558781.778261 +Executable: ./dgemmoptimized 2752 46080 46080 1 0 +m=2752, n=46080, k=46080, time(sec)=20.916922, speed(mflops)=558734.627110 +Executable: ./dgemmoptimized 2752 46080 46080 1 0 +m=2752, n=46080, k=46080, time(sec)=20.944244, speed(mflops)=558005.750121 +Max repetitions 3, Elasped time 387.414, Relative error 0.339724, Mean 29026.7, Standard Deviation 5849.31 +Total Energy 29026.733333 +87 +Executable: ./dgemmoptimized 2784 46080 46080 1 0 +m=2784, n=46080, k=46080, time(sec)=21.812682, speed(mflops)=542019.737057 +Executable: ./dgemmoptimized 2784 46080 46080 1 0 +m=2784, n=46080, k=46080, time(sec)=21.734303, speed(mflops)=543974.385399 +Executable: ./dgemmoptimized 2784 46080 46080 1 0 +m=2784, n=46080, k=46080, time(sec)=21.900612, speed(mflops)=539843.552379 +Max repetitions 3, Elasped time 343.522, Relative error 0.00381581, Mean 25858.1, Standard Deviation 58.528 +Total Energy 25858.116667 +88 +Executable: ./dgemmoptimized 2816 46080 46080 1 0 +m=2816, n=46080, k=46080, time(sec)=22.894212, speed(mflops)=522350.346056 +Executable: ./dgemmoptimized 2816 46080 46080 1 0 +m=2816, n=46080, k=46080, time(sec)=22.809672, speed(mflops)=524286.347841 +Executable: ./dgemmoptimized 2816 46080 46080 1 0 +m=2816, n=46080, k=46080, time(sec)=22.705999, speed(mflops)=526680.179047 +Max repetitions 3, Elasped time 346.72, Relative error 0.0256313, Mean 26261.3, Standard Deviation 399.27 +Total Energy 26261.283333 +89 +Executable: ./dgemmoptimized 2848 46080 46080 1 0 +m=2848, n=46080, k=46080, time(sec)=22.883357, speed(mflops)=528536.743495 +Executable: ./dgemmoptimized 2848 46080 46080 1 0 +m=2848, n=46080, k=46080, time(sec)=22.836324, speed(mflops)=529625.303391 +Executable: ./dgemmoptimized 2848 46080 46080 1 0 +m=2848, n=46080, k=46080, time(sec)=22.760363, speed(mflops)=531392.885088 +Max repetitions 3, Elasped time 347.191, Relative error 0.00503356, Mean 26650.1, Standard Deviation 79.5708 +Total Energy 26650.083333 +90 +Executable: ./dgemmoptimized 2880 46080 46080 1 0 +m=2880, n=46080, k=46080, time(sec)=21.798485, speed(mflops)=561075.250926 +Executable: ./dgemmoptimized 2880 46080 46080 1 0 +m=2880, n=46080, k=46080, time(sec)=22.140268, speed(mflops)=552413.837797 +Executable: ./dgemmoptimized 2880 46080 46080 1 0 +m=2880, n=46080, k=46080, time(sec)=21.791358, speed(mflops)=561258.755298 +Max repetitions 3, Elasped time 344.768, Relative error 0.00763067, Mean 25888.5, Standard Deviation 117.179 +Total Energy 25888.500000 +91 +Executable: ./dgemmoptimized 2912 46080 46080 1 0 +m=2912, n=46080, k=46080, time(sec)=22.811895, speed(mflops)=542106.907033 +Executable: ./dgemmoptimized 2912 46080 46080 1 0 +m=2912, n=46080, k=46080, time(sec)=22.835478, speed(mflops)=541547.061385 +Executable: ./dgemmoptimized 2912 46080 46080 1 0 +m=2912, n=46080, k=46080, time(sec)=22.820030, speed(mflops)=541913.657769 +Max repetitions 3, Elasped time 347.83, Relative error 0.0046554, Mean 26625.3, Standard Deviation 73.5245 +Total Energy 26625.350000 +92 +Executable: ./dgemmoptimized 2944 46080 46080 1 0 +m=2944, n=46080, k=46080, time(sec)=23.683106, speed(mflops)=527902.944484 +Executable: ./dgemmoptimized 2944 46080 46080 1 0 +m=2944, n=46080, k=46080, time(sec)=23.682305, speed(mflops)=527920.796210 +Executable: ./dgemmoptimized 2944 46080 46080 1 0 +m=2944, n=46080, k=46080, time(sec)=23.731430, speed(mflops)=526827.980231 +Max repetitions 3, Elasped time 350.787, Relative error 0.00262498, Mean 26625.2, Standard Deviation 41.457 +Total Energy 26625.166667 +93 +Executable: ./dgemmoptimized 2976 46080 46080 1 0 +m=2976, n=46080, k=46080, time(sec)=24.579252, speed(mflops)=514184.760807 +Executable: ./dgemmoptimized 2976 46080 46080 1 0 +m=2976, n=46080, k=46080, time(sec)=24.698814, speed(mflops)=511695.697460 +Executable: ./dgemmoptimized 2976 46080 46080 1 0 +m=2976, n=46080, k=46080, time(sec)=24.490833, speed(mflops)=516041.115877 +Max repetitions 3, Elasped time 353.763, Relative error 0.00241841, Mean 27233.8, Standard Deviation 39.0679 +Total Energy 27233.850000 +94 +Executable: ./dgemmoptimized 3008 46080 46080 1 0 +m=3008, n=46080, k=46080, time(sec)=25.657216, speed(mflops)=497878.344498 +Executable: ./dgemmoptimized 3008 46080 46080 1 0 +m=3008, n=46080, k=46080, time(sec)=25.725195, speed(mflops)=496562.700366 +Executable: ./dgemmoptimized 3008 46080 46080 1 0 +m=3008, n=46080, k=46080, time(sec)=25.736640, speed(mflops)=496341.879673 +Max repetitions 3, Elasped time 357.405, Relative error 0.00155727, Mean 27272.2, Standard Deviation 25.1921 +Total Energy 27272.200000 +95 +Executable: ./dgemmoptimized 3040 46080 46080 1 0 +m=3040, n=46080, k=46080, time(sec)=24.730133, speed(mflops)=522037.939805 +Executable: ./dgemmoptimized 3040 46080 46080 1 0 +m=3040, n=46080, k=46080, time(sec)=24.732884, speed(mflops)=521979.877010 +Executable: ./dgemmoptimized 3040 46080 46080 1 0 +m=3040, n=46080, k=46080, time(sec)=24.825445, speed(mflops)=520033.684025 +Max repetitions 3, Elasped time 354.959, Relative error 0.00380039, Mean 27267.4, Standard Deviation 61.4684 +Total Energy 27267.433333 +96 +Executable: ./dgemmoptimized 3072 46080 46080 1 0 +m=3072, n=46080, k=46080, time(sec)=22.175628, speed(mflops)=588301.859720 +Executable: ./dgemmoptimized 3072 46080 46080 1 0 +m=3072, n=46080, k=46080, time(sec)=22.198580, speed(mflops)=587693.588777 +Executable: ./dgemmoptimized 3072 46080 46080 1 0 +m=3072, n=46080, k=46080, time(sec)=22.159739, speed(mflops)=588723.682680 +Max repetitions 3, Elasped time 347.47, Relative error 0.00825941, Mean 26607.3, Standard Deviation 130.355 +Total Energy 26607.250000 +97 +Executable: ./dgemmoptimized 3104 46080 46080 1 0 +m=3104, n=46080, k=46080, time(sec)=23.180182, speed(mflops)=568669.332385 +Executable: ./dgemmoptimized 3104 46080 46080 1 0 +m=3104, n=46080, k=46080, time(sec)=23.550941, speed(mflops)=559716.854479 +Executable: ./dgemmoptimized 3104 46080 46080 1 0 +m=3104, n=46080, k=46080, time(sec)=23.171731, speed(mflops)=568876.732340 +Max repetitions 3, Elasped time 351.142, Relative error 0.00276949, Mean 26689.5, Standard Deviation 43.845 +Total Energy 26689.466667 +98 +Executable: ./dgemmoptimized 3136 46080 46080 1 0 +m=3136, n=46080, k=46080, time(sec)=24.065347, speed(mflops)=553399.628312 +Executable: ./dgemmoptimized 3136 46080 46080 1 0 +m=3136, n=46080, k=46080, time(sec)=24.091976, speed(mflops)=552787.947704 +Executable: ./dgemmoptimized 3136 46080 46080 1 0 +m=3136, n=46080, k=46080, time(sec)=24.155455, speed(mflops)=551335.262790 +Max repetitions 3, Elasped time 353.815, Relative error 0.00169447, Mean 27317.7, Standard Deviation 27.4573 +Total Energy 27317.683333 +99 +Executable: ./dgemmoptimized 3168 46080 46080 1 0 +m=3168, n=46080, k=46080, time(sec)=24.957856, speed(mflops)=539054.693412 +Executable: ./dgemmoptimized 3168 46080 46080 1 0 +m=3168, n=46080, k=46080, time(sec)=24.873106, speed(mflops)=540891.415366 +Executable: ./dgemmoptimized 3168 46080 46080 1 0 +m=3168, n=46080, k=46080, time(sec)=24.985820, speed(mflops)=538451.388859 +Max repetitions 3, Elasped time 359.459, Relative error 0.0380464, Mean 27553.6, Standard Deviation 621.831 +Total Energy 27553.616667 +100 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=26.021850, speed(mflops)=522235.924926 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=25.944218, speed(mflops)=523798.592691 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=26.004103, speed(mflops)=522592.333370 +Max repetitions 3, Elasped time 364.164, Relative error 0.0168217, Mean 28279.6, Standard Deviation 282.178 +Total Energy 28279.583333 +101 +Executable: ./dgemmoptimized 3232 46080 46080 1 0 +m=3232, n=46080, k=46080, time(sec)=25.913506, speed(mflops)=529663.581345 +Executable: ./dgemmoptimized 3232 46080 46080 1 0 +m=3232, n=46080, k=46080, time(sec)=25.992257, speed(mflops)=528058.811790 +Executable: ./dgemmoptimized 3232 46080 46080 1 0 +m=3232, n=46080, k=46080, time(sec)=25.939803, speed(mflops)=529126.622290 +Max repetitions 3, Elasped time 361.696, Relative error 0.00682389, Mean 27859.6, Standard Deviation 112.768 +Total Energy 27859.583333 +102 +Executable: ./dgemmoptimized 3264 46080 46080 1 0 +m=3264, n=46080, k=46080, time(sec)=24.975488, speed(mflops)=554997.599581 +Executable: ./dgemmoptimized 3264 46080 46080 1 0 +m=3264, n=46080, k=46080, time(sec)=24.964697, speed(mflops)=555237.498918 +Executable: ./dgemmoptimized 3264 46080 46080 1 0 +m=3264, n=46080, k=46080, time(sec)=24.940962, speed(mflops)=555765.884927 +Max repetitions 3, Elasped time 359.761, Relative error 0.0155086, Mean 27338.6, Standard Deviation 251.494 +Total Energy 27338.616667 +103 +Executable: ./dgemmoptimized 3296 46080 46080 1 0 +m=3296, n=46080, k=46080, time(sec)=25.949832, speed(mflops)=539395.836126 +Executable: ./dgemmoptimized 3296 46080 46080 1 0 +m=3296, n=46080, k=46080, time(sec)=25.956175, speed(mflops)=539264.024435 +Executable: ./dgemmoptimized 3296 46080 46080 1 0 +m=3296, n=46080, k=46080, time(sec)=25.949475, speed(mflops)=539403.255050 +Max repetitions 3, Elasped time 363.78, Relative error 0.0147678, Mean 28043.5, Standard Deviation 245.656 +Total Energy 28043.533333 +104 +Executable: ./dgemmoptimized 3328 46080 46080 1 0 +m=3328, n=46080, k=46080, time(sec)=26.839747, speed(mflops)=526574.515909 +Executable: ./dgemmoptimized 3328 46080 46080 1 0 +m=3328, n=46080, k=46080, time(sec)=26.865069, speed(mflops)=526078.187420 +Executable: ./dgemmoptimized 3328 46080 46080 1 0 +m=3328, n=46080, k=46080, time(sec)=26.829844, speed(mflops)=526768.875715 +Max repetitions 3, Elasped time 364.223, Relative error 0.0312758, Mean 28270.8, Standard Deviation 524.476 +Total Energy 28270.750000 +105 +Executable: ./dgemmoptimized 3360 46080 46080 1 0 +m=3360, n=46080, k=46080, time(sec)=27.641886, speed(mflops)=516210.153321 +Executable: ./dgemmoptimized 3360 46080 46080 1 0 +m=3360, n=46080, k=46080, time(sec)=27.683883, speed(mflops)=515427.048655 +Executable: ./dgemmoptimized 3360 46080 46080 1 0 +m=3360, n=46080, k=46080, time(sec)=27.959144, speed(mflops)=510352.615615 +Max repetitions 3, Elasped time 367.056, Relative error 0.00164983, Mean 28431.8, Standard Deviation 27.8243 +Total Energy 28431.783333 +106 +Executable: ./dgemmoptimized 3392 46080 46080 1 0 +m=3392, n=46080, k=46080, time(sec)=28.664494, speed(mflops)=502535.214426 +Executable: ./dgemmoptimized 3392 46080 46080 1 0 +m=3392, n=46080, k=46080, time(sec)=28.652787, speed(mflops)=502740.542224 +Executable: ./dgemmoptimized 3392 46080 46080 1 0 +m=3392, n=46080, k=46080, time(sec)=28.661685, speed(mflops)=502584.466428 +Max repetitions 3, Elasped time 371.978, Relative error 0.0145512, Mean 28673, Standard Deviation 247.487 +Total Energy 28673.016667 +107 +Executable: ./dgemmoptimized 3424 46080 46080 1 0 +m=3424, n=46080, k=46080, time(sec)=27.285110, speed(mflops)=532921.183345 +Executable: ./dgemmoptimized 3424 46080 46080 1 0 +m=3424, n=46080, k=46080, time(sec)=27.292099, speed(mflops)=532784.707424 +Executable: ./dgemmoptimized 3424 46080 46080 1 0 +m=3424, n=46080, k=46080, time(sec)=27.310979, speed(mflops)=532416.397051 +Max repetitions 3, Elasped time 370.925, Relative error 0.0267017, Mean 28722.8, Standard Deviation 454.931 +Total Energy 28722.750000 +108 +Executable: ./dgemmoptimized 3456 46080 46080 1 0 +m=3456, n=46080, k=46080, time(sec)=23.466542, speed(mflops)=625431.243910 +Executable: ./dgemmoptimized 3456 46080 46080 1 0 +m=3456, n=46080, k=46080, time(sec)=23.449387, speed(mflops)=625888.792350 +Executable: ./dgemmoptimized 3456 46080 46080 1 0 +m=3456, n=46080, k=46080, time(sec)=23.474705, speed(mflops)=625213.759609 +Max repetitions 3, Elasped time 357.015, Relative error 0.0203327, Mean 27278, Standard Deviation 328.992 +Total Energy 27277.950000 +109 +Executable: ./dgemmoptimized 3488 46080 46080 1 0 +m=3488, n=46080, k=46080, time(sec)=24.534339, speed(mflops)=603749.872206 +Executable: ./dgemmoptimized 3488 46080 46080 1 0 +m=3488, n=46080, k=46080, time(sec)=25.597387, speed(mflops)=578676.407977 +Executable: ./dgemmoptimized 3488 46080 46080 1 0 +m=3488, n=46080, k=46080, time(sec)=24.522149, speed(mflops)=604049.993924 +Max repetitions 3, Elasped time 366.395, Relative error 0.0289756, Mean 28114.9, Standard Deviation 483.224 +Total Energy 28114.916667 +110 +Executable: ./dgemmoptimized 3520 46080 46080 1 0 +m=3520, n=46080, k=46080, time(sec)=25.439340, speed(mflops)=587613.491099 +Executable: ./dgemmoptimized 3520 46080 46080 1 0 +m=3520, n=46080, k=46080, time(sec)=25.454941, speed(mflops)=587253.352339 +Executable: ./dgemmoptimized 3520 46080 46080 1 0 +m=3520, n=46080, k=46080, time(sec)=25.443209, speed(mflops)=587524.140349 +Max repetitions 3, Elasped time 361.703, Relative error 0.0104268, Mean 27829.7, Standard Deviation 172.122 +Total Energy 27829.683333 +111 +Executable: ./dgemmoptimized 3552 46080 46080 1 0 +m=3552, n=46080, k=46080, time(sec)=26.260201, speed(mflops)=574420.385498 +Executable: ./dgemmoptimized 3552 46080 46080 1 0 +m=3552, n=46080, k=46080, time(sec)=26.488258, speed(mflops)=569474.777667 +Executable: ./dgemmoptimized 3552 46080 46080 1 0 +m=3552, n=46080, k=46080, time(sec)=26.227779, speed(mflops)=575130.468322 +Max repetitions 3, Elasped time 366.685, Relative error 0.0186981, Mean 28365.3, Standard Deviation 314.605 +Total Energy 28365.316667 +112 +Executable: ./dgemmoptimized 3584 46080 46080 1 0 +m=3584, n=46080, k=46080, time(sec)=27.235411, speed(mflops)=558841.957444 +Executable: ./dgemmoptimized 3584 46080 46080 1 0 +m=3584, n=46080, k=46080, time(sec)=27.257944, speed(mflops)=558379.987447 +Executable: ./dgemmoptimized 3584 46080 46080 1 0 +m=3584, n=46080, k=46080, time(sec)=27.250220, speed(mflops)=558538.254792 +Max repetitions 3, Elasped time 369.592, Relative error 0.0170905, Mean 28559.8, Standard Deviation 289.528 +Total Energy 28559.783333 +113 +Executable: ./dgemmoptimized 3616 46080 46080 1 0 +m=3616, n=46080, k=46080, time(sec)=27.618108, speed(mflops)=556018.746317 +Executable: ./dgemmoptimized 3616 46080 46080 1 0 +m=3616, n=46080, k=46080, time(sec)=27.247216, speed(mflops)=563587.333566 +Executable: ./dgemmoptimized 3616 46080 46080 1 0 +m=3616, n=46080, k=46080, time(sec)=27.315393, speed(mflops)=562180.665718 +Max repetitions 3, Elasped time 368.38, Relative error 0.00839047, Mean 28485.2, Standard Deviation 141.77 +Total Energy 28485.166667 +114 +Executable: ./dgemmoptimized 3648 46080 46080 1 0 +m=3648, n=46080, k=46080, time(sec)=26.291122, speed(mflops)=589251.431649 +Executable: ./dgemmoptimized 3648 46080 46080 1 0 +m=3648, n=46080, k=46080, time(sec)=26.305352, speed(mflops)=588932.673113 +Executable: ./dgemmoptimized 3648 46080 46080 1 0 +m=3648, n=46080, k=46080, time(sec)=26.327504, speed(mflops)=588437.145493 +Max repetitions 3, Elasped time 365.582, Relative error 0.00528983, Mean 28510.2, Standard Deviation 89.4586 +Total Energy 28510.233333 +115 +Executable: ./dgemmoptimized 3680 46080 46080 1 0 +m=3680, n=46080, k=46080, time(sec)=27.313763, speed(mflops)=572164.910393 +Executable: ./dgemmoptimized 3680 46080 46080 1 0 +m=3680, n=46080, k=46080, time(sec)=27.316357, speed(mflops)=572110.571930 +Executable: ./dgemmoptimized 3680 46080 46080 1 0 +m=3680, n=46080, k=46080, time(sec)=27.331245, speed(mflops)=571798.928253 +Max repetitions 3, Elasped time 370.905, Relative error 0.00877827, Mean 28538.3, Standard Deviation 148.599 +Total Energy 28538.283333 +116 +Executable: ./dgemmoptimized 3712 46080 46080 1 0 +m=3712, n=46080, k=46080, time(sec)=28.236557, speed(mflops)=558278.835121 +Executable: ./dgemmoptimized 3712 46080 46080 1 0 +m=3712, n=46080, k=46080, time(sec)=28.371055, speed(mflops)=555632.213306 +Executable: ./dgemmoptimized 3712 46080 46080 1 0 +m=3712, n=46080, k=46080, time(sec)=28.243248, speed(mflops)=558146.575830 +Max repetitions 3, Elasped time 372.093, Relative error 0.00216076, Mean 29079, Standard Deviation 37.2705 +Total Energy 29078.983333 +117 +Executable: ./dgemmoptimized 3744 46080 46080 1 0 +m=3744, n=46080, k=46080, time(sec)=29.066060, speed(mflops)=547021.769272 +Executable: ./dgemmoptimized 3744 46080 46080 1 0 +m=3744, n=46080, k=46080, time(sec)=29.011613, speed(mflops)=548048.385393 +Executable: ./dgemmoptimized 3744 46080 46080 1 0 +m=3744, n=46080, k=46080, time(sec)=29.083390, speed(mflops)=546695.815191 +Max repetitions 3, Elasped time 376.732, Relative error 0.0133059, Mean 29216, Standard Deviation 230.592 +Total Energy 29215.966667 +118 +Executable: ./dgemmoptimized 3776 46080 46080 1 0 +m=3776, n=46080, k=46080, time(sec)=30.053329, speed(mflops)=533573.603697 +Executable: ./dgemmoptimized 3776 46080 46080 1 0 +m=3776, n=46080, k=46080, time(sec)=30.011924, speed(mflops)=534309.730947 +Executable: ./dgemmoptimized 3776 46080 46080 1 0 +m=3776, n=46080, k=46080, time(sec)=30.022192, speed(mflops)=534126.990197 +Max repetitions 3, Elasped time 381.959, Relative error 0.0168722, Mean 29961.2, Standard Deviation 299.855 +Total Energy 29961.216667 +119 +Executable: ./dgemmoptimized 3808 46080 46080 1 0 +m=3808, n=46080, k=46080, time(sec)=29.229891, speed(mflops)=553254.153432 +Executable: ./dgemmoptimized 3808 46080 46080 1 0 +m=3808, n=46080, k=46080, time(sec)=29.379702, speed(mflops)=550433.032037 +Executable: ./dgemmoptimized 3808 46080 46080 1 0 +m=3808, n=46080, k=46080, time(sec)=29.281834, speed(mflops)=552272.735538 +Max repetitions 3, Elasped time 380.947, Relative error 0.0328636, Mean 29520.3, Standard Deviation 575.461 +Total Energy 29520.283333 +120 +Executable: ./dgemmoptimized 3840 46080 46080 1 0 +m=3840, n=46080, k=46080, time(sec)=26.648109, speed(mflops)=611955.386068 +Executable: ./dgemmoptimized 3840 46080 46080 1 0 +m=3840, n=46080, k=46080, time(sec)=26.615666, speed(mflops)=612701.331822 +Executable: ./dgemmoptimized 3840 46080 46080 1 0 +m=3840, n=46080, k=46080, time(sec)=26.646261, speed(mflops)=611997.826648 +Max repetitions 3, Elasped time 370.338, Relative error 0.010757, Mean 28558.7, Standard Deviation 182.225 +Total Energy 28558.750000 +121 +Executable: ./dgemmoptimized 3872 46080 46080 1 0 +m=3872, n=46080, k=46080, time(sec)=27.672768, speed(mflops)=594206.887171 +Executable: ./dgemmoptimized 3872 46080 46080 1 0 +m=3872, n=46080, k=46080, time(sec)=27.672078, speed(mflops)=594221.703292 +Executable: ./dgemmoptimized 3872 46080 46080 1 0 +m=3872, n=46080, k=46080, time(sec)=27.686895, speed(mflops)=593903.702989 +Max repetitions 3, Elasped time 373.854, Relative error 0.0103925, Mean 29283.5, Standard Deviation 180.519 +Total Energy 29283.533333 +122 +Executable: ./dgemmoptimized 3904 46080 46080 1 0 +m=3904, n=46080, k=46080, time(sec)=28.598625, speed(mflops)=579721.748275 +Executable: ./dgemmoptimized 3904 46080 46080 1 0 +m=3904, n=46080, k=46080, time(sec)=30.037944, speed(mflops)=551943.395590 +Executable: ./dgemmoptimized 3904 46080 46080 1 0 +m=3904, n=46080, k=46080, time(sec)=28.603353, speed(mflops)=579625.921393 +Max repetitions 3, Elasped time 376.419, Relative error 0.0259074, Mean 29338, Standard Deviation 450.852 +Total Energy 29338.033333 +123 +Executable: ./dgemmoptimized 3936 46080 46080 1 0 +m=3936, n=46080, k=46080, time(sec)=29.464214, speed(mflops)=567303.115127 +Executable: ./dgemmoptimized 3936 46080 46080 1 0 +m=3936, n=46080, k=46080, time(sec)=29.461593, speed(mflops)=567353.583031 +Executable: ./dgemmoptimized 3936 46080 46080 1 0 +m=3936, n=46080, k=46080, time(sec)=29.353778, speed(mflops)=569437.441077 +Max repetitions 3, Elasped time 377.748, Relative error 0.00203705, Mean 29717.7, Standard Deviation 35.9085 +Total Energy 29717.733333 +124 +Executable: ./dgemmoptimized 3968 46080 46080 1 0 +m=3968, n=46080, k=46080, time(sec)=30.391727, speed(mflops)=554461.277132 +Executable: ./dgemmoptimized 3968 46080 46080 1 0 +m=3968, n=46080, k=46080, time(sec)=33.323737, speed(mflops)=505676.653189 +Executable: ./dgemmoptimized 3968 46080 46080 1 0 +m=3968, n=46080, k=46080, time(sec)=30.409236, speed(mflops)=554142.025917 +Max repetitions 3, Elasped time 383.953, Relative error 0.0423306, Mean 30126.7, Standard Deviation 756.46 +Total Energy 30126.733333 +125 +Executable: ./dgemmoptimized 4000 46080 46080 1 0 +m=4000, n=46080, k=46080, time(sec)=30.421011, speed(mflops)=558394.696881 +Executable: ./dgemmoptimized 4000 46080 46080 1 0 +m=4000, n=46080, k=46080, time(sec)=30.405059, speed(mflops)=558687.656044 +Executable: ./dgemmoptimized 4000 46080 46080 1 0 +m=4000, n=46080, k=46080, time(sec)=30.461414, speed(mflops)=557654.058506 +Max repetitions 3, Elasped time 383.377, Relative error 0.0181163, Mean 29861, Standard Deviation 320.888 +Total Energy 29860.983333 +126 +Executable: ./dgemmoptimized 4032 46080 46080 1 0 +m=4032, n=46080, k=46080, time(sec)=29.443750, speed(mflops)=581543.679221 +Executable: ./dgemmoptimized 4032 46080 46080 1 0 +m=4032, n=46080, k=46080, time(sec)=29.449013, speed(mflops)=581439.746474 +Executable: ./dgemmoptimized 4032 46080 46080 1 0 +m=4032, n=46080, k=46080, time(sec)=29.418429, speed(mflops)=582044.225035 +Max repetitions 3, Elasped time 378.724, Relative error 0.00145782, Mean 29790.5, Standard Deviation 25.7609 +Total Energy 29790.466667 +127 +Executable: ./dgemmoptimized 4064 46080 46080 1 0 +m=4064, n=46080, k=46080, time(sec)=30.466051, speed(mflops)=566490.293627 +Executable: ./dgemmoptimized 4064 46080 46080 1 0 +m=4064, n=46080, k=46080, time(sec)=30.515517, speed(mflops)=565572.003950 +Executable: ./dgemmoptimized 4064 46080 46080 1 0 +m=4064, n=46080, k=46080, time(sec)=30.484900, speed(mflops)=566140.026718 +Max repetitions 3, Elasped time 382.165, Relative error 0.00786031, Mean 29777.4, Standard Deviation 138.837 +Total Energy 29777.400000 +128 +Executable: ./dgemmoptimized 4096 46080 46080 1 0 +m=4096, n=46080, k=46080, time(sec)=31.344382, speed(mflops)=554951.686547 +Executable: ./dgemmoptimized 4096 46080 46080 1 0 +m=4096, n=46080, k=46080, time(sec)=31.371099, speed(mflops)=554479.062128 +Executable: ./dgemmoptimized 4096 46080 46080 1 0 +m=4096, n=46080, k=46080, time(sec)=31.386053, speed(mflops)=554214.881165 +Max repetitions 3, Elasped time 385.159, Relative error 0.00517036, Mean 30388.9, Standard Deviation 93.2 +Total Energy 30388.900000 +129 +Executable: ./dgemmoptimized 4128 46080 46080 1 0 +m=4128, n=46080, k=46080, time(sec)=32.187953, speed(mflops)=544629.632116 +Executable: ./dgemmoptimized 4128 46080 46080 1 0 +m=4128, n=46080, k=46080, time(sec)=32.189992, speed(mflops)=544595.134571 +Executable: ./dgemmoptimized 4128 46080 46080 1 0 +m=4128, n=46080, k=46080, time(sec)=32.162464, speed(mflops)=545061.252803 +Max repetitions 3, Elasped time 391.866, Relative error 0.016058, Mean 30724, Standard Deviation 292.649 +Total Energy 30723.966667 +130 +Executable: ./dgemmoptimized 4160 46080 46080 1 0 +m=4160, n=46080, k=46080, time(sec)=33.188330, speed(mflops)=532307.846841 +Executable: ./dgemmoptimized 4160 46080 46080 1 0 +m=4160, n=46080, k=46080, time(sec)=33.223777, speed(mflops)=531739.920634 +Executable: ./dgemmoptimized 4160 46080 46080 1 0 +m=4160, n=46080, k=46080, time(sec)=33.231582, speed(mflops)=531615.026947 +Max repetitions 3, Elasped time 391.291, Relative error 0.00420108, Mean 31107.8, Standard Deviation 77.5193 +Total Energy 31107.750000 +131 +Executable: ./dgemmoptimized 4192 46080 46080 1 0 +m=4192, n=46080, k=46080, time(sec)=32.573951, speed(mflops)=546519.637558 +Executable: ./dgemmoptimized 4192 46080 46080 1 0 +m=4192, n=46080, k=46080, time(sec)=32.422603, speed(mflops)=549070.777138 +Executable: ./dgemmoptimized 4192 46080 46080 1 0 +m=4192, n=46080, k=46080, time(sec)=32.385135, speed(mflops)=549706.024139 +Max repetitions 3, Elasped time 389.439, Relative error 0.00719752, Mean 31196.5, Standard Deviation 133.189 +Total Energy 31196.516667 +132 +Executable: ./dgemmoptimized 4224 46080 46080 1 0 +m=4224, n=46080, k=46080, time(sec)=29.798856, speed(mflops)=601976.107243 +Executable: ./dgemmoptimized 4224 46080 46080 1 0 +m=4224, n=46080, k=46080, time(sec)=31.664473, speed(mflops)=566508.700464 +Executable: ./dgemmoptimized 4224 46080 46080 1 0 +m=4224, n=46080, k=46080, time(sec)=29.790007, speed(mflops)=602154.924699 +Max repetitions 3, Elasped time 387.396, Relative error 0.00463861, Mean 30335.3, Standard Deviation 83.4671 +Total Energy 30335.250000 +133 +Executable: ./dgemmoptimized 4256 46080 46080 1 0 +m=4256, n=46080, k=46080, time(sec)=30.837476, speed(mflops)=586108.110403 +Executable: ./dgemmoptimized 4256 46080 46080 1 0 +m=4256, n=46080, k=46080, time(sec)=30.846355, speed(mflops)=585939.398017 +Executable: ./dgemmoptimized 4256 46080 46080 1 0 +m=4256, n=46080, k=46080, time(sec)=30.846767, speed(mflops)=585931.576779 +Max repetitions 3, Elasped time 385.086, Relative error 0.00790279, Mean 30532.2, Standard Deviation 143.126 +Total Energy 30532.216667 +134 +Executable: ./dgemmoptimized 4288 46080 46080 1 0 +m=4288, n=46080, k=46080, time(sec)=31.741217, speed(mflops)=573701.700478 +Executable: ./dgemmoptimized 4288 46080 46080 1 0 +m=4288, n=46080, k=46080, time(sec)=32.345126, speed(mflops)=562990.241405 +Executable: ./dgemmoptimized 4288 46080 46080 1 0 +m=4288, n=46080, k=46080, time(sec)=31.751867, speed(mflops)=573509.274725 +Max repetitions 3, Elasped time 390.71, Relative error 0.0207431, Mean 30815.7, Standard Deviation 379.162 +Total Energy 30815.716667 +135 +Executable: ./dgemmoptimized 4320 46080 46080 1 0 +m=4320, n=46080, k=46080, time(sec)=32.584811, speed(mflops)=563019.552627 +Executable: ./dgemmoptimized 4320 46080 46080 1 0 +m=4320, n=46080, k=46080, time(sec)=32.558565, speed(mflops)=563473.409140 +Executable: ./dgemmoptimized 4320 46080 46080 1 0 +m=4320, n=46080, k=46080, time(sec)=33.110097, speed(mflops)=554087.344836 +Max repetitions 3, Elasped time 391.5, Relative error 0.00589205, Mean 31110.6, Standard Deviation 108.731 +Total Energy 31110.600000 +136 +Executable: ./dgemmoptimized 4352 46080 46080 1 0 +m=4352, n=46080, k=46080, time(sec)=33.547925, speed(mflops)=550906.833973 +Executable: ./dgemmoptimized 4352 46080 46080 1 0 +m=4352, n=46080, k=46080, time(sec)=33.592497, speed(mflops)=550175.864714 +Executable: ./dgemmoptimized 4352 46080 46080 1 0 +m=4352, n=46080, k=46080, time(sec)=33.574275, speed(mflops)=550474.467025 +Max repetitions 3, Elasped time 396.25, Relative error 0.00965081, Mean 31273.7, Standard Deviation 179.029 +Total Energy 31273.700000 +137 +Executable: ./dgemmoptimized 4384 46080 46080 1 0 +m=4384, n=46080, k=46080, time(sec)=33.572300, speed(mflops)=554554.695952 +Executable: ./dgemmoptimized 4384 46080 46080 1 0 +m=4384, n=46080, k=46080, time(sec)=33.588231, speed(mflops)=554291.670772 +Executable: ./dgemmoptimized 4384 46080 46080 1 0 +m=4384, n=46080, k=46080, time(sec)=33.585840, speed(mflops)=554331.128908 +Max repetitions 3, Elasped time 396.69, Relative error 0.0128201, Mean 31537.1, Standard Deviation 239.823 +Total Energy 31537.100000 +138 +Executable: ./dgemmoptimized 4416 46080 46080 1 0 +m=4416, n=46080, k=46080, time(sec)=32.594442, speed(mflops)=575361.041851 +Executable: ./dgemmoptimized 4416 46080 46080 1 0 +m=4416, n=46080, k=46080, time(sec)=32.569632, speed(mflops)=575799.321714 +Executable: ./dgemmoptimized 4416 46080 46080 1 0 +m=4416, n=46080, k=46080, time(sec)=32.615137, speed(mflops)=574995.959305 +Max repetitions 3, Elasped time 392.025, Relative error 0.00145861, Mean 31097, Standard Deviation 26.9052 +Total Energy 31096.966667 +139 +Executable: ./dgemmoptimized 4448 46080 46080 1 0 +m=4448, n=46080, k=46080, time(sec)=33.883116, speed(mflops)=557489.089568 +Executable: ./dgemmoptimized 4448 46080 46080 1 0 +m=4448, n=46080, k=46080, time(sec)=33.622190, speed(mflops)=561815.500274 +Executable: ./dgemmoptimized 4448 46080 46080 1 0 +m=4448, n=46080, k=46080, time(sec)=33.623063, speed(mflops)=561800.915616 +Max repetitions 3, Elasped time 395.664, Relative error 0.00560767, Mean 31986.6, Standard Deviation 106.397 +Total Energy 31986.616667 +140 +Executable: ./dgemmoptimized 4480 46080 46080 1 0 +m=4480, n=46080, k=46080, time(sec)=34.517340, speed(mflops)=551182.767108 +Executable: ./dgemmoptimized 4480 46080 46080 1 0 +m=4480, n=46080, k=46080, time(sec)=34.628419, speed(mflops)=549414.712108 +Executable: ./dgemmoptimized 4480 46080 46080 1 0 +m=4480, n=46080, k=46080, time(sec)=34.509918, speed(mflops)=551301.308745 +Max repetitions 3, Elasped time 400.398, Relative error 0.0126855, Mean 32183.4, Standard Deviation 242.17 +Total Energy 32183.416667 +141 +Executable: ./dgemmoptimized 4512 46080 46080 1 0 +m=4512, n=46080, k=46080, time(sec)=35.334435, speed(mflops)=542282.858099 +Executable: ./dgemmoptimized 4512 46080 46080 1 0 +m=4512, n=46080, k=46080, time(sec)=35.339084, speed(mflops)=542211.519755 +Executable: ./dgemmoptimized 4512 46080 46080 1 0 +m=4512, n=46080, k=46080, time(sec)=35.641139, speed(mflops)=537616.330871 +Max repetitions 3, Elasped time 401.484, Relative error 0.00443738, Mean 32654.4, Standard Deviation 85.9505 +Total Energy 32654.400000 +142 +Executable: ./dgemmoptimized 4544 46080 46080 1 0 +m=4544, n=46080, k=46080, time(sec)=36.394565, speed(mflops)=530220.756514 +Executable: ./dgemmoptimized 4544 46080 46080 1 0 +m=4544, n=46080, k=46080, time(sec)=36.341586, speed(mflops)=530993.715663 +Executable: ./dgemmoptimized 4544 46080 46080 1 0 +m=4544, n=46080, k=46080, time(sec)=36.324295, speed(mflops)=531246.482458 +Max repetitions 3, Elasped time 404.516, Relative error 0.0165902, Mean 32583.2, Standard Deviation 320.646 +Total Energy 32583.216667 +143 +Executable: ./dgemmoptimized 4576 46080 46080 1 0 +m=4576, n=46080, k=46080, time(sec)=34.948800, speed(mflops)=556043.394251 +Executable: ./dgemmoptimized 4576 46080 46080 1 0 +m=4576, n=46080, k=46080, time(sec)=34.920024, speed(mflops)=556501.603159 +Executable: ./dgemmoptimized 4576 46080 46080 1 0 +m=4576, n=46080, k=46080, time(sec)=34.937372, speed(mflops)=556225.273896 +Max repetitions 3, Elasped time 400.489, Relative error 0.0130122, Mean 31969.3, Standard Deviation 246.755 +Total Energy 31969.350000 +144 +Executable: ./dgemmoptimized 4608 46080 46080 1 0 +m=4608, n=46080, k=46080, time(sec)=31.136386, speed(mflops)=628491.206210 +Executable: ./dgemmoptimized 4608 46080 46080 1 0 +m=4608, n=46080, k=46080, time(sec)=31.140053, speed(mflops)=628417.193803 +Executable: ./dgemmoptimized 4608 46080 46080 1 0 +m=4608, n=46080, k=46080, time(sec)=31.132274, speed(mflops)=628574.218428 +Max repetitions 3, Elasped time 391.339, Relative error 0.0195718, Mean 31286.6, Standard Deviation 363.219 +Total Energy 31286.600000 +145 +Executable: ./dgemmoptimized 4640 46080 46080 1 0 +m=4640, n=46080, k=46080, time(sec)=32.186494, speed(mflops)=612208.341903 +Executable: ./dgemmoptimized 4640 46080 46080 1 0 +m=4640, n=46080, k=46080, time(sec)=32.147939, speed(mflops)=612942.565692 +Executable: ./dgemmoptimized 4640 46080 46080 1 0 +m=4640, n=46080, k=46080, time(sec)=32.144789, speed(mflops)=613002.625645 +Max repetitions 3, Elasped time 394.903, Relative error 0.00786396, Mean 31305.3, Standard Deviation 146.029 +Total Energy 31305.283333 +146 +Executable: ./dgemmoptimized 4672 46080 46080 1 0 +m=4672, n=46080, k=46080, time(sec)=33.080425, speed(mflops)=599772.694190 +Executable: ./dgemmoptimized 4672 46080 46080 1 0 +m=4672, n=46080, k=46080, time(sec)=33.072620, speed(mflops)=599914.235690 +Executable: ./dgemmoptimized 4672 46080 46080 1 0 +m=4672, n=46080, k=46080, time(sec)=33.057505, speed(mflops)=600188.537009 +Max repetitions 3, Elasped time 399.744, Relative error 0.0161839, Mean 32118.5, Standard Deviation 308.331 +Total Energy 32118.516667 +147 +Executable: ./dgemmoptimized 4704 46080 46080 1 0 +m=4704, n=46080, k=46080, time(sec)=33.902483, speed(mflops)=589237.994727 +Executable: ./dgemmoptimized 4704 46080 46080 1 0 +m=4704, n=46080, k=46080, time(sec)=33.906679, speed(mflops)=589165.076924 +Executable: ./dgemmoptimized 4704 46080 46080 1 0 +m=4704, n=46080, k=46080, time(sec)=33.862261, speed(mflops)=589937.901615 +Max repetitions 3, Elasped time 404.218, Relative error 0.00358575, Mean 32121.9, Standard Deviation 68.3222 +Total Energy 32121.916667 +148 +Executable: ./dgemmoptimized 4736 46080 46080 1 0 +m=4736, n=46080, k=46080, time(sec)=34.899315, speed(mflops)=576301.472099 +Executable: ./dgemmoptimized 4736 46080 46080 1 0 +m=4736, n=46080, k=46080, time(sec)=34.931595, speed(mflops)=575768.913234 +Executable: ./dgemmoptimized 4736 46080 46080 1 0 +m=4736, n=46080, k=46080, time(sec)=34.909065, speed(mflops)=576140.510670 +Max repetitions 3, Elasped time 406.759, Relative error 0.0258409, Mean 32619.9, Standard Deviation 499.999 +Total Energy 32619.900000 +149 +Executable: ./dgemmoptimized 4768 46080 46080 1 0 +m=4768, n=46080, k=46080, time(sec)=34.909075, speed(mflops)=580033.185577 +Executable: ./dgemmoptimized 4768 46080 46080 1 0 +m=4768, n=46080, k=46080, time(sec)=34.937590, speed(mflops)=579559.778438 +Executable: ./dgemmoptimized 4768 46080 46080 1 0 +m=4768, n=46080, k=46080, time(sec)=35.370616, speed(mflops)=572464.500301 +Max repetitions 3, Elasped time 404.823, Relative error 0.011191, Mean 32614.8, Standard Deviation 216.503 +Total Energy 32614.800000 +150 +Executable: ./dgemmoptimized 4800 46080 46080 1 0 +m=4800, n=46080, k=46080, time(sec)=33.927628, speed(mflops)=600817.640885 +Executable: ./dgemmoptimized 4800 46080 46080 1 0 +m=4800, n=46080, k=46080, time(sec)=33.922453, speed(mflops)=600909.299928 +Executable: ./dgemmoptimized 4800 46080 46080 1 0 +m=4800, n=46080, k=46080, time(sec)=33.945411, speed(mflops)=600502.891536 +Max repetitions 3, Elasped time 399.828, Relative error 0.00217149, Mean 31610.7, Standard Deviation 40.7166 +Total Energy 31610.683333 +151 +Executable: ./dgemmoptimized 4832 46080 46080 1 0 +m=4832, n=46080, k=46080, time(sec)=35.168923, speed(mflops)=583475.727911 +Executable: ./dgemmoptimized 4832 46080 46080 1 0 +m=4832, n=46080, k=46080, time(sec)=34.940141, speed(mflops)=587296.221030 +Executable: ./dgemmoptimized 4832 46080 46080 1 0 +m=4832, n=46080, k=46080, time(sec)=35.220514, speed(mflops)=582621.050198 +Max repetitions 3, Elasped time 403.664, Relative error 0.00549639, Mean 32371.6, Standard Deviation 105.541 +Total Energy 32371.583333 +152 +Executable: ./dgemmoptimized 4864 46080 46080 1 0 +m=4864, n=46080, k=46080, time(sec)=35.906958, speed(mflops)=575267.568392 +Executable: ./dgemmoptimized 4864 46080 46080 1 0 +m=4864, n=46080, k=46080, time(sec)=35.852928, speed(mflops)=576134.489865 +Executable: ./dgemmoptimized 4864 46080 46080 1 0 +m=4864, n=46080, k=46080, time(sec)=35.853681, speed(mflops)=576122.387233 +Max repetitions 3, Elasped time 408.136, Relative error 0.016309, Mean 32484.6, Standard Deviation 314.256 +Total Energy 32484.566667 +153 +Executable: ./dgemmoptimized 4896 46080 46080 1 0 +m=4896, n=46080, k=46080, time(sec)=36.667195, speed(mflops)=567046.476898 +Executable: ./dgemmoptimized 4896 46080 46080 1 0 +m=4896, n=46080, k=46080, time(sec)=37.241560, speed(mflops)=558301.096911 +Executable: ./dgemmoptimized 4896 46080 46080 1 0 +m=4896, n=46080, k=46080, time(sec)=36.626577, speed(mflops)=567675.320718 +Max repetitions 3, Elasped time 409.456, Relative error 0.00146143, Mean 33004.9, Standard Deviation 28.6112 +Total Energy 33004.916667 +154 +Executable: ./dgemmoptimized 4928 46080 46080 1 0 +m=4928, n=46080, k=46080, time(sec)=37.655128, speed(mflops)=555778.199378 +Executable: ./dgemmoptimized 4928 46080 46080 1 0 +m=4928, n=46080, k=46080, time(sec)=37.690518, speed(mflops)=555256.345710 +Executable: ./dgemmoptimized 4928 46080 46080 1 0 +m=4928, n=46080, k=46080, time(sec)=37.635751, speed(mflops)=556064.345133 +Max repetitions 3, Elasped time 419.148, Relative error 0.0408783, Mean 33594.1, Standard Deviation 814.583 +Total Energy 33594.083333 +155 +Executable: ./dgemmoptimized 4960 46080 46080 1 0 +m=4960, n=46080, k=46080, time(sec)=36.908955, speed(mflops)=570696.044701 +Executable: ./dgemmoptimized 4960 46080 46080 1 0 +m=4960, n=46080, k=46080, time(sec)=36.895916, speed(mflops)=570897.730158 +Executable: ./dgemmoptimized 4960 46080 46080 1 0 +m=4960, n=46080, k=46080, time(sec)=36.868875, speed(mflops)=571316.447077 +Max repetitions 3, Elasped time 410.266, Relative error 0.00205014, Mean 32993.3, Standard Deviation 40.1226 +Total Energy 32993.316667 +156 +Executable: ./dgemmoptimized 4992 46080 46080 1 0 +m=4992, n=46080, k=46080, time(sec)=34.273707, speed(mflops)=618540.918011 +Executable: ./dgemmoptimized 4992 46080 46080 1 0 +m=4992, n=46080, k=46080, time(sec)=34.260670, speed(mflops)=618776.286938 +Executable: ./dgemmoptimized 4992 46080 46080 1 0 +m=4992, n=46080, k=46080, time(sec)=34.289543, speed(mflops)=618255.256161 +Max repetitions 3, Elasped time 402.669, Relative error 0.00523903, Mean 32457, Standard Deviation 100.865 +Total Energy 32457.033333 +157 +Executable: ./dgemmoptimized 5024 46080 46080 1 0 +m=5024, n=46080, k=46080, time(sec)=35.306874, speed(mflops)=604289.849194 +Executable: ./dgemmoptimized 5024 46080 46080 1 0 +m=5024, n=46080, k=46080, time(sec)=35.325249, speed(mflops)=603975.519419 +Executable: ./dgemmoptimized 5024 46080 46080 1 0 +m=5024, n=46080, k=46080, time(sec)=35.316174, speed(mflops)=604130.718375 +Max repetitions 3, Elasped time 408.143, Relative error 0.00987547, Mean 32524.1, Standard Deviation 190.521 +Total Energy 32524.050000 +158 +Executable: ./dgemmoptimized 5056 46080 46080 1 0 +m=5056, n=46080, k=46080, time(sec)=36.222956, speed(mflops)=592758.941901 +Executable: ./dgemmoptimized 5056 46080 46080 1 0 +m=5056, n=46080, k=46080, time(sec)=36.205557, speed(mflops)=593043.800270 +Executable: ./dgemmoptimized 5056 46080 46080 1 0 +m=5056, n=46080, k=46080, time(sec)=36.231968, speed(mflops)=592611.500964 +Max repetitions 3, Elasped time 409.174, Relative error 0.00173351, Mean 33009.1, Standard Deviation 33.9423 +Total Energy 33009.100000 +159 +Executable: ./dgemmoptimized 5088 46080 46080 1 0 +m=5088, n=46080, k=46080, time(sec)=37.026194, speed(mflops)=583570.014508 +Executable: ./dgemmoptimized 5088 46080 46080 1 0 +m=5088, n=46080, k=46080, time(sec)=36.981809, speed(mflops)=584270.405602 +Executable: ./dgemmoptimized 5088 46080 46080 1 0 +m=5088, n=46080, k=46080, time(sec)=37.011487, speed(mflops)=583801.901346 +Max repetitions 3, Elasped time 411.833, Relative error 0.000294185, Mean 32904.8, Standard Deviation 5.74195 +Total Energy 32904.750000 +160 +Executable: ./dgemmoptimized 5120 46080 46080 1 0 +m=5120, n=46080, k=46080, time(sec)=38.084535, speed(mflops)=570921.293972 +Executable: ./dgemmoptimized 5120 46080 46080 1 0 +m=5120, n=46080, k=46080, time(sec)=38.053880, speed(mflops)=571381.208685 +Executable: ./dgemmoptimized 5120 46080 46080 1 0 +m=5120, n=46080, k=46080, time(sec)=38.025549, speed(mflops)=571806.917849 +Max repetitions 3, Elasped time 415.362, Relative error 0.00155569, Mean 33672.5, Standard Deviation 31.0726 +Total Energy 33672.516667 +161 +Executable: ./dgemmoptimized 5152 46080 46080 1 0 +m=5152, n=46080, k=46080, time(sec)=38.041672, speed(mflops)=575136.849678 +Executable: ./dgemmoptimized 5152 46080 46080 1 0 +m=5152, n=46080, k=46080, time(sec)=38.067942, speed(mflops)=574739.959432 +Executable: ./dgemmoptimized 5152 46080 46080 1 0 +m=5152, n=46080, k=46080, time(sec)=38.042496, speed(mflops)=575124.392605 +Max repetitions 3, Elasped time 416.064, Relative error 0.00669673, Mean 33759.6, Standard Deviation 134.104 +Total Energy 33759.633333 +162 +Executable: ./dgemmoptimized 5184 46080 46080 1 0 +m=5184, n=46080, k=46080, time(sec)=39.096892, speed(mflops)=563089.846189 +Executable: ./dgemmoptimized 5184 46080 46080 1 0 +m=5184, n=46080, k=46080, time(sec)=37.057132, speed(mflops)=594084.367668 +Executable: ./dgemmoptimized 5184 46080 46080 1 0 +m=5184, n=46080, k=46080, time(sec)=37.050223, speed(mflops)=594195.152624 +Max repetitions 3, Elasped time 415.036, Relative error 0.0175403, Mean 33925.5, Standard Deviation 352.975 +Total Energy 33925.516667 +163 +Executable: ./dgemmoptimized 5216 46080 46080 1 0 +m=5216, n=46080, k=46080, time(sec)=38.095195, speed(mflops)=581463.311917 +Executable: ./dgemmoptimized 5216 46080 46080 1 0 +m=5216, n=46080, k=46080, time(sec)=38.122256, speed(mflops)=581050.561678 +Executable: ./dgemmoptimized 5216 46080 46080 1 0 +m=5216, n=46080, k=46080, time(sec)=38.076640, speed(mflops)=581746.661725 +Max repetitions 3, Elasped time 418.388, Relative error 0.0084899, Mean 33831.2, Standard Deviation 170.373 +Total Energy 33831.200000 +164 +Executable: ./dgemmoptimized 5248 46080 46080 1 0 +m=5248, n=46080, k=46080, time(sec)=39.020342, speed(mflops)=571159.875294 +Executable: ./dgemmoptimized 5248 46080 46080 1 0 +m=5248, n=46080, k=46080, time(sec)=39.019783, speed(mflops)=571168.059109 +Executable: ./dgemmoptimized 5248 46080 46080 1 0 +m=5248, n=46080, k=46080, time(sec)=39.015629, speed(mflops)=571228.870975 +Max repetitions 3, Elasped time 419.406, Relative error 0.00355242, Mean 34433.9, Standard Deviation 72.5588 +Total Energy 34433.900000 +165 +Executable: ./dgemmoptimized 5280 46080 46080 1 0 +m=5280, n=46080, k=46080, time(sec)=39.813169, speed(mflops)=563199.306807 +Executable: ./dgemmoptimized 5280 46080 46080 1 0 +m=5280, n=46080, k=46080, time(sec)=39.777427, speed(mflops)=563705.370074 +Executable: ./dgemmoptimized 5280 46080 46080 1 0 +m=5280, n=46080, k=46080, time(sec)=39.793891, speed(mflops)=563472.143905 +Max repetitions 3, Elasped time 424.022, Relative error 0.011305, Mean 34420.5, Standard Deviation 230.818 +Total Energy 34420.500000 +166 +Executable: ./dgemmoptimized 5312 46080 46080 1 0 +m=5312, n=46080, k=46080, time(sec)=40.803945, speed(mflops)=552854.499679 +Executable: ./dgemmoptimized 5312 46080 46080 1 0 +m=5312, n=46080, k=46080, time(sec)=40.827054, speed(mflops)=552541.575795 +Executable: ./dgemmoptimized 5312 46080 46080 1 0 +m=5312, n=46080, k=46080, time(sec)=44.115369, speed(mflops)=511355.681779 +Max repetitions 3, Elasped time 432.017, Relative error 0.0222419, Mean 35426.5, Standard Deviation 467.391 +Total Energy 35426.516667 +167 +Executable: ./dgemmoptimized 5344 46080 46080 1 0 +m=5344, n=46080, k=46080, time(sec)=40.033335, speed(mflops)=566891.069653 +Executable: ./dgemmoptimized 5344 46080 46080 1 0 +m=5344, n=46080, k=46080, time(sec)=40.035828, speed(mflops)=566855.767760 +Executable: ./dgemmoptimized 5344 46080 46080 1 0 +m=5344, n=46080, k=46080, time(sec)=40.023373, speed(mflops)=567032.172585 +Max repetitions 3, Elasped time 423.501, Relative error 0.00111211, Mean 34227.5, Standard Deviation 22.5789 +Total Energy 34227.516667 +168 +Executable: ./dgemmoptimized 5376 46080 46080 1 0 +m=5376, n=46080, k=46080, time(sec)=37.418683, speed(mflops)=610134.661902 +Executable: ./dgemmoptimized 5376 46080 46080 1 0 +m=5376, n=46080, k=46080, time(sec)=37.395615, speed(mflops)=610511.031072 +Executable: ./dgemmoptimized 5376 46080 46080 1 0 +m=5376, n=46080, k=46080, time(sec)=37.472523, speed(mflops)=609258.030174 +Max repetitions 3, Elasped time 418.028, Relative error 0.0106665, Mean 33882, Standard Deviation 214.372 +Total Energy 33881.950000 +169 +Executable: ./dgemmoptimized 5408 46080 46080 1 0 +m=5408, n=46080, k=46080, time(sec)=38.524358, speed(mflops)=596150.906968 +Executable: ./dgemmoptimized 5408 46080 46080 1 0 +m=5408, n=46080, k=46080, time(sec)=39.896037, speed(mflops)=575654.442165 +Executable: ./dgemmoptimized 5408 46080 46080 1 0 +m=5408, n=46080, k=46080, time(sec)=38.472287, speed(mflops)=596957.779465 +Max repetitions 3, Elasped time 422.89, Relative error 0.014606, Mean 34543.6, Standard Deviation 299.281 +Total Energy 34543.566667 +170 +Executable: ./dgemmoptimized 5440 46080 46080 1 0 +m=5440, n=46080, k=46080, time(sec)=39.401020, speed(mflops)=586335.744675 +Executable: ./dgemmoptimized 5440 46080 46080 1 0 +m=5440, n=46080, k=46080, time(sec)=39.360668, speed(mflops)=586936.849367 +Executable: ./dgemmoptimized 5440 46080 46080 1 0 +m=5440, n=46080, k=46080, time(sec)=39.359297, speed(mflops)=586957.292713 +Max repetitions 3, Elasped time 422.512, Relative error 0.00255908, Mean 34383.8, Standard Deviation 52.1935 +Total Energy 34383.766667 +171 +Executable: ./dgemmoptimized 5472 46080 46080 1 0 +m=5472, n=46080, k=46080, time(sec)=40.179778, speed(mflops)=578353.663983 +Executable: ./dgemmoptimized 5472 46080 46080 1 0 +m=5472, n=46080, k=46080, time(sec)=40.689002, speed(mflops)=571115.552562 +Executable: ./dgemmoptimized 5472 46080 46080 1 0 +m=5472, n=46080, k=46080, time(sec)=40.192368, speed(mflops)=578172.499414 +Max repetitions 3, Elasped time 429.653, Relative error 0.0146956, Mean 35285.6, Standard Deviation 307.584 +Total Energy 35285.616667 +172 +Executable: ./dgemmoptimized 5504 46080 46080 1 0 +m=5504, n=46080, k=46080, time(sec)=41.165624, speed(mflops)=567804.277329 +Executable: ./dgemmoptimized 5504 46080 46080 1 0 +m=5504, n=46080, k=46080, time(sec)=41.174226, speed(mflops)=567685.651342 +Executable: ./dgemmoptimized 5504 46080 46080 1 0 +m=5504, n=46080, k=46080, time(sec)=41.171720, speed(mflops)=567720.204921 +Max repetitions 3, Elasped time 430.413, Relative error 0.0120394, Mean 35127.8, Standard Deviation 250.863 +Total Energy 35127.800000 +173 +Executable: ./dgemmoptimized 5536 46080 46080 1 0 +m=5536, n=46080, k=46080, time(sec)=41.196317, speed(mflops)=570679.963187 +Executable: ./dgemmoptimized 5536 46080 46080 1 0 +m=5536, n=46080, k=46080, time(sec)=41.190324, speed(mflops)=570762.996231 +Executable: ./dgemmoptimized 5536 46080 46080 1 0 +m=5536, n=46080, k=46080, time(sec)=41.196414, speed(mflops)=570678.622278 +Max repetitions 3, Elasped time 436.047, Relative error 0.0491739, Mean 35602.6, Standard Deviation 1038.48 +Total Energy 35602.600000 +174 +Executable: ./dgemmoptimized 5568 46080 46080 1 0 +m=5568, n=46080, k=46080, time(sec)=40.201696, speed(mflops)=588179.367801 +Executable: ./dgemmoptimized 5568 46080 46080 1 0 +m=5568, n=46080, k=46080, time(sec)=40.260263, speed(mflops)=587323.740291 +Executable: ./dgemmoptimized 5568 46080 46080 1 0 +m=5568, n=46080, k=46080, time(sec)=40.182307, speed(mflops)=588463.181756 +Max repetitions 3, Elasped time 430.213, Relative error 0.0240396, Mean 35291.9, Standard Deviation 503.248 +Total Energy 35291.916667 +175 +Executable: ./dgemmoptimized 5600 46080 46080 1 0 +m=5600, n=46080, k=46080, time(sec)=41.257345, speed(mflops)=576423.512041 +Executable: ./dgemmoptimized 5600 46080 46080 1 0 +m=5600, n=46080, k=46080, time(sec)=41.247751, speed(mflops)=576557.584471 +Executable: ./dgemmoptimized 5600 46080 46080 1 0 +m=5600, n=46080, k=46080, time(sec)=41.254370, speed(mflops)=576465.076487 +Max repetitions 3, Elasped time 429.477, Relative error 0.00351347, Mean 34976.2, Standard Deviation 72.8935 +Total Energy 34976.233333 +176 +Executable: ./dgemmoptimized 5632 46080 46080 1 0 +m=5632, n=46080, k=46080, time(sec)=42.123051, speed(mflops)=567803.105488 +Executable: ./dgemmoptimized 5632 46080 46080 1 0 +m=5632, n=46080, k=46080, time(sec)=42.144789, speed(mflops)=567510.235742 +Executable: ./dgemmoptimized 5632 46080 46080 1 0 +m=5632, n=46080, k=46080, time(sec)=42.144692, speed(mflops)=567511.542410 +Max repetitions 3, Elasped time 432.614, Relative error 0.00329481, Mean 35648.5, Standard Deviation 69.6711 +Total Energy 35648.533333 +177 +Executable: ./dgemmoptimized 5664 46080 46080 1 0 +m=5664, n=46080, k=46080, time(sec)=42.959878, speed(mflops)=559906.026670 +Executable: ./dgemmoptimized 5664 46080 46080 1 0 +m=5664, n=46080, k=46080, time(sec)=43.831644, speed(mflops)=548770.074589 +Executable: ./dgemmoptimized 5664 46080 46080 1 0 +m=5664, n=46080, k=46080, time(sec)=42.967659, speed(mflops)=559804.633087 +Max repetitions 3, Elasped time 436.299, Relative error 0.0164909, Mean 35861.4, Standard Deviation 350.794 +Total Energy 35861.383333 +178 +Executable: ./dgemmoptimized 5696 46080 46080 1 0 +m=5696, n=46080, k=46080, time(sec)=43.968238, speed(mflops)=550156.000460 +Executable: ./dgemmoptimized 5696 46080 46080 1 0 +m=5696, n=46080, k=46080, time(sec)=43.937104, speed(mflops)=550545.844717 +Executable: ./dgemmoptimized 5696 46080 46080 1 0 +m=5696, n=46080, k=46080, time(sec)=43.935898, speed(mflops)=550560.958694 +Max repetitions 3, Elasped time 438.649, Relative error 0.00672544, Mean 36413.4, Standard Deviation 145.265 +Total Energy 36413.400000 +179 +Executable: ./dgemmoptimized 5728 46080 46080 1 0 +m=5728, n=46080, k=46080, time(sec)=42.567992, speed(mflops)=571445.453533 +Executable: ./dgemmoptimized 5728 46080 46080 1 0 +m=5728, n=46080, k=46080, time(sec)=42.620056, speed(mflops)=570747.385398 +Executable: ./dgemmoptimized 5728 46080 46080 1 0 +m=5728, n=46080, k=46080, time(sec)=42.618934, speed(mflops)=570762.411052 +Max repetitions 3, Elasped time 434.901, Relative error 0.00178092, Mean 35863.8, Standard Deviation 37.8862 +Total Energy 35863.833333 +180 +Executable: ./dgemmoptimized 5760 46080 46080 1 0 +m=5760, n=46080, k=46080, time(sec)=38.733371, speed(mflops)=631527.292468 +Executable: ./dgemmoptimized 5760 46080 46080 1 0 +m=5760, n=46080, k=46080, time(sec)=38.754625, speed(mflops)=631180.946177 +Executable: ./dgemmoptimized 5760 46080 46080 1 0 +m=5760, n=46080, k=46080, time(sec)=38.786450, speed(mflops)=630663.053341 +Max repetitions 3, Elasped time 425.667, Relative error 0.0154464, Mean 34421.4, Standard Deviation 315.38 +Total Energy 34421.383333 +181 +Executable: ./dgemmoptimized 5792 46080 46080 1 0 +m=5792, n=46080, k=46080, time(sec)=39.787280, speed(mflops)=618214.576967 +Executable: ./dgemmoptimized 5792 46080 46080 1 0 +m=5792, n=46080, k=46080, time(sec)=39.791716, speed(mflops)=618145.654149 +Executable: ./dgemmoptimized 5792 46080 46080 1 0 +m=5792, n=46080, k=46080, time(sec)=40.347521, speed(mflops)=609630.424059 +Max repetitions 3, Elasped time 429.706, Relative error 0.0106956, Mean 35253.2, Standard Deviation 223.658 +Total Energy 35253.150000 +182 +Executable: ./dgemmoptimized 5824 46080 46080 1 0 +m=5824, n=46080, k=46080, time(sec)=40.723820, speed(mflops)=607334.278679 +Executable: ./dgemmoptimized 5824 46080 46080 1 0 +m=5824, n=46080, k=46080, time(sec)=40.727871, speed(mflops)=607273.870587 +Executable: ./dgemmoptimized 5824 46080 46080 1 0 +m=5824, n=46080, k=46080, time(sec)=41.842836, speed(mflops)=591092.149787 +Max repetitions 3, Elasped time 433.357, Relative error 0.0150108, Mean 35347.9, Standard Deviation 314.736 +Total Energy 35347.900000 +183 +Executable: ./dgemmoptimized 5856 46080 46080 1 0 +m=5856, n=46080, k=46080, time(sec)=41.565945, speed(mflops)=598299.096306 +Executable: ./dgemmoptimized 5856 46080 46080 1 0 +m=5856, n=46080, k=46080, time(sec)=41.519395, speed(mflops)=598969.887493 +Executable: ./dgemmoptimized 5856 46080 46080 1 0 +m=5856, n=46080, k=46080, time(sec)=41.538621, speed(mflops)=598692.655383 +Max repetitions 3, Elasped time 434.374, Relative error 0.0142319, Mean 35805.6, Standard Deviation 302.268 +Total Energy 35805.566667 +184 +Executable: ./dgemmoptimized 5888 46080 46080 1 0 +m=5888, n=46080, k=46080, time(sec)=42.508938, speed(mflops)=588223.653648 +Executable: ./dgemmoptimized 5888 46080 46080 1 0 +m=5888, n=46080, k=46080, time(sec)=42.531529, speed(mflops)=587911.211844 +Executable: ./dgemmoptimized 5888 46080 46080 1 0 +m=5888, n=46080, k=46080, time(sec)=42.542370, speed(mflops)=587761.393614 +Max repetitions 3, Elasped time 436.308, Relative error 0.00537984, Mean 35663.6, Standard Deviation 113.808 +Total Energy 35663.566667 +185 +Executable: ./dgemmoptimized 5920 46080 46080 1 0 +m=5920, n=46080, k=46080, time(sec)=42.562932, speed(mflops)=590670.261331 +Executable: ./dgemmoptimized 5920 46080 46080 1 0 +m=5920, n=46080, k=46080, time(sec)=42.546944, speed(mflops)=590892.220916 +Executable: ./dgemmoptimized 5920 46080 46080 1 0 +m=5920, n=46080, k=46080, time(sec)=42.599195, speed(mflops)=590167.447388 +Max repetitions 3, Elasped time 436.78, Relative error 0.00813887, Mean 36169.5, Standard Deviation 174.617 +Total Energy 36169.533333 +186 +Executable: ./dgemmoptimized 5952 46080 46080 1 0 +m=5952, n=46080, k=46080, time(sec)=41.564811, speed(mflops)=608123.867829 +Executable: ./dgemmoptimized 5952 46080 46080 1 0 +m=5952, n=46080, k=46080, time(sec)=41.615826, speed(mflops)=607378.397139 +Executable: ./dgemmoptimized 5952 46080 46080 1 0 +m=5952, n=46080, k=46080, time(sec)=45.689392, speed(mflops)=553225.868619 +Max repetitions 3, Elasped time 438.302, Relative error 0.0329655, Mean 36119.7, Standard Deviation 706.292 +Total Energy 36119.700000 +187 +Executable: ./dgemmoptimized 5984 46080 46080 1 0 +m=5984, n=46080, k=46080, time(sec)=42.586713, speed(mflops)=596722.480790 +Executable: ./dgemmoptimized 5984 46080 46080 1 0 +m=5984, n=46080, k=46080, time(sec)=42.623549, speed(mflops)=596206.784293 +Executable: ./dgemmoptimized 5984 46080 46080 1 0 +m=5984, n=46080, k=46080, time(sec)=42.605581, speed(mflops)=596458.221008 +Max repetitions 3, Elasped time 437.507, Relative error 0.00171042, Mean 36415.3, Standard Deviation 36.946 +Total Energy 36415.333333 +188 +Executable: ./dgemmoptimized 6016 46080 46080 1 0 +m=6016, n=46080, k=46080, time(sec)=43.545165, speed(mflops)=586709.098208 +Executable: ./dgemmoptimized 6016 46080 46080 1 0 +m=6016, n=46080, k=46080, time(sec)=43.491552, speed(mflops)=587432.350025 +Executable: ./dgemmoptimized 6016 46080 46080 1 0 +m=6016, n=46080, k=46080, time(sec)=48.813872, speed(mflops)=523382.871021 +Max repetitions 3, Elasped time 447.736, Relative error 0.0450411, Mean 37064.9, Standard Deviation 990.265 +Total Energy 37064.866667 +189 +Executable: ./dgemmoptimized 6048 46080 46080 1 0 +m=6048, n=46080, k=46080, time(sec)=44.363546, speed(mflops)=578949.209727 +Executable: ./dgemmoptimized 6048 46080 46080 1 0 +m=6048, n=46080, k=46080, time(sec)=44.451465, speed(mflops)=577804.129451 +Executable: ./dgemmoptimized 6048 46080 46080 1 0 +m=6048, n=46080, k=46080, time(sec)=44.325792, speed(mflops)=579442.324040 +Max repetitions 3, Elasped time 445.303, Relative error 0.0131944, Mean 37137, Standard Deviation 290.653 +Total Energy 37136.950000 +190 +Executable: ./dgemmoptimized 6080 46080 46080 1 0 +m=6080, n=46080, k=46080, time(sec)=45.290409, speed(mflops)=570101.616299 +Executable: ./dgemmoptimized 6080 46080 46080 1 0 +m=6080, n=46080, k=46080, time(sec)=45.284524, speed(mflops)=570175.706044 +Executable: ./dgemmoptimized 6080 46080 46080 1 0 +m=6080, n=46080, k=46080, time(sec)=45.364918, speed(mflops)=569165.261749 +Max repetitions 3, Elasped time 448.542, Relative error 0.011445, Mean 37170.9, Standard Deviation 252.348 +Total Energy 37170.850000 +191 +Executable: ./dgemmoptimized 6112 46080 46080 1 0 +m=6112, n=46080, k=46080, time(sec)=44.645600, speed(mflops)=581379.370572 +Executable: ./dgemmoptimized 6112 46080 46080 1 0 +m=6112, n=46080, k=46080, time(sec)=44.537985, speed(mflops)=582784.129619 +Executable: ./dgemmoptimized 6112 46080 46080 1 0 +m=6112, n=46080, k=46080, time(sec)=44.552463, speed(mflops)=582594.745475 +Max repetitions 3, Elasped time 444.729, Relative error 0.000515676, Mean 36948, Standard Deviation 11.3018 +Total Energy 36947.983333 +192 +Executable: ./dgemmoptimized 6144 46080 46080 1 0 +m=6144, n=46080, k=46080, time(sec)=41.920655, speed(mflops)=622412.181194 +Executable: ./dgemmoptimized 6144 46080 46080 1 0 +m=6144, n=46080, k=46080, time(sec)=41.895664, speed(mflops)=622783.454100 +Executable: ./dgemmoptimized 6144 46080 46080 1 0 +m=6144, n=46080, k=46080, time(sec)=41.899089, speed(mflops)=622732.543473 +Max repetitions 3, Elasped time 437.015, Relative error 0.00424203, Mean 36472.2, Standard Deviation 91.7731 +Total Energy 36472.166667 +193 +Executable: ./dgemmoptimized 6176 46080 46080 1 0 +m=6176, n=46080, k=46080, time(sec)=44.485839, speed(mflops)=589576.869553 +Executable: ./dgemmoptimized 6176 46080 46080 1 0 +m=6176, n=46080, k=46080, time(sec)=42.935764, speed(mflops)=610861.884917 +Executable: ./dgemmoptimized 6176 46080 46080 1 0 +m=6176, n=46080, k=46080, time(sec)=42.985838, speed(mflops)=610150.296747 +Max repetitions 3, Elasped time 447.975, Relative error 0.0137482, Mean 37015.6, Standard Deviation 301.863 +Total Energy 37015.633333 +194 +Executable: ./dgemmoptimized 6208 46080 46080 1 0 +m=6208, n=46080, k=46080, time(sec)=43.844192, speed(mflops)=601304.665520 +Executable: ./dgemmoptimized 6208 46080 46080 1 0 +m=6208, n=46080, k=46080, time(sec)=43.852408, speed(mflops)=601192.005688 +Executable: ./dgemmoptimized 6208 46080 46080 1 0 +m=6208, n=46080, k=46080, time(sec)=46.183697, speed(mflops)=570844.669079 +Max repetitions 3, Elasped time 447.784, Relative error 0.0309108, Mean 37500, Standard Deviation 687.578 +Total Energy 37500.033333 +195 +Executable: ./dgemmoptimized 6240 46080 46080 1 0 +m=6240, n=46080, k=46080, time(sec)=44.693659, speed(mflops)=592916.606631 +Executable: ./dgemmoptimized 6240 46080 46080 1 0 +m=6240, n=46080, k=46080, time(sec)=44.717327, speed(mflops)=592602.786882 +Executable: ./dgemmoptimized 6240 46080 46080 1 0 +m=6240, n=46080, k=46080, time(sec)=44.691801, speed(mflops)=592941.256268 +Max repetitions 3, Elasped time 448.204, Relative error 0.00889261, Mean 37050, Standard Deviation 195.433 +Total Energy 37050.016667 +196 +Executable: ./dgemmoptimized 6272 46080 46080 1 0 +m=6272, n=46080, k=46080, time(sec)=45.649598, speed(mflops)=583477.384634 +Executable: ./dgemmoptimized 6272 46080 46080 1 0 +m=6272, n=46080, k=46080, time(sec)=45.658330, speed(mflops)=583365.798591 +Executable: ./dgemmoptimized 6272 46080 46080 1 0 +m=6272, n=46080, k=46080, time(sec)=45.656617, speed(mflops)=583387.683445 +Max repetitions 3, Elasped time 449.454, Relative error 0.00323806, Mean 37694.7, Standard Deviation 72.401 +Total Energy 37694.683333 +197 +Executable: ./dgemmoptimized 6304 46080 46080 1 0 +m=6304, n=46080, k=46080, time(sec)=45.704305, speed(mflops)=585752.340182 +Executable: ./dgemmoptimized 6304 46080 46080 1 0 +m=6304, n=46080, k=46080, time(sec)=45.707667, speed(mflops)=585709.256284 +Executable: ./dgemmoptimized 6304 46080 46080 1 0 +m=6304, n=46080, k=46080, time(sec)=45.722707, speed(mflops)=585516.591390 +Max repetitions 3, Elasped time 449.937, Relative error 0.00110721, Mean 37694.1, Standard Deviation 24.7561 +Total Energy 37694.116667 +198 +Executable: ./dgemmoptimized 6336 46080 46080 1 0 +m=6336, n=46080, k=46080, time(sec)=44.722131, speed(mflops)=601655.118189 +Executable: ./dgemmoptimized 6336 46080 46080 1 0 +m=6336, n=46080, k=46080, time(sec)=44.704681, speed(mflops)=601889.969177 +Executable: ./dgemmoptimized 6336 46080 46080 1 0 +m=6336, n=46080, k=46080, time(sec)=44.755233, speed(mflops)=601210.122947 +Max repetitions 3, Elasped time 447.389, Relative error 0.0027326, Mean 37013.8, Standard Deviation 59.9956 +Total Energy 37013.783333 +199 +Executable: ./dgemmoptimized 6368 46080 46080 1 0 +m=6368, n=46080, k=46080, time(sec)=45.724138, speed(mflops)=591442.411833 +Executable: ./dgemmoptimized 6368 46080 46080 1 0 +m=6368, n=46080, k=46080, time(sec)=45.772891, speed(mflops)=590812.465503 +Executable: ./dgemmoptimized 6368 46080 46080 1 0 +m=6368, n=46080, k=46080, time(sec)=45.735580, speed(mflops)=591294.447116 +Max repetitions 3, Elasped time 450.757, Relative error 0.00228627, Mean 37627.9, Standard Deviation 51.029 +Total Energy 37627.883333 +200 +Executable: ./dgemmoptimized 6400 46080 46080 1 0 +m=6400, n=46080, k=46080, time(sec)=46.680633, speed(mflops)=582234.821434 +Executable: ./dgemmoptimized 6400 46080 46080 1 0 +m=6400, n=46080, k=46080, time(sec)=46.702142, speed(mflops)=581966.666965 +Executable: ./dgemmoptimized 6400 46080 46080 1 0 +m=6400, n=46080, k=46080, time(sec)=46.659537, speed(mflops)=582498.061976 +Max repetitions 3, Elasped time 455.749, Relative error 0.0110618, Mean 37831.6, Standard Deviation 248.233 +Total Energy 37831.583333 +201 +Executable: ./dgemmoptimized 6432 46080 46080 1 0 +m=6432, n=46080, k=46080, time(sec)=47.459462, speed(mflops)=575543.511458 +Executable: ./dgemmoptimized 6432 46080 46080 1 0 +m=6432, n=46080, k=46080, time(sec)=47.428981, speed(mflops)=575913.392104 +Executable: ./dgemmoptimized 6432 46080 46080 1 0 +m=6432, n=46080, k=46080, time(sec)=53.354766, speed(mflops)=511950.240824 +Max repetitions 3, Elasped time 463.892, Relative error 0.0468164, Mean 38856.1, Standard Deviation 1079.04 +Total Energy 38856.133333 +202 +Executable: ./dgemmoptimized 6464 46080 46080 1 0 +m=6464, n=46080, k=46080, time(sec)=48.458863, speed(mflops)=566478.020912 +Executable: ./dgemmoptimized 6464 46080 46080 1 0 +m=6464, n=46080, k=46080, time(sec)=48.481663, speed(mflops)=566211.617486 +Executable: ./dgemmoptimized 6464 46080 46080 1 0 +m=6464, n=46080, k=46080, time(sec)=48.479070, speed(mflops)=566241.902919 +Max repetitions 3, Elasped time 459.889, Relative error 0.00269321, Mean 38273.4, Standard Deviation 61.143 +Total Energy 38273.400000 +203 +Executable: ./dgemmoptimized 6496 46080 46080 1 0 +m=6496, n=46080, k=46080, time(sec)=47.687135, speed(mflops)=578495.149262 +Executable: ./dgemmoptimized 6496 46080 46080 1 0 +m=6496, n=46080, k=46080, time(sec)=47.723792, speed(mflops)=578050.801680 +Executable: ./dgemmoptimized 6496 46080 46080 1 0 +m=6496, n=46080, k=46080, time(sec)=47.651411, speed(mflops)=578928.842969 +Max repetitions 3, Elasped time 459.797, Relative error 0.0125787, Mean 38454.3, Standard Deviation 286.92 +Total Energy 38454.350000 +204 +Executable: ./dgemmoptimized 6528 46080 46080 1 0 +m=6528, n=46080, k=46080, time(sec)=45.058454, speed(mflops)=615260.161740 +Executable: ./dgemmoptimized 6528 46080 46080 1 0 +m=6528, n=46080, k=46080, time(sec)=45.070328, speed(mflops)=615098.068958 +Executable: ./dgemmoptimized 6528 46080 46080 1 0 +m=6528, n=46080, k=46080, time(sec)=45.095187, speed(mflops)=614758.993014 +Max repetitions 3, Elasped time 450.233, Relative error 0.00151617, Mean 37659.1, Standard Deviation 33.8687 +Total Energy 37659.100000 +205 +Executable: ./dgemmoptimized 6560 46080 46080 1 0 +m=6560, n=46080, k=46080, time(sec)=46.051130, speed(mflops)=604948.611118 +Executable: ./dgemmoptimized 6560 46080 46080 1 0 +m=6560, n=46080, k=46080, time(sec)=46.157732, speed(mflops)=603551.473500 +Executable: ./dgemmoptimized 6560 46080 46080 1 0 +m=6560, n=46080, k=46080, time(sec)=46.172020, speed(mflops)=603364.704274 +Max repetitions 3, Elasped time 455.737, Relative error 0.0257913, Mean 37932.1, Standard Deviation 580.309 +Total Energy 37932.066667 +206 +Executable: ./dgemmoptimized 6592 46080 46080 1 0 +m=6592, n=46080, k=46080, time(sec)=47.038221, speed(mflops)=595142.884883 +Executable: ./dgemmoptimized 6592 46080 46080 1 0 +m=6592, n=46080, k=46080, time(sec)=46.981813, speed(mflops)=595857.436260 +Executable: ./dgemmoptimized 6592 46080 46080 1 0 +m=6592, n=46080, k=46080, time(sec)=47.203926, speed(mflops)=593053.691474 +Max repetitions 3, Elasped time 456.846, Relative error 0.00174027, Mean 38198.9, Standard Deviation 39.4319 +Total Energy 38198.866667 +207 +Executable: ./dgemmoptimized 6624 46080 46080 1 0 +m=6624, n=46080, k=46080, time(sec)=47.832105, speed(mflops)=588106.212626 +Executable: ./dgemmoptimized 6624 46080 46080 1 0 +m=6624, n=46080, k=46080, time(sec)=47.835927, speed(mflops)=588059.222968 +Executable: ./dgemmoptimized 6624 46080 46080 1 0 +m=6624, n=46080, k=46080, time(sec)=47.830578, speed(mflops)=588124.985966 +Max repetitions 3, Elasped time 459.54, Relative error 0.00654091, Mean 38241.1, Standard Deviation 148.371 +Total Energy 38241.083333 +208 +Executable: ./dgemmoptimized 6656 46080 46080 1 0 +m=6656, n=46080, k=46080, time(sec)=48.863454, speed(mflops)=578474.325513 +Executable: ./dgemmoptimized 6656 46080 46080 1 0 +m=6656, n=46080, k=46080, time(sec)=48.842245, speed(mflops)=578725.519185 +Executable: ./dgemmoptimized 6656 46080 46080 1 0 +m=6656, n=46080, k=46080, time(sec)=48.864351, speed(mflops)=578463.704492 +Max repetitions 3, Elasped time 464.764, Relative error 0.00847369, Mean 39233.1, Standard Deviation 197.199 +Total Energy 39233.116667 +209 +Executable: ./dgemmoptimized 6688 46080 46080 1 0 +m=6688, n=46080, k=46080, time(sec)=48.887766, speed(mflops)=580966.389322 +Executable: ./dgemmoptimized 6688 46080 46080 1 0 +m=6688, n=46080, k=46080, time(sec)=49.787534, speed(mflops)=570467.076503 +Executable: ./dgemmoptimized 6688 46080 46080 1 0 +m=6688, n=46080, k=46080, time(sec)=48.872654, speed(mflops)=581146.032891 +Max repetitions 3, Elasped time 464.191, Relative error 0.00261827, Mean 39107, Standard Deviation 60.7363 +Total Energy 39107.000000 +210 +Executable: ./dgemmoptimized 6720 46080 46080 1 0 +m=6720, n=46080, k=46080, time(sec)=47.878390, speed(mflops)=596052.715474 +Executable: ./dgemmoptimized 6720 46080 46080 1 0 +m=6720, n=46080, k=46080, time(sec)=47.870043, speed(mflops)=596156.648377 +Executable: ./dgemmoptimized 6720 46080 46080 1 0 +m=6720, n=46080, k=46080, time(sec)=47.931832, speed(mflops)=595388.141460 +Max repetitions 3, Elasped time 460.668, Relative error 0.00631357, Mean 38560.2, Standard Deviation 144.409 +Total Energy 38560.200000 +211 +Executable: ./dgemmoptimized 6752 46080 46080 1 0 +m=6752, n=46080, k=46080, time(sec)=48.944473, speed(mflops)=585846.329351 +Executable: ./dgemmoptimized 6752 46080 46080 1 0 +m=6752, n=46080, k=46080, time(sec)=48.940578, speed(mflops)=585892.955229 +Executable: ./dgemmoptimized 6752 46080 46080 1 0 +m=6752, n=46080, k=46080, time(sec)=48.911614, speed(mflops)=586239.901229 +Max repetitions 3, Elasped time 464.093, Relative error 0.00332424, Mean 38812.9, Standard Deviation 76.5329 +Total Energy 38812.916667 +212 +Executable: ./dgemmoptimized 6784 46080 46080 1 0 +m=6784, n=46080, k=46080, time(sec)=49.839009, speed(mflops)=578057.951074 +Executable: ./dgemmoptimized 6784 46080 46080 1 0 +m=6784, n=46080, k=46080, time(sec)=50.241425, speed(mflops)=573427.909216 +Executable: ./dgemmoptimized 6784 46080 46080 1 0 +m=6784, n=46080, k=46080, time(sec)=49.817635, speed(mflops)=578305.960949 +Max repetitions 3, Elasped time 467.492, Relative error 0.0113572, Mean 39764.7, Standard Deviation 267.885 +Total Energy 39764.716667 +213 +Executable: ./dgemmoptimized 6816 46080 46080 1 0 +m=6816, n=46080, k=46080, time(sec)=50.590208, speed(mflops)=572160.740485 +Executable: ./dgemmoptimized 6816 46080 46080 1 0 +m=6816, n=46080, k=46080, time(sec)=50.624453, speed(mflops)=571773.698494 +Executable: ./dgemmoptimized 6816 46080 46080 1 0 +m=6816, n=46080, k=46080, time(sec)=50.627303, speed(mflops)=571741.510588 +Max repetitions 3, Elasped time 469.786, Relative error 0.00177577, Mean 39419.3, Standard Deviation 41.5217 +Total Energy 39419.316667 +214 +Executable: ./dgemmoptimized 6848 46080 46080 1 0 +m=6848, n=46080, k=46080, time(sec)=51.670996, speed(mflops)=562823.024394 +Executable: ./dgemmoptimized 6848 46080 46080 1 0 +m=6848, n=46080, k=46080, time(sec)=51.615766, speed(mflops)=563425.256289 +Executable: ./dgemmoptimized 6848 46080 46080 1 0 +m=6848, n=46080, k=46080, time(sec)=51.601525, speed(mflops)=563580.750296 +Max repetitions 3, Elasped time 473.167, Relative error 0.00326015, Mean 40165.7, Standard Deviation 77.6736 +Total Energy 40165.750000 +215 +Executable: ./dgemmoptimized 6880 46080 46080 1 0 +m=6880, n=46080, k=46080, time(sec)=50.396248, speed(mflops)=579755.889858 +Executable: ./dgemmoptimized 6880 46080 46080 1 0 +m=6880, n=46080, k=46080, time(sec)=50.560297, speed(mflops)=577874.802770 +Executable: ./dgemmoptimized 6880 46080 46080 1 0 +m=6880, n=46080, k=46080, time(sec)=50.273883, speed(mflops)=581166.999612 +Max repetitions 3, Elasped time 469.779, Relative error 0.0119149, Mean 39632.3, Standard Deviation 280.104 +Total Energy 39632.316667 +216 +Executable: ./dgemmoptimized 6912 46080 46080 1 0 +m=6912, n=46080, k=46080, time(sec)=46.498798, speed(mflops)=631272.598279 +Executable: ./dgemmoptimized 6912 46080 46080 1 0 +m=6912, n=46080, k=46080, time(sec)=46.457647, speed(mflops)=631831.764096 +Executable: ./dgemmoptimized 6912 46080 46080 1 0 +m=6912, n=46080, k=46080, time(sec)=47.678886, speed(mflops)=615648.129987 +Max repetitions 3, Elasped time 461.454, Relative error 0.0251565, Mean 38547.4, Standard Deviation 575.208 +Total Energy 38547.400000 +217 +Executable: ./dgemmoptimized 6944 46080 46080 1 0 +m=6944, n=46080, k=46080, time(sec)=47.401353, speed(mflops)=622119.636291 +Executable: ./dgemmoptimized 6944 46080 46080 1 0 +m=6944, n=46080, k=46080, time(sec)=47.435338, speed(mflops)=621673.920624 +Executable: ./dgemmoptimized 6944 46080 46080 1 0 +m=6944, n=46080, k=46080, time(sec)=47.496908, speed(mflops)=620868.045696 +Max repetitions 3, Elasped time 465.642, Relative error 0.0208352, Mean 39193.6, Standard Deviation 484.388 +Total Energy 39193.650000 +218 +Executable: ./dgemmoptimized 6976 46080 46080 1 0 +m=6976, n=46080, k=46080, time(sec)=48.521513, speed(mflops)=610558.207899 +Executable: ./dgemmoptimized 6976 46080 46080 1 0 +m=6976, n=46080, k=46080, time(sec)=48.374658, speed(mflops)=612411.732044 +Executable: ./dgemmoptimized 6976 46080 46080 1 0 +m=6976, n=46080, k=46080, time(sec)=48.468707, speed(mflops)=611223.404552 +Max repetitions 3, Elasped time 466.73, Relative error 0.00308018, Mean 39210.7, Standard Deviation 71.6409 +Total Energy 39210.750000 +219 +Executable: ./dgemmoptimized 7008 46080 46080 1 0 +m=7008, n=46080, k=46080, time(sec)=49.270267, speed(mflops)=604037.795381 +Executable: ./dgemmoptimized 7008 46080 46080 1 0 +m=7008, n=46080, k=46080, time(sec)=53.107867, speed(mflops)=560389.733992 +Executable: ./dgemmoptimized 7008 46080 46080 1 0 +m=7008, n=46080, k=46080, time(sec)=49.218996, speed(mflops)=604667.015828 +Max repetitions 3, Elasped time 471.401, Relative error 0.0281588, Mean 39863, Standard Deviation 665.832 +Total Energy 39862.966667 +220 +Executable: ./dgemmoptimized 7040 46080 46080 1 0 +m=7040, n=46080, k=46080, time(sec)=50.200275, speed(mflops)=595554.485412 +Executable: ./dgemmoptimized 7040 46080 46080 1 0 +m=7040, n=46080, k=46080, time(sec)=50.199498, speed(mflops)=595563.703622 +Executable: ./dgemmoptimized 7040 46080 46080 1 0 +m=7040, n=46080, k=46080, time(sec)=50.252429, speed(mflops)=594936.394158 +Max repetitions 3, Elasped time 477.728, Relative error 0.0131897, Mean 40224.9, Standard Deviation 314.709 +Total Energy 40224.883333 +221 +Executable: ./dgemmoptimized 7072 46080 46080 1 0 +m=7072, n=46080, k=46080, time(sec)=50.306461, speed(mflops)=596998.752243 +Executable: ./dgemmoptimized 7072 46080 46080 1 0 +m=7072, n=46080, k=46080, time(sec)=50.236432, speed(mflops)=597830.958944 +Executable: ./dgemmoptimized 7072 46080 46080 1 0 +m=7072, n=46080, k=46080, time(sec)=50.221989, speed(mflops)=598002.886974 +Max repetitions 3, Elasped time 471.181, Relative error 0.0100029, Mean 39580.9, Standard Deviation 234.85 +Total Energy 39580.900000 +222 +Executable: ./dgemmoptimized 7104 46080 46080 1 0 +m=7104, n=46080, k=46080, time(sec)=49.201627, speed(mflops)=613166.510683 +Executable: ./dgemmoptimized 7104 46080 46080 1 0 +m=7104, n=46080, k=46080, time(sec)=49.257626, speed(mflops)=612469.426003 +Executable: ./dgemmoptimized 7104 46080 46080 1 0 +m=7104, n=46080, k=46080, time(sec)=49.251856, speed(mflops)=612541.175238 +Max repetitions 3, Elasped time 469.967, Relative error 0.0113682, Mean 39791.1, Standard Deviation 268.324 +Total Energy 39791.100000 +223 +Executable: ./dgemmoptimized 7136 46080 46080 1 0 +m=7136, n=46080, k=46080, time(sec)=50.274627, speed(mflops)=602782.896404 +Executable: ./dgemmoptimized 7136 46080 46080 1 0 +m=7136, n=46080, k=46080, time(sec)=50.260734, speed(mflops)=602949.518317 +Executable: ./dgemmoptimized 7136 46080 46080 1 0 +m=7136, n=46080, k=46080, time(sec)=50.384237, speed(mflops)=601471.554953 +Max repetitions 3, Elasped time 473.852, Relative error 0.0195015, Mean 39818.8, Standard Deviation 460.613 +Total Energy 39818.816667 +224 +Executable: ./dgemmoptimized 7168 46080 46080 1 0 +m=7168, n=46080, k=46080, time(sec)=51.197745, speed(mflops)=594568.777590 +Executable: ./dgemmoptimized 7168 46080 46080 1 0 +m=7168, n=46080, k=46080, time(sec)=51.152202, speed(mflops)=595098.147161 +Executable: ./dgemmoptimized 7168 46080 46080 1 0 +m=7168, n=46080, k=46080, time(sec)=51.202262, speed(mflops)=594516.327328 +Max repetitions 3, Elasped time 474.945, Relative error 0.000116241, Mean 40181.3, Standard Deviation 2.77053 +Total Energy 40181.316667 +225 +Executable: ./dgemmoptimized 7200 46080 46080 1 0 +m=7200, n=46080, k=46080, time(sec)=52.016552, speed(mflops)=587822.048966 +Executable: ./dgemmoptimized 7200 46080 46080 1 0 +m=7200, n=46080, k=46080, time(sec)=52.028929, speed(mflops)=587682.213540 +Executable: ./dgemmoptimized 7200 46080 46080 1 0 +m=7200, n=46080, k=46080, time(sec)=52.037717, speed(mflops)=587582.968696 +Max repetitions 3, Elasped time 477.9, Relative error 0.00139125, Mean 40061, Standard Deviation 33.0603 +Total Energy 40061.050000 +226 +Executable: ./dgemmoptimized 7232 46080 46080 1 0 +m=7232, n=46080, k=46080, time(sec)=53.012283, speed(mflops)=579344.442859 +Executable: ./dgemmoptimized 7232 46080 46080 1 0 +m=7232, n=46080, k=46080, time(sec)=53.061760, speed(mflops)=578804.239424 +Executable: ./dgemmoptimized 7232 46080 46080 1 0 +m=7232, n=46080, k=46080, time(sec)=54.335077, speed(mflops)=565240.232987 +Max repetitions 3, Elasped time 484.422, Relative error 0.018313, Mean 41219.5, Standard Deviation 447.755 +Total Energy 41219.466667 +227 +Executable: ./dgemmoptimized 7264 46080 46080 1 0 +m=7264, n=46080, k=46080, time(sec)=52.208982, speed(mflops)=590861.301694 +Executable: ./dgemmoptimized 7264 46080 46080 1 0 +m=7264, n=46080, k=46080, time(sec)=52.235084, speed(mflops)=590566.046101 +Executable: ./dgemmoptimized 7264 46080 46080 1 0 +m=7264, n=46080, k=46080, time(sec)=52.240583, speed(mflops)=590503.882640 +Max repetitions 3, Elasped time 478.985, Relative error 0.0117904, Mean 40972.4, Standard Deviation 286.55 +Total Energy 40972.450000 +228 +Executable: ./dgemmoptimized 7296 46080 46080 1 0 +m=7296, n=46080, k=46080, time(sec)=49.548943, speed(mflops)=625324.388495 +Executable: ./dgemmoptimized 7296 46080 46080 1 0 +m=7296, n=46080, k=46080, time(sec)=49.615575, speed(mflops)=624484.599077 +Executable: ./dgemmoptimized 7296 46080 46080 1 0 +m=7296, n=46080, k=46080, time(sec)=49.540100, speed(mflops)=625436.009369 +Max repetitions 3, Elasped time 473.33, Relative error 0.0126262, Mean 39698.5, Standard Deviation 297.321 +Total Energy 39698.500000 +229 +Executable: ./dgemmoptimized 7328 46080 46080 1 0 +m=7328, n=46080, k=46080, time(sec)=50.600588, speed(mflops)=615013.760456 +Executable: ./dgemmoptimized 7328 46080 46080 1 0 +m=7328, n=46080, k=46080, time(sec)=50.646395, speed(mflops)=614457.514262 +Executable: ./dgemmoptimized 7328 46080 46080 1 0 +m=7328, n=46080, k=46080, time(sec)=50.648387, speed(mflops)=614433.344924 +Max repetitions 3, Elasped time 474.856, Relative error 0.00793734, Mean 40303.3, Standard Deviation 189.756 +Total Energy 40303.316667 +230 +Executable: ./dgemmoptimized 7360 46080 46080 1 0 +m=7360, n=46080, k=46080, time(sec)=51.559992, speed(mflops)=606205.551051 +Executable: ./dgemmoptimized 7360 46080 46080 1 0 +m=7360, n=46080, k=46080, time(sec)=56.196745, speed(mflops)=556187.966412 +Executable: ./dgemmoptimized 7360 46080 46080 1 0 +m=7360, n=46080, k=46080, time(sec)=51.537218, speed(mflops)=606473.432378 +Max repetitions 3, Elasped time 484.605, Relative error 0.060298, Mean 40918.6, Standard Deviation 1463.54 +Total Energy 40918.633333 +231 +Executable: ./dgemmoptimized 7392 46080 46080 1 0 +m=7392, n=46080, k=46080, time(sec)=52.483388, speed(mflops)=598129.235610 +Executable: ./dgemmoptimized 7392 46080 46080 1 0 +m=7392, n=46080, k=46080, time(sec)=52.396897, speed(mflops)=599116.562401 +Executable: ./dgemmoptimized 7392 46080 46080 1 0 +m=7392, n=46080, k=46080, time(sec)=52.381026, speed(mflops)=599298.092839 +Max repetitions 3, Elasped time 482.825, Relative error 0.00356795, Mean 41046.4, Standard Deviation 86.8707 +Total Energy 41046.416667 +232 +Executable: ./dgemmoptimized 7424 46080 46080 1 0 +m=7424, n=46080, k=46080, time(sec)=53.314984, speed(mflops)=591348.658344 +Executable: ./dgemmoptimized 7424 46080 46080 1 0 +m=7424, n=46080, k=46080, time(sec)=53.358459, speed(mflops)=590866.844743 +Executable: ./dgemmoptimized 7424 46080 46080 1 0 +m=7424, n=46080, k=46080, time(sec)=53.463169, speed(mflops)=589709.607189 +Max repetitions 3, Elasped time 485.366, Relative error 0.0116327, Mean 41032.8, Standard Deviation 283.133 +Total Energy 41032.816667 +233 +Executable: ./dgemmoptimized 7456 46080 46080 1 0 +m=7456, n=46080, k=46080, time(sec)=53.483133, speed(mflops)=592030.385580 +Executable: ./dgemmoptimized 7456 46080 46080 1 0 +m=7456, n=46080, k=46080, time(sec)=53.664705, speed(mflops)=590027.276482 +Executable: ./dgemmoptimized 7456 46080 46080 1 0 +m=7456, n=46080, k=46080, time(sec)=53.350661, speed(mflops)=593500.420425 +Max repetitions 3, Elasped time 486.769, Relative error 0.0278322, Mean 41361.3, Standard Deviation 682.844 +Total Energy 41361.333333 +234 +Executable: ./dgemmoptimized 7488 46080 46080 1 0 +m=7488, n=46080, k=46080, time(sec)=52.747688, speed(mflops)=602861.213049 +Executable: ./dgemmoptimized 7488 46080 46080 1 0 +m=7488, n=46080, k=46080, time(sec)=52.377506, speed(mflops)=607121.980868 +Executable: ./dgemmoptimized 7488 46080 46080 1 0 +m=7488, n=46080, k=46080, time(sec)=52.381935, speed(mflops)=607070.649042 +Max repetitions 3, Elasped time 482.178, Relative error 0.0035532, Mean 40825.5, Standard Deviation 86.0461 +Total Energy 40825.466667 +235 +Executable: ./dgemmoptimized 7520 46080 46080 1 0 +m=7520, n=46080, k=46080, time(sec)=53.453206, speed(mflops)=597446.495890 +Executable: ./dgemmoptimized 7520 46080 46080 1 0 +m=7520, n=46080, k=46080, time(sec)=53.407218, speed(mflops)=597960.947307 +Executable: ./dgemmoptimized 7520 46080 46080 1 0 +m=7520, n=46080, k=46080, time(sec)=53.769925, speed(mflops)=593927.380926 +Max repetitions 3, Elasped time 485.529, Relative error 0.0016027, Mean 41496.4, Standard Deviation 39.4495 +Total Energy 41496.433333 +236 +Executable: ./dgemmoptimized 7552 46080 46080 1 0 +m=7552, n=46080, k=46080, time(sec)=54.306242, speed(mflops)=590564.269058 +Executable: ./dgemmoptimized 7552 46080 46080 1 0 +m=7552, n=46080, k=46080, time(sec)=54.314023, speed(mflops)=590479.664801 +Executable: ./dgemmoptimized 7552 46080 46080 1 0 +m=7552, n=46080, k=46080, time(sec)=54.705858, speed(mflops)=586250.308151 +Max repetitions 3, Elasped time 488.493, Relative error 0.00990491, Mean 41548.6, Standard Deviation 244.111 +Total Energy 41548.583333 +237 +Executable: ./dgemmoptimized 7584 46080 46080 1 0 +m=7584, n=46080, k=46080, time(sec)=55.143973, speed(mflops)=584056.967186 +Executable: ./dgemmoptimized 7584 46080 46080 1 0 +m=7584, n=46080, k=46080, time(sec)=55.130761, speed(mflops)=584196.935153 +Executable: ./dgemmoptimized 7584 46080 46080 1 0 +m=7584, n=46080, k=46080, time(sec)=55.597332, speed(mflops)=579294.372521 +Max repetitions 3, Elasped time 491.341, Relative error 0.00726317, Mean 42222.7, Standard Deviation 181.908 +Total Energy 42222.666667 +238 +Executable: ./dgemmoptimized 7616 46080 46080 1 0 +m=7616, n=46080, k=46080, time(sec)=56.164111, speed(mflops)=575868.049669 +Executable: ./dgemmoptimized 7616 46080 46080 1 0 +m=7616, n=46080, k=46080, time(sec)=56.117617, speed(mflops)=576345.159662 +Executable: ./dgemmoptimized 7616 46080 46080 1 0 +m=7616, n=46080, k=46080, time(sec)=56.198337, speed(mflops)=575517.331765 +Max repetitions 3, Elasped time 496.455, Relative error 0.014687, Mean 42383.6, Standard Deviation 369.242 +Total Energy 42383.633333 +239 +Executable: ./dgemmoptimized 7648 46080 46080 1 0 +m=7648, n=46080, k=46080, time(sec)=55.395308, speed(mflops)=586313.419252 +Executable: ./dgemmoptimized 7648 46080 46080 1 0 +m=7648, n=46080, k=46080, time(sec)=55.372451, speed(mflops)=586555.443518 +Executable: ./dgemmoptimized 7648 46080 46080 1 0 +m=7648, n=46080, k=46080, time(sec)=55.354879, speed(mflops)=586741.640455 +Max repetitions 3, Elasped time 494.214, Relative error 0.0096571, Mean 42543.4, Standard Deviation 243.702 +Total Energy 42543.383333 +240 +Executable: ./dgemmoptimized 7680 46080 46080 1 0 +m=7680, n=46080, k=46080, time(sec)=52.728408, speed(mflops)=618545.279107 +Executable: ./dgemmoptimized 7680 46080 46080 1 0 +m=7680, n=46080, k=46080, time(sec)=52.705643, speed(mflops)=618812.447502 +Executable: ./dgemmoptimized 7680 46080 46080 1 0 +m=7680, n=46080, k=46080, time(sec)=52.839583, speed(mflops)=617243.855867 +Max repetitions 3, Elasped time 484.724, Relative error 0.00865367, Mean 41369.2, Standard Deviation 212.352 +Total Energy 41369.200000 +241 +Executable: ./dgemmoptimized 7712 46080 46080 1 0 +m=7712, n=46080, k=46080, time(sec)=53.781881, speed(mflops)=608956.080237 +Executable: ./dgemmoptimized 7712 46080 46080 1 0 +m=7712, n=46080, k=46080, time(sec)=53.742121, speed(mflops)=609406.602412 +Executable: ./dgemmoptimized 7712 46080 46080 1 0 +m=7712, n=46080, k=46080, time(sec)=53.765980, speed(mflops)=609136.174034 +Max repetitions 3, Elasped time 488.076, Relative error 0.00346795, Mean 41583.5, Standard Deviation 85.541 +Total Energy 41583.516667 +242 +Executable: ./dgemmoptimized 7744 46080 46080 1 0 +m=7744, n=46080, k=46080, time(sec)=55.232710, speed(mflops)=595420.700376 +Executable: ./dgemmoptimized 7744 46080 46080 1 0 +m=7744, n=46080, k=46080, time(sec)=54.730954, speed(mflops)=600879.325087 +Executable: ./dgemmoptimized 7744 46080 46080 1 0 +m=7744, n=46080, k=46080, time(sec)=54.660697, speed(mflops)=601651.654995 +Max repetitions 3, Elasped time 491.713, Relative error 0.00293569, Mean 42219, Standard Deviation 73.5188 +Total Energy 42219.033333 +243 +Executable: ./dgemmoptimized 7776 46080 46080 1 0 +m=7776, n=46080, k=46080, time(sec)=55.938891, speed(mflops)=590333.374535 +Executable: ./dgemmoptimized 7776 46080 46080 1 0 +m=7776, n=46080, k=46080, time(sec)=55.515799, speed(mflops)=594832.371367 +Executable: ./dgemmoptimized 7776 46080 46080 1 0 +m=7776, n=46080, k=46080, time(sec)=55.563440, speed(mflops)=594322.351969 +Max repetitions 3, Elasped time 494.487, Relative error 0.00230339, Mean 42022.4, Standard Deviation 57.4154 +Total Energy 42022.366667 +244 +Executable: ./dgemmoptimized 7808 46080 46080 1 0 +m=7808, n=46080, k=46080, time(sec)=56.522564, speed(mflops)=586641.641751 +Executable: ./dgemmoptimized 7808 46080 46080 1 0 +m=7808, n=46080, k=46080, time(sec)=56.554042, speed(mflops)=586315.115076 +Executable: ./dgemmoptimized 7808 46080 46080 1 0 +m=7808, n=46080, k=46080, time(sec)=56.493742, speed(mflops)=586940.931773 +Max repetitions 3, Elasped time 497.304, Relative error 0.00281296, Mean 42783.8, Standard Deviation 71.3876 +Total Energy 42783.850000 +245 +Executable: ./dgemmoptimized 7840 46080 46080 1 0 +m=7840, n=46080, k=46080, time(sec)=56.507040, speed(mflops)=589207.736558 +Executable: ./dgemmoptimized 7840 46080 46080 1 0 +m=7840, n=46080, k=46080, time(sec)=56.543013, speed(mflops)=588832.880836 +Executable: ./dgemmoptimized 7840 46080 46080 1 0 +m=7840, n=46080, k=46080, time(sec)=56.557095, speed(mflops)=588686.266897 +Max repetitions 3, Elasped time 497.607, Relative error 0.00116225, Mean 42722, Standard Deviation 29.4531 +Total Energy 42722.033333 +246 +Executable: ./dgemmoptimized 7872 46080 46080 1 0 +m=7872, n=46080, k=46080, time(sec)=55.666585, speed(mflops)=600544.844281 +Executable: ./dgemmoptimized 7872 46080 46080 1 0 +m=7872, n=46080, k=46080, time(sec)=55.551931, speed(mflops)=601784.310894 +Executable: ./dgemmoptimized 7872 46080 46080 1 0 +m=7872, n=46080, k=46080, time(sec)=55.542699, speed(mflops)=601884.336630 +Max repetitions 3, Elasped time 495.052, Relative error 0.00978563, Mean 42139.6, Standard Deviation 244.601 +Total Energy 42139.566667 +247 +Executable: ./dgemmoptimized 7904 46080 46080 1 0 +m=7904, n=46080, k=46080, time(sec)=56.642118, speed(mflops)=592601.005223 +Executable: ./dgemmoptimized 7904 46080 46080 1 0 +m=7904, n=46080, k=46080, time(sec)=56.578235, speed(mflops)=593270.114605 +Executable: ./dgemmoptimized 7904 46080 46080 1 0 +m=7904, n=46080, k=46080, time(sec)=56.625664, speed(mflops)=592773.200041 +Max repetitions 3, Elasped time 500.474, Relative error 0.0172172, Mean 43103.1, Standard Deviation 440.202 +Total Energy 43103.150000 +248 +Executable: ./dgemmoptimized 7936 46080 46080 1 0 +m=7936, n=46080, k=46080, time(sec)=57.433505, speed(mflops)=586801.579785 +Executable: ./dgemmoptimized 7936 46080 46080 1 0 +m=7936, n=46080, k=46080, time(sec)=57.508771, speed(mflops)=586033.590152 +Executable: ./dgemmoptimized 7936 46080 46080 1 0 +m=7936, n=46080, k=46080, time(sec)=57.475947, speed(mflops)=586368.269105 +Max repetitions 3, Elasped time 501.298, Relative error 0.00184291, Mean 42752.8, Standard Deviation 46.7357 +Total Energy 42752.800000 +249 +Executable: ./dgemmoptimized 7968 46080 46080 1 0 +m=7968, n=46080, k=46080, time(sec)=58.286326, speed(mflops)=580547.262323 +Executable: ./dgemmoptimized 7968 46080 46080 1 0 +m=7968, n=46080, k=46080, time(sec)=58.384037, speed(mflops)=579575.662780 +Executable: ./dgemmoptimized 7968 46080 46080 1 0 +m=7968, n=46080, k=46080, time(sec)=58.277671, speed(mflops)=580633.479555 +Max repetitions 3, Elasped time 504.447, Relative error 0.00435739, Mean 43399.1, Standard Deviation 112.173 +Total Energy 43399.150000 +250 +Executable: ./dgemmoptimized 8000 46080 46080 1 0 +m=8000, n=46080, k=46080, time(sec)=59.335448, speed(mflops)=572572.779508 +Executable: ./dgemmoptimized 8000 46080 46080 1 0 +m=8000, n=46080, k=46080, time(sec)=59.332452, speed(mflops)=572601.691336 +Executable: ./dgemmoptimized 8000 46080 46080 1 0 +m=8000, n=46080, k=46080, time(sec)=59.727062, speed(mflops)=568818.576870 +Max repetitions 3, Elasped time 508.021, Relative error 0.00450069, Mean 43606.2, Standard Deviation 116.415 +Total Energy 43606.233333 +251 +Executable: ./dgemmoptimized 8032 46080 46080 1 0 +m=8032, n=46080, k=46080, time(sec)=57.956221, speed(mflops)=588543.513369 +Executable: ./dgemmoptimized 8032 46080 46080 1 0 +m=8032, n=46080, k=46080, time(sec)=58.006896, speed(mflops)=588029.358413 +Executable: ./dgemmoptimized 8032 46080 46080 1 0 +m=8032, n=46080, k=46080, time(sec)=57.943336, speed(mflops)=588674.387745 +Max repetitions 3, Elasped time 503.893, Relative error 0.00228763, Mean 43418.4, Standard Deviation 58.9169 +Total Energy 43418.450000 +252 +Executable: ./dgemmoptimized 8064 46080 46080 1 0 +m=8064, n=46080, k=46080, time(sec)=54.139685, speed(mflops)=632542.527756 +Executable: ./dgemmoptimized 8064 46080 46080 1 0 +m=8064, n=46080, k=46080, time(sec)=54.155125, speed(mflops)=632362.185665 +Executable: ./dgemmoptimized 8064 46080 46080 1 0 +m=8064, n=46080, k=46080, time(sec)=54.047362, speed(mflops)=633623.032217 +Max repetitions 3, Elasped time 492.613, Relative error 0.00195545, Mean 42073.3, Standard Deviation 48.8014 +Total Energy 42073.316667 +253 +Executable: ./dgemmoptimized 8096 46080 46080 1 0 +m=8096, n=46080, k=46080, time(sec)=55.116499, speed(mflops)=623797.763021 +Executable: ./dgemmoptimized 8096 46080 46080 1 0 +m=8096, n=46080, k=46080, time(sec)=55.031110, speed(mflops)=624765.677426 +Executable: ./dgemmoptimized 8096 46080 46080 1 0 +m=8096, n=46080, k=46080, time(sec)=55.131275, speed(mflops)=623630.576059 +Max repetitions 3, Elasped time 497.846, Relative error 0.00726726, Mean 42143.1, Standard Deviation 181.667 +Total Energy 42143.100000 +254 +Executable: ./dgemmoptimized 8128 46080 46080 1 0 +m=8128, n=46080, k=46080, time(sec)=56.004427, speed(mflops)=616334.209176 +Executable: ./dgemmoptimized 8128 46080 46080 1 0 +m=8128, n=46080, k=46080, time(sec)=55.981538, speed(mflops)=616586.206743 +Executable: ./dgemmoptimized 8128 46080 46080 1 0 +m=8128, n=46080, k=46080, time(sec)=56.013052, speed(mflops)=616239.304486 +Max repetitions 3, Elasped time 498.875, Relative error 3.71668e-05, Mean 42811.8, Standard Deviation 0.94384 +Total Energy 42811.816667 +255 +Executable: ./dgemmoptimized 8160 46080 46080 1 0 +m=8160, n=46080, k=46080, time(sec)=56.886831, speed(mflops)=609162.771266 +Executable: ./dgemmoptimized 8160 46080 46080 1 0 +m=8160, n=46080, k=46080, time(sec)=56.858173, speed(mflops)=609469.806793 +Executable: ./dgemmoptimized 8160 46080 46080 1 0 +m=8160, n=46080, k=46080, time(sec)=56.886783, speed(mflops)=609163.284432 +Max repetitions 3, Elasped time 503.868, Relative error 0.00414079, Mean 42663.8, Standard Deviation 104.791 +Total Energy 42663.833333 +256 +Executable: ./dgemmoptimized 8192 46080 46080 1 0 +m=8192, n=46080, k=46080, time(sec)=57.877360, speed(mflops)=601085.381817 +Executable: ./dgemmoptimized 8192 46080 46080 1 0 +m=8192, n=46080, k=46080, time(sec)=57.836113, speed(mflops)=601514.059425 +Executable: ./dgemmoptimized 8192 46080 46080 1 0 +m=8192, n=46080, k=46080, time(sec)=57.845354, speed(mflops)=601417.966822 +Max repetitions 3, Elasped time 505.15, Relative error 0.00299959, Mean 43410.1, Standard Deviation 77.2384 +Total Energy 43410.150000 +257 +Executable: ./dgemmoptimized 8224 46080 46080 1 0 +m=8224, n=46080, k=46080, time(sec)=57.890379, speed(mflops)=603297.664234 +Executable: ./dgemmoptimized 8224 46080 46080 1 0 +m=8224, n=46080, k=46080, time(sec)=57.874847, speed(mflops)=603459.575215 +Executable: ./dgemmoptimized 8224 46080 46080 1 0 +m=8224, n=46080, k=46080, time(sec)=57.887003, speed(mflops)=603332.851425 +Max repetitions 3, Elasped time 505.481, Relative error 0.000888927, Mean 43369.9, Standard Deviation 22.8683 +Total Energy 43369.916667 +258 +Executable: ./dgemmoptimized 8256 46080 46080 1 0 +m=8256, n=46080, k=46080, time(sec)=56.902087, speed(mflops)=616164.146430 +Executable: ./dgemmoptimized 8256 46080 46080 1 0 +m=8256, n=46080, k=46080, time(sec)=57.099084, speed(mflops)=614038.325230 +Executable: ./dgemmoptimized 8256 46080 46080 1 0 +m=8256, n=46080, k=46080, time(sec)=56.899235, speed(mflops)=616195.033036 +Max repetitions 3, Elasped time 502.988, Relative error 0.0160574, Mean 43382.5, Standard Deviation 413.208 +Total Energy 43382.483333 +259 +Executable: ./dgemmoptimized 8288 46080 46080 1 0 +m=8288, n=46080, k=46080, time(sec)=57.985879, speed(mflops)=606991.255236 +Executable: ./dgemmoptimized 8288 46080 46080 1 0 +m=8288, n=46080, k=46080, time(sec)=57.907240, speed(mflops)=607815.559828 +Executable: ./dgemmoptimized 8288 46080 46080 1 0 +m=8288, n=46080, k=46080, time(sec)=57.918734, speed(mflops)=607694.936869 +Max repetitions 3, Elasped time 506.178, Relative error 0.0105659, Mean 43598.4, Standard Deviation 273.248 +Total Energy 43598.450000 +260 +Executable: ./dgemmoptimized 8320 46080 46080 1 0 +m=8320, n=46080, k=46080, time(sec)=58.833381, speed(mflops)=600557.305899 +Executable: ./dgemmoptimized 8320 46080 46080 1 0 +m=8320, n=46080, k=46080, time(sec)=58.821051, speed(mflops)=600683.194584 +Executable: ./dgemmoptimized 8320 46080 46080 1 0 +m=8320, n=46080, k=46080, time(sec)=58.982409, speed(mflops)=599039.908590 +Max repetitions 3, Elasped time 509.261, Relative error 0.00274715, Mean 44180.4, Standard Deviation 71.9933 +Total Energy 44180.366667 +261 +Executable: ./dgemmoptimized 8352 46080 46080 1 0 +m=8352, n=46080, k=46080, time(sec)=59.669884, speed(mflops)=594415.641323 +Executable: ./dgemmoptimized 8352 46080 46080 1 0 +m=8352, n=46080, k=46080, time(sec)=59.668809, speed(mflops)=594426.348300 +Executable: ./dgemmoptimized 8352 46080 46080 1 0 +m=8352, n=46080, k=46080, time(sec)=59.682216, speed(mflops)=594292.818949 +Max repetitions 3, Elasped time 515.018, Relative error 0.0249121, Mean 44623.9, Standard Deviation 659.412 +Total Energy 44623.850000 +262 +Executable: ./dgemmoptimized 8384 46080 46080 1 0 +m=8384, n=46080, k=46080, time(sec)=60.709786, speed(mflops)=586472.300057 +Executable: ./dgemmoptimized 8384 46080 46080 1 0 +m=8384, n=46080, k=46080, time(sec)=60.841474, speed(mflops)=585202.912117 +Executable: ./dgemmoptimized 8384 46080 46080 1 0 +m=8384, n=46080, k=46080, time(sec)=60.649476, speed(mflops)=587055.488576 +Max repetitions 3, Elasped time 515.583, Relative error 0.00345611, Mean 44870.5, Standard Deviation 91.9873 +Total Energy 44870.483333 +263 +Executable: ./dgemmoptimized 8416 46080 46080 1 0 +m=8416, n=46080, k=46080, time(sec)=59.911308, speed(mflops)=596556.883967 +Executable: ./dgemmoptimized 8416 46080 46080 1 0 +m=8416, n=46080, k=46080, time(sec)=59.879150, speed(mflops)=596877.265229 +Executable: ./dgemmoptimized 8416 46080 46080 1 0 +m=8416, n=46080, k=46080, time(sec)=59.937015, speed(mflops)=596301.022886 +Max repetitions 3, Elasped time 513.428, Relative error 0.000101956, Mean 44090.1, Standard Deviation 2.66646 +Total Energy 44090.150000 +264 +Executable: ./dgemmoptimized 8448 46080 46080 1 0 +m=8448, n=46080, k=46080, time(sec)=57.194994, speed(mflops)=627264.664307 +Executable: ./dgemmoptimized 8448 46080 46080 1 0 +m=8448, n=46080, k=46080, time(sec)=57.218862, speed(mflops)=627003.009232 +Executable: ./dgemmoptimized 8448 46080 46080 1 0 +m=8448, n=46080, k=46080, time(sec)=57.391098, speed(mflops)=625121.315511 +Max repetitions 3, Elasped time 507.844, Relative error 0.0101622, Mean 43653.6, Standard Deviation 263.14 +Total Energy 43653.633333 +265 +Executable: ./dgemmoptimized 8480 46080 46080 1 0 +m=8480, n=46080, k=46080, time(sec)=58.270022, speed(mflops)=618024.379607 +Executable: ./dgemmoptimized 8480 46080 46080 1 0 +m=8480, n=46080, k=46080, time(sec)=58.301505, speed(mflops)=617690.642620 +Executable: ./dgemmoptimized 8480 46080 46080 1 0 +m=8480, n=46080, k=46080, time(sec)=58.351098, speed(mflops)=617165.663388 +Max repetitions 3, Elasped time 509.235, Relative error 0.00786625, Mean 44284.5, Standard Deviation 206.633 +Total Energy 44284.516667 +266 +Executable: ./dgemmoptimized 8512 46080 46080 1 0 +m=8512, n=46080, k=46080, time(sec)=59.083583, speed(mflops)=611814.444671 +Executable: ./dgemmoptimized 8512 46080 46080 1 0 +m=8512, n=46080, k=46080, time(sec)=59.147870, speed(mflops)=611149.472578 +Executable: ./dgemmoptimized 8512 46080 46080 1 0 +m=8512, n=46080, k=46080, time(sec)=59.179232, speed(mflops)=610825.593681 +Max repetitions 3, Elasped time 512.034, Relative error 0.00731511, Mean 44156.5, Standard Deviation 191.6 +Total Energy 44156.516667 +267 +Executable: ./dgemmoptimized 8544 46080 46080 1 0 +m=8544, n=46080, k=46080, time(sec)=60.166437, speed(mflops)=603061.888094 +Executable: ./dgemmoptimized 8544 46080 46080 1 0 +m=8544, n=46080, k=46080, time(sec)=60.025494, speed(mflops)=604477.909464 +Executable: ./dgemmoptimized 8544 46080 46080 1 0 +m=8544, n=46080, k=46080, time(sec)=60.056133, speed(mflops)=604169.519605 +Max repetitions 3, Elasped time 515.207, Relative error 0.00258967, Mean 44756.8, Standard Deviation 68.7517 +Total Energy 44756.816667 +268 +Executable: ./dgemmoptimized 8576 46080 46080 1 0 +m=8576, n=46080, k=46080, time(sec)=61.005928, speed(mflops)=596990.846718 +Executable: ./dgemmoptimized 8576 46080 46080 1 0 +m=8576, n=46080, k=46080, time(sec)=61.024667, speed(mflops)=596807.525031 +Executable: ./dgemmoptimized 8576 46080 46080 1 0 +m=8576, n=46080, k=46080, time(sec)=60.990590, speed(mflops)=597140.975940 +Max repetitions 3, Elasped time 573.501, Relative error 0.240896, Mean 48663.7, Standard Deviation 6953.69 +Total Energy 48663.716667 +269 +Executable: ./dgemmoptimized 8608 46080 46080 1 0 +m=8608, n=46080, k=46080, time(sec)=61.115877, speed(mflops)=598140.412053 +Executable: ./dgemmoptimized 8608 46080 46080 1 0 +m=8608, n=46080, k=46080, time(sec)=61.055522, speed(mflops)=598731.691514 +Executable: ./dgemmoptimized 8608 46080 46080 1 0 +m=8608, n=46080, k=46080, time(sec)=61.189565, speed(mflops)=597420.096610 +Max repetitions 3, Elasped time 519.001, Relative error 0.00125489, Mean 44678, Standard Deviation 33.2568 +Total Energy 44678.000000 +270 +Executable: ./dgemmoptimized 8640 46080 46080 1 0 +m=8640, n=46080, k=46080, time(sec)=60.028952, speed(mflops)=611234.580900 +Executable: ./dgemmoptimized 8640 46080 46080 1 0 +m=8640, n=46080, k=46080, time(sec)=59.991218, speed(mflops)=611619.042923 +Executable: ./dgemmoptimized 8640 46080 46080 1 0 +m=8640, n=46080, k=46080, time(sec)=60.072121, speed(mflops)=610795.335568 +Max repetitions 3, Elasped time 516.098, Relative error 0.00119237, Mean 44691.4, Standard Deviation 31.6093 +Total Energy 44691.416667 +271 +Executable: ./dgemmoptimized 8672 46080 46080 1 0 +m=8672, n=46080, k=46080, time(sec)=61.123247, speed(mflops)=602514.897432 +Executable: ./dgemmoptimized 8672 46080 46080 1 0 +m=8672, n=46080, k=46080, time(sec)=61.117283, speed(mflops)=602573.692968 +Executable: ./dgemmoptimized 8672 46080 46080 1 0 +m=8672, n=46080, k=46080, time(sec)=61.196937, speed(mflops)=601789.380258 +Max repetitions 3, Elasped time 519.666, Relative error 0.00791769, Mean 44933.6, Standard Deviation 211.033 +Total Energy 44933.583333 +272 +Executable: ./dgemmoptimized 8704 46080 46080 1 0 +m=8704, n=46080, k=46080, time(sec)=62.075665, speed(mflops)=595459.787550 +Executable: ./dgemmoptimized 8704 46080 46080 1 0 +m=8704, n=46080, k=46080, time(sec)=62.058000, speed(mflops)=595629.288423 +Executable: ./dgemmoptimized 8704 46080 46080 1 0 +m=8704, n=46080, k=46080, time(sec)=61.996087, speed(mflops)=596224.117288 +Max repetitions 3, Elasped time 529.896, Relative error 0.0225209, Mean 46037.8, Standard Deviation 615.009 +Total Energy 46037.850000 +273 +Executable: ./dgemmoptimized 8736 46080 46080 1 0 +m=8736, n=46080, k=46080, time(sec)=62.799498, speed(mflops)=590760.420309 +Executable: ./dgemmoptimized 8736 46080 46080 1 0 +m=8736, n=46080, k=46080, time(sec)=62.824492, speed(mflops)=590525.391817 +Executable: ./dgemmoptimized 8736 46080 46080 1 0 +m=8736, n=46080, k=46080, time(sec)=66.875908, speed(mflops)=554750.713293 +Max repetitions 3, Elasped time 529.385, Relative error 0.027015, Mean 45655.3, Standard Deviation 731.605 +Total Energy 45655.316667 +274 +Executable: ./dgemmoptimized 8768 46080 46080 1 0 +m=8768, n=46080, k=46080, time(sec)=63.825147, speed(mflops)=583396.276420 +Executable: ./dgemmoptimized 8768 46080 46080 1 0 +m=8768, n=46080, k=46080, time(sec)=63.827802, speed(mflops)=583372.011208 +Executable: ./dgemmoptimized 8768 46080 46080 1 0 +m=8768, n=46080, k=46080, time(sec)=63.812721, speed(mflops)=583509.880142 +Max repetitions 3, Elasped time 528.655, Relative error 0.00620814, Mean 46037.8, Standard Deviation 169.534 +Total Energy 46037.766667 +275 +Executable: ./dgemmoptimized 8800 46080 46080 1 0 +m=8800, n=46080, k=46080, time(sec)=63.022476, speed(mflops)=592982.869556 +Executable: ./dgemmoptimized 8800 46080 46080 1 0 +m=8800, n=46080, k=46080, time(sec)=63.056594, speed(mflops)=592662.025200 +Executable: ./dgemmoptimized 8800 46080 46080 1 0 +m=8800, n=46080, k=46080, time(sec)=63.051537, speed(mflops)=592709.557867 +Max repetitions 3, Elasped time 526.706, Relative error 0.00700904, Mean 45718.4, Standard Deviation 190.077 +Total Energy 45718.433333 +276 +Executable: ./dgemmoptimized 8832 46080 46080 1 0 +m=8832, n=46080, k=46080, time(sec)=60.407090, speed(mflops)=620906.322776 +Executable: ./dgemmoptimized 8832 46080 46080 1 0 +m=8832, n=46080, k=46080, time(sec)=60.466887, speed(mflops)=620292.294712 +Executable: ./dgemmoptimized 8832 46080 46080 1 0 +m=8832, n=46080, k=46080, time(sec)=60.394708, speed(mflops)=621033.617587 +Max repetitions 3, Elasped time 519.075, Relative error 0.00695607, Mean 44805.4, Standard Deviation 184.873 +Total Energy 44805.433333 +277 +Executable: ./dgemmoptimized 8864 46080 46080 1 0 +m=8864, n=46080, k=46080, time(sec)=61.455535, speed(mflops)=612524.804788 +Executable: ./dgemmoptimized 8864 46080 46080 1 0 +m=8864, n=46080, k=46080, time(sec)=61.416829, speed(mflops)=612910.829675 +Executable: ./dgemmoptimized 8864 46080 46080 1 0 +m=8864, n=46080, k=46080, time(sec)=61.449701, speed(mflops)=612582.958571 +Max repetitions 3, Elasped time 523.838, Relative error 0.00515811, Mean 45215.1, Standard Deviation 138.342 +Total Energy 45215.150000 +278 +Executable: ./dgemmoptimized 8896 46080 46080 1 0 +m=8896, n=46080, k=46080, time(sec)=62.352757, speed(mflops)=605890.367578 +Executable: ./dgemmoptimized 8896 46080 46080 1 0 +m=8896, n=46080, k=46080, time(sec)=62.285730, speed(mflops)=606542.382316 +Executable: ./dgemmoptimized 8896 46080 46080 1 0 +m=8896, n=46080, k=46080, time(sec)=62.353088, speed(mflops)=605887.154268 +Max repetitions 3, Elasped time 525.469, Relative error 0.00636541, Mean 45440.1, Standard Deviation 171.572 +Total Energy 45440.066667 +279 +Executable: ./dgemmoptimized 8928 46080 46080 1 0 +m=8928, n=46080, k=46080, time(sec)=63.188691, speed(mflops)=600025.572581 +Executable: ./dgemmoptimized 8928 46080 46080 1 0 +m=8928, n=46080, k=46080, time(sec)=63.185951, speed(mflops)=600051.591242 +Executable: ./dgemmoptimized 8928 46080 46080 1 0 +m=8928, n=46080, k=46080, time(sec)=63.302723, speed(mflops)=598944.698429 +Max repetitions 3, Elasped time 528.49, Relative error 0.00651029, Mean 46027.6, Standard Deviation 177.745 +Total Energy 46027.566667 +280 +Executable: ./dgemmoptimized 8960 46080 46080 1 0 +m=8960, n=46080, k=46080, time(sec)=64.117749, speed(mflops)=593450.744854 +Executable: ./dgemmoptimized 8960 46080 46080 1 0 +m=8960, n=46080, k=46080, time(sec)=64.160848, speed(mflops)=593052.104703 +Executable: ./dgemmoptimized 8960 46080 46080 1 0 +m=8960, n=46080, k=46080, time(sec)=64.097140, speed(mflops)=593641.554743 +Max repetitions 3, Elasped time 531.453, Relative error 0.00241386, Mean 45957.4, Standard Deviation 65.8034 +Total Energy 45957.433333 +281 +Executable: ./dgemmoptimized 8992 46080 46080 1 0 +m=8992, n=46080, k=46080, time(sec)=64.209624, speed(mflops)=594718.033338 +Executable: ./dgemmoptimized 8992 46080 46080 1 0 +m=8992, n=46080, k=46080, time(sec)=64.195579, speed(mflops)=594848.150657 +Executable: ./dgemmoptimized 8992 46080 46080 1 0 +m=8992, n=46080, k=46080, time(sec)=64.222790, speed(mflops)=594596.113559 +Max repetitions 3, Elasped time 534.029, Relative error 0.0127063, Mean 46145.2, Standard Deviation 347.796 +Total Energy 46145.216667 +282 +Executable: ./dgemmoptimized 9024 46080 46080 1 0 +m=9024, n=46080, k=46080, time(sec)=63.214588, speed(mflops)=606229.005741 +Executable: ./dgemmoptimized 9024 46080 46080 1 0 +m=9024, n=46080, k=46080, time(sec)=63.243345, speed(mflops)=605953.350092 +Executable: ./dgemmoptimized 9024 46080 46080 1 0 +m=9024, n=46080, k=46080, time(sec)=63.112622, speed(mflops)=607208.440389 +Max repetitions 3, Elasped time 529.257, Relative error 0.00368003, Mean 46282.5, Standard Deviation 101.029 +Total Energy 46282.450000 +283 +Executable: ./dgemmoptimized 9056 46080 46080 1 0 +m=9056, n=46080, k=46080, time(sec)=64.213260, speed(mflops)=598916.988103 +Executable: ./dgemmoptimized 9056 46080 46080 1 0 +m=9056, n=46080, k=46080, time(sec)=64.230198, speed(mflops)=598759.049330 +Executable: ./dgemmoptimized 9056 46080 46080 1 0 +m=9056, n=46080, k=46080, time(sec)=64.331735, speed(mflops)=597814.007335 +Max repetitions 3, Elasped time 532.795, Relative error 0.00521262, Mean 46569, Standard Deviation 143.99 +Total Energy 46569.016667 +284 +Executable: ./dgemmoptimized 9088 46080 46080 1 0 +m=9088, n=46080, k=46080, time(sec)=65.134576, speed(mflops)=592531.801200 +Executable: ./dgemmoptimized 9088 46080 46080 1 0 +m=9088, n=46080, k=46080, time(sec)=65.116741, speed(mflops)=592694.092611 +Executable: ./dgemmoptimized 9088 46080 46080 1 0 +m=9088, n=46080, k=46080, time(sec)=65.119942, speed(mflops)=592664.956225 +Max repetitions 3, Elasped time 535.703, Relative error 0.000627258, Mean 46700, Standard Deviation 17.3757 +Total Energy 46699.983333 +285 +Executable: ./dgemmoptimized 9120 46080 46080 1 0 +m=9120, n=46080, k=46080, time(sec)=65.965846, speed(mflops)=587125.087424 +Executable: ./dgemmoptimized 9120 46080 46080 1 0 +m=9120, n=46080, k=46080, time(sec)=65.938428, speed(mflops)=587369.222390 +Executable: ./dgemmoptimized 9120 46080 46080 1 0 +m=9120, n=46080, k=46080, time(sec)=65.947408, speed(mflops)=587289.240526 +Max repetitions 3, Elasped time 538.535, Relative error 0.0055743, Mean 46707.2, Standard Deviation 154.438 +Total Energy 46707.166667 +286 +Executable: ./dgemmoptimized 9152 46080 46080 1 0 +m=9152, n=46080, k=46080, time(sec)=66.964744, speed(mflops)=580396.434744 +Executable: ./dgemmoptimized 9152 46080 46080 1 0 +m=9152, n=46080, k=46080, time(sec)=66.976446, speed(mflops)=580295.028433 +Executable: ./dgemmoptimized 9152 46080 46080 1 0 +m=9152, n=46080, k=46080, time(sec)=66.961718, speed(mflops)=580422.660867 +Max repetitions 3, Elasped time 541.874, Relative error 0.00149302, Mean 47368.6, Standard Deviation 41.9504 +Total Energy 47368.600000 +287 +Executable: ./dgemmoptimized 9184 46080 46080 1 0 +m=9184, n=46080, k=46080, time(sec)=65.615180, speed(mflops)=594405.045082 +Executable: ./dgemmoptimized 9184 46080 46080 1 0 +m=9184, n=46080, k=46080, time(sec)=65.588283, speed(mflops)=594648.803329 +Executable: ./dgemmoptimized 9184 46080 46080 1 0 +m=9184, n=46080, k=46080, time(sec)=66.243936, speed(mflops)=588763.234099 +Max repetitions 3, Elasped time 540.766, Relative error 0.0150068, Mean 47007.3, Standard Deviation 418.439 +Total Energy 47007.333333 +288 +Executable: ./dgemmoptimized 9216 46080 46080 1 0 +m=9216, n=46080, k=46080, time(sec)=61.763890, speed(mflops)=633669.438033 +Executable: ./dgemmoptimized 9216 46080 46080 1 0 +m=9216, n=46080, k=46080, time(sec)=61.782649, speed(mflops)=633477.037531 +Executable: ./dgemmoptimized 9216 46080 46080 1 0 +m=9216, n=46080, k=46080, time(sec)=61.729243, speed(mflops)=634025.102342 +Max repetitions 3, Elasped time 528.769, Relative error 0.0100499, Mean 45860.6, Standard Deviation 273.389 +Total Energy 45860.550000 +289 +Executable: ./dgemmoptimized 9248 46080 46080 1 0 +m=9248, n=46080, k=46080, time(sec)=62.701460, speed(mflops)=626361.568890 +Executable: ./dgemmoptimized 9248 46080 46080 1 0 +m=9248, n=46080, k=46080, time(sec)=62.830638, speed(mflops)=625073.789272 +Executable: ./dgemmoptimized 9248 46080 46080 1 0 +m=9248, n=46080, k=46080, time(sec)=62.756695, speed(mflops)=625810.280709 +Max repetitions 3, Elasped time 530.215, Relative error 0.00355605, Mean 46225, Standard Deviation 97.5046 +Total Energy 46225.016667 +290 +Executable: ./dgemmoptimized 9280 46080 46080 1 0 +m=9280, n=46080, k=46080, time(sec)=63.658860, speed(mflops)=619076.125518 +Executable: ./dgemmoptimized 9280 46080 46080 1 0 +m=9280, n=46080, k=46080, time(sec)=63.658453, speed(mflops)=619080.083389 +Executable: ./dgemmoptimized 9280 46080 46080 1 0 +m=9280, n=46080, k=46080, time(sec)=63.704536, speed(mflops)=618632.249484 +Max repetitions 3, Elasped time 533.239, Relative error 0.00522703, Mean 46939.3, Standard Deviation 145.536 +Total Energy 46939.266667 +291 +Executable: ./dgemmoptimized 9312 46080 46080 1 0 +m=9312, n=46080, k=46080, time(sec)=64.579023, speed(mflops)=612359.461654 +Executable: ./dgemmoptimized 9312 46080 46080 1 0 +m=9312, n=46080, k=46080, time(sec)=64.528534, speed(mflops)=612838.591267 +Executable: ./dgemmoptimized 9312 46080 46080 1 0 +m=9312, n=46080, k=46080, time(sec)=64.549027, speed(mflops)=612644.027219 +Max repetitions 3, Elasped time 536.238, Relative error 0.00339558, Mean 46591.4, Standard Deviation 93.8424 +Total Energy 46591.383333 +292 +Executable: ./dgemmoptimized 9344 46080 46080 1 0 +m=9344, n=46080, k=46080, time(sec)=65.510768, speed(mflops)=605724.410398 +Executable: ./dgemmoptimized 9344 46080 46080 1 0 +m=9344, n=46080, k=46080, time(sec)=65.494716, speed(mflops)=605872.866541 +Executable: ./dgemmoptimized 9344 46080 46080 1 0 +m=9344, n=46080, k=46080, time(sec)=65.504548, speed(mflops)=605781.928051 +Max repetitions 3, Elasped time 541.396, Relative error 0.0131344, Mean 47585.6, Standard Deviation 370.738 +Total Energy 47585.600000 +293 +Executable: ./dgemmoptimized 9376 46080 46080 1 0 +m=9376, n=46080, k=46080, time(sec)=65.594117, speed(mflops)=607026.492598 +Executable: ./dgemmoptimized 9376 46080 46080 1 0 +m=9376, n=46080, k=46080, time(sec)=65.560479, speed(mflops)=607337.947880 +Executable: ./dgemmoptimized 9376 46080 46080 1 0 +m=9376, n=46080, k=46080, time(sec)=65.563045, speed(mflops)=607314.177029 +Max repetitions 3, Elasped time 539.89, Relative error 0.000609663, Mean 47342, Standard Deviation 17.1205 +Total Energy 47341.983333 +294 +Executable: ./dgemmoptimized 9408 46080 46080 1 0 +m=9408, n=46080, k=46080, time(sec)=64.522563, speed(mflops)=619213.811987 +Executable: ./dgemmoptimized 9408 46080 46080 1 0 +m=9408, n=46080, k=46080, time(sec)=64.598207, speed(mflops)=618488.717254 +Executable: ./dgemmoptimized 9408 46080 46080 1 0 +m=9408, n=46080, k=46080, time(sec)=64.518432, speed(mflops)=619253.459897 +Max repetitions 3, Elasped time 537.074, Relative error 0.00151028, Mean 46555.4, Standard Deviation 41.7069 +Total Energy 46555.366667 +295 +Executable: ./dgemmoptimized 9440 46080 46080 1 0 +m=9440, n=46080, k=46080, time(sec)=65.549210, speed(mflops)=611588.722247 +Executable: ./dgemmoptimized 9440 46080 46080 1 0 +m=9440, n=46080, k=46080, time(sec)=65.569067, speed(mflops)=611403.508779 +Executable: ./dgemmoptimized 9440 46080 46080 1 0 +m=9440, n=46080, k=46080, time(sec)=65.547044, speed(mflops)=611608.932483 +Max repetitions 3, Elasped time 542.53, Relative error 0.0122247, Mean 47593, Standard Deviation 345.113 +Total Energy 47593.016667 +296 +Executable: ./dgemmoptimized 9472 46080 46080 1 0 +m=9472, n=46080, k=46080, time(sec)=66.484702, speed(mflops)=605027.200981 +Executable: ./dgemmoptimized 9472 46080 46080 1 0 +m=9472, n=46080, k=46080, time(sec)=66.600781, speed(mflops)=603972.693705 +Executable: ./dgemmoptimized 9472 46080 46080 1 0 +m=9472, n=46080, k=46080, time(sec)=66.557361, speed(mflops)=604366.705667 +Max repetitions 3, Elasped time 543.819, Relative error 0.00170663, Mean 47341.6, Standard Deviation 47.925 +Total Energy 47341.583333 +297 +Executable: ./dgemmoptimized 9504 46080 46080 1 0 +m=9504, n=46080, k=46080, time(sec)=67.368154, speed(mflops)=599110.204235 +Executable: ./dgemmoptimized 9504 46080 46080 1 0 +m=9504, n=46080, k=46080, time(sec)=67.343494, speed(mflops)=599329.588811 +Executable: ./dgemmoptimized 9504 46080 46080 1 0 +m=9504, n=46080, k=46080, time(sec)=67.349284, speed(mflops)=599278.064648 +Max repetitions 3, Elasped time 546.487, Relative error 0.00587214, Mean 47976.4, Standard Deviation 167.111 +Total Energy 47976.433333 +298 +Executable: ./dgemmoptimized 9536 46080 46080 1 0 +m=9536, n=46080, k=46080, time(sec)=68.339482, speed(mflops)=592583.421706 +Executable: ./dgemmoptimized 9536 46080 46080 1 0 +m=9536, n=46080, k=46080, time(sec)=68.307580, speed(mflops)=592860.177220 +Executable: ./dgemmoptimized 9536 46080 46080 1 0 +m=9536, n=46080, k=46080, time(sec)=68.304366, speed(mflops)=592888.074767 +Max repetitions 3, Elasped time 549.691, Relative error 0.0053994, Mean 48075.4, Standard Deviation 153.974 +Total Energy 48075.416667 +299 +Executable: ./dgemmoptimized 9568 46080 46080 1 0 +m=9568, n=46080, k=46080, time(sec)=67.455093, speed(mflops)=602367.259155 +Executable: ./dgemmoptimized 9568 46080 46080 1 0 +m=9568, n=46080, k=46080, time(sec)=67.522138, speed(mflops)=601769.148696 +Executable: ./dgemmoptimized 9568 46080 46080 1 0 +m=9568, n=46080, k=46080, time(sec)=67.521596, speed(mflops)=601773.978470 +Max repetitions 3, Elasped time 547.549, Relative error 0.0247236, Mean 48246.8, Standard Deviation 707.554 +Total Energy 48246.766667 +300 +Executable: ./dgemmoptimized 9600 46080 46080 1 0 +m=9600, n=46080, k=46080, time(sec)=65.040256, speed(mflops)=626821.562100 +Executable: ./dgemmoptimized 9600 46080 46080 1 0 +m=9600, n=46080, k=46080, time(sec)=64.844131, speed(mflops)=628717.422159 +Executable: ./dgemmoptimized 9600 46080 46080 1 0 +m=9600, n=46080, k=46080, time(sec)=64.845698, speed(mflops)=628702.227952 +Max repetitions 3, Elasped time 542.121, Relative error 0.0052325, Mean 47231.3, Standard Deviation 146.595 +Total Energy 47231.316667 +301 +Executable: ./dgemmoptimized 9632 46080 46080 1 0 +m=9632, n=46080, k=46080, time(sec)=65.913484, speed(mflops)=620579.095314 +Executable: ./dgemmoptimized 9632 46080 46080 1 0 +m=9632, n=46080, k=46080, time(sec)=65.921954, speed(mflops)=620499.361736 +Executable: ./dgemmoptimized 9632 46080 46080 1 0 +m=9632, n=46080, k=46080, time(sec)=65.823513, speed(mflops)=621427.335705 +Max repetitions 3, Elasped time 543.495, Relative error 0.00180506, Mean 47535.1, Standard Deviation 50.8962 +Total Energy 47535.133333 +302 +Executable: ./dgemmoptimized 9664 46080 46080 1 0 +m=9664, n=46080, k=46080, time(sec)=66.919791, speed(mflops)=613277.853625 +Executable: ./dgemmoptimized 9664 46080 46080 1 0 +m=9664, n=46080, k=46080, time(sec)=66.878139, speed(mflops)=613659.807637 +Executable: ./dgemmoptimized 9664 46080 46080 1 0 +m=9664, n=46080, k=46080, time(sec)=66.806273, speed(mflops)=614319.940327 +Max repetitions 3, Elasped time 546.711, Relative error 0.0015788, Mean 48141.2, Standard Deviation 45.0842 +Total Energy 48141.250000 +303 +Executable: ./dgemmoptimized 9696 46080 46080 1 0 +m=9696, n=46080, k=46080, time(sec)=67.710260, speed(mflops)=608125.284645 +Executable: ./dgemmoptimized 9696 46080 46080 1 0 +m=9696, n=46080, k=46080, time(sec)=67.744776, speed(mflops)=607815.445761 +Executable: ./dgemmoptimized 9696 46080 46080 1 0 +m=9696, n=46080, k=46080, time(sec)=67.683061, speed(mflops)=608369.667251 +Max repetitions 3, Elasped time 551.538, Relative error 0.00638207, Mean 47770.9, Standard Deviation 180.844 +Total Energy 47770.866667 +304 +Executable: ./dgemmoptimized 9728 46080 46080 1 0 +m=9728, n=46080, k=46080, time(sec)=68.710419, speed(mflops)=601251.122794 +Executable: ./dgemmoptimized 9728 46080 46080 1 0 +m=9728, n=46080, k=46080, time(sec)=68.678411, speed(mflops)=601531.341111 +Executable: ./dgemmoptimized 9728 46080 46080 1 0 +m=9728, n=46080, k=46080, time(sec)=68.734498, speed(mflops)=601040.494454 +Max repetitions 3, Elasped time 552.882, Relative error 0.00632916, Mean 48601.8, Standard Deviation 182.465 +Total Energy 48601.800000 +305 +Executable: ./dgemmoptimized 9760 46080 46080 1 0 +m=9760, n=46080, k=46080, time(sec)=68.749794, speed(mflops)=602883.437355 +Executable: ./dgemmoptimized 9760 46080 46080 1 0 +m=9760, n=46080, k=46080, time(sec)=68.664096, speed(mflops)=603635.882737 +Executable: ./dgemmoptimized 9760 46080 46080 1 0 +m=9760, n=46080, k=46080, time(sec)=68.685404, speed(mflops)=603448.617561 +Max repetitions 3, Elasped time 555.122, Relative error 0.00652177, Mean 48598, Standard Deviation 188.002 +Total Energy 48598.000000 +306 +Executable: ./dgemmoptimized 9792 46080 46080 1 0 +m=9792, n=46080, k=46080, time(sec)=70.686021, speed(mflops)=588291.816075 +Executable: ./dgemmoptimized 9792 46080 46080 1 0 +m=9792, n=46080, k=46080, time(sec)=67.677146, speed(mflops)=614446.824589 +Executable: ./dgemmoptimized 9792 46080 46080 1 0 +m=9792, n=46080, k=46080, time(sec)=67.648736, speed(mflops)=614704.871612 +Max repetitions 3, Elasped time 553.323, Relative error 0.0243469, Mean 48223.4, Standard Deviation 696.437 +Total Energy 48223.383333 +307 +Executable: ./dgemmoptimized 9824 46080 46080 1 0 +m=9824, n=46080, k=46080, time(sec)=71.832392, speed(mflops)=580795.124300 +Executable: ./dgemmoptimized 9824 46080 46080 1 0 +m=9824, n=46080, k=46080, time(sec)=68.840098, speed(mflops)=606040.725578 +Executable: ./dgemmoptimized 9824 46080 46080 1 0 +m=9824, n=46080, k=46080, time(sec)=68.771531, speed(mflops)=606644.966332 +Max repetitions 3, Elasped time 557.127, Relative error 0.0302123, Mean 48979.6, Standard Deviation 877.767 +Total Energy 48979.566667 +308 +Executable: ./dgemmoptimized 9856 46080 46080 1 0 +m=9856, n=46080, k=46080, time(sec)=69.676628, speed(mflops)=600715.040473 +Executable: ./dgemmoptimized 9856 46080 46080 1 0 +m=9856, n=46080, k=46080, time(sec)=69.667355, speed(mflops)=600794.998467 +Executable: ./dgemmoptimized 9856 46080 46080 1 0 +m=9856, n=46080, k=46080, time(sec)=69.664180, speed(mflops)=600822.380347 +Max repetitions 3, Elasped time 558.82, Relative error 0.00953926, Mean 49188.4, Standard Deviation 278.329 +Total Energy 49188.450000 +309 +Executable: ./dgemmoptimized 9888 46080 46080 1 0 +m=9888, n=46080, k=46080, time(sec)=70.493490, speed(mflops)=595681.869885 +Executable: ./dgemmoptimized 9888 46080 46080 1 0 +m=9888, n=46080, k=46080, time(sec)=70.446962, speed(mflops)=596075.299856 +Executable: ./dgemmoptimized 9888 46080 46080 1 0 +m=9888, n=46080, k=46080, time(sec)=70.481104, speed(mflops)=595786.552772 +Max repetitions 3, Elasped time 560.332, Relative error 0.00358959, Mean 49101.4, Standard Deviation 104.549 +Total Energy 49101.450000 +310 +Executable: ./dgemmoptimized 9920 46080 46080 1 0 +m=9920, n=46080, k=46080, time(sec)=71.512708, speed(mflops)=589092.352736 +Executable: ./dgemmoptimized 9920 46080 46080 1 0 +m=9920, n=46080, k=46080, time(sec)=71.461285, speed(mflops)=589516.257770 +Executable: ./dgemmoptimized 9920 46080 46080 1 0 +m=9920, n=46080, k=46080, time(sec)=71.494058, speed(mflops)=589246.022349 +Max repetitions 3, Elasped time 567.201, Relative error 0.00520584, Mean 50101.9, Standard Deviation 154.712 +Total Energy 50101.850000 +311 +Executable: ./dgemmoptimized 9952 46080 46080 1 0 +m=9952, n=46080, k=46080, time(sec)=70.677556, speed(mflops)=597976.036451 +Executable: ./dgemmoptimized 9952 46080 46080 1 0 +m=9952, n=46080, k=46080, time(sec)=70.692302, speed(mflops)=597851.302571 +Executable: ./dgemmoptimized 9952 46080 46080 1 0 +m=9952, n=46080, k=46080, time(sec)=70.713780, speed(mflops)=597669.716845 +Max repetitions 3, Elasped time 560.996, Relative error 0.0023476, Mean 49178.4, Standard Deviation 68.4824 +Total Energy 49178.450000 +312 +Executable: ./dgemmoptimized 9984 46080 46080 1 0 +m=9984, n=46080, k=46080, time(sec)=67.977591, speed(mflops)=623725.843001 +Executable: ./dgemmoptimized 9984 46080 46080 1 0 +m=9984, n=46080, k=46080, time(sec)=68.173593, speed(mflops)=621932.604427 +Executable: ./dgemmoptimized 9984 46080 46080 1 0 +m=9984, n=46080, k=46080, time(sec)=68.008778, speed(mflops)=623439.818545 +Max repetitions 3, Elasped time 553.38, Relative error 0.00537953, Mean 48651.8, Standard Deviation 155.247 +Total Energy 48651.783333 +313 +Executable: ./dgemmoptimized 10016 46080 46080 1 0 +m=10016, n=46080, k=46080, time(sec)=69.064741, speed(mflops)=615875.409449 +Executable: ./dgemmoptimized 10016 46080 46080 1 0 +m=10016, n=46080, k=46080, time(sec)=69.083859, speed(mflops)=615704.975966 +Executable: ./dgemmoptimized 10016 46080 46080 1 0 +m=10016, n=46080, k=46080, time(sec)=69.197906, speed(mflops)=614690.214963 +Max repetitions 3, Elasped time 559.005, Relative error 0.0171354, Mean 49273, Standard Deviation 500.822 +Total Energy 49272.966667 +314 +Executable: ./dgemmoptimized 10048 46080 46080 1 0 +m=10048, n=46080, k=46080, time(sec)=69.976405, speed(mflops)=609793.702417 +Executable: ./dgemmoptimized 10048 46080 46080 1 0 +m=10048, n=46080, k=46080, time(sec)=69.986615, speed(mflops)=609704.742315 +Executable: ./dgemmoptimized 10048 46080 46080 1 0 +m=10048, n=46080, k=46080, time(sec)=69.974948, speed(mflops)=609806.401249 +Max repetitions 3, Elasped time 561.076, Relative error 0.0118221, Mean 49452.6, Standard Deviation 346.788 +Total Energy 49452.583333 +315 +Executable: ./dgemmoptimized 10080 46080 46080 1 0 +m=10080, n=46080, k=46080, time(sec)=70.844261, speed(mflops)=604241.838610 +Executable: ./dgemmoptimized 10080 46080 46080 1 0 +m=10080, n=46080, k=46080, time(sec)=70.815263, speed(mflops)=604489.269553 +Executable: ./dgemmoptimized 10080 46080 46080 1 0 +m=10080, n=46080, k=46080, time(sec)=70.920863, speed(mflops)=603589.195981 +Max repetitions 3, Elasped time 562.761, Relative error 0.00733995, Mean 49346, Standard Deviation 214.845 +Total Energy 49345.983333 +316 +Executable: ./dgemmoptimized 10112 46080 46080 1 0 +m=10112, n=46080, k=46080, time(sec)=71.919348, speed(mflops)=597098.879049 +Executable: ./dgemmoptimized 10112 46080 46080 1 0 +m=10112, n=46080, k=46080, time(sec)=71.916288, speed(mflops)=597124.286141 +Executable: ./dgemmoptimized 10112 46080 46080 1 0 +m=10112, n=46080, k=46080, time(sec)=71.865105, speed(mflops)=597549.561539 +Max repetitions 3, Elasped time 568.253, Relative error 0.00206655, Mean 49889.4, Standard Deviation 61.1552 +Total Energy 49889.383333 +317 +Executable: ./dgemmoptimized 10144 46080 46080 1 0 +m=10144, n=46080, k=46080, time(sec)=73.540041, speed(mflops)=585787.782480 +Executable: ./dgemmoptimized 10144 46080 46080 1 0 +m=10144, n=46080, k=46080, time(sec)=71.899799, speed(mflops)=599151.293887 +Executable: ./dgemmoptimized 10144 46080 46080 1 0 +m=10144, n=46080, k=46080, time(sec)=71.801873, speed(mflops)=599968.437341 +Max repetitions 3, Elasped time 568.085, Relative error 0.0141495, Mean 50102.3, Standard Deviation 420.513 +Total Energy 50102.316667 +318 +Executable: ./dgemmoptimized 10176 46080 46080 1 0 +m=10176, n=46080, k=46080, time(sec)=70.842057, speed(mflops)=610015.502219 +Executable: ./dgemmoptimized 10176 46080 46080 1 0 +m=10176, n=46080, k=46080, time(sec)=70.898740, speed(mflops)=609527.798948 +Executable: ./dgemmoptimized 10176 46080 46080 1 0 +m=10176, n=46080, k=46080, time(sec)=70.882906, speed(mflops)=609663.957586 +Max repetitions 3, Elasped time 563.76, Relative error 0.00123526, Mean 49966.4, Standard Deviation 36.6113 +Total Energy 49966.383333 +319 +Executable: ./dgemmoptimized 10208 46080 46080 1 0 +m=10208, n=46080, k=46080, time(sec)=71.937194, speed(mflops)=602618.007319 +Executable: ./dgemmoptimized 10208 46080 46080 1 0 +m=10208, n=46080, k=46080, time(sec)=71.894474, speed(mflops)=602976.084151 +Executable: ./dgemmoptimized 10208 46080 46080 1 0 +m=10208, n=46080, k=46080, time(sec)=71.955063, speed(mflops)=602468.355882 +Max repetitions 3, Elasped time 567.304, Relative error 0.00117949, Mean 49842.3, Standard Deviation 34.8717 +Total Energy 49842.316667 +320 +Executable: ./dgemmoptimized 10240 46080 46080 1 0 +m=10240, n=46080, k=46080, time(sec)=72.818311, speed(mflops)=597192.427140 +Executable: ./dgemmoptimized 10240 46080 46080 1 0 +m=10240, n=46080, k=46080, time(sec)=72.751117, speed(mflops)=597744.002712 +Executable: ./dgemmoptimized 10240 46080 46080 1 0 +m=10240, n=46080, k=46080, time(sec)=73.242519, speed(mflops)=593733.592509 +Max repetitions 3, Elasped time 570.518, Relative error 0.00405822, Mean 50542.2, Standard Deviation 121.666 +Total Energy 50542.233333 +321 +Executable: ./dgemmoptimized 10272 46080 46080 1 0 +m=10272, n=46080, k=46080, time(sec)=73.670614, speed(mflops)=592128.081343 +Executable: ./dgemmoptimized 10272 46080 46080 1 0 +m=10272, n=46080, k=46080, time(sec)=73.644867, speed(mflops)=592335.095875 +Executable: ./dgemmoptimized 10272 46080 46080 1 0 +m=10272, n=46080, k=46080, time(sec)=73.634782, speed(mflops)=592416.222783 +Max repetitions 3, Elasped time 574.991, Relative error 0.00109187, Mean 50445.5, Standard Deviation 32.6719 +Total Energy 50445.516667 +322 +Executable: ./dgemmoptimized 10304 46080 46080 1 0 +m=10304, n=46080, k=46080, time(sec)=74.597264, speed(mflops)=586594.365459 +Executable: ./dgemmoptimized 10304 46080 46080 1 0 +m=10304, n=46080, k=46080, time(sec)=74.593993, speed(mflops)=586620.086976 +Executable: ./dgemmoptimized 10304 46080 46080 1 0 +m=10304, n=46080, k=46080, time(sec)=74.648456, speed(mflops)=586192.093706 +Max repetitions 3, Elasped time 577.681, Relative error 0.00648265, Mean 50996.4, Standard Deviation 196.097 +Total Energy 50996.416667 +323 +Executable: ./dgemmoptimized 10336 46080 46080 1 0 +m=10336, n=46080, k=46080, time(sec)=73.325229, speed(mflops)=598623.839556 +Executable: ./dgemmoptimized 10336 46080 46080 1 0 +m=10336, n=46080, k=46080, time(sec)=73.272812, speed(mflops)=599052.077965 +Executable: ./dgemmoptimized 10336 46080 46080 1 0 +m=10336, n=46080, k=46080, time(sec)=73.288841, speed(mflops)=598921.058328 +Max repetitions 3, Elasped time 572.513, Relative error 0.00493614, Mean 50504.7, Standard Deviation 147.877 +Total Energy 50504.733333 +324 +Executable: ./dgemmoptimized 10368 46080 46080 1 0 +m=10368, n=46080, k=46080, time(sec)=69.419083, speed(mflops)=634265.447536 +Executable: ./dgemmoptimized 10368 46080 46080 1 0 +m=10368, n=46080, k=46080, time(sec)=69.370082, speed(mflops)=634713.471747 +Executable: ./dgemmoptimized 10368 46080 46080 1 0 +m=10368, n=46080, k=46080, time(sec)=69.527257, speed(mflops)=633278.624701 +Max repetitions 3, Elasped time 561.345, Relative error 0.00351234, Mean 49170.8, Standard Deviation 102.443 +Total Energy 49170.783333 +325 +Executable: ./dgemmoptimized 10400 46080 46080 1 0 +m=10400, n=46080, k=46080, time(sec)=70.453585, speed(mflops)=626881.104443 +Executable: ./dgemmoptimized 10400 46080 46080 1 0 +m=10400, n=46080, k=46080, time(sec)=70.381369, speed(mflops)=627524.326759 +Executable: ./dgemmoptimized 10400 46080 46080 1 0 +m=10400, n=46080, k=46080, time(sec)=70.487112, speed(mflops)=626582.928970 +Max repetitions 3, Elasped time 564.647, Relative error 0.0031946, Mean 50025.5, Standard Deviation 94.7955 +Total Energy 50025.500000 +326 +Executable: ./dgemmoptimized 10432 46080 46080 1 0 +m=10432, n=46080, k=46080, time(sec)=71.297958, speed(mflops)=621363.049885 +Executable: ./dgemmoptimized 10432 46080 46080 1 0 +m=10432, n=46080, k=46080, time(sec)=74.331008, speed(mflops)=596008.553993 +Executable: ./dgemmoptimized 10432 46080 46080 1 0 +m=10432, n=46080, k=46080, time(sec)=71.284200, speed(mflops)=621482.973769 +Max repetitions 3, Elasped time 574.518, Relative error 0.0295906, Mean 50203.4, Standard Deviation 881.186 +Total Energy 50203.416667 +327 +Executable: ./dgemmoptimized 10464 46080 46080 1 0 +m=10464, n=46080, k=46080, time(sec)=72.268627, speed(mflops)=614897.691590 +Executable: ./dgemmoptimized 10464 46080 46080 1 0 +m=10464, n=46080, k=46080, time(sec)=72.211583, speed(mflops)=615383.436218 +Executable: ./dgemmoptimized 10464 46080 46080 1 0 +m=10464, n=46080, k=46080, time(sec)=72.181066, speed(mflops)=615643.609321 +Max repetitions 3, Elasped time 572.619, Relative error 0.00653895, Mean 50508, Standard Deviation 195.906 +Total Energy 50508.033333 +328 +Executable: ./dgemmoptimized 10496 46080 46080 1 0 +m=10496, n=46080, k=46080, time(sec)=73.129687, speed(mflops)=609515.905977 +Executable: ./dgemmoptimized 10496 46080 46080 1 0 +m=10496, n=46080, k=46080, time(sec)=73.212939, speed(mflops)=608822.812785 +Executable: ./dgemmoptimized 10496 46080 46080 1 0 +m=10496, n=46080, k=46080, time(sec)=73.167664, speed(mflops)=609199.544528 +Max repetitions 3, Elasped time 577.031, Relative error 0.0187919, Mean 50766.4, Standard Deviation 565.883 +Total Energy 50766.400000 +329 +Executable: ./dgemmoptimized 10528 46080 46080 1 0 +m=10528, n=46080, k=46080, time(sec)=73.260988, speed(mflops)=610278.459802 +Executable: ./dgemmoptimized 10528 46080 46080 1 0 +m=10528, n=46080, k=46080, time(sec)=73.209354, speed(mflops)=610708.883175 +Executable: ./dgemmoptimized 10528 46080 46080 1 0 +m=10528, n=46080, k=46080, time(sec)=73.261989, speed(mflops)=610270.120392 +Max repetitions 3, Elasped time 576.302, Relative error 0.00538162, Mean 50484.4, Standard Deviation 161.157 +Total Energy 50484.416667 +330 +Executable: ./dgemmoptimized 10560 46080 46080 1 0 +m=10560, n=46080, k=46080, time(sec)=72.351749, speed(mflops)=619826.042565 +Executable: ./dgemmoptimized 10560 46080 46080 1 0 +m=10560, n=46080, k=46080, time(sec)=72.299932, speed(mflops)=620270.270325 +Executable: ./dgemmoptimized 10560 46080 46080 1 0 +m=10560, n=46080, k=46080, time(sec)=72.197076, speed(mflops)=621153.941427 +Max repetitions 3, Elasped time 571.795, Relative error 0.00304263, Mean 50389.3, Standard Deviation 90.9427 +Total Energy 50389.316667 +331 +Executable: ./dgemmoptimized 10592 46080 46080 1 0 +m=10592, n=46080, k=46080, time(sec)=73.284642, speed(mflops)=613790.183067 +Executable: ./dgemmoptimized 10592 46080 46080 1 0 +m=10592, n=46080, k=46080, time(sec)=73.232342, speed(mflops)=614228.530540 +Executable: ./dgemmoptimized 10592 46080 46080 1 0 +m=10592, n=46080, k=46080, time(sec)=73.192270, speed(mflops)=614564.813917 +Max repetitions 3, Elasped time 574.927, Relative error 0.00449, Mean 50890.2, Standard Deviation 135.538 +Total Energy 50890.200000 +332 +Executable: ./dgemmoptimized 10624 46080 46080 1 0 +m=10624, n=46080, k=46080, time(sec)=74.184804, speed(mflops)=608174.273668 +Executable: ./dgemmoptimized 10624 46080 46080 1 0 +m=10624, n=46080, k=46080, time(sec)=74.146185, speed(mflops)=608491.041247 +Executable: ./dgemmoptimized 10624 46080 46080 1 0 +m=10624, n=46080, k=46080, time(sec)=74.144635, speed(mflops)=608503.761469 +Max repetitions 3, Elasped time 580.003, Relative error 0.00549825, Mean 51183.2, Standard Deviation 166.929 +Total Energy 51183.150000 +333 +Executable: ./dgemmoptimized 10656 46080 46080 1 0 +m=10656, n=46080, k=46080, time(sec)=75.106675, speed(mflops)=602518.814357 +Executable: ./dgemmoptimized 10656 46080 46080 1 0 +m=10656, n=46080, k=46080, time(sec)=75.000795, speed(mflops)=603369.399495 +Executable: ./dgemmoptimized 10656 46080 46080 1 0 +m=10656, n=46080, k=46080, time(sec)=75.008587, speed(mflops)=603306.722563 +Max repetitions 3, Elasped time 581.008, Relative error 0.00588055, Mean 51571.4, Standard Deviation 179.89 +Total Energy 51571.416667 +334 +Executable: ./dgemmoptimized 10688 46080 46080 1 0 +m=10688, n=46080, k=46080, time(sec)=76.065288, speed(mflops)=596712.131380 +Executable: ./dgemmoptimized 10688 46080 46080 1 0 +m=10688, n=46080, k=46080, time(sec)=76.091992, speed(mflops)=596502.720355 +Executable: ./dgemmoptimized 10688 46080 46080 1 0 +m=10688, n=46080, k=46080, time(sec)=76.984191, speed(mflops)=589589.623684 +Max repetitions 3, Elasped time 585.348, Relative error 0.0149189, Mean 51920.5, Standard Deviation 459.468 +Total Energy 51920.533333 +335 +Executable: ./dgemmoptimized 10720 46080 46080 1 0 +m=10720, n=46080, k=46080, time(sec)=75.224260, speed(mflops)=605190.075123 +Executable: ./dgemmoptimized 10720 46080 46080 1 0 +m=10720, n=46080, k=46080, time(sec)=75.179670, speed(mflops)=605549.020875 +Executable: ./dgemmoptimized 10720 46080 46080 1 0 +m=10720, n=46080, k=46080, time(sec)=75.171183, speed(mflops)=605617.390566 +Max repetitions 3, Elasped time 585.336, Relative error 0.00553537, Mean 51964, Standard Deviation 170.62 +Total Energy 51964.000000 +336 +Executable: ./dgemmoptimized 10752 46080 46080 1 0 +m=10752, n=46080, k=46080, time(sec)=72.665496, speed(mflops)=628370.735207 +Executable: ./dgemmoptimized 10752 46080 46080 1 0 +m=10752, n=46080, k=46080, time(sec)=72.635063, speed(mflops)=628634.012581 +Executable: ./dgemmoptimized 10752 46080 46080 1 0 +m=10752, n=46080, k=46080, time(sec)=72.644612, speed(mflops)=628551.380645 +Max repetitions 3, Elasped time 576.811, Relative error 0.00418019, Mean 50912.3, Standard Deviation 126.241 +Total Energy 50912.333333 +337 +Executable: ./dgemmoptimized 10784 46080 46080 1 0 +m=10784, n=46080, k=46080, time(sec)=73.640734, speed(mflops)=621894.487659 +Executable: ./dgemmoptimized 10784 46080 46080 1 0 +m=10784, n=46080, k=46080, time(sec)=73.507303, speed(mflops)=623023.354775 +Executable: ./dgemmoptimized 10784 46080 46080 1 0 +m=10784, n=46080, k=46080, time(sec)=73.584769, speed(mflops)=622367.469940 +Max repetitions 3, Elasped time 579.83, Relative error 0.00570557, Mean 51300.1, Standard Deviation 173.619 +Total Energy 51300.083333 +338 +Executable: ./dgemmoptimized 10816 46080 46080 1 0 +m=10816, n=46080, k=46080, time(sec)=74.543467, speed(mflops)=616186.284134 +Executable: ./dgemmoptimized 10816 46080 46080 1 0 +m=10816, n=46080, k=46080, time(sec)=74.518625, speed(mflops)=616391.700087 +Executable: ./dgemmoptimized 10816 46080 46080 1 0 +m=10816, n=46080, k=46080, time(sec)=74.525922, speed(mflops)=616331.347471 +Max repetitions 3, Elasped time 581.065, Relative error 0.00320328, Mean 51960.8, Standard Deviation 98.7304 +Total Energy 51960.800000 +339 +Executable: ./dgemmoptimized 10848 46080 46080 1 0 +m=10848, n=46080, k=46080, time(sec)=75.353180, speed(mflops)=611368.457923 +Executable: ./dgemmoptimized 10848 46080 46080 1 0 +m=10848, n=46080, k=46080, time(sec)=75.421329, speed(mflops)=610816.038541 +Executable: ./dgemmoptimized 10848 46080 46080 1 0 +m=10848, n=46080, k=46080, time(sec)=75.467740, speed(mflops)=610440.399811 +Max repetitions 3, Elasped time 583.979, Relative error 0.00380829, Mean 51692.9, Standard Deviation 116.773 +Total Energy 51692.933333 +340 +Executable: ./dgemmoptimized 10880 46080 46080 1 0 +m=10880, n=46080, k=46080, time(sec)=76.352263, speed(mflops)=605148.440458 +Executable: ./dgemmoptimized 10880 46080 46080 1 0 +m=10880, n=46080, k=46080, time(sec)=76.326890, speed(mflops)=605349.607052 +Executable: ./dgemmoptimized 10880 46080 46080 1 0 +m=10880, n=46080, k=46080, time(sec)=76.390732, speed(mflops)=604843.697974 +Max repetitions 3, Elasped time 587.139, Relative error 0.00305948, Mean 52537.6, Standard Deviation 95.3451 +Total Energy 52537.616667 +341 +Executable: ./dgemmoptimized 10912 46080 46080 1 0 +m=10912, n=46080, k=46080, time(sec)=76.383556, speed(mflops)=606679.639741 +Executable: ./dgemmoptimized 10912 46080 46080 1 0 +m=10912, n=46080, k=46080, time(sec)=76.368035, speed(mflops)=606802.943285 +Executable: ./dgemmoptimized 10912 46080 46080 1 0 +m=10912, n=46080, k=46080, time(sec)=76.340517, speed(mflops)=607021.672212 +Max repetitions 3, Elasped time 587.476, Relative error 0.00187466, Mean 52545.9, Standard Deviation 58.4308 +Total Energy 52545.900000 +342 +Executable: ./dgemmoptimized 10944 46080 46080 1 0 +m=10944, n=46080, k=46080, time(sec)=75.421937, speed(mflops)=616216.522921 +Executable: ./dgemmoptimized 10944 46080 46080 1 0 +m=10944, n=46080, k=46080, time(sec)=75.310954, speed(mflops)=617124.617824 +Executable: ./dgemmoptimized 10944 46080 46080 1 0 +m=10944, n=46080, k=46080, time(sec)=75.330506, speed(mflops)=616964.443461 +Max repetitions 3, Elasped time 590.837, Relative error 0.00104107, Mean 52063, Standard Deviation 32.1505 +Total Energy 52063.000000 +343 +Executable: ./dgemmoptimized 10976 46080 46080 1 0 +m=10976, n=46080, k=46080, time(sec)=76.457340, speed(mflops)=609648.978261 +Executable: ./dgemmoptimized 10976 46080 46080 1 0 +m=10976, n=46080, k=46080, time(sec)=76.370348, speed(mflops)=610343.417933 +Executable: ./dgemmoptimized 10976 46080 46080 1 0 +m=10976, n=46080, k=46080, time(sec)=76.391077, speed(mflops)=610177.798480 +Max repetitions 3, Elasped time 590.273, Relative error 0.00391908, Mean 52616.4, Standard Deviation 122.317 +Total Energy 52616.383333 +344 +Executable: ./dgemmoptimized 11008 46080 46080 1 0 +m=11008, n=46080, k=46080, time(sec)=77.378150, speed(mflops)=604150.327589 +Executable: ./dgemmoptimized 11008 46080 46080 1 0 +m=11008, n=46080, k=46080, time(sec)=77.376397, speed(mflops)=604164.015626 +Executable: ./dgemmoptimized 11008 46080 46080 1 0 +m=11008, n=46080, k=46080, time(sec)=77.467417, speed(mflops)=603454.154943 +Max repetitions 3, Elasped time 593.589, Relative error 0.00666063, Mean 52516.5, Standard Deviation 207.487 +Total Energy 52516.533333 +345 +Executable: ./dgemmoptimized 11040 46080 46080 1 0 +m=11040, n=46080, k=46080, time(sec)=78.192265, speed(mflops)=599598.056045 +Executable: ./dgemmoptimized 11040 46080 46080 1 0 +m=11040, n=46080, k=46080, time(sec)=78.224623, speed(mflops)=599350.028062 +Executable: ./dgemmoptimized 11040 46080 46080 1 0 +m=11040, n=46080, k=46080, time(sec)=78.251639, speed(mflops)=599143.107767 +Max repetitions 3, Elasped time 594.281, Relative error 0.000459723, Mean 53047.9, Standard Deviation 14.4659 +Total Energy 53047.883333 +346 +Executable: ./dgemmoptimized 11072 46080 46080 1 0 +m=11072, n=46080, k=46080, time(sec)=79.463796, speed(mflops)=591713.809890 +Executable: ./dgemmoptimized 11072 46080 46080 1 0 +m=11072, n=46080, k=46080, time(sec)=79.193908, speed(mflops)=593730.335618 +Executable: ./dgemmoptimized 11072 46080 46080 1 0 +m=11072, n=46080, k=46080, time(sec)=79.252168, speed(mflops)=593293.869963 +Max repetitions 3, Elasped time 597.863, Relative error 0.00285009, Mean 53076.8, Standard Deviation 89.7311 +Total Energy 53076.816667 +347 +Executable: ./dgemmoptimized 11104 46080 46080 1 0 +m=11104, n=46080, k=46080, time(sec)=78.490603, speed(mflops)=600781.739811 +Executable: ./dgemmoptimized 11104 46080 46080 1 0 +m=11104, n=46080, k=46080, time(sec)=78.286204, speed(mflops)=602350.331754 +Executable: ./dgemmoptimized 11104 46080 46080 1 0 +m=11104, n=46080, k=46080, time(sec)=78.401360, speed(mflops)=601465.599451 +Max repetitions 3, Elasped time 597.445, Relative error 0.00441152, Mean 53326.8, Standard Deviation 139.545 +Total Energy 53326.766667 +348 +Executable: ./dgemmoptimized 11136 46080 46080 1 0 +m=11136, n=46080, k=46080, time(sec)=75.728274, speed(mflops)=624490.880947 +Executable: ./dgemmoptimized 11136 46080 46080 1 0 +m=11136, n=46080, k=46080, time(sec)=75.688419, speed(mflops)=624819.717070 +Executable: ./dgemmoptimized 11136 46080 46080 1 0 +m=11136, n=46080, k=46080, time(sec)=75.840781, speed(mflops)=623564.470906 +Max repetitions 3, Elasped time 587.869, Relative error 0.000976196, Mean 52517.5, Standard Deviation 30.4104 +Total Energy 52517.550000 +349 +Executable: ./dgemmoptimized 11168 46080 46080 1 0 +m=11168, n=46080, k=46080, time(sec)=76.722274, speed(mflops)=618171.352301 +Executable: ./dgemmoptimized 11168 46080 46080 1 0 +m=11168, n=46080, k=46080, time(sec)=76.839332, speed(mflops)=617229.622017 +Executable: ./dgemmoptimized 11168 46080 46080 1 0 +m=11168, n=46080, k=46080, time(sec)=76.746250, speed(mflops)=617978.231068 +Max repetitions 3, Elasped time 591.264, Relative error 0.00910413, Mean 52637.3, Standard Deviation 284.258 +Total Energy 52637.300000 +350 +Executable: ./dgemmoptimized 11200 46080 46080 1 0 +m=11200, n=46080, k=46080, time(sec)=88.163690, speed(mflops)=539489.754115 +Executable: ./dgemmoptimized 11200 46080 46080 1 0 +m=11200, n=46080, k=46080, time(sec)=77.623690, speed(mflops)=612743.447618 +Executable: ./dgemmoptimized 11200 46080 46080 1 0 +m=11200, n=46080, k=46080, time(sec)=78.324462, speed(mflops)=607261.207850 +Max repetitions 3, Elasped time 608.922, Relative error 0.0637832, Mean 54350.7, Standard Deviation 2056.32 +Total Energy 54350.716667 +351 +Executable: ./dgemmoptimized 11232 46080 46080 1 0 +m=11232, n=46080, k=46080, time(sec)=78.536875, speed(mflops)=607349.131269 +Executable: ./dgemmoptimized 11232 46080 46080 1 0 +m=11232, n=46080, k=46080, time(sec)=78.536260, speed(mflops)=607353.886368 +Executable: ./dgemmoptimized 11232 46080 46080 1 0 +m=11232, n=46080, k=46080, time(sec)=78.475114, speed(mflops)=607827.124525 +Max repetitions 3, Elasped time 597.121, Relative error 0.00159907, Mean 53055.5, Standard Deviation 50.3243 +Total Energy 53055.483333 +352 +Executable: ./dgemmoptimized 11264 46080 46080 1 0 +m=11264, n=46080, k=46080, time(sec)=79.553595, speed(mflops)=601295.242779 +Executable: ./dgemmoptimized 11264 46080 46080 1 0 +m=11264, n=46080, k=46080, time(sec)=79.508366, speed(mflops)=601637.296102 +Executable: ./dgemmoptimized 11264 46080 46080 1 0 +m=11264, n=46080, k=46080, time(sec)=80.830835, speed(mflops)=591793.938509 +Max repetitions 3, Elasped time 603.5, Relative error 0.014403, Mean 54116.9, Standard Deviation 462.346 +Total Energy 54116.916667 +353 +Executable: ./dgemmoptimized 11296 46080 46080 1 0 +m=11296, n=46080, k=46080, time(sec)=79.488791, speed(mflops)=603495.071042 +Executable: ./dgemmoptimized 11296 46080 46080 1 0 +m=11296, n=46080, k=46080, time(sec)=97.054005, speed(mflops)=494272.170988 +Executable: ./dgemmoptimized 11296 46080 46080 1 0 +m=11296, n=46080, k=46080, time(sec)=109.382625, speed(mflops)=438562.282297 +Max repetitions 3, Elasped time 649.487, Relative error 0.113905, Mean 58248.2, Standard Deviation 3935.56 +Total Energy 58248.166667 +354 +Executable: ./dgemmoptimized 11328 46080 46080 1 0 +m=11328, n=46080, k=46080, time(sec)=78.547197, speed(mflops)=612459.653971 +Executable: ./dgemmoptimized 11328 46080 46080 1 0 +m=11328, n=46080, k=46080, time(sec)=78.577877, speed(mflops)=612220.527121 +Executable: ./dgemmoptimized 11328 46080 46080 1 0 +m=11328, n=46080, k=46080, time(sec)=78.463862, speed(mflops)=613110.137171 +Max repetitions 3, Elasped time 598.1, Relative error 0.00169803, Mean 53090.5, Standard Deviation 53.474 +Total Energy 53090.466667 +355 +Executable: ./dgemmoptimized 11360 46080 46080 1 0 +m=11360, n=46080, k=46080, time(sec)=79.556574, speed(mflops)=606397.212230 +Executable: ./dgemmoptimized 11360 46080 46080 1 0 +m=11360, n=46080, k=46080, time(sec)=79.646640, speed(mflops)=605711.484756 +Executable: ./dgemmoptimized 11360 46080 46080 1 0 +m=11360, n=46080, k=46080, time(sec)=79.799338, speed(mflops)=604552.440600 +Max repetitions 3, Elasped time 603.799, Relative error 0.000309488, Mean 53862.3, Standard Deviation 9.888 +Total Energy 53862.350000 +356 +Executable: ./dgemmoptimized 11392 46080 46080 1 0 +m=11392, n=46080, k=46080, time(sec)=80.566460, speed(mflops)=600482.880568 +Executable: ./dgemmoptimized 11392 46080 46080 1 0 +m=11392, n=46080, k=46080, time(sec)=80.534951, speed(mflops)=600717.818462 +Executable: ./dgemmoptimized 11392 46080 46080 1 0 +m=11392, n=46080, k=46080, time(sec)=80.530777, speed(mflops)=600748.954292 +Max repetitions 3, Elasped time 608.121, Relative error 0.00883281, Mean 54427.9, Standard Deviation 285.168 +Total Energy 54427.883333 +357 +Executable: ./dgemmoptimized 11424 46080 46080 1 0 +m=11424, n=46080, k=46080, time(sec)=81.385330, speed(mflops)=596110.816654 +Executable: ./dgemmoptimized 11424 46080 46080 1 0 +m=11424, n=46080, k=46080, time(sec)=81.433773, speed(mflops)=595756.204037 +Executable: ./dgemmoptimized 11424 46080 46080 1 0 +m=11424, n=46080, k=46080, time(sec)=81.327849, speed(mflops)=596532.136982 +Max repetitions 3, Elasped time 607.745, Relative error 0.0012958, Mean 54380.2, Standard Deviation 41.7981 +Total Energy 54380.150000 +358 +Executable: ./dgemmoptimized 11456 46080 46080 1 0 +m=11456, n=46080, k=46080, time(sec)=82.356598, speed(mflops)=590730.702786 +Executable: ./dgemmoptimized 11456 46080 46080 1 0 +m=11456, n=46080, k=46080, time(sec)=82.902778, speed(mflops)=586838.851280 +Executable: ./dgemmoptimized 11456 46080 46080 1 0 +m=11456, n=46080, k=46080, time(sec)=82.367044, speed(mflops)=590655.784288 +Max repetitions 3, Elasped time 611.427, Relative error 0.0130486, Mean 54965.9, Standard Deviation 425.437 +Total Energy 54965.883333 +359 +Executable: ./dgemmoptimized 11488 46080 46080 1 0 +m=11488, n=46080, k=46080, time(sec)=80.903676, speed(mflops)=603019.155600 +Executable: ./dgemmoptimized 11488 46080 46080 1 0 +m=11488, n=46080, k=46080, time(sec)=80.932056, speed(mflops)=602807.698799 +Executable: ./dgemmoptimized 11488 46080 46080 1 0 +m=11488, n=46080, k=46080, time(sec)=80.865882, speed(mflops)=603300.985586 +Max repetitions 3, Elasped time 608.075, Relative error 0.00310112, Mean 54445.1, Standard Deviation 100.151 +Total Energy 54445.133333 +360 +Executable: ./dgemmoptimized 11520 46080 46080 1 0 +m=11520, n=46080, k=46080, time(sec)=77.157580, speed(mflops)=634057.752576 +Executable: ./dgemmoptimized 11520 46080 46080 1 0 +m=11520, n=46080, k=46080, time(sec)=77.162095, speed(mflops)=634020.652390 +Executable: ./dgemmoptimized 11520 46080 46080 1 0 +m=11520, n=46080, k=46080, time(sec)=77.073046, speed(mflops)=634753.190832 +Max repetitions 3, Elasped time 595.847, Relative error 0.00472715, Mean 53213.8, Standard Deviation 149.212 +Total Energy 53213.800000 +361 +Executable: ./dgemmoptimized 11552 46080 46080 1 0 +m=11552, n=46080, k=46080, time(sec)=78.048964, speed(mflops)=628557.443642 +Executable: ./dgemmoptimized 11552 46080 46080 1 0 +m=11552, n=46080, k=46080, time(sec)=78.064791, speed(mflops)=628430.009223 +Executable: ./dgemmoptimized 11552 46080 46080 1 0 +m=11552, n=46080, k=46080, time(sec)=78.111722, speed(mflops)=628052.436359 +Max repetitions 3, Elasped time 600.973, Relative error 0.0131799, Mean 53891.5, Standard Deviation 421.321 +Total Energy 53891.533333 +362 +Executable: ./dgemmoptimized 11584 46080 46080 1 0 +m=11584, n=46080, k=46080, time(sec)=78.939452, speed(mflops)=623188.425440 +Executable: ./dgemmoptimized 11584 46080 46080 1 0 +m=11584, n=46080, k=46080, time(sec)=79.055356, speed(mflops)=622274.760729 +Executable: ./dgemmoptimized 11584 46080 46080 1 0 +m=11584, n=46080, k=46080, time(sec)=79.034293, speed(mflops)=622440.600498 +Max repetitions 3, Elasped time 602.088, Relative error 0.00494547, Mean 53853.2, Standard Deviation 157.979 +Total Energy 53853.250000 +363 +Executable: ./dgemmoptimized 11616 46080 46080 1 0 +m=11616, n=46080, k=46080, time(sec)=79.938873, speed(mflops)=617097.118349 +Executable: ./dgemmoptimized 11616 46080 46080 1 0 +m=11616, n=46080, k=46080, time(sec)=79.924141, speed(mflops)=617210.865587 +Executable: ./dgemmoptimized 11616 46080 46080 1 0 +m=11616, n=46080, k=46080, time(sec)=79.968265, speed(mflops)=616870.306863 +Max repetitions 3, Elasped time 610.723, Relative error 0.0174203, Mean 54537.7, Standard Deviation 563.549 +Total Energy 54537.666667 +364 +Executable: ./dgemmoptimized 11648 46080 46080 1 0 +m=11648, n=46080, k=46080, time(sec)=80.903389, speed(mflops)=611419.920474 +Executable: ./dgemmoptimized 11648 46080 46080 1 0 +m=11648, n=46080, k=46080, time(sec)=80.894921, speed(mflops)=611483.922644 +Executable: ./dgemmoptimized 11648 46080 46080 1 0 +m=11648, n=46080, k=46080, time(sec)=80.907382, speed(mflops)=611389.744973 +Max repetitions 3, Elasped time 673.272, Relative error 0.198263, Mean 58997, Standard Deviation 6938.26 +Total Energy 58996.983333 +365 +Executable: ./dgemmoptimized 11680 46080 46080 1 0 +m=11680, n=46080, k=46080, time(sec)=80.916494, speed(mflops)=613000.348528 +Executable: ./dgemmoptimized 11680 46080 46080 1 0 +m=11680, n=46080, k=46080, time(sec)=80.857112, speed(mflops)=613450.539764 +Executable: ./dgemmoptimized 11680 46080 46080 1 0 +m=11680, n=46080, k=46080, time(sec)=80.926799, speed(mflops)=612922.291266 +Max repetitions 3, Elasped time 616.731, Relative error 0.0238918, Mean 54981.5, Standard Deviation 779.194 +Total Energy 54981.550000 +366 +Executable: ./dgemmoptimized 11712 46080 46080 1 0 +m=11712, n=46080, k=46080, time(sec)=80.276300, speed(mflops)=619581.799793 +Executable: ./dgemmoptimized 11712 46080 46080 1 0 +m=11712, n=46080, k=46080, time(sec)=79.933953, speed(mflops)=622235.391317 +Executable: ./dgemmoptimized 11712 46080 46080 1 0 +m=11712, n=46080, k=46080, time(sec)=79.964606, speed(mflops)=621996.868522 +Max repetitions 3, Elasped time 612.002, Relative error 0.0143541, Mean 54716.5, Standard Deviation 465.879 +Total Energy 54716.533333 +367 +Executable: ./dgemmoptimized 11744 46080 46080 1 0 +m=11744, n=46080, k=46080, time(sec)=80.919062, speed(mflops)=616339.695897 +Executable: ./dgemmoptimized 11744 46080 46080 1 0 +m=11744, n=46080, k=46080, time(sec)=81.052373, speed(mflops)=615325.968286 +Executable: ./dgemmoptimized 11744 46080 46080 1 0 +m=11744, n=46080, k=46080, time(sec)=80.973151, speed(mflops)=615927.986744 +Max repetitions 3, Elasped time 609.483, Relative error 0.00118079, Mean 54492.8, Standard Deviation 38.1674 +Total Energy 54492.850000 +368 +Executable: ./dgemmoptimized 11776 46080 46080 1 0 +m=11776, n=46080, k=46080, time(sec)=81.812804, speed(mflops)=611267.711381 +Executable: ./dgemmoptimized 11776 46080 46080 1 0 +m=11776, n=46080, k=46080, time(sec)=81.883518, speed(mflops)=610739.825134 +Executable: ./dgemmoptimized 11776 46080 46080 1 0 +m=11776, n=46080, k=46080, time(sec)=81.869805, speed(mflops)=610842.123526 +Max repetitions 3, Elasped time 612.495, Relative error 0.00240512, Mean 55222.9, Standard Deviation 78.7838 +Total Energy 55222.950000 +369 +Executable: ./dgemmoptimized 11808 46080 46080 1 0 +m=11808, n=46080, k=46080, time(sec)=82.765016, speed(mflops)=605877.016915 +Executable: ./dgemmoptimized 11808 46080 46080 1 0 +m=11808, n=46080, k=46080, time(sec)=82.755351, speed(mflops)=605947.775656 +Executable: ./dgemmoptimized 11808 46080 46080 1 0 +m=11808, n=46080, k=46080, time(sec)=82.746219, speed(mflops)=606014.650059 +Max repetitions 3, Elasped time 615.468, Relative error 0.00308616, Mean 54993.3, Standard Deviation 100.672 +Total Energy 54993.350000 +370 +Executable: ./dgemmoptimized 11840 46080 46080 1 0 +m=11840, n=46080, k=46080, time(sec)=83.870061, speed(mflops)=599514.484669 +Executable: ./dgemmoptimized 11840 46080 46080 1 0 +m=11840, n=46080, k=46080, time(sec)=83.730112, speed(mflops)=600516.529901 +Executable: ./dgemmoptimized 11840 46080 46080 1 0 +m=11840, n=46080, k=46080, time(sec)=83.743119, speed(mflops)=600423.258073 +Max repetitions 3, Elasped time 618.897, Relative error 0.00359594, Mean 55815.8, Standard Deviation 119.056 +Total Energy 55815.766667 +371 +Executable: ./dgemmoptimized 11872 46080 46080 1 0 +m=11872, n=46080, k=46080, time(sec)=82.959415, speed(mflops)=607733.452335 +Executable: ./dgemmoptimized 11872 46080 46080 1 0 +m=11872, n=46080, k=46080, time(sec)=82.875085, speed(mflops)=608351.857213 +Executable: ./dgemmoptimized 11872 46080 46080 1 0 +m=11872, n=46080, k=46080, time(sec)=82.935637, speed(mflops)=607907.693568 +Max repetitions 3, Elasped time 616.624, Relative error 0.00414437, Mean 55402.4, Standard Deviation 136.197 +Total Energy 55402.366667 +372 +Executable: ./dgemmoptimized 11904 46080 46080 1 0 +m=11904, n=46080, k=46080, time(sec)=80.250415, speed(mflops)=629942.003372 +Executable: ./dgemmoptimized 11904 46080 46080 1 0 +m=11904, n=46080, k=46080, time(sec)=80.158608, speed(mflops)=630663.487527 +Executable: ./dgemmoptimized 11904 46080 46080 1 0 +m=11904, n=46080, k=46080, time(sec)=80.364854, speed(mflops)=629044.972071 +Max repetitions 3, Elasped time 611.218, Relative error 0.00417368, Mean 54660.4, Standard Deviation 135.323 +Total Energy 54660.383333 +373 +Executable: ./dgemmoptimized 11936 46080 46080 1 0 +m=11936, n=46080, k=46080, time(sec)=81.384490, speed(mflops)=622833.695863 +Executable: ./dgemmoptimized 11936 46080 46080 1 0 +m=11936, n=46080, k=46080, time(sec)=81.233193, speed(mflops)=623993.725696 +Executable: ./dgemmoptimized 11936 46080 46080 1 0 +m=11936, n=46080, k=46080, time(sec)=81.377127, speed(mflops)=622890.050457 +Max repetitions 3, Elasped time 616.379, Relative error 0.0202438, Mean 55464.8, Standard Deviation 666.022 +Total Energy 55464.783333 +374 +Executable: ./dgemmoptimized 11968 46080 46080 1 0 +m=11968, n=46080, k=46080, time(sec)=82.179447, speed(mflops)=618462.400249 +Executable: ./dgemmoptimized 11968 46080 46080 1 0 +m=11968, n=46080, k=46080, time(sec)=82.197078, speed(mflops)=618329.743508 +Executable: ./dgemmoptimized 11968 46080 46080 1 0 +m=11968, n=46080, k=46080, time(sec)=82.158734, speed(mflops)=618618.321199 +Max repetitions 3, Elasped time 620.984, Relative error 0.0188851, Mean 55397.9, Standard Deviation 620.572 +Total Energy 55397.866667 +375 +Executable: ./dgemmoptimized 12000 46080 46080 1 0 +m=12000, n=46080, k=46080, time(sec)=83.020358, speed(mflops)=613834.904776 +Executable: ./dgemmoptimized 12000 46080 46080 1 0 +m=12000, n=46080, k=46080, time(sec)=83.099556, speed(mflops)=613249.890515 +Executable: ./dgemmoptimized 12000 46080 46080 1 0 +m=12000, n=46080, k=46080, time(sec)=83.036913, speed(mflops)=613712.526262 +Max repetitions 3, Elasped time 618.281, Relative error 0.00381238, Mean 55842.5, Standard Deviation 126.282 +Total Energy 55842.483333 +376 +Executable: ./dgemmoptimized 12032 46080 46080 1 0 +m=12032, n=46080, k=46080, time(sec)=84.000071, speed(mflops)=608293.402751 +Executable: ./dgemmoptimized 12032 46080 46080 1 0 +m=12032, n=46080, k=46080, time(sec)=83.960667, speed(mflops)=608578.885081 +Executable: ./dgemmoptimized 12032 46080 46080 1 0 +m=12032, n=46080, k=46080, time(sec)=84.063681, speed(mflops)=607833.115447 +Max repetitions 3, Elasped time 626.756, Relative error 0.0225091, Mean 56144.9, Standard Deviation 749.63 +Total Energy 56144.866667 +377 +Executable: ./dgemmoptimized 12064 46080 46080 1 0 +m=12064, n=46080, k=46080, time(sec)=84.041777, speed(mflops)=609608.535085 +Executable: ./dgemmoptimized 12064 46080 46080 1 0 +m=12064, n=46080, k=46080, time(sec)=84.066337, speed(mflops)=609430.437992 +Executable: ./dgemmoptimized 12064 46080 46080 1 0 +m=12064, n=46080, k=46080, time(sec)=84.077434, speed(mflops)=609350.000630 +Max repetitions 3, Elasped time 621.96, Relative error 0.00330305, Mean 55787.4, Standard Deviation 109.303 +Total Energy 55787.383333 +378 +Executable: ./dgemmoptimized 12096 46080 46080 1 0 +m=12096, n=46080, k=46080, time(sec)=83.280739, speed(mflops)=616811.048065 +Executable: ./dgemmoptimized 12096 46080 46080 1 0 +m=12096, n=46080, k=46080, time(sec)=82.981641, speed(mflops)=619034.274283 +Executable: ./dgemmoptimized 12096 46080 46080 1 0 +m=12096, n=46080, k=46080, time(sec)=83.036232, speed(mflops)=618627.299371 +Max repetitions 3, Elasped time 619.378, Relative error 0.00133385, Mean 55822.5, Standard Deviation 44.167 +Total Energy 55822.500000 +379 +Executable: ./dgemmoptimized 12128 46080 46080 1 0 +m=12128, n=46080, k=46080, time(sec)=84.081159, speed(mflops)=612555.489085 +Executable: ./dgemmoptimized 12128 46080 46080 1 0 +m=12128, n=46080, k=46080, time(sec)=84.100414, speed(mflops)=612415.243536 +Executable: ./dgemmoptimized 12128 46080 46080 1 0 +m=12128, n=46080, k=46080, time(sec)=84.030211, speed(mflops)=612926.882565 +Max repetitions 3, Elasped time 624.618, Relative error 0.00731802, Mean 56120.4, Standard Deviation 243.61 +Total Energy 56120.433333 +380 +Executable: ./dgemmoptimized 12160 46080 46080 1 0 +m=12160, n=46080, k=46080, time(sec)=84.999628, speed(mflops)=607535.256593 +Executable: ./dgemmoptimized 12160 46080 46080 1 0 +m=12160, n=46080, k=46080, time(sec)=85.783159, speed(mflops)=601986.117548 +Executable: ./dgemmoptimized 12160 46080 46080 1 0 +m=12160, n=46080, k=46080, time(sec)=85.078092, speed(mflops)=606974.953471 +Max repetitions 3, Elasped time 626.529, Relative error 0.00102263, Mean 56544.2, Standard Deviation 34.2993 +Total Energy 56544.233333 +381 +Executable: ./dgemmoptimized 12192 46080 46080 1 0 +m=12192, n=46080, k=46080, time(sec)=85.891305, speed(mflops)=602810.334711 +Executable: ./dgemmoptimized 12192 46080 46080 1 0 +m=12192, n=46080, k=46080, time(sec)=85.918165, speed(mflops)=602621.880634 +Executable: ./dgemmoptimized 12192 46080 46080 1 0 +m=12192, n=46080, k=46080, time(sec)=85.800949, speed(mflops)=603445.146501 +Max repetitions 3, Elasped time 628.672, Relative error 0.00385615, Mean 56571.3, Standard Deviation 129.399 +Total Energy 56571.316667 +382 +Executable: ./dgemmoptimized 12224 46080 46080 1 0 +m=12224, n=46080, k=46080, time(sec)=86.883819, speed(mflops)=597488.258263 +Executable: ./dgemmoptimized 12224 46080 46080 1 0 +m=12224, n=46080, k=46080, time(sec)=86.952912, speed(mflops)=597013.492684 +Executable: ./dgemmoptimized 12224 46080 46080 1 0 +m=12224, n=46080, k=46080, time(sec)=87.840241, speed(mflops)=590982.688374 +Max repetitions 3, Elasped time 632.963, Relative error 0.0019058, Mean 57216.9, Standard Deviation 64.6816 +Total Energy 57216.883333 +383 +Executable: ./dgemmoptimized 12256 46080 46080 1 0 +m=12256, n=46080, k=46080, time(sec)=86.062260, speed(mflops)=604770.979169 +Executable: ./dgemmoptimized 12256 46080 46080 1 0 +m=12256, n=46080, k=46080, time(sec)=86.257651, speed(mflops)=603401.049515 +Executable: ./dgemmoptimized 12256 46080 46080 1 0 +m=12256, n=46080, k=46080, time(sec)=86.026757, speed(mflops)=605020.565818 +Max repetitions 3, Elasped time 630.032, Relative error 0.00330938, Mean 57364.3, Standard Deviation 112.608 +Total Energy 57364.333333 +384 +Executable: ./dgemmoptimized 12288 46080 46080 1 0 +m=12288, n=46080, k=46080, time(sec)=83.441499, speed(mflops)=625394.477269 +Executable: ./dgemmoptimized 12288 46080 46080 1 0 +m=12288, n=46080, k=46080, time(sec)=83.347562, speed(mflops)=626099.328492 +Executable: ./dgemmoptimized 12288 46080 46080 1 0 +m=12288, n=46080, k=46080, time(sec)=83.464632, speed(mflops)=625221.143070 +Max repetitions 3, Elasped time 622.193, Relative error 0.00218826, Mean 55931.8, Standard Deviation 72.6001 +Total Energy 55931.750000 +385 +Executable: ./dgemmoptimized 12320 46080 46080 1 0 +m=12320, n=46080, k=46080, time(sec)=84.954720, speed(mflops)=615854.517365 +Executable: ./dgemmoptimized 12320 46080 46080 1 0 +m=12320, n=46080, k=46080, time(sec)=84.442581, speed(mflops)=619589.635548 +Executable: ./dgemmoptimized 12320 46080 46080 1 0 +m=12320, n=46080, k=46080, time(sec)=84.446773, speed(mflops)=619558.881325 +Max repetitions 3, Elasped time 628.129, Relative error 0.00209513, Mean 56566.1, Standard Deviation 70.2987 +Total Energy 56566.050000 +386 +Executable: ./dgemmoptimized 12352 46080 46080 1 0 +m=12352, n=46080, k=46080, time(sec)=85.409447, speed(mflops)=614166.762763 +Executable: ./dgemmoptimized 12352 46080 46080 1 0 +m=12352, n=46080, k=46080, time(sec)=85.351963, speed(mflops)=614580.399505 +Executable: ./dgemmoptimized 12352 46080 46080 1 0 +m=12352, n=46080, k=46080, time(sec)=85.360421, speed(mflops)=614519.504081 +Max repetitions 3, Elasped time 630.66, Relative error 0.00396501, Mean 56739.7, Standard Deviation 133.448 +Total Energy 56739.750000 +387 +Executable: ./dgemmoptimized 12384 46080 46080 1 0 +m=12384, n=46080, k=46080, time(sec)=86.150589, speed(mflops)=610460.585496 +Executable: ./dgemmoptimized 12384 46080 46080 1 0 +m=12384, n=46080, k=46080, time(sec)=86.262928, speed(mflops)=609665.591106 +Executable: ./dgemmoptimized 12384 46080 46080 1 0 +m=12384, n=46080, k=46080, time(sec)=86.320741, speed(mflops)=609257.268628 +Max repetitions 3, Elasped time 633.677, Relative error 0.00483062, Mean 57160.7, Standard Deviation 163.787 +Total Energy 57160.666667 +388 +Executable: ./dgemmoptimized 12416 46080 46080 1 0 +m=12416, n=46080, k=46080, time(sec)=87.226159, speed(mflops)=604491.072304 +Executable: ./dgemmoptimized 12416 46080 46080 1 0 +m=12416, n=46080, k=46080, time(sec)=87.203245, speed(mflops)=604649.911208 +Executable: ./dgemmoptimized 12416 46080 46080 1 0 +m=12416, n=46080, k=46080, time(sec)=87.166316, speed(mflops)=604906.078917 +Max repetitions 3, Elasped time 634.869, Relative error 0.00891454, Mean 57562.7, Standard Deviation 304.382 +Total Energy 57562.650000 +389 +Executable: ./dgemmoptimized 12448 46080 46080 1 0 +m=12448, n=46080, k=46080, time(sec)=87.247158, speed(mflops)=605903.172958 +Executable: ./dgemmoptimized 12448 46080 46080 1 0 +m=12448, n=46080, k=46080, time(sec)=87.278255, speed(mflops)=605687.291789 +Executable: ./dgemmoptimized 12448 46080 46080 1 0 +m=12448, n=46080, k=46080, time(sec)=89.772230, speed(mflops)=588860.606527 +Max repetitions 3, Elasped time 639.094, Relative error 0.0114503, Mean 57894.2, Standard Deviation 393.215 +Total Energy 57894.200000 +390 +Executable: ./dgemmoptimized 12480 46080 46080 1 0 +m=12480, n=46080, k=46080, time(sec)=86.200007, speed(mflops)=614840.151550 +Executable: ./dgemmoptimized 12480 46080 46080 1 0 +m=12480, n=46080, k=46080, time(sec)=86.250453, speed(mflops)=614480.544779 +Executable: ./dgemmoptimized 12480 46080 46080 1 0 +m=12480, n=46080, k=46080, time(sec)=86.215527, speed(mflops)=614729.471045 +Max repetitions 3, Elasped time 637.922, Relative error 0.0133075, Mean 57593.6, Standard Deviation 454.622 +Total Energy 57593.600000 +391 +Executable: ./dgemmoptimized 12512 46080 46080 1 0 +m=12512, n=46080, k=46080, time(sec)=87.301642, speed(mflops)=608638.275434 +Executable: ./dgemmoptimized 12512 46080 46080 1 0 +m=12512, n=46080, k=46080, time(sec)=87.252266, speed(mflops)=608982.701847 +Executable: ./dgemmoptimized 12512 46080 46080 1 0 +m=12512, n=46080, k=46080, time(sec)=87.231693, speed(mflops)=609126.327236 +Max repetitions 3, Elasped time 635.992, Relative error 0.000353596, Mean 57853.5, Standard Deviation 12.1344 +Total Energy 57853.450000 +392 +Executable: ./dgemmoptimized 12544 46080 46080 1 0 +m=12544, n=46080, k=46080, time(sec)=88.287577, speed(mflops)=603380.656277 +Executable: ./dgemmoptimized 12544 46080 46080 1 0 +m=12544, n=46080, k=46080, time(sec)=88.213582, speed(mflops)=603886.784279 +Executable: ./dgemmoptimized 12544 46080 46080 1 0 +m=12544, n=46080, k=46080, time(sec)=88.228994, speed(mflops)=603781.293982 +Max repetitions 3, Elasped time 639.214, Relative error 0.00436436, Mean 57784.9, Standard Deviation 149.594 +Total Energy 57784.900000 +393 +Executable: ./dgemmoptimized 12576 46080 46080 1 0 +m=12576, n=46080, k=46080, time(sec)=89.233142, speed(mflops)=598509.819963 +Executable: ./dgemmoptimized 12576 46080 46080 1 0 +m=12576, n=46080, k=46080, time(sec)=89.051694, speed(mflops)=599729.318378 +Executable: ./dgemmoptimized 12576 46080 46080 1 0 +m=12576, n=46080, k=46080, time(sec)=89.066662, speed(mflops)=599628.530470 +Max repetitions 3, Elasped time 644.213, Relative error 0.0039305, Mean 58588.2, Standard Deviation 136.596 +Total Energy 58588.233333 +394 +Executable: ./dgemmoptimized 12608 46080 46080 1 0 +m=12608, n=46080, k=46080, time(sec)=90.109109, speed(mflops)=594199.716761 +Executable: ./dgemmoptimized 12608 46080 46080 1 0 +m=12608, n=46080, k=46080, time(sec)=90.140237, speed(mflops)=593994.523080 +Executable: ./dgemmoptimized 12608 46080 46080 1 0 +m=12608, n=46080, k=46080, time(sec)=91.521424, speed(mflops)=585030.310610 +Max repetitions 3, Elasped time 648.971, Relative error 0.0172779, Mean 58734.5, Standard Deviation 601.956 +Total Energy 58734.483333 +395 +Executable: ./dgemmoptimized 12640 46080 46080 1 0 +m=12640, n=46080, k=46080, time(sec)=88.632719, speed(mflops)=605630.778041 +Executable: ./dgemmoptimized 12640 46080 46080 1 0 +m=12640, n=46080, k=46080, time(sec)=88.644169, speed(mflops)=605552.549499 +Executable: ./dgemmoptimized 12640 46080 46080 1 0 +m=12640, n=46080, k=46080, time(sec)=88.624702, speed(mflops)=605685.563897 +Max repetitions 3, Elasped time 641.743, Relative error 0.000376649, Mean 58730.8, Standard Deviation 13.1215 +Total Energy 58730.833333 +396 +Executable: ./dgemmoptimized 12672 46080 46080 1 0 +m=12672, n=46080, k=46080, time(sec)=84.836324, speed(mflops)=634334.392618 +Executable: ./dgemmoptimized 12672 46080 46080 1 0 +m=12672, n=46080, k=46080, time(sec)=84.941192, speed(mflops)=633551.246815 +Executable: ./dgemmoptimized 12672 46080 46080 1 0 +m=12672, n=46080, k=46080, time(sec)=84.802728, speed(mflops)=634585.694945 +Max repetitions 3, Elasped time 630.321, Relative error 0.00224569, Mean 57038.3, Standard Deviation 75.9796 +Total Energy 57038.316667 +397 +Executable: ./dgemmoptimized 12704 46080 46080 1 0 +m=12704, n=46080, k=46080, time(sec)=85.772384, speed(mflops)=628996.080910 +Executable: ./dgemmoptimized 12704 46080 46080 1 0 +m=12704, n=46080, k=46080, time(sec)=85.808302, speed(mflops)=628732.794852 +Executable: ./dgemmoptimized 12704 46080 46080 1 0 +m=12704, n=46080, k=46080, time(sec)=85.780946, speed(mflops)=628933.300420 +Max repetitions 3, Elasped time 633.386, Relative error 0.00585056, Mean 57130, Standard Deviation 198.263 +Total Energy 57130.016667 +398 +Executable: ./dgemmoptimized 12736 46080 46080 1 0 +m=12736, n=46080, k=46080, time(sec)=86.727764, speed(mflops)=623634.074781 +Executable: ./dgemmoptimized 12736 46080 46080 1 0 +m=12736, n=46080, k=46080, time(sec)=86.977424, speed(mflops)=621843.997116 +Executable: ./dgemmoptimized 12736 46080 46080 1 0 +m=12736, n=46080, k=46080, time(sec)=86.638420, speed(mflops)=624277.184132 +Max repetitions 3, Elasped time 636.686, Relative error 0.00529452, Mean 57989.2, Standard Deviation 182.118 +Total Energy 57989.216667 +399 +Executable: ./dgemmoptimized 12768 46080 46080 1 0 +m=12768, n=46080, k=46080, time(sec)=87.507837, speed(mflops)=619627.752369 +Executable: ./dgemmoptimized 12768 46080 46080 1 0 +m=12768, n=46080, k=46080, time(sec)=87.711818, speed(mflops)=618186.756265 +Executable: ./dgemmoptimized 12768 46080 46080 1 0 +m=12768, n=46080, k=46080, time(sec)=87.720594, speed(mflops)=618124.911855 +Max repetitions 3, Elasped time 639.677, Relative error 0.00308581, Mean 57682.1, Standard Deviation 105.582 +Total Energy 57682.100000 +400 +Executable: ./dgemmoptimized 12800 46080 46080 1 0 +m=12800, n=46080, k=46080, time(sec)=88.575462, speed(mflops)=613693.439422 +Executable: ./dgemmoptimized 12800 46080 46080 1 0 +m=12800, n=46080, k=46080, time(sec)=88.738767, speed(mflops)=612564.065669 +Executable: ./dgemmoptimized 12800 46080 46080 1 0 +m=12800, n=46080, k=46080, time(sec)=88.649045, speed(mflops)=613184.043278 +Max repetitions 3, Elasped time 644.309, Relative error 0.00686005, Mean 58708.7, Standard Deviation 238.896 +Total Energy 58708.683333 diff --git a/tests/dgemmresultsdvfs/dgemmse_nxn_2.00GHz.txt b/tests/dgemmresultsdvfs/dgemmse_nxn_2.00GHz.txt new file mode 100644 index 0000000..3382781 --- /dev/null +++ b/tests/dgemmresultsdvfs/dgemmse_nxn_2.00GHz.txt @@ -0,0 +1,3601 @@ +1024 +Executable: ./dgemmoptimized 1024 1024 1024 1 0 +m=1024, n=1024, k=1024, time(sec)=0.006497, speed(mflops)=330527.292750 +Executable: ./dgemmoptimized 1024 1024 1024 1 0 +m=1024, n=1024, k=1024, time(sec)=0.006528, speed(mflops)=328958.009377 +Executable: ./dgemmoptimized 1024 1024 1024 1 0 +m=1024, n=1024, k=1024, time(sec)=0.006547, speed(mflops)=328011.626174 +Max repetitions 3, Elasped time 26.2189, Relative error 0.184638, Mean 316.5, Standard Deviation 34.6637 +Total Energy 316.500000 +1448 +Executable: ./dgemmoptimized 1448 1448 1448 1 0 +m=1448, n=1448, k=1448, time(sec)=0.015869, speed(mflops)=382632.867619 +Executable: ./dgemmoptimized 1448 1448 1448 1 0 +m=1448, n=1448, k=1448, time(sec)=0.015937, speed(mflops)=381001.476083 +Executable: ./dgemmoptimized 1448 1448 1448 1 0 +m=1448, n=1448, k=1448, time(sec)=0.015937, speed(mflops)=381001.476083 +Max repetitions 3, Elasped time 24.6732, Relative error 0.0213188, Mean 221.467, Standard Deviation 2.8006 +Total Energy 221.466667 +1774 +Executable: ./dgemmoptimized 1774 1774 1774 1 0 +m=1774, n=1774, k=1774, time(sec)=0.026399, speed(mflops)=422961.790173 +Executable: ./dgemmoptimized 1774 1774 1774 1 0 +m=1774, n=1774, k=1774, time(sec)=0.026039, speed(mflops)=428813.507107 +Executable: ./dgemmoptimized 1774 1774 1774 1 0 +m=1774, n=1774, k=1774, time(sec)=0.026385, speed(mflops)=423187.284183 +Max repetitions 3, Elasped time 25.0474, Relative error 0.00918516, Mean 221.267, Standard Deviation 1.20554 +Total Energy 221.266667 +2048 +Executable: ./dgemmoptimized 2048 2048 2048 1 0 +m=2048, n=2048, k=2048, time(sec)=0.040679, speed(mflops)=422327.945364 +Executable: ./dgemmoptimized 2048 2048 2048 1 0 +m=2048, n=2048, k=2048, time(sec)=0.041237, speed(mflops)=416614.211598 +Executable: ./dgemmoptimized 2048 2048 2048 1 0 +m=2048, n=2048, k=2048, time(sec)=0.040874, speed(mflops)=420312.848015 +Max repetitions 3, Elasped time 27.3277, Relative error 0.427277, Mean 261.867, Standard Deviation 66.3696 +Total Energy 261.866667 +2290 +Executable: ./dgemmoptimized 2290 2290 2290 1 0 +m=2290, n=2290, k=2290, time(sec)=0.048223, speed(mflops)=498060.442383 +Executable: ./dgemmoptimized 2290 2290 2290 1 0 +m=2290, n=2290, k=2290, time(sec)=0.047815, speed(mflops)=502312.147581 +Executable: ./dgemmoptimized 2290 2290 2290 1 0 +m=2290, n=2290, k=2290, time(sec)=0.047922, speed(mflops)=501190.061629 +Max repetitions 3, Elasped time 27.783, Relative error 0.407978, Mean 257.183, Standard Deviation 62.2385 +Total Energy 257.183333 +2508 +Executable: ./dgemmoptimized 2508 2508 2508 1 0 +m=2508, n=2508, k=2508, time(sec)=0.060820, speed(mflops)=518760.793058 +Executable: ./dgemmoptimized 2508 2508 2508 1 0 +m=2508, n=2508, k=2508, time(sec)=0.060761, speed(mflops)=519263.574757 +Executable: ./dgemmoptimized 2508 2508 2508 1 0 +m=2508, n=2508, k=2508, time(sec)=0.060627, speed(mflops)=520411.195286 +Max repetitions 3, Elasped time 26.5197, Relative error 0.0120378, Mean 220.1, Standard Deviation 1.57162 +Total Energy 220.100000 +2709 +Executable: ./dgemmoptimized 2709 2709 2709 1 0 +m=2709, n=2709, k=2709, time(sec)=0.072858, speed(mflops)=545733.506740 +Executable: ./dgemmoptimized 2709 2709 2709 1 0 +m=2709, n=2709, k=2709, time(sec)=0.072674, speed(mflops)=547115.672595 +Executable: ./dgemmoptimized 2709 2709 2709 1 0 +m=2709, n=2709, k=2709, time(sec)=0.072693, speed(mflops)=546972.117895 +Max repetitions 3, Elasped time 28.5296, Relative error 0.39402, Mean 253.5, Standard Deviation 59.2483 +Total Energy 253.500000 +2896 +Executable: ./dgemmoptimized 2896 2896 2896 1 0 +m=2896, n=2896, k=2896, time(sec)=0.094013, speed(mflops)=516699.295114 +Executable: ./dgemmoptimized 2896 2896 2896 1 0 +m=2896, n=2896, k=2896, time(sec)=0.093850, speed(mflops)=517597.137831 +Executable: ./dgemmoptimized 2896 2896 2896 1 0 +m=2896, n=2896, k=2896, time(sec)=0.093834, speed(mflops)=517685.252231 +Max repetitions 3, Elasped time 26.9242, Relative error 0.0175303, Mean 219.367, Standard Deviation 2.28108 +Total Energy 219.366667 +3072 +Executable: ./dgemmoptimized 3072 3072 3072 1 0 +m=3072, n=3072, k=3072, time(sec)=0.104408, speed(mflops)=555341.010274 +Executable: ./dgemmoptimized 3072 3072 3072 1 0 +m=3072, n=3072, k=3072, time(sec)=0.105657, speed(mflops)=548775.786239 +Executable: ./dgemmoptimized 3072 3072 3072 1 0 +m=3072, n=3072, k=3072, time(sec)=0.104761, speed(mflops)=553470.490097 +Max repetitions 3, Elasped time 29.3049, Relative error 0.398347, Mean 255.383, Standard Deviation 60.3441 +Total Energy 255.383333 +3238 +Executable: ./dgemmoptimized 3238 3238 3238 1 0 +m=3238, n=3238, k=3238, time(sec)=0.134624, speed(mflops)=504356.967131 +Executable: ./dgemmoptimized 3238 3238 3238 1 0 +m=3238, n=3238, k=3238, time(sec)=0.133753, speed(mflops)=507641.125271 +Executable: ./dgemmoptimized 3238 3238 3238 1 0 +m=3238, n=3238, k=3238, time(sec)=0.134054, speed(mflops)=506501.724136 +Max repetitions 3, Elasped time 29.6448, Relative error 0.442312, Mean 260.383, Standard Deviation 68.3159 +Total Energy 260.383333 +3396 +Executable: ./dgemmoptimized 3396 3396 3396 1 0 +m=3396, n=3396, k=3396, time(sec)=0.166423, speed(mflops)=470673.209300 +Executable: ./dgemmoptimized 3396 3396 3396 1 0 +m=3396, n=3396, k=3396, time(sec)=0.166594, speed(mflops)=470190.240251 +Executable: ./dgemmoptimized 3396 3396 3396 1 0 +m=3396, n=3396, k=3396, time(sec)=0.166607, speed(mflops)=470153.906145 +Max repetitions 3, Elasped time 30.1527, Relative error 0.418502, Mean 254.933, Standard Deviation 63.2855 +Total Energy 254.933333 +3547 +Executable: ./dgemmoptimized 3547 3547 3547 1 0 +m=3547, n=3547, k=3547, time(sec)=0.161211, speed(mflops)=553629.026613 +Executable: ./dgemmoptimized 3547 3547 3547 1 0 +m=3547, n=3547, k=3547, time(sec)=0.162745, speed(mflops)=548410.686852 +Executable: ./dgemmoptimized 3547 3547 3547 1 0 +m=3547, n=3547, k=3547, time(sec)=0.162033, speed(mflops)=550820.215632 +Max repetitions 3, Elasped time 28.4818, Relative error 0.00740048, Mean 327.95, Standard Deviation 1.43962 +Total Energy 327.950000 +3692 +Executable: ./dgemmoptimized 3692 3692 3692 1 0 +m=3692, n=3692, k=3692, time(sec)=0.186886, speed(mflops)=538565.012434 +Executable: ./dgemmoptimized 3692 3692 3692 1 0 +m=3692, n=3692, k=3692, time(sec)=0.187165, speed(mflops)=537762.338049 +Executable: ./dgemmoptimized 3692 3692 3692 1 0 +m=3692, n=3692, k=3692, time(sec)=0.186733, speed(mflops)=539006.473257 +Max repetitions 3, Elasped time 28.8865, Relative error 0.0139742, Mean 447.767, Standard Deviation 3.71158 +Total Energy 447.766667 +3831 +Executable: ./dgemmoptimized 3831 3831 3831 1 0 +m=3831, n=3831, k=3831, time(sec)=0.198145, speed(mflops)=567522.393235 +Executable: ./dgemmoptimized 3831 3831 3831 1 0 +m=3831, n=3831, k=3831, time(sec)=0.197759, speed(mflops)=568630.807347 +Executable: ./dgemmoptimized 3831 3831 3831 1 0 +m=3831, n=3831, k=3831, time(sec)=0.295229, speed(mflops)=380896.644697 +Max repetitions 3, Elasped time 31.2538, Relative error 0.570025, Mean 562.417, Standard Deviation 190.165 +Total Energy 562.416667 +3966 +Executable: ./dgemmoptimized 3966 3966 3966 1 0 +m=3966, n=3966, k=3966, time(sec)=0.235753, speed(mflops)=529213.881214 +Executable: ./dgemmoptimized 3966 3966 3966 1 0 +m=3966, n=3966, k=3966, time(sec)=0.236037, speed(mflops)=528576.693399 +Executable: ./dgemmoptimized 3966 3966 3966 1 0 +m=3966, n=3966, k=3966, time(sec)=0.236833, speed(mflops)=526799.960546 +Max repetitions 3, Elasped time 31.7097, Relative error 0.542791, Mean 555.667, Standard Deviation 178.907 +Total Energy 555.666667 +4096 +Executable: ./dgemmoptimized 4096 4096 4096 1 0 +m=4096, n=4096, k=4096, time(sec)=0.273816, speed(mflops)=501938.889289 +Executable: ./dgemmoptimized 4096 4096 4096 1 0 +m=4096, n=4096, k=4096, time(sec)=0.273814, speed(mflops)=501942.822777 +Executable: ./dgemmoptimized 4096 4096 4096 1 0 +m=4096, n=4096, k=4096, time(sec)=0.272736, speed(mflops)=503926.569712 +Max repetitions 3, Elasped time 34.1562, Relative error 0.47073, Mean 667.817, Standard Deviation 186.47 +Total Energy 667.816667 +4222 +Executable: ./dgemmoptimized 4222 4222 4222 1 0 +m=4222, n=4222, k=4222, time(sec)=0.258227, speed(mflops)=582884.957931 +Executable: ./dgemmoptimized 4222 4222 4222 1 0 +m=4222, n=4222, k=4222, time(sec)=0.261280, speed(mflops)=576074.187226 +Executable: ./dgemmoptimized 4222 4222 4222 1 0 +m=4222, n=4222, k=4222, time(sec)=0.258024, speed(mflops)=583343.841463 +Max repetitions 3, Elasped time 30.4561, Relative error 0.00618641, Mean 448.4, Standard Deviation 1.64545 +Total Energy 448.400000 +4344 +Executable: ./dgemmoptimized 4344 4344 4344 1 0 +m=4344, n=4344, k=4344, time(sec)=0.304743, speed(mflops)=537979.384092 +Executable: ./dgemmoptimized 4344 4344 4344 1 0 +m=4344, n=4344, k=4344, time(sec)=0.305271, speed(mflops)=537049.137852 +Executable: ./dgemmoptimized 4344 4344 4344 1 0 +m=4344, n=4344, k=4344, time(sec)=0.306763, speed(mflops)=534436.640550 +Max repetitions 3, Elasped time 30.9275, Relative error 0.0114852, Mean 448.017, Standard Deviation 3.05219 +Total Energy 448.016667 +4464 +Executable: ./dgemmoptimized 4464 4464 4464 1 0 +m=4464, n=4464, k=4464, time(sec)=0.326146, speed(mflops)=545494.840116 +Executable: ./dgemmoptimized 4464 4464 4464 1 0 +m=4464, n=4464, k=4464, time(sec)=0.325887, speed(mflops)=545927.845377 +Executable: ./dgemmoptimized 4464 4464 4464 1 0 +m=4464, n=4464, k=4464, time(sec)=0.325737, speed(mflops)=546179.583390 +Max repetitions 3, Elasped time 33.3297, Relative error 0.582008, Mean 561.983, Standard Deviation 194.014 +Total Energy 561.983333 +4579 +Executable: ./dgemmoptimized 4579 4579 4579 1 0 +m=4579, n=4579, k=4579, time(sec)=0.348895, speed(mflops)=550360.664820 +Executable: ./dgemmoptimized 4579 4579 4579 1 0 +m=4579, n=4579, k=4579, time(sec)=0.350484, speed(mflops)=547865.383187 +Executable: ./dgemmoptimized 4579 4579 4579 1 0 +m=4579, n=4579, k=4579, time(sec)=0.348502, speed(mflops)=550981.161574 +Max repetitions 3, Elasped time 33.7318, Relative error 0.571877, Mean 559.467, Standard Deviation 189.783 +Total Energy 559.466667 +4693 +Executable: ./dgemmoptimized 4693 4693 4693 1 0 +m=4693, n=4693, k=4693, time(sec)=0.358891, speed(mflops)=575995.483838 +Executable: ./dgemmoptimized 4693 4693 4693 1 0 +m=4693, n=4693, k=4693, time(sec)=0.357580, speed(mflops)=578106.980818 +Executable: ./dgemmoptimized 4693 4693 4693 1 0 +m=4693, n=4693, k=4693, time(sec)=0.357869, speed(mflops)=577640.570143 +Max repetitions 3, Elasped time 32.1033, Relative error 0.0122036, Mean 448.65, Standard Deviation 3.24769 +Total Energy 448.650000 +4803 +Executable: ./dgemmoptimized 4803 4803 4803 1 0 +m=4803, n=4803, k=4803, time(sec)=0.375451, speed(mflops)=590220.634232 +Executable: ./dgemmoptimized 4803 4803 4803 1 0 +m=4803, n=4803, k=4803, time(sec)=0.375379, speed(mflops)=590333.845943 +Executable: ./dgemmoptimized 4803 4803 4803 1 0 +m=4803, n=4803, k=4803, time(sec)=0.375464, speed(mflops)=590200.395655 +Max repetitions 3, Elasped time 32.4784, Relative error 0.0167325, Mean 449.717, Standard Deviation 4.46356 +Total Energy 449.716667 +4911 +Executable: ./dgemmoptimized 4911 4911 4911 1 0 +m=4911, n=4911, k=4911, time(sec)=0.430730, speed(mflops)=549964.392125 +Executable: ./dgemmoptimized 4911 4911 4911 1 0 +m=4911, n=4911, k=4911, time(sec)=0.430941, speed(mflops)=549695.418776 +Executable: ./dgemmoptimized 4911 4911 4911 1 0 +m=4911, n=4911, k=4911, time(sec)=0.430732, speed(mflops)=549961.956797 +Max repetitions 3, Elasped time 32.9928, Relative error 0.00618838, Mean 448.533, Standard Deviation 1.64646 +Total Energy 448.533333 +5017 +Executable: ./dgemmoptimized 5017 5017 5017 1 0 +m=5017, n=5017, k=5017, time(sec)=0.425523, speed(mflops)=593525.272418 +Executable: ./dgemmoptimized 5017 5017 5017 1 0 +m=5017, n=5017, k=5017, time(sec)=0.425280, speed(mflops)=593864.333887 +Executable: ./dgemmoptimized 5017 5017 5017 1 0 +m=5017, n=5017, k=5017, time(sec)=0.425470, speed(mflops)=593599.107579 +Max repetitions 3, Elasped time 33.316, Relative error 0.00131753, Mean 449.367, Standard Deviation 0.351188 +Total Energy 449.366667 +5120 +Executable: ./dgemmoptimized 5120 5120 5120 1 0 +m=5120, n=5120, k=5120, time(sec)=0.492021, speed(mflops)=545577.404906 +Executable: ./dgemmoptimized 5120 5120 5120 1 0 +m=5120, n=5120, k=5120, time(sec)=0.491709, speed(mflops)=545923.420811 +Executable: ./dgemmoptimized 5120 5120 5120 1 0 +m=5120, n=5120, k=5120, time(sec)=0.490749, speed(mflops)=546991.477078 +Max repetitions 3, Elasped time 37.7667, Relative error 0.471314, Mean 668.233, Standard Deviation 186.818 +Total Energy 668.233333 +5221 +Executable: ./dgemmoptimized 5221 5221 5221 1 0 +m=5221, n=5221, k=5221, time(sec)=0.500323, speed(mflops)=568906.057077 +Executable: ./dgemmoptimized 5221 5221 5221 1 0 +m=5221, n=5221, k=5221, time(sec)=0.501898, speed(mflops)=567120.787872 +Executable: ./dgemmoptimized 5221 5221 5221 1 0 +m=5221, n=5221, k=5221, time(sec)=0.501334, speed(mflops)=567758.909236 +Max repetitions 3, Elasped time 36.2884, Relative error 0.445372, Mean 630.617, Standard Deviation 166.598 +Total Energy 630.616667 +5321 +Executable: ./dgemmoptimized 5321 5321 5321 1 0 +m=5321, n=5321, k=5321, time(sec)=0.559310, speed(mflops)=538712.707063 +Executable: ./dgemmoptimized 5321 5321 5321 1 0 +m=5321, n=5321, k=5321, time(sec)=0.558763, speed(mflops)=539240.013493 +Executable: ./dgemmoptimized 5321 5321 5321 1 0 +m=5321, n=5321, k=5321, time(sec)=0.559505, speed(mflops)=538524.928221 +Max repetitions 3, Elasped time 36.6143, Relative error 0.108925, Mean 928.65, Standard Deviation 60.0014 +Total Energy 928.650000 +5418 +Executable: ./dgemmoptimized 5418 5418 5418 1 0 +m=5418, n=5418, k=5418, time(sec)=0.549159, speed(mflops)=579227.073233 +Executable: ./dgemmoptimized 5418 5418 5418 1 0 +m=5418, n=5418, k=5418, time(sec)=0.548621, speed(mflops)=579795.203763 +Executable: ./dgemmoptimized 5418 5418 5418 1 0 +m=5418, n=5418, k=5418, time(sec)=0.549310, speed(mflops)=579067.683429 +Max repetitions 3, Elasped time 37.0223, Relative error 0.310974, Mean 996.583, Standard Deviation 183.831 +Total Energy 996.583333 +5514 +Executable: ./dgemmoptimized 5514 5514 5514 1 0 +m=5514, n=5514, k=5514, time(sec)=0.654000, speed(mflops)=512687.233940 +Executable: ./dgemmoptimized 5514 5514 5514 1 0 +m=5514, n=5514, k=5514, time(sec)=0.609622, speed(mflops)=550008.812972 +Executable: ./dgemmoptimized 5514 5514 5514 1 0 +m=5514, n=5514, k=5514, time(sec)=0.605077, speed(mflops)=554140.147155 +Max repetitions 3, Elasped time 35.7346, Relative error 0.00492726, Mean 892.433, Standard Deviation 2.60832 +Total Energy 892.433333 +5609 +Executable: ./dgemmoptimized 5609 5609 5609 1 0 +m=5609, n=5609, k=5609, time(sec)=0.623540, speed(mflops)=566007.322261 +Executable: ./dgemmoptimized 5609 5609 5609 1 0 +m=5609, n=5609, k=5609, time(sec)=0.622874, speed(mflops)=566612.430217 +Executable: ./dgemmoptimized 5609 5609 5609 1 0 +m=5609, n=5609, k=5609, time(sec)=0.622695, speed(mflops)=566775.356358 +Max repetitions 3, Elasped time 37.9147, Relative error 0.306828, Mean 1004.75, Standard Deviation 182.866 +Total Energy 1004.750000 +5701 +Executable: ./dgemmoptimized 5701 5701 5701 1 0 +m=5701, n=5701, k=5701, time(sec)=0.686409, speed(mflops)=539883.620476 +Executable: ./dgemmoptimized 5701 5701 5701 1 0 +m=5701, n=5701, k=5701, time(sec)=0.687868, speed(mflops)=538738.406899 +Executable: ./dgemmoptimized 5701 5701 5701 1 0 +m=5701, n=5701, k=5701, time(sec)=0.688982, speed(mflops)=537867.417267 +Max repetitions 3, Elasped time 40.3529, Relative error 0.290286, Mean 1116.38, Standard Deviation 192.229 +Total Energy 1116.383333 +5793 +Executable: ./dgemmoptimized 5793 5793 5793 1 0 +m=5793, n=5793, k=5793, time(sec)=0.637035, speed(mflops)=610347.538646 +Executable: ./dgemmoptimized 5793 5793 5793 1 0 +m=5793, n=5793, k=5793, time(sec)=0.636592, speed(mflops)=610772.486427 +Executable: ./dgemmoptimized 5793 5793 5793 1 0 +m=5793, n=5793, k=5793, time(sec)=0.634087, speed(mflops)=613185.443234 +Max repetitions 3, Elasped time 36.667, Relative error 0.00327424, Mean 895.267, Standard Deviation 1.73877 +Total Energy 895.266667 +5882 +Executable: ./dgemmoptimized 5882 5882 5882 1 0 +m=5882, n=5882, k=5882, time(sec)=0.703071, speed(mflops)=578902.998377 +Executable: ./dgemmoptimized 5882 5882 5882 1 0 +m=5882, n=5882, k=5882, time(sec)=0.701479, speed(mflops)=580216.944812 +Executable: ./dgemmoptimized 5882 5882 5882 1 0 +m=5882, n=5882, k=5882, time(sec)=0.700791, speed(mflops)=580786.436947 +Max repetitions 3, Elasped time 37.2122, Relative error 0.00390535, Mean 891.583, Standard Deviation 2.06539 +Total Energy 891.583333 +5971 +Executable: ./dgemmoptimized 5971 5971 5971 1 0 +m=5971, n=5971, k=5971, time(sec)=0.710754, speed(mflops)=599034.654080 +Executable: ./dgemmoptimized 5971 5971 5971 1 0 +m=5971, n=5971, k=5971, time(sec)=0.711322, speed(mflops)=598556.189491 +Executable: ./dgemmoptimized 5971 5971 5971 1 0 +m=5971, n=5971, k=5971, time(sec)=0.778920, speed(mflops)=546611.028896 +Max repetitions 3, Elasped time 39.5769, Relative error 0.317418, Mean 1005.33, Standard Deviation 189.287 +Total Energy 1005.333333 +6058 +Executable: ./dgemmoptimized 6058 6058 6058 1 0 +m=6058, n=6058, k=6058, time(sec)=0.777316, speed(mflops)=572031.761562 +Executable: ./dgemmoptimized 6058 6058 6058 1 0 +m=6058, n=6058, k=6058, time(sec)=0.778087, speed(mflops)=571465.081622 +Executable: ./dgemmoptimized 6058 6058 6058 1 0 +m=6058, n=6058, k=6058, time(sec)=0.835950, speed(mflops)=531909.111533 +Max repetitions 3, Elasped time 38.1238, Relative error 0.0109974, Mean 893.083, Standard Deviation 5.82588 +Total Energy 893.083333 +6144 +Executable: ./dgemmoptimized 6144 6144 6144 1 0 +m=6144, n=6144, k=6144, time(sec)=0.759839, speed(mflops)=610466.733885 +Executable: ./dgemmoptimized 6144 6144 6144 1 0 +m=6144, n=6144, k=6144, time(sec)=0.838498, speed(mflops)=553199.334935 +Executable: ./dgemmoptimized 6144 6144 6144 1 0 +m=6144, n=6144, k=6144, time(sec)=0.761444, speed(mflops)=609179.942382 +Max repetitions 3, Elasped time 40.4299, Relative error 0.328493, Mean 1004.15, Standard Deviation 195.661 +Total Energy 1004.150000 +6229 +Executable: ./dgemmoptimized 6229 6229 6229 1 0 +m=6229, n=6229, k=6229, time(sec)=0.908370, speed(mflops)=532135.595922 +Executable: ./dgemmoptimized 6229 6229 6229 1 0 +m=6229, n=6229, k=6229, time(sec)=0.837828, speed(mflops)=576939.347463 +Executable: ./dgemmoptimized 6229 6229 6229 1 0 +m=6229, n=6229, k=6229, time(sec)=0.909322, speed(mflops)=531578.481860 +Max repetitions 3, Elasped time 39.0679, Relative error 0.0106919, Mean 892.133, Standard Deviation 5.65803 +Total Energy 892.133333 +6312 +Executable: ./dgemmoptimized 6312 6312 6312 1 0 +m=6312, n=6312, k=6312, time(sec)=0.875669, speed(mflops)=574368.996962 +Executable: ./dgemmoptimized 6312 6312 6312 1 0 +m=6312, n=6312, k=6312, time(sec)=0.875955, speed(mflops)=574181.554259 +Executable: ./dgemmoptimized 6312 6312 6312 1 0 +m=6312, n=6312, k=6312, time(sec)=0.873155, speed(mflops)=576022.652612 +Max repetitions 3, Elasped time 39.3604, Relative error 0.00463733, Mean 892.217, Standard Deviation 2.45425 +Total Energy 892.216667 +6395 +Executable: ./dgemmoptimized 6395 6395 6395 1 0 +m=6395, n=6395, k=6395, time(sec)=0.956150, speed(mflops)=547048.192961 +Executable: ./dgemmoptimized 6395 6395 6395 1 0 +m=6395, n=6395, k=6395, time(sec)=0.922097, speed(mflops)=567250.710146 +Executable: ./dgemmoptimized 6395 6395 6395 1 0 +m=6395, n=6395, k=6395, time(sec)=0.920650, speed(mflops)=568142.243758 +Max repetitions 3, Elasped time 40.0427, Relative error 0.00533575, Mean 896.767, Standard Deviation 2.83828 +Total Energy 896.766667 +6476 +Executable: ./dgemmoptimized 6476 6476 6476 1 0 +m=6476, n=6476, k=6476, time(sec)=1.003371, speed(mflops)=541363.499837 +Executable: ./dgemmoptimized 6476 6476 6476 1 0 +m=6476, n=6476, k=6476, time(sec)=1.000070, speed(mflops)=543150.493682 +Executable: ./dgemmoptimized 6476 6476 6476 1 0 +m=6476, n=6476, k=6476, time(sec)=1.002505, speed(mflops)=541831.114727 +Max repetitions 3, Elasped time 44.5114, Relative error 0.0601621, Mean 1388.75, Standard Deviation 49.5595 +Total Energy 1388.750000 +6557 +Executable: ./dgemmoptimized 6557 6557 6557 1 0 +m=6557, n=6557, k=6557, time(sec)=0.956753, speed(mflops)=589312.573089 +Executable: ./dgemmoptimized 6557 6557 6557 1 0 +m=6557, n=6557, k=6557, time(sec)=0.956860, speed(mflops)=589246.789814 +Executable: ./dgemmoptimized 6557 6557 6557 1 0 +m=6557, n=6557, k=6557, time(sec)=0.957077, speed(mflops)=589113.065984 +Max repetitions 3, Elasped time 40.8952, Relative error 0.00785388, Mean 1333.37, Standard Deviation 6.21175 +Total Energy 1333.366667 +6636 +Executable: ./dgemmoptimized 6636 6636 6636 1 0 +m=6636, n=6636, k=6636, time(sec)=1.032921, speed(mflops)=565824.943935 +Executable: ./dgemmoptimized 6636 6636 6636 1 0 +m=6636, n=6636, k=6636, time(sec)=1.024661, speed(mflops)=570386.180711 +Executable: ./dgemmoptimized 6636 6636 6636 1 0 +m=6636, n=6636, k=6636, time(sec)=1.031767, speed(mflops)=566457.772331 +Max repetitions 3, Elasped time 41.196, Relative error 0.013719, Mean 1329.12, Standard Deviation 10.816 +Total Energy 1329.116667 +6715 +Executable: ./dgemmoptimized 6715 6715 6715 1 0 +m=6715, n=6715, k=6715, time(sec)=1.049587, speed(mflops)=576965.173167 +Executable: ./dgemmoptimized 6715 6715 6715 1 0 +m=6715, n=6715, k=6715, time(sec)=1.048889, speed(mflops)=577349.173206 +Executable: ./dgemmoptimized 6715 6715 6715 1 0 +m=6715, n=6715, k=6715, time(sec)=1.049373, speed(mflops)=577082.758239 +Max repetitions 3, Elasped time 43.5075, Relative error 0.222335, Mean 1438.03, Standard Deviation 189.652 +Total Energy 1438.033333 +6792 +Executable: ./dgemmoptimized 6792 6792 6792 1 0 +m=6792, n=6792, k=6792, time(sec)=1.110785, speed(mflops)=564147.954787 +Executable: ./dgemmoptimized 6792 6792 6792 1 0 +m=6792, n=6792, k=6792, time(sec)=1.254901, speed(mflops)=499359.714368 +Executable: ./dgemmoptimized 6792 6792 6792 1 0 +m=6792, n=6792, k=6792, time(sec)=1.115150, speed(mflops)=561939.622784 +Max repetitions 3, Elasped time 42.3217, Relative error 0.0111175, Mean 1325.53, Standard Deviation 8.74133 +Total Energy 1325.533333 +6869 +Executable: ./dgemmoptimized 6869 6869 6869 1 0 +m=6869, n=6869, k=6869, time(sec)=1.170100, speed(mflops)=553971.582191 +Executable: ./dgemmoptimized 6869 6869 6869 1 0 +m=6869, n=6869, k=6869, time(sec)=1.172292, speed(mflops)=552935.846259 +Executable: ./dgemmoptimized 6869 6869 6869 1 0 +m=6869, n=6869, k=6869, time(sec)=1.171305, speed(mflops)=553401.802580 +Max repetitions 3, Elasped time 42.6092, Relative error 0.00121691, Mean 1321.55, Standard Deviation 0.953939 +Total Energy 1321.550000 +6945 +Executable: ./dgemmoptimized 6945 6945 6945 1 0 +m=6945, n=6945, k=6945, time(sec)=1.105062, speed(mflops)=606261.650892 +Executable: ./dgemmoptimized 6945 6945 6945 1 0 +m=6945, n=6945, k=6945, time(sec)=1.106021, speed(mflops)=605736.022380 +Executable: ./dgemmoptimized 6945 6945 6945 1 0 +m=6945, n=6945, k=6945, time(sec)=1.105534, speed(mflops)=606002.904712 +Max repetitions 3, Elasped time 46.6425, Relative error 0.209492, Mean 1541.07, Standard Deviation 191.5 +Total Energy 1541.066667 +7020 +Executable: ./dgemmoptimized 7020 7020 7020 1 0 +m=7020, n=7020, k=7020, time(sec)=1.170795, speed(mflops)=590963.266303 +Executable: ./dgemmoptimized 7020 7020 7020 1 0 +m=7020, n=7020, k=7020, time(sec)=1.176310, speed(mflops)=588192.669898 +Executable: ./dgemmoptimized 7020 7020 7020 1 0 +m=7020, n=7020, k=7020, time(sec)=1.179843, speed(mflops)=586431.284466 +Max repetitions 3, Elasped time 43.2944, Relative error 0.0116259, Mean 1324.05, Standard Deviation 9.13085 +Total Energy 1324.050000 +7094 +Executable: ./dgemmoptimized 7094 7094 7094 1 0 +m=7094, n=7094, k=7094, time(sec)=1.202734, speed(mflops)=593654.770721 +Executable: ./dgemmoptimized 7094 7094 7094 1 0 +m=7094, n=7094, k=7094, time(sec)=1.201558, speed(mflops)=594235.738900 +Executable: ./dgemmoptimized 7094 7094 7094 1 0 +m=7094, n=7094, k=7094, time(sec)=1.199911, speed(mflops)=595051.385659 +Max repetitions 3, Elasped time 45.7035, Relative error 0.208572, Mean 1436.8, Standard Deviation 177.759 +Total Energy 1436.800000 +7168 +Executable: ./dgemmoptimized 7168 7168 7168 1 0 +m=7168, n=7168, k=7168, time(sec)=1.301371, speed(mflops)=566008.337393 +Executable: ./dgemmoptimized 7168 7168 7168 1 0 +m=7168, n=7168, k=7168, time(sec)=1.299761, speed(mflops)=566709.567476 +Executable: ./dgemmoptimized 7168 7168 7168 1 0 +m=7168, n=7168, k=7168, time(sec)=1.298436, speed(mflops)=567287.823963 +Max repetitions 3, Elasped time 48.2484, Relative error 0.204755, Mean 1549.22, Standard Deviation 188.16 +Total Energy 1549.216667 +7241 +Executable: ./dgemmoptimized 7241 7241 7241 1 0 +m=7241, n=7241, k=7241, time(sec)=1.359755, speed(mflops)=558425.139193 +Executable: ./dgemmoptimized 7241 7241 7241 1 0 +m=7241, n=7241, k=7241, time(sec)=1.340040, speed(mflops)=566640.857658 +Executable: ./dgemmoptimized 7241 7241 7241 1 0 +m=7241, n=7241, k=7241, time(sec)=1.344512, speed(mflops)=564756.138341 +Max repetitions 3, Elasped time 44.8477, Relative error 0.00642704, Mean 1328.88, Standard Deviation 5.06615 +Total Energy 1328.883333 +7313 +Executable: ./dgemmoptimized 7313 7313 7313 1 0 +m=7313, n=7313, k=7313, time(sec)=1.277897, speed(mflops)=612097.808693 +Executable: ./dgemmoptimized 7313 7313 7313 1 0 +m=7313, n=7313, k=7313, time(sec)=1.276958, speed(mflops)=612547.972206 +Executable: ./dgemmoptimized 7313 7313 7313 1 0 +m=7313, n=7313, k=7313, time(sec)=1.276847, speed(mflops)=612601.272217 +Max repetitions 3, Elasped time 44.9911, Relative error 0.00303249, Mean 1323.28, Standard Deviation 2.3803 +Total Energy 1323.283333 +7384 +Executable: ./dgemmoptimized 7384 7384 7384 1 0 +m=7384, n=7384, k=7384, time(sec)=1.368454, speed(mflops)=588402.979037 +Executable: ./dgemmoptimized 7384 7384 7384 1 0 +m=7384, n=7384, k=7384, time(sec)=1.367558, speed(mflops)=588788.480454 +Executable: ./dgemmoptimized 7384 7384 7384 1 0 +m=7384, n=7384, k=7384, time(sec)=1.368953, speed(mflops)=588188.494666 +Max repetitions 3, Elasped time 45.6104, Relative error 0.0090458, Mean 1326.83, Standard Deviation 7.1194 +Total Energy 1326.833333 +7455 +Executable: ./dgemmoptimized 7455 7455 7455 1 0 +m=7455, n=7455, k=7455, time(sec)=1.417805, speed(mflops)=584462.227324 +Executable: ./dgemmoptimized 7455 7455 7455 1 0 +m=7455, n=7455, k=7455, time(sec)=1.422543, speed(mflops)=582515.547361 +Executable: ./dgemmoptimized 7455 7455 7455 1 0 +m=7455, n=7455, k=7455, time(sec)=1.418661, speed(mflops)=584109.602892 +Max repetitions 3, Elasped time 48.051, Relative error 0.224474, Mean 1436.82, Standard Deviation 191.314 +Total Energy 1436.816667 +7525 +Executable: ./dgemmoptimized 7525 7525 7525 1 0 +m=7525, n=7525, k=7525, time(sec)=1.452979, speed(mflops)=586529.884283 +Executable: ./dgemmoptimized 7525 7525 7525 1 0 +m=7525, n=7525, k=7525, time(sec)=1.451211, speed(mflops)=587244.494805 +Executable: ./dgemmoptimized 7525 7525 7525 1 0 +m=7525, n=7525, k=7525, time(sec)=1.450712, speed(mflops)=587446.492813 +Max repetitions 3, Elasped time 46.5404, Relative error 0.0137957, Mean 1555.48, Standard Deviation 12.7288 +Total Energy 1555.483333 +7594 +Executable: ./dgemmoptimized 7594 7594 7594 1 0 +m=7594, n=7594, k=7594, time(sec)=1.530069, speed(mflops)=572441.081474 +Executable: ./dgemmoptimized 7594 7594 7594 1 0 +m=7594, n=7594, k=7594, time(sec)=1.532995, speed(mflops)=571348.431930 +Executable: ./dgemmoptimized 7594 7594 7594 1 0 +m=7594, n=7594, k=7594, time(sec)=1.513899, speed(mflops)=578555.351611 +Max repetitions 3, Elasped time 47.0448, Relative error 0.0100179, Mean 1779.87, Standard Deviation 10.5765 +Total Energy 1779.866667 +7663 +Executable: ./dgemmoptimized 7663 7663 7663 1 0 +m=7663, n=7663, k=7663, time(sec)=1.526453, speed(mflops)=589580.390468 +Executable: ./dgemmoptimized 7663 7663 7663 1 0 +m=7663, n=7663, k=7663, time(sec)=1.506728, speed(mflops)=597298.786500 +Executable: ./dgemmoptimized 7663 7663 7663 1 0 +m=7663, n=7663, k=7663, time(sec)=1.524781, speed(mflops)=590226.906794 +Max repetitions 3, Elasped time 49.3705, Relative error 0.169184, Mean 1887.7, Standard Deviation 189.44 +Total Energy 1887.700000 +7731 +Executable: ./dgemmoptimized 7731 7731 7731 1 0 +m=7731, n=7731, k=7731, time(sec)=1.556327, speed(mflops)=593794.450453 +Executable: ./dgemmoptimized 7731 7731 7731 1 0 +m=7731, n=7731, k=7731, time(sec)=1.546032, speed(mflops)=597748.483871 +Executable: ./dgemmoptimized 7731 7731 7731 1 0 +m=7731, n=7731, k=7731, time(sec)=1.571695, speed(mflops)=587988.347135 +Max repetitions 3, Elasped time 49.7488, Relative error 0.186228, Mean 1882.85, Standard Deviation 207.989 +Total Energy 1882.850000 +7799 +Executable: ./dgemmoptimized 7799 7799 7799 1 0 +m=7799, n=7799, k=7799, time(sec)=1.634158, speed(mflops)=580567.526000 +Executable: ./dgemmoptimized 7799 7799 7799 1 0 +m=7799, n=7799, k=7799, time(sec)=1.630686, speed(mflops)=581803.597256 +Executable: ./dgemmoptimized 7799 7799 7799 1 0 +m=7799, n=7799, k=7799, time(sec)=1.631522, speed(mflops)=581505.515435 +Max repetitions 3, Elasped time 50.4163, Relative error 0.170438, Mean 1876.78, Standard Deviation 189.74 +Total Energy 1876.783333 +7865 +Executable: ./dgemmoptimized 7865 7865 7865 1 0 +m=7865, n=7865, k=7865, time(sec)=1.648642, speed(mflops)=590200.808899 +Executable: ./dgemmoptimized 7865 7865 7865 1 0 +m=7865, n=7865, k=7865, time(sec)=1.651405, speed(mflops)=589213.319963 +Executable: ./dgemmoptimized 7865 7865 7865 1 0 +m=7865, n=7865, k=7865, time(sec)=1.653731, speed(mflops)=588384.577585 +Max repetitions 3, Elasped time 50.7906, Relative error 0.17764, Mean 1872.82, Standard Deviation 197.34 +Total Energy 1872.816667 +7932 +Executable: ./dgemmoptimized 7932 7932 7932 1 0 +m=7932, n=7932, k=7932, time(sec)=1.727064, speed(mflops)=577922.559008 +Executable: ./dgemmoptimized 7932 7932 7932 1 0 +m=7932, n=7932, k=7932, time(sec)=1.725831, speed(mflops)=578335.482875 +Executable: ./dgemmoptimized 7932 7932 7932 1 0 +m=7932, n=7932, k=7932, time(sec)=1.752349, speed(mflops)=569583.595725 +Max repetitions 3, Elasped time 49.3877, Relative error 0.0021378, Mean 1759.97, Standard Deviation 2.23178 +Total Energy 1759.966667 +7998 +Executable: ./dgemmoptimized 7998 7998 7998 1 0 +m=7998, n=7998, k=7998, time(sec)=1.835505, speed(mflops)=557466.303353 +Executable: ./dgemmoptimized 7998 7998 7998 1 0 +m=7998, n=7998, k=7998, time(sec)=2.114407, speed(mflops)=483933.396798 +Executable: ./dgemmoptimized 7998 7998 7998 1 0 +m=7998, n=7998, k=7998, time(sec)=1.842240, speed(mflops)=555428.249925 +Max repetitions 3, Elasped time 50.3177, Relative error 0.00922521, Mean 1756.68, Standard Deviation 9.6128 +Total Energy 1756.683333 +8063 +Executable: ./dgemmoptimized 8063 8063 8063 1 0 +m=8063, n=8063, k=8063, time(sec)=1.682176, speed(mflops)=623230.322022 +Executable: ./dgemmoptimized 8063 8063 8063 1 0 +m=8063, n=8063, k=8063, time(sec)=1.678430, speed(mflops)=624621.289412 +Executable: ./dgemmoptimized 8063 8063 8063 1 0 +m=8063, n=8063, k=8063, time(sec)=1.682844, speed(mflops)=622982.914465 +Max repetitions 3, Elasped time 49.9662, Relative error 0.0130807, Mean 1765.48, Standard Deviation 13.6986 +Total Energy 1765.483333 +8128 +Executable: ./dgemmoptimized 8128 8128 8128 1 0 +m=8128, n=8128, k=8128, time(sec)=1.791684, speed(mflops)=599404.068399 +Executable: ./dgemmoptimized 8128 8128 8128 1 0 +m=8128, n=8128, k=8128, time(sec)=1.750201, speed(mflops)=613611.027742 +Executable: ./dgemmoptimized 8128 8128 8128 1 0 +m=8128, n=8128, k=8128, time(sec)=1.794488, speed(mflops)=598467.448275 +Max repetitions 3, Elasped time 50.6369, Relative error 0.00411703, Mean 1758.43, Standard Deviation 4.29428 +Total Energy 1758.433333 +8192 +Executable: ./dgemmoptimized 8192 8192 8192 1 0 +m=8192, n=8192, k=8192, time(sec)=2.061604, speed(mflops)=533328.231571 +Executable: ./dgemmoptimized 8192 8192 8192 1 0 +m=8192, n=8192, k=8192, time(sec)=2.025275, speed(mflops)=542894.980743 +Executable: ./dgemmoptimized 8192 8192 8192 1 0 +m=8192, n=8192, k=8192, time(sec)=2.018241, speed(mflops)=544787.038198 +Max repetitions 3, Elasped time 53.5847, Relative error 0.181146, Mean 1871.42, Standard Deviation 201.085 +Total Energy 1871.416667 +8256 +Executable: ./dgemmoptimized 8256 8256 8256 1 0 +m=8256, n=8256, k=8256, time(sec)=1.833650, speed(mflops)=613793.995546 +Executable: ./dgemmoptimized 8256 8256 8256 1 0 +m=8256, n=8256, k=8256, time(sec)=1.827909, speed(mflops)=615721.727332 +Executable: ./dgemmoptimized 8256 8256 8256 1 0 +m=8256, n=8256, k=8256, time(sec)=1.831796, speed(mflops)=614415.210488 +Max repetitions 3, Elasped time 53.5453, Relative error 0.169374, Mean 1860.23, Standard Deviation 186.894 +Total Energy 1860.233333 +8319 +Executable: ./dgemmoptimized 8319 8319 8319 1 0 +m=8319, n=8319, k=8319, time(sec)=1.931073, speed(mflops)=596272.373502 +Executable: ./dgemmoptimized 8319 8319 8319 1 0 +m=8319, n=8319, k=8319, time(sec)=1.928693, speed(mflops)=597008.138684 +Executable: ./dgemmoptimized 8319 8319 8319 1 0 +m=8319, n=8319, k=8319, time(sec)=1.927102, speed(mflops)=597501.013638 +Max repetitions 3, Elasped time 54.0704, Relative error 0.161585, Mean 1866.52, Standard Deviation 178.901 +Total Energy 1866.516667 +8382 +Executable: ./dgemmoptimized 8382 8382 8382 1 0 +m=8382, n=8382, k=8382, time(sec)=2.041967, speed(mflops)=576798.688171 +Executable: ./dgemmoptimized 8382 8382 8382 1 0 +m=8382, n=8382, k=8382, time(sec)=2.034805, speed(mflops)=578828.833001 +Executable: ./dgemmoptimized 8382 8382 8382 1 0 +m=8382, n=8382, k=8382, time(sec)=2.039410, speed(mflops)=577521.886047 +Max repetitions 3, Elasped time 54.6771, Relative error 0.111187, Mean 2385.37, Standard Deviation 157.322 +Total Energy 2385.366667 +8444 +Executable: ./dgemmoptimized 8444 8444 8444 1 0 +m=8444, n=8444, k=8444, time(sec)=1.957965, speed(mflops)=614992.352463 +Executable: ./dgemmoptimized 8444 8444 8444 1 0 +m=8444, n=8444, k=8444, time(sec)=1.958571, speed(mflops)=614802.124146 +Executable: ./dgemmoptimized 8444 8444 8444 1 0 +m=8444, n=8444, k=8444, time(sec)=1.953669, speed(mflops)=616344.778892 +Max repetitions 3, Elasped time 54.7566, Relative error 0.123566, Mean 2366.17, Standard Deviation 173.43 +Total Energy 2366.166667 +8506 +Executable: ./dgemmoptimized 8506 8506 8506 1 0 +m=8506, n=8506, k=8506, time(sec)=2.033428, speed(mflops)=605309.292705 +Executable: ./dgemmoptimized 8506 8506 8506 1 0 +m=8506, n=8506, k=8506, time(sec)=2.036664, speed(mflops)=604347.516790 +Executable: ./dgemmoptimized 8506 8506 8506 1 0 +m=8506, n=8506, k=8506, time(sec)=2.035934, speed(mflops)=604564.221492 +Max repetitions 3, Elasped time 53.5798, Relative error 0.011322, Mean 2237.37, Standard Deviation 15.0258 +Total Energy 2237.366667 +8567 +Executable: ./dgemmoptimized 8567 8567 8567 1 0 +m=8567, n=8567, k=8567, time(sec)=2.108474, speed(mflops)=596414.293404 +Executable: ./dgemmoptimized 8567 8567 8567 1 0 +m=8567, n=8567, k=8567, time(sec)=2.102495, speed(mflops)=598110.372392 +Executable: ./dgemmoptimized 8567 8567 8567 1 0 +m=8567, n=8567, k=8567, time(sec)=2.106676, speed(mflops)=596923.295195 +Max repetitions 3, Elasped time 55.7342, Relative error 0.149931, Mean 2349.9, Standard Deviation 208.987 +Total Energy 2349.900000 +8628 +Executable: ./dgemmoptimized 8628 8628 8628 1 0 +m=8628, n=8628, k=8628, time(sec)=2.140971, speed(mflops)=599997.763206 +Executable: ./dgemmoptimized 8628 8628 8628 1 0 +m=8628, n=8628, k=8628, time(sec)=2.143932, speed(mflops)=599169.057565 +Executable: ./dgemmoptimized 8628 8628 8628 1 0 +m=8628, n=8628, k=8628, time(sec)=2.146378, speed(mflops)=598486.265782 +Max repetitions 3, Elasped time 56.2756, Relative error 0.190392, Mean 2371.5, Standard Deviation 267.825 +Total Energy 2371.500000 +8689 +Executable: ./dgemmoptimized 8689 8689 8689 1 0 +m=8689, n=8689, k=8689, time(sec)=2.206699, speed(mflops)=594560.787180 +Executable: ./dgemmoptimized 8689 8689 8689 1 0 +m=8689, n=8689, k=8689, time(sec)=2.192786, speed(mflops)=598333.255736 +Executable: ./dgemmoptimized 8689 8689 8689 1 0 +m=8689, n=8689, k=8689, time(sec)=2.205020, speed(mflops)=595013.496889 +Max repetitions 3, Elasped time 54.7984, Relative error 0.0214463, Mean 2228.03, Standard Deviation 28.3435 +Total Energy 2228.033333 +8749 +Executable: ./dgemmoptimized 8749 8749 8749 1 0 +m=8749, n=8749, k=8749, time(sec)=2.285651, speed(mflops)=585996.919883 +Executable: ./dgemmoptimized 8749 8749 8749 1 0 +m=8749, n=8749, k=8749, time(sec)=2.289428, speed(mflops)=585030.160383 +Executable: ./dgemmoptimized 8749 8749 8749 1 0 +m=8749, n=8749, k=8749, time(sec)=2.290176, speed(mflops)=584839.102910 +Max repetitions 3, Elasped time 55.4316, Relative error 0.0106235, Mean 2210.43, Standard Deviation 13.9291 +Total Energy 2210.433333 +8809 +Executable: ./dgemmoptimized 8809 8809 8809 1 0 +m=8809, n=8809, k=8809, time(sec)=2.302193, speed(mflops)=593838.171674 +Executable: ./dgemmoptimized 8809 8809 8809 1 0 +m=8809, n=8809, k=8809, time(sec)=2.297465, speed(mflops)=595060.263798 +Executable: ./dgemmoptimized 8809 8809 8809 1 0 +m=8809, n=8809, k=8809, time(sec)=2.292242, speed(mflops)=596416.088849 +Max repetitions 3, Elasped time 57.8546, Relative error 0.121302, Mean 2303.88, Standard Deviation 165.772 +Total Energy 2303.883333 +8868 +Executable: ./dgemmoptimized 8868 8868 8868 1 0 +m=8868, n=8868, k=8868, time(sec)=2.313490, speed(mflops)=602891.885398 +Executable: ./dgemmoptimized 8868 8868 8868 1 0 +m=8868, n=8868, k=8868, time(sec)=2.313394, speed(mflops)=602916.863300 +Executable: ./dgemmoptimized 8868 8868 8868 1 0 +m=8868, n=8868, k=8868, time(sec)=2.308181, speed(mflops)=604278.549818 +Max repetitions 3, Elasped time 56.1245, Relative error 0.0066138, Mean 2202.45, Standard Deviation 8.64046 +Total Energy 2202.450000 +8927 +Executable: ./dgemmoptimized 8927 8927 8927 1 0 +m=8927, n=8927, k=8927, time(sec)=2.376334, speed(mflops)=598741.177265 +Executable: ./dgemmoptimized 8927 8927 8927 1 0 +m=8927, n=8927, k=8927, time(sec)=2.349290, speed(mflops)=605633.577679 +Executable: ./dgemmoptimized 8927 8927 8927 1 0 +m=8927, n=8927, k=8927, time(sec)=2.379870, speed(mflops)=597851.573865 +Max repetitions 3, Elasped time 56.6366, Relative error 0.00711695, Mean 2185.02, Standard Deviation 9.2242 +Total Energy 2185.016667 +8986 +Executable: ./dgemmoptimized 8986 8986 8986 1 0 +m=8986, n=8986, k=8986, time(sec)=2.473350, speed(mflops)=586737.239093 +Executable: ./dgemmoptimized 8986 8986 8986 1 0 +m=8986, n=8986, k=8986, time(sec)=2.474185, speed(mflops)=586539.237939 +Executable: ./dgemmoptimized 8986 8986 8986 1 0 +m=8986, n=8986, k=8986, time(sec)=2.465097, speed(mflops)=588701.624169 +Max repetitions 3, Elasped time 57.2933, Relative error 0.00760548, Mean 2180.85, Standard Deviation 9.83857 +Total Energy 2180.850000 +9044 +Executable: ./dgemmoptimized 9044 9044 9044 1 0 +m=9044, n=9044, k=9044, time(sec)=2.481290, speed(mflops)=596257.855207 +Executable: ./dgemmoptimized 9044 9044 9044 1 0 +m=9044, n=9044, k=9044, time(sec)=2.479444, speed(mflops)=596701.857575 +Executable: ./dgemmoptimized 9044 9044 9044 1 0 +m=9044, n=9044, k=9044, time(sec)=2.477714, speed(mflops)=597118.423476 +Max repetitions 3, Elasped time 59.6958, Relative error 0.142223, Mean 2297.07, Standard Deviation 193.787 +Total Energy 2297.066667 +9102 +Executable: ./dgemmoptimized 9102 9102 9102 1 0 +m=9102, n=9102, k=9102, time(sec)=2.579901, speed(mflops)=584571.249094 +Executable: ./dgemmoptimized 9102 9102 9102 1 0 +m=9102, n=9102, k=9102, time(sec)=2.586189, speed(mflops)=583149.924459 +Executable: ./dgemmoptimized 9102 9102 9102 1 0 +m=9102, n=9102, k=9102, time(sec)=2.588179, speed(mflops)=582701.587635 +Max repetitions 3, Elasped time 58.321, Relative error 0.0130954, Mean 2473.73, Standard Deviation 19.2155 +Total Energy 2473.733333 +9159 +Executable: ./dgemmoptimized 9159 9159 9159 1 0 +m=9159, n=9159, k=9159, time(sec)=2.666228, speed(mflops)=576337.500435 +Executable: ./dgemmoptimized 9159 9159 9159 1 0 +m=9159, n=9159, k=9159, time(sec)=2.667861, speed(mflops)=575984.739127 +Executable: ./dgemmoptimized 9159 9159 9159 1 0 +m=9159, n=9159, k=9159, time(sec)=2.666930, speed(mflops)=576185.815249 +Max repetitions 3, Elasped time 58.9323, Relative error 0.0117059, Mean 2767.42, Standard Deviation 19.2159 +Total Energy 2767.416667 +9216 +Executable: ./dgemmoptimized 9216 9216 9216 1 0 +m=9216, n=9216, k=9216, time(sec)=2.539492, speed(mflops)=616468.036149 +Executable: ./dgemmoptimized 9216 9216 9216 1 0 +m=9216, n=9216, k=9216, time(sec)=2.530429, speed(mflops)=618675.983268 +Executable: ./dgemmoptimized 9216 9216 9216 1 0 +m=9216, n=9216, k=9216, time(sec)=2.528307, speed(mflops)=619195.217790 +Max repetitions 3, Elasped time 58.8159, Relative error 0.0168051, Mean 2763.18, Standard Deviation 27.5442 +Total Energy 2763.183333 +9273 +Executable: ./dgemmoptimized 9273 9273 9273 1 0 +m=9273, n=9273, k=9273, time(sec)=2.564959, speed(mflops)=621742.248692 +Executable: ./dgemmoptimized 9273 9273 9273 1 0 +m=9273, n=9273, k=9273, time(sec)=2.568332, speed(mflops)=620925.676906 +Executable: ./dgemmoptimized 9273 9273 9273 1 0 +m=9273, n=9273, k=9273, time(sec)=2.568414, speed(mflops)=620905.849169 +Max repetitions 3, Elasped time 59.7214, Relative error 0.0354397, Mean 2754.38, Standard Deviation 57.902 +Total Energy 2754.383333 +9329 +Executable: ./dgemmoptimized 9329 9329 9329 1 0 +m=9329, n=9329, k=9329, time(sec)=2.657267, speed(mflops)=611082.807766 +Executable: ./dgemmoptimized 9329 9329 9329 1 0 +m=9329, n=9329, k=9329, time(sec)=2.659209, speed(mflops)=610636.557205 +Executable: ./dgemmoptimized 9329 9329 9329 1 0 +m=9329, n=9329, k=9329, time(sec)=2.656348, speed(mflops)=611294.244078 +Max repetitions 3, Elasped time 61.8679, Relative error 0.119459, Mean 2807.15, Standard Deviation 198.914 +Total Energy 2807.150000 +9385 +Executable: ./dgemmoptimized 9385 9385 9385 1 0 +m=9385, n=9385, k=9385, time(sec)=2.718299, speed(mflops)=608184.874711 +Executable: ./dgemmoptimized 9385 9385 9385 1 0 +m=9385, n=9385, k=9385, time(sec)=2.712182, speed(mflops)=609556.532648 +Executable: ./dgemmoptimized 9385 9385 9385 1 0 +m=9385, n=9385, k=9385, time(sec)=2.712791, speed(mflops)=609419.709793 +Max repetitions 3, Elasped time 60.4028, Relative error 0.00557567, Mean 2712.65, Standard Deviation 8.97162 +Total Energy 2712.650000 +9441 +Executable: ./dgemmoptimized 9441 9441 9441 1 0 +m=9441, n=9441, k=9441, time(sec)=2.748123, speed(mflops)=612417.838935 +Executable: ./dgemmoptimized 9441 9441 9441 1 0 +m=9441, n=9441, k=9441, time(sec)=2.752226, speed(mflops)=611504.809693 +Executable: ./dgemmoptimized 9441 9441 9441 1 0 +m=9441, n=9441, k=9441, time(sec)=2.749922, speed(mflops)=612017.224284 +Max repetitions 3, Elasped time 62.8219, Relative error 0.0944113, Mean 2799.07, Standard Deviation 156.754 +Total Energy 2799.066667 +9496 +Executable: ./dgemmoptimized 9496 9496 9496 1 0 +m=9496, n=9496, k=9496, time(sec)=2.863964, speed(mflops)=597977.091733 +Executable: ./dgemmoptimized 9496 9496 9496 1 0 +m=9496, n=9496, k=9496, time(sec)=2.872856, speed(mflops)=596126.234080 +Executable: ./dgemmoptimized 9496 9496 9496 1 0 +m=9496, n=9496, k=9496, time(sec)=2.868304, speed(mflops)=597072.312903 +Max repetitions 3, Elasped time 63.3948, Relative error 0.126197, Mean 2806.17, Standard Deviation 210.059 +Total Energy 2806.166667 +9551 +Executable: ./dgemmoptimized 9551 9551 9551 1 0 +m=9551, n=9551, k=9551, time(sec)=2.968750, speed(mflops)=586952.428565 +Executable: ./dgemmoptimized 9551 9551 9551 1 0 +m=9551, n=9551, k=9551, time(sec)=2.959325, speed(mflops)=588821.815258 +Executable: ./dgemmoptimized 9551 9551 9551 1 0 +m=9551, n=9551, k=9551, time(sec)=2.938924, speed(mflops)=592909.166186 +Max repetitions 3, Elasped time 62.1084, Relative error 0.0145254, Mean 2683.82, Standard Deviation 23.1239 +Total Energy 2683.816667 +9606 +Executable: ./dgemmoptimized 9606 9606 9606 1 0 +m=9606, n=9606, k=9606, time(sec)=2.827863, speed(mflops)=626901.550171 +Executable: ./dgemmoptimized 9606 9606 9606 1 0 +m=9606, n=9606, k=9606, time(sec)=2.827998, speed(mflops)=626871.636015 +Executable: ./dgemmoptimized 9606 9606 9606 1 0 +m=9606, n=9606, k=9606, time(sec)=2.825136, speed(mflops)=627506.735161 +Max repetitions 3, Elasped time 64.3412, Relative error 0.116996, Mean 2760.03, Standard Deviation 191.542 +Total Energy 2760.033333 +9660 +Executable: ./dgemmoptimized 9660 9660 9660 1 0 +m=9660, n=9660, k=9660, time(sec)=2.925664, speed(mflops)=616221.624905 +Executable: ./dgemmoptimized 9660 9660 9660 1 0 +m=9660, n=9660, k=9660, time(sec)=2.926744, speed(mflops)=615994.224886 +Executable: ./dgemmoptimized 9660 9660 9660 1 0 +m=9660, n=9660, k=9660, time(sec)=2.930031, speed(mflops)=615303.167223 +Max repetitions 3, Elasped time 62.8442, Relative error 0.00326834, Mean 2672.83, Standard Deviation 5.18178 +Total Energy 2672.833333 +9715 +9715 +Executable: ./dgemmoptimized 9715 9715 9715 1 0 +m=9715, n=9715, k=9715, time(sec)=3.035859, speed(mflops)=604055.437532 +Executable: ./dgemmoptimized 9715 9715 9715 1 0 +m=9715, n=9715, k=9715, time(sec)=3.024632, speed(mflops)=606297.630801 +Executable: ./dgemmoptimized 9715 9715 9715 1 0 +m=9715, n=9715, k=9715, time(sec)=3.032059, speed(mflops)=604812.515003 +Max repetitions 3, Elasped time 70.7932, Relative error 0.429537, Mean 3552.78, Standard Deviation 905.209 +Total Energy 3552.783333 +9768 +Executable: ./dgemmoptimized 9768 9768 9768 1 0 +m=9768, n=9768, k=9768, time(sec)=3.066944, speed(mflops)=607772.602378 +Executable: ./dgemmoptimized 9768 9768 9768 1 0 +m=9768, n=9768, k=9768, time(sec)=3.067665, speed(mflops)=607629.713428 +Executable: ./dgemmoptimized 9768 9768 9768 1 0 +m=9768, n=9768, k=9768, time(sec)=3.068552, speed(mflops)=607454.087533 +Max repetitions 3, Elasped time 69.3789, Relative error 0.423021, Mean 3079.43, Standard Deviation 772.702 +Total Energy 3079.433333 +9822 +Executable: ./dgemmoptimized 9822 9822 9822 1 0 +m=9822, n=9822, k=9822, time(sec)=3.098751, speed(mflops)=611565.665921 +Executable: ./dgemmoptimized 9822 9822 9822 1 0 +m=9822, n=9822, k=9822, time(sec)=3.119106, speed(mflops)=607574.647191 +Executable: ./dgemmoptimized 9822 9822 9822 1 0 +m=9822, n=9822, k=9822, time(sec)=3.123547, speed(mflops)=606710.804630 +Max repetitions 3, Elasped time 66.1944, Relative error 0.131776, Mean 2895.3, Standard Deviation 226.314 +Total Energy 2895.300000 +9875 +Executable: ./dgemmoptimized 9875 9875 9875 1 0 +m=9875, n=9875, k=9875, time(sec)=3.210570, speed(mflops)=599872.775109 +Executable: ./dgemmoptimized 9875 9875 9875 1 0 +m=9875, n=9875, k=9875, time(sec)=3.209154, speed(mflops)=600137.500226 +Executable: ./dgemmoptimized 9875 9875 9875 1 0 +m=9875, n=9875, k=9875, time(sec)=3.205066, speed(mflops)=600902.950014 +Max repetitions 3, Elasped time 66.8878, Relative error 0.0742951, Mean 3404.3, Standard Deviation 150.027 +Total Energy 3404.300000 +9928 +Executable: ./dgemmoptimized 9928 9928 9928 1 0 +m=9928, n=9928, k=9928, time(sec)=3.339417, speed(mflops)=586063.467003 +Executable: ./dgemmoptimized 9928 9928 9928 1 0 +m=9928, n=9928, k=9928, time(sec)=3.307739, speed(mflops)=591676.151604 +Executable: ./dgemmoptimized 9928 9928 9928 1 0 +m=9928, n=9928, k=9928, time(sec)=3.329272, speed(mflops)=587849.318055 +Max repetitions 3, Elasped time 65.5664, Relative error 0.0162429, Mean 3306.45, Standard Deviation 31.8571 +Total Energy 3306.450000 +9981 +Executable: ./dgemmoptimized 9981 9981 9981 1 0 +m=9981, n=9981, k=9981, time(sec)=3.168416, speed(mflops)=627639.057399 +Executable: ./dgemmoptimized 9981 9981 9981 1 0 +m=9981, n=9981, k=9981, time(sec)=3.167003, speed(mflops)=627919.060736 +Executable: ./dgemmoptimized 9981 9981 9981 1 0 +m=9981, n=9981, k=9981, time(sec)=3.168260, speed(mflops)=627669.993855 +Max repetitions 3, Elasped time 67.4334, Relative error 0.120956, Mean 3429.82, Standard Deviation 246.082 +Total Energy 3429.816667 +10033 +Executable: ./dgemmoptimized 10033 10033 10033 1 0 +m=10033, n=10033, k=10033, time(sec)=3.280255, speed(mflops)=615764.783492 +Executable: ./dgemmoptimized 10033 10033 10033 1 0 +m=10033, n=10033, k=10033, time(sec)=3.278003, speed(mflops)=616187.745681 +Executable: ./dgemmoptimized 10033 10033 10033 1 0 +m=10033, n=10033, k=10033, time(sec)=3.278246, speed(mflops)=616142.125249 +Max repetitions 3, Elasped time 68.1387, Relative error 0.0857844, Mean 3337.37, Standard Deviation 169.821 +Total Energy 3337.366667 +10085 +Executable: ./dgemmoptimized 10085 10085 10085 1 0 +m=10085, n=10085, k=10085, time(sec)=3.378969, speed(mflops)=607118.506082 +Executable: ./dgemmoptimized 10085 10085 10085 1 0 +m=10085, n=10085, k=10085, time(sec)=3.378568, speed(mflops)=607190.568175 +Executable: ./dgemmoptimized 10085 10085 10085 1 0 +m=10085, n=10085, k=10085, time(sec)=3.377104, speed(mflops)=607453.812955 +Max repetitions 3, Elasped time 66.8105, Relative error 0.0134799, Mean 3229.3, Standard Deviation 25.8211 +Total Energy 3229.300000 +10137 +Executable: ./dgemmoptimized 10137 10137 10137 1 0 +m=10137, n=10137, k=10137, time(sec)=3.479261, speed(mflops)=598785.583986 +Executable: ./dgemmoptimized 10137 10137 10137 1 0 +m=10137, n=10137, k=10137, time(sec)=3.474762, speed(mflops)=599560.863436 +Executable: ./dgemmoptimized 10137 10137 10137 1 0 +m=10137, n=10137, k=10137, time(sec)=3.479947, speed(mflops)=598667.516700 +Max repetitions 3, Elasped time 71.3765, Relative error 0.107197, Mean 3457.48, Standard Deviation 219.848 +Total Energy 3457.483333 +10189 +Executable: ./dgemmoptimized 10189 10189 10189 1 0 +m=10189, n=10189, k=10189, time(sec)=3.453296, speed(mflops)=612619.552302 +Executable: ./dgemmoptimized 10189 10189 10189 1 0 +m=10189, n=10189, k=10189, time(sec)=3.458088, speed(mflops)=611770.669451 +Executable: ./dgemmoptimized 10189 10189 10189 1 0 +m=10189, n=10189, k=10189, time(sec)=3.454750, speed(mflops)=612361.741128 +Max repetitions 3, Elasped time 67.6523, Relative error 0.00770818, Mean 3195.88, Standard Deviation 14.6124 +Total Energy 3195.883333 +10240 +Executable: ./dgemmoptimized 10240 10240 10240 1 0 +m=10240, n=10240, k=10240, time(sec)=3.687520, speed(mflops)=582365.284034 +Executable: ./dgemmoptimized 10240 10240 10240 1 0 +m=10240, n=10240, k=10240, time(sec)=3.682435, speed(mflops)=583169.496873 +Executable: ./dgemmoptimized 10240 10240 10240 1 0 +m=10240, n=10240, k=10240, time(sec)=3.676569, speed(mflops)=584099.919455 +Max repetitions 3, Elasped time 68.6691, Relative error 0.00209479, Mean 3164.1, Standard Deviation 3.9316 +Total Energy 3164.100000 +10291 +Executable: ./dgemmoptimized 10291 10291 10291 1 0 +m=10291, n=10291, k=10291, time(sec)=3.671279, speed(mflops)=593725.012978 +Executable: ./dgemmoptimized 10291 10291 10291 1 0 +m=10291, n=10291, k=10291, time(sec)=3.671259, speed(mflops)=593728.251819 +Executable: ./dgemmoptimized 10291 10291 10291 1 0 +m=10291, n=10291, k=10291, time(sec)=3.678683, speed(mflops)=592530.022061 +Max repetitions 3, Elasped time 71.0156, Relative error 0.128895, Mean 3332.47, Standard Deviation 254.79 +Total Energy 3332.466667 +10342 +Executable: ./dgemmoptimized 10342 10342 10342 1 0 +m=10342, n=10342, k=10342, time(sec)=3.603179, speed(mflops)=613984.999609 +Executable: ./dgemmoptimized 10342 10342 10342 1 0 +m=10342, n=10342, k=10342, time(sec)=3.605086, speed(mflops)=613660.198193 +Executable: ./dgemmoptimized 10342 10342 10342 1 0 +m=10342, n=10342, k=10342, time(sec)=3.600790, speed(mflops)=614392.349665 +Max repetitions 3, Elasped time 71.0304, Relative error 0.101358, Mean 3270.87, Standard Deviation 196.652 +Total Energy 3270.866667 +10392 +Executable: ./dgemmoptimized 10392 10392 10392 1 0 +m=10392, n=10392, k=10392, time(sec)=3.532479, speed(mflops)=635400.884823 +Executable: ./dgemmoptimized 10392 10392 10392 1 0 +m=10392, n=10392, k=10392, time(sec)=3.536447, speed(mflops)=634687.945837 +Executable: ./dgemmoptimized 10392 10392 10392 1 0 +m=10392, n=10392, k=10392, time(sec)=3.535604, speed(mflops)=634839.284184 +Max repetitions 3, Elasped time 74.9234, Relative error 0.00895822, Mean 3480.03, Standard Deviation 18.492 +Total Energy 3480.033333 +10443 +Executable: ./dgemmoptimized 10443 10443 10443 1 0 +m=10443, n=10443, k=10443, time(sec)=3.660560, speed(mflops)=622240.554289 +Executable: ./dgemmoptimized 10443 10443 10443 1 0 +m=10443, n=10443, k=10443, time(sec)=3.650951, speed(mflops)=623878.237095 +Executable: ./dgemmoptimized 10443 10443 10443 1 0 +m=10443, n=10443, k=10443, time(sec)=3.650466, speed(mflops)=623961.115727 +Max repetitions 3, Elasped time 71.9166, Relative error 0.0782908, Mean 3224.87, Standard Deviation 149.762 +Total Energy 3224.866667 +10493 +Executable: ./dgemmoptimized 10493 10493 10493 1 0 +m=10493, n=10493, k=10493, time(sec)=3.761187, speed(mflops)=614333.331280 +Executable: ./dgemmoptimized 10493 10493 10493 1 0 +m=10493, n=10493, k=10493, time(sec)=3.767027, speed(mflops)=613380.962464 +Executable: ./dgemmoptimized 10493 10493 10493 1 0 +m=10493, n=10493, k=10493, time(sec)=3.767347, speed(mflops)=613328.829698 +Max repetitions 3, Elasped time 72.5945, Relative error 0.059757, Mean 3954.43, Standard Deviation 140.169 +Total Energy 3954.433333 +10543 +Executable: ./dgemmoptimized 10543 10543 10543 1 0 +m=10543, n=10543, k=10543, time(sec)=3.781027, speed(mflops)=619887.426689 +Executable: ./dgemmoptimized 10543 10543 10543 1 0 +m=10543, n=10543, k=10543, time(sec)=3.785434, speed(mflops)=619165.765743 +Executable: ./dgemmoptimized 10543 10543 10543 1 0 +m=10543, n=10543, k=10543, time(sec)=3.778941, speed(mflops)=620229.596123 +Max repetitions 3, Elasped time 71.032, Relative error 0.00886735, Mean 3826.3, Standard Deviation 20.1258 +Total Energy 3826.300000 +10592 +Executable: ./dgemmoptimized 10592 10592 10592 1 0 +m=10592, n=10592, k=10592, time(sec)=3.850730, speed(mflops)=617192.760288 +Executable: ./dgemmoptimized 10592 10592 10592 1 0 +m=10592, n=10592, k=10592, time(sec)=3.851918, speed(mflops)=617002.438894 +Executable: ./dgemmoptimized 10592 10592 10592 1 0 +m=10592, n=10592, k=10592, time(sec)=3.854062, speed(mflops)=616659.225210 +Max repetitions 3, Elasped time 73.5627, Relative error 0.0714351, Mean 3902.2, Standard Deviation 165.349 +Total Energy 3902.200000 +10642 +Executable: ./dgemmoptimized 10642 10642 10642 1 0 +m=10642, n=10642, k=10642, time(sec)=3.964171, speed(mflops)=608061.332232 +Executable: ./dgemmoptimized 10642 10642 10642 1 0 +m=10642, n=10642, k=10642, time(sec)=3.967769, speed(mflops)=607509.905415 +Executable: ./dgemmoptimized 10642 10642 10642 1 0 +m=10642, n=10642, k=10642, time(sec)=3.923477, speed(mflops)=614368.097190 +Max repetitions 3, Elasped time 74.1685, Relative error 0.129153, Mean 3915.13, Standard Deviation 299.937 +Total Energy 3915.133333 +10691 +Executable: ./dgemmoptimized 10691 10691 10691 1 0 +m=10691, n=10691, k=10691, time(sec)=4.053678, speed(mflops)=602886.740683 +Executable: ./dgemmoptimized 10691 10691 10691 1 0 +m=10691, n=10691, k=10691, time(sec)=4.053999, speed(mflops)=602839.016637 +Executable: ./dgemmoptimized 10691 10691 10691 1 0 +m=10691, n=10691, k=10691, time(sec)=4.057819, speed(mflops)=602271.481707 +Max repetitions 3, Elasped time 72.8076, Relative error 0.0101006, Mean 3774.5, Standard Deviation 22.6144 +Total Energy 3774.500000 +10740 +Executable: ./dgemmoptimized 10740 10740 10740 1 0 +m=10740, n=10740, k=10740, time(sec)=3.988726, speed(mflops)=621167.387711 +Executable: ./dgemmoptimized 10740 10740 10740 1 0 +m=10740, n=10740, k=10740, time(sec)=3.998156, speed(mflops)=619702.320752 +Executable: ./dgemmoptimized 10740 10740 10740 1 0 +m=10740, n=10740, k=10740, time(sec)=3.998194, speed(mflops)=619696.408141 +Max repetitions 3, Elasped time 75.0161, Relative error 0.0622509, Mean 3847.37, Standard Deviation 142.066 +Total Energy 3847.366667 +10789 +Executable: ./dgemmoptimized 10789 10789 10789 1 0 +m=10789, n=10789, k=10789, time(sec)=3.997109, speed(mflops)=628387.539179 +Executable: ./dgemmoptimized 10789 10789 10789 1 0 +m=10789, n=10789, k=10789, time(sec)=3.994937, speed(mflops)=628729.222499 +Executable: ./dgemmoptimized 10789 10789 10789 1 0 +m=10789, n=10789, k=10789, time(sec)=3.997399, speed(mflops)=628341.964489 +Max repetitions 3, Elasped time 75.4006, Relative error 0.0581954, Mean 3835.08, Standard Deviation 132.386 +Total Energy 3835.083333 +10837 +Executable: ./dgemmoptimized 10837 10837 10837 1 0 +m=10837, n=10837, k=10837, time(sec)=4.099612, speed(mflops)=620889.707122 +Executable: ./dgemmoptimized 10837 10837 10837 1 0 +m=10837, n=10837, k=10837, time(sec)=4.102053, speed(mflops)=620520.210209 +Executable: ./dgemmoptimized 10837 10837 10837 1 0 +m=10837, n=10837, k=10837, time(sec)=4.102893, speed(mflops)=620393.176650 +Max repetitions 3, Elasped time 73.9639, Relative error 0.00829758, Mean 3719.38, Standard Deviation 18.3064 +Total Energy 3719.383333 +10885 +Executable: ./dgemmoptimized 10885 10885 10885 1 0 +m=10885, n=10885, k=10885, time(sec)=4.217077, speed(mflops)=611651.102874 +Executable: ./dgemmoptimized 10885 10885 10885 1 0 +m=10885, n=10885, k=10885, time(sec)=4.237300, speed(mflops)=608731.907664 +Executable: ./dgemmoptimized 10885 10885 10885 1 0 +m=10885, n=10885, k=10885, time(sec)=4.194594, speed(mflops)=614929.530533 +Max repetitions 3, Elasped time 74.6408, Relative error 0.015073, Mean 3748.9, Standard Deviation 33.5183 +Total Energy 3748.900000 +10933 +Executable: ./dgemmoptimized 10933 10933 10933 1 0 +m=10933, n=10933, k=10933, time(sec)=4.216095, speed(mflops)=619922.864792 +Executable: ./dgemmoptimized 10933 10933 10933 1 0 +m=10933, n=10933, k=10933, time(sec)=4.180833, speed(mflops)=625151.437097 +Executable: ./dgemmoptimized 10933 10933 10933 1 0 +m=10933, n=10933, k=10933, time(sec)=4.214894, speed(mflops)=620099.494210 +Max repetitions 3, Elasped time 74.9357, Relative error 0.00327249, Mean 3673.23, Standard Deviation 7.13028 +Total Energy 3673.233333 +10981 +Executable: ./dgemmoptimized 10981 10981 10981 1 0 +m=10981, n=10981, k=10981, time(sec)=4.287290, speed(mflops)=617693.170466 +Executable: ./dgemmoptimized 10981 10981 10981 1 0 +m=10981, n=10981, k=10981, time(sec)=4.291805, speed(mflops)=617043.363909 +Executable: ./dgemmoptimized 10981 10981 10981 1 0 +m=10981, n=10981, k=10981, time(sec)=4.291933, speed(mflops)=617024.991434 +Max repetitions 3, Elasped time 75.526, Relative error 0.00614952, Mean 3689.15, Standard Deviation 13.457 +Total Energy 3689.150000 +11029 +Executable: ./dgemmoptimized 11029 11029 11029 1 0 +m=11029, n=11029, k=11029, time(sec)=4.407580, speed(mflops)=608748.931696 +Executable: ./dgemmoptimized 11029 11029 11029 1 0 +m=11029, n=11029, k=11029, time(sec)=4.407697, speed(mflops)=608732.731075 +Executable: ./dgemmoptimized 11029 11029 11029 1 0 +m=11029, n=11029, k=11029, time(sec)=4.412139, speed(mflops)=608119.914611 +Max repetitions 3, Elasped time 76.2301, Relative error 0.00723074, Mean 3645.35, Standard Deviation 15.6351 +Total Energy 3645.350000 +11076 +Executable: ./dgemmoptimized 11076 11076 11076 1 0 +m=11076, n=11076, k=11076, time(sec)=4.551149, speed(mflops)=597114.710243 +Executable: ./dgemmoptimized 11076 11076 11076 1 0 +m=11076, n=11076, k=11076, time(sec)=4.551366, speed(mflops)=597086.246141 +Executable: ./dgemmoptimized 11076 11076 11076 1 0 +m=11076, n=11076, k=11076, time(sec)=4.549602, speed(mflops)=597317.759886 +Max repetitions 3, Elasped time 78.9724, Relative error 0.0695986, Mean 4479.78, Standard Deviation 184.943 +Total Energy 4479.783333 +11123 +Executable: ./dgemmoptimized 11123 11123 11123 1 0 +m=11123, n=11123, k=11123, time(sec)=4.414795, speed(mflops)=623426.520244 +Executable: ./dgemmoptimized 11123 11123 11123 1 0 +m=11123, n=11123, k=11123, time(sec)=4.424898, speed(mflops)=622003.070791 +Executable: ./dgemmoptimized 11123 11123 11123 1 0 +m=11123, n=11123, k=11123, time(sec)=4.419390, speed(mflops)=622778.315261 +Max repetitions 3, Elasped time 78.9123, Relative error 0.0649771, Mean 4480.42, Standard Deviation 172.687 +Total Energy 4480.416667 +11171 +Executable: ./dgemmoptimized 11171 11171 11171 1 0 +m=11171, n=11171, k=11171, time(sec)=4.459568, speed(mflops)=625191.922540 +Executable: ./dgemmoptimized 11171 11171 11171 1 0 +m=11171, n=11171, k=11171, time(sec)=4.458685, speed(mflops)=625315.750195 +Executable: ./dgemmoptimized 11171 11171 11171 1 0 +m=11171, n=11171, k=11171, time(sec)=4.463409, speed(mflops)=624653.922492 +Max repetitions 3, Elasped time 77.3905, Relative error 0.00997643, Mean 4361.35, Standard Deviation 25.8093 +Total Energy 4361.350000 +11217 +Executable: ./dgemmoptimized 11217 11217 11217 1 0 +m=11217, n=11217, k=11217, time(sec)=4.573008, speed(mflops)=617245.896021 +Executable: ./dgemmoptimized 11217 11217 11217 1 0 +m=11217, n=11217, k=11217, time(sec)=4.575196, speed(mflops)=616950.682223 +Executable: ./dgemmoptimized 11217 11217 11217 1 0 +m=11217, n=11217, k=11217, time(sec)=4.572696, speed(mflops)=617287.991333 +Max repetitions 3, Elasped time 78.0657, Relative error 0.00136171, Mean 4331.52, Standard Deviation 3.49869 +Total Energy 4331.516667 +11264 +Executable: ./dgemmoptimized 11264 11264 11264 1 0 +m=11264, n=11264, k=11264, time(sec)=4.842146, speed(mflops)=590296.253374 +Executable: ./dgemmoptimized 11264 11264 11264 1 0 +m=11264, n=11264, k=11264, time(sec)=4.846216, speed(mflops)=589800.499292 +Executable: ./dgemmoptimized 11264 11264 11264 1 0 +m=11264, n=11264, k=11264, time(sec)=4.835819, speed(mflops)=591068.592923 +Max repetitions 3, Elasped time 81.197, Relative error 0.0607428, Mean 4409.35, Standard Deviation 158.873 +Total Energy 4409.350000 +11310 +Executable: ./dgemmoptimized 11310 11310 11310 1 0 +m=11310, n=11310, k=11310, time(sec)=4.747198, speed(mflops)=609509.496635 +Executable: ./dgemmoptimized 11310 11310 11310 1 0 +m=11310, n=11310, k=11310, time(sec)=4.748408, speed(mflops)=609354.183350 +Executable: ./dgemmoptimized 11310 11310 11310 1 0 +m=11310, n=11310, k=11310, time(sec)=4.699003, speed(mflops)=615760.873867 +Max repetitions 3, Elasped time 79.6016, Relative error 0.0286548, Mean 4289.27, Standard Deviation 72.9055 +Total Energy 4289.266667 +11357 +Executable: ./dgemmoptimized 11357 11357 11357 1 0 +m=11357, n=11357, k=11357, time(sec)=4.778966, speed(mflops)=613037.352270 +Executable: ./dgemmoptimized 11357 11357 11357 1 0 +m=11357, n=11357, k=11357, time(sec)=4.775304, speed(mflops)=613507.450852 +Executable: ./dgemmoptimized 11357 11357 11357 1 0 +m=11357, n=11357, k=11357, time(sec)=4.783569, speed(mflops)=612447.436811 +Max repetitions 3, Elasped time 81.7146, Relative error 0.0624946, Mean 4377.5, Standard Deviation 162.274 +Total Energy 4377.500000 +11403 +Executable: ./dgemmoptimized 11403 11403 11403 1 0 +m=11403, n=11403, k=11403, time(sec)=4.892112, speed(mflops)=606165.166608 +Executable: ./dgemmoptimized 11403 11403 11403 1 0 +m=11403, n=11403, k=11403, time(sec)=4.887623, speed(mflops)=606721.887545 +Executable: ./dgemmoptimized 11403 11403 11403 1 0 +m=11403, n=11403, k=11403, time(sec)=4.894623, speed(mflops)=605854.223128 +Max repetitions 3, Elasped time 84.3163, Relative error 0.0561159, Mean 4480.22, Standard Deviation 149.13 +Total Energy 4480.216667 +11449 +Executable: ./dgemmoptimized 11449 11449 11449 1 0 +m=11449, n=11449, k=11449, time(sec)=5.006820, speed(mflops)=599474.461955 +Executable: ./dgemmoptimized 11449 11449 11449 1 0 +m=11449, n=11449, k=11449, time(sec)=5.007559, speed(mflops)=599385.981694 +Executable: ./dgemmoptimized 11449 11449 11449 1 0 +m=11449, n=11449, k=11449, time(sec)=5.003400, speed(mflops)=599884.237582 +Max repetitions 3, Elasped time 81.0568, Relative error 0.00741327, Mean 4234.67, Standard Deviation 18.6212 +Total Energy 4234.666667 +11494 +Executable: ./dgemmoptimized 11494 11494 11494 1 0 +m=11494, n=11494, k=11494, time(sec)=4.864211, speed(mflops)=624354.377737 +Executable: ./dgemmoptimized 11494 11494 11494 1 0 +m=11494, n=11494, k=11494, time(sec)=4.862927, speed(mflops)=624519.247061 +Executable: ./dgemmoptimized 11494 11494 11494 1 0 +m=11494, n=11494, k=11494, time(sec)=4.864917, speed(mflops)=624263.776479 +Max repetitions 3, Elasped time 80.9502, Relative error 0.0106323, Mean 4233.57, Standard Deviation 26.7002 +Total Energy 4233.566667 +11540 +Executable: ./dgemmoptimized 11540 11540 11540 1 0 +m=11540, n=11540, k=11540, time(sec)=4.813306, speed(mflops)=638563.280306 +Executable: ./dgemmoptimized 11540 11540 11540 1 0 +m=11540, n=11540, k=11540, time(sec)=4.804227, speed(mflops)=639770.030692 +Executable: ./dgemmoptimized 11540 11540 11540 1 0 +m=11540, n=11540, k=11540, time(sec)=4.800185, speed(mflops)=640308.769417 +Max repetitions 3, Elasped time 81.1125, Relative error 0.00869555, Mean 4246.43, Standard Deviation 21.9029 +Total Energy 4246.433333 +11585 +Executable: ./dgemmoptimized 11585 11585 11585 1 0 +m=11585, n=11585, k=11585, time(sec)=4.915626, speed(mflops)=632614.721513 +Executable: ./dgemmoptimized 11585 11585 11585 1 0 +m=11585, n=11585, k=11585, time(sec)=4.909704, speed(mflops)=633377.749917 +Executable: ./dgemmoptimized 11585 11585 11585 1 0 +m=11585, n=11585, k=11585, time(sec)=4.912374, speed(mflops)=633033.486625 +Max repetitions 3, Elasped time 81.7841, Relative error 0.0128042, Mean 4197.5, Standard Deviation 31.8804 +Total Energy 4197.500000 +11630 +Executable: ./dgemmoptimized 11630 11630 11630 1 0 +m=11630, n=11630, k=11630, time(sec)=4.998638, speed(mflops)=629386.554440 +Executable: ./dgemmoptimized 11630 11630 11630 1 0 +m=11630, n=11630, k=11630, time(sec)=5.035069, speed(mflops)=624832.648966 +Executable: ./dgemmoptimized 11630 11630 11630 1 0 +m=11630, n=11630, k=11630, time(sec)=5.033230, speed(mflops)=625060.935534 +Max repetitions 3, Elasped time 84.3535, Relative error 0.0224828, Mean 4550.13, Standard Deviation 60.6811 +Total Energy 4550.133333 +11675 +Executable: ./dgemmoptimized 11675 11675 11675 1 0 +m=11675, n=11675, k=11675, time(sec)=5.111251, speed(mflops)=622692.227723 +Executable: ./dgemmoptimized 11675 11675 11675 1 0 +m=11675, n=11675, k=11675, time(sec)=5.114464, speed(mflops)=622301.049731 +Executable: ./dgemmoptimized 11675 11675 11675 1 0 +m=11675, n=11675, k=11675, time(sec)=5.115779, speed(mflops)=622141.103365 +Max repetitions 3, Elasped time 83.041, Relative error 0.010132, Mean 4953.97, Standard Deviation 29.7735 +Total Energy 4953.966667 +11720 +Executable: ./dgemmoptimized 11720 11720 11720 1 0 +m=11720, n=11720, k=11720, time(sec)=5.111993, speed(mflops)=629828.884572 +Executable: ./dgemmoptimized 11720 11720 11720 1 0 +m=11720, n=11720, k=11720, time(sec)=5.105981, speed(mflops)=630570.496838 +Executable: ./dgemmoptimized 11720 11720 11720 1 0 +m=11720, n=11720, k=11720, time(sec)=5.107215, speed(mflops)=630418.132308 +Max repetitions 3, Elasped time 83.4037, Relative error 0.01495, Mean 4937.98, Standard Deviation 43.7896 +Total Energy 4937.983333 +11765 +Executable: ./dgemmoptimized 11765 11765 11765 1 0 +m=11765, n=11765, k=11765, time(sec)=5.249160, speed(mflops)=620463.124079 +Executable: ./dgemmoptimized 11765 11765 11765 1 0 +m=11765, n=11765, k=11765, time(sec)=5.252559, speed(mflops)=620061.626601 +Executable: ./dgemmoptimized 11765 11765 11765 1 0 +m=11765, n=11765, k=11765, time(sec)=5.259947, speed(mflops)=619190.688831 +Max repetitions 3, Elasped time 84.1459, Relative error 0.00893804, Mean 4887.85, Standard Deviation 25.9143 +Total Energy 4887.850000 +11809 +Executable: ./dgemmoptimized 11809 11809 11809 1 0 +m=11809, n=11809, k=11809, time(sec)=5.349379, speed(mflops)=615695.514878 +Executable: ./dgemmoptimized 11809 11809 11809 1 0 +m=11809, n=11809, k=11809, time(sec)=5.354370, speed(mflops)=615121.596784 +Executable: ./dgemmoptimized 11809 11809 11809 1 0 +m=11809, n=11809, k=11809, time(sec)=5.348263, speed(mflops)=615824.021278 +Max repetitions 3, Elasped time 86.666, Relative error 0.0676452, Mean 5003.98, Standard Deviation 200.786 +Total Energy 5003.983333 +11854 +Executable: ./dgemmoptimized 11854 11854 11854 1 0 +m=11854, n=11854, k=11854, time(sec)=5.448308, speed(mflops)=611453.021274 +Executable: ./dgemmoptimized 11854 11854 11854 1 0 +m=11854, n=11854, k=11854, time(sec)=5.438909, speed(mflops)=612509.695377 +Executable: ./dgemmoptimized 11854 11854 11854 1 0 +m=11854, n=11854, k=11854, time(sec)=5.432839, speed(mflops)=613194.055403 +Max repetitions 3, Elasped time 85.3764, Relative error 0.0147116, Mean 4835.65, Standard Deviation 42.1983 +Total Energy 4835.650000 +11898 +Executable: ./dgemmoptimized 11898 11898 11898 1 0 +m=11898, n=11898, k=11898, time(sec)=5.247152, speed(mflops)=641989.960984 +Executable: ./dgemmoptimized 11898 11898 11898 1 0 +m=11898, n=11898, k=11898, time(sec)=5.240447, speed(mflops)=642811.374118 +Executable: ./dgemmoptimized 11898 11898 11898 1 0 +m=11898, n=11898, k=11898, time(sec)=5.253905, speed(mflops)=641164.796177 +Max repetitions 3, Elasped time 87.0252, Relative error 0.0735943, Mean 4954.77, Standard Deviation 216.295 +Total Energy 4954.766667 +11942 +Executable: ./dgemmoptimized 11942 11942 11942 1 0 +m=11942, n=11942, k=11942, time(sec)=5.441367, speed(mflops)=625969.489705 +Executable: ./dgemmoptimized 11942 11942 11942 1 0 +m=11942, n=11942, k=11942, time(sec)=5.434752, speed(mflops)=626731.417669 +Executable: ./dgemmoptimized 11942 11942 11942 1 0 +m=11942, n=11942, k=11942, time(sec)=5.424913, speed(mflops)=627868.080525 +Max repetitions 3, Elasped time 87.9288, Relative error 0.0827105, Mean 4945.73, Standard Deviation 242.645 +Total Energy 4945.733333 +11986 +Executable: ./dgemmoptimized 11986 11986 11986 1 0 +m=11986, n=11986, k=11986, time(sec)=5.514891, speed(mflops)=624476.170849 +Executable: ./dgemmoptimized 11986 11986 11986 1 0 +m=11986, n=11986, k=11986, time(sec)=5.527383, speed(mflops)=623064.875289 +Executable: ./dgemmoptimized 11986 11986 11986 1 0 +m=11986, n=11986, k=11986, time(sec)=5.525878, speed(mflops)=623234.531685 +Max repetitions 3, Elasped time 87.1023, Relative error 0.0214105, Mean 4776.92, Standard Deviation 60.6673 +Total Energy 4776.916667 +12029 +Executable: ./dgemmoptimized 12029 12029 12029 1 0 +m=12029, n=12029, k=12029, time(sec)=5.639534, speed(mflops)=617270.257239 +Executable: ./dgemmoptimized 12029 12029 12029 1 0 +m=12029, n=12029, k=12029, time(sec)=5.641203, speed(mflops)=617087.640003 +Executable: ./dgemmoptimized 12029 12029 12029 1 0 +m=12029, n=12029, k=12029, time(sec)=5.642158, speed(mflops)=616983.179373 +Max repetitions 3, Elasped time 89.2276, Relative error 0.0685531, Mean 4917.78, Standard Deviation 199.975 +Total Energy 4917.783333 +12073 +Executable: ./dgemmoptimized 12073 12073 12073 1 0 +m=12073, n=12073, k=12073, time(sec)=5.660850, speed(mflops)=621718.723540 +Executable: ./dgemmoptimized 12073 12073 12073 1 0 +m=12073, n=12073, k=12073, time(sec)=5.660398, speed(mflops)=621768.374243 +Executable: ./dgemmoptimized 12073 12073 12073 1 0 +m=12073, n=12073, k=12073, time(sec)=5.657705, speed(mflops)=622064.321729 +Max repetitions 3, Elasped time 89.7297, Relative error 0.0628388, Mean 4838.88, Standard Deviation 180.365 +Total Energy 4838.883333 +12116 +Executable: ./dgemmoptimized 12116 12116 12116 1 0 +m=12116, n=12116, k=12116, time(sec)=5.728272, speed(mflops)=620989.362565 +Executable: ./dgemmoptimized 12116 12116 12116 1 0 +m=12116, n=12116, k=12116, time(sec)=5.732396, speed(mflops)=620542.592614 +Executable: ./dgemmoptimized 12116 12116 12116 1 0 +m=12116, n=12116, k=12116, time(sec)=5.724086, speed(mflops)=621443.480246 +Max repetitions 3, Elasped time 88.2698, Relative error 0.0694452, Mean 4851.87, Standard Deviation 199.862 +Total Energy 4851.866667 +12159 +Executable: ./dgemmoptimized 12159 12159 12159 1 0 +m=12159, n=12159, k=12159, time(sec)=5.819644, speed(mflops)=617770.483423 +Executable: ./dgemmoptimized 12159 12159 12159 1 0 +m=12159, n=12159, k=12159, time(sec)=5.808879, speed(mflops)=618915.342203 +Executable: ./dgemmoptimized 12159 12159 12159 1 0 +m=12159, n=12159, k=12159, time(sec)=5.818488, speed(mflops)=617893.204656 +Max repetitions 3, Elasped time 88.8631, Relative error 0.0123428, Mean 5479.22, Standard Deviation 40.1155 +Total Energy 5479.216667 +12202 +Executable: ./dgemmoptimized 12202 12202 12202 1 0 +m=12202, n=12202, k=12202, time(sec)=5.935860, speed(mflops)=612124.009435 +Executable: ./dgemmoptimized 12202 12202 12202 1 0 +m=12202, n=12202, k=12202, time(sec)=5.932508, speed(mflops)=612469.865670 +Executable: ./dgemmoptimized 12202 12202 12202 1 0 +m=12202, n=12202, k=12202, time(sec)=5.907274, speed(mflops)=615086.165745 +Max repetitions 3, Elasped time 91.5258, Relative error 0.0470938, Mean 5570.85, Standard Deviation 155.62 +Total Energy 5570.850000 +12245 +Executable: ./dgemmoptimized 12245 12245 12245 1 0 +m=12245, n=12245, k=12245, time(sec)=6.015431, speed(mflops)=610435.247467 +Executable: ./dgemmoptimized 12245 12245 12245 1 0 +m=12245, n=12245, k=12245, time(sec)=6.016212, speed(mflops)=610356.021441 +Executable: ./dgemmoptimized 12245 12245 12245 1 0 +m=12245, n=12245, k=12245, time(sec)=6.017879, speed(mflops)=610186.945701 +Max repetitions 3, Elasped time 92.1325, Relative error 0.0538958, Mean 5513.97, Standard Deviation 176.278 +Total Energy 5513.966667 +12288 +Executable: ./dgemmoptimized 12288 12288 12288 1 0 +m=12288, n=12288, k=12288, time(sec)=6.391942, speed(mflops)=580551.533427 +Executable: ./dgemmoptimized 12288 12288 12288 1 0 +m=12288, n=12288, k=12288, time(sec)=6.442078, speed(mflops)=576033.356887 +Executable: ./dgemmoptimized 12288 12288 12288 1 0 +m=12288, n=12288, k=12288, time(sec)=6.406437, speed(mflops)=579238.005460 +Max repetitions 3, Elasped time 93.793, Relative error 0.0530473, Mean 5491.07, Standard Deviation 172.782 +Total Energy 5491.066667 +12331 +Executable: ./dgemmoptimized 12331 12331 12331 1 0 +m=12331, n=12331, k=12331, time(sec)=6.000140, speed(mflops)=624976.242482 +Executable: ./dgemmoptimized 12331 12331 12331 1 0 +m=12331, n=12331, k=12331, time(sec)=6.010888, speed(mflops)=623858.714253 +Executable: ./dgemmoptimized 12331 12331 12331 1 0 +m=12331, n=12331, k=12331, time(sec)=6.017640, speed(mflops)=623158.721766 +Max repetitions 3, Elasped time 92.6799, Relative error 0.0596096, Mean 5531.33, Standard Deviation 195.581 +Total Energy 5531.333333 +12373 +Executable: ./dgemmoptimized 12373 12373 12373 1 0 +m=12373, n=12373, k=12373, time(sec)=6.151879, speed(mflops)=615810.743449 +Executable: ./dgemmoptimized 12373 12373 12373 1 0 +m=12373, n=12373, k=12373, time(sec)=6.154327, speed(mflops)=615565.784870 +Executable: ./dgemmoptimized 12373 12373 12373 1 0 +m=12373, n=12373, k=12373, time(sec)=6.150904, speed(mflops)=615908.346979 +Max repetitions 3, Elasped time 93.5419, Relative error 0.035103, Mean 5494.9, Standard Deviation 114.415 +Total Energy 5494.900000 +12415 +Executable: ./dgemmoptimized 12415 12415 12415 1 0 +m=12415, n=12415, k=12415, time(sec)=6.290125, speed(mflops)=608430.390769 +Executable: ./dgemmoptimized 12415 12415 12415 1 0 +m=12415, n=12415, k=12415, time(sec)=6.287710, speed(mflops)=608664.072664 +Executable: ./dgemmoptimized 12415 12415 12415 1 0 +m=12415, n=12415, k=12415, time(sec)=6.291440, speed(mflops)=608303.208904 +Max repetitions 3, Elasped time 92.3066, Relative error 0.00874132, Mean 5350.45, Standard Deviation 27.7426 +Total Energy 5350.450000 +12457 +Executable: ./dgemmoptimized 12457 12457 12457 1 0 +m=12457, n=12457, k=12457, time(sec)=6.324563, speed(mflops)=611279.546086 +Executable: ./dgemmoptimized 12457 12457 12457 1 0 +m=12457, n=12457, k=12457, time(sec)=6.330526, speed(mflops)=610703.769682 +Executable: ./dgemmoptimized 12457 12457 12457 1 0 +m=12457, n=12457, k=12457, time(sec)=6.321098, speed(mflops)=611614.644677 +Max repetitions 3, Elasped time 94.6387, Relative error 0.0579153, Mean 5504.4, Standard Deviation 189.096 +Total Energy 5504.400000 +12500 +Executable: ./dgemmoptimized 12500 12500 12500 1 0 +m=12500, n=12500, k=12500, time(sec)=6.352945, speed(mflops)=614872.306476 +Executable: ./dgemmoptimized 12500 12500 12500 1 0 +m=12500, n=12500, k=12500, time(sec)=6.343634, speed(mflops)=615774.817343 +Executable: ./dgemmoptimized 12500 12500 12500 1 0 +m=12500, n=12500, k=12500, time(sec)=6.350975, speed(mflops)=615063.037955 +Max repetitions 3, Elasped time 95.1507, Relative error 0.0471939, Mean 5409.25, Standard Deviation 151.427 +Total Energy 5409.250000 +12541 +Executable: ./dgemmoptimized 12541 12541 12541 1 0 +m=12541, n=12541, k=12541, time(sec)=6.472370, speed(mflops)=609485.184379 +Executable: ./dgemmoptimized 12541 12541 12541 1 0 +m=12541, n=12541, k=12541, time(sec)=6.470527, speed(mflops)=609658.804187 +Executable: ./dgemmoptimized 12541 12541 12541 1 0 +m=12541, n=12541, k=12541, time(sec)=6.471000, speed(mflops)=609614.238848 +Max repetitions 3, Elasped time 93.823, Relative error 0.010908, Mean 5345.83, Standard Deviation 34.5892 +Total Energy 5345.833333 +12583 +Executable: ./dgemmoptimized 12583 12583 12583 1 0 +m=12583, n=12583, k=12583, time(sec)=6.584477, speed(mflops)=605147.584261 +Executable: ./dgemmoptimized 12583 12583 12583 1 0 +m=12583, n=12583, k=12583, time(sec)=6.583291, speed(mflops)=605256.593705 +Executable: ./dgemmoptimized 12583 12583 12583 1 0 +m=12583, n=12583, k=12583, time(sec)=6.589953, speed(mflops)=604644.707973 +Max repetitions 3, Elasped time 98.5715, Relative error 0.0447021, Mean 5852.83, Standard Deviation 155.194 +Total Energy 5852.833333 +12625 +Executable: ./dgemmoptimized 12625 12625 12625 1 0 +m=12625, n=12625, k=12625, time(sec)=6.751596, speed(mflops)=596098.062853 +Executable: ./dgemmoptimized 12625 12625 12625 1 0 +m=12625, n=12625, k=12625, time(sec)=6.721075, speed(mflops)=598804.989757 +Executable: ./dgemmoptimized 12625 12625 12625 1 0 +m=12625, n=12625, k=12625, time(sec)=6.749846, speed(mflops)=596252.609648 +Max repetitions 3, Elasped time 95.3816, Relative error 0.00981943, Mean 6066.8, Standard Deviation 35.3367 +Total Energy 6066.800000 +12666 +Executable: ./dgemmoptimized 12666 12666 12666 1 0 +m=12666, n=12666, k=12666, time(sec)=6.343831, speed(mflops)=640614.607903 +Executable: ./dgemmoptimized 12666 12666 12666 1 0 +m=12666, n=12666, k=12666, time(sec)=6.346992, speed(mflops)=640295.566538 +Executable: ./dgemmoptimized 12666 12666 12666 1 0 +m=12666, n=12666, k=12666, time(sec)=6.354170, speed(mflops)=639572.248597 +Max repetitions 3, Elasped time 94.4828, Relative error 0.0158873, Mean 5639.62, Standard Deviation 53.147 +Total Energy 5639.616667 +12708 +Executable: ./dgemmoptimized 12708 12708 12708 1 0 +m=12708, n=12708, k=12708, time(sec)=6.503450, speed(mflops)=631128.531827 +Executable: ./dgemmoptimized 12708 12708 12708 1 0 +m=12708, n=12708, k=12708, time(sec)=6.511469, speed(mflops)=630351.287681 +Executable: ./dgemmoptimized 12708 12708 12708 1 0 +m=12708, n=12708, k=12708, time(sec)=6.499705, speed(mflops)=631492.159982 +Max repetitions 3, Elasped time 95.3223, Relative error 0.014792, Mean 6014.2, Standard Deviation 52.7696 +Total Energy 6014.200000 +12749 +Executable: ./dgemmoptimized 12749 12749 12749 1 0 +m=12749, n=12749, k=12749, time(sec)=6.605598, speed(mflops)=627402.465079 +Executable: ./dgemmoptimized 12749 12749 12749 1 0 +m=12749, n=12749, k=12749, time(sec)=6.607341, speed(mflops)=627236.950453 +Executable: ./dgemmoptimized 12749 12749 12749 1 0 +m=12749, n=12749, k=12749, time(sec)=6.602725, speed(mflops)=627675.457224 +Max repetitions 3, Elasped time 95.9456, Relative error 0.00441091, Mean 5968.72, Standard Deviation 15.6167 +Total Energy 5968.716667 +12790 +Executable: ./dgemmoptimized 12790 12790 12790 1 0 +m=12790, n=12790, k=12790, time(sec)=6.707206, speed(mflops)=623878.448232 +Executable: ./dgemmoptimized 12790 12790 12790 1 0 +m=12790, n=12790, k=12790, time(sec)=6.712546, speed(mflops)=623382.150075 +Executable: ./dgemmoptimized 12790 12790 12790 1 0 +m=12790, n=12790, k=12790, time(sec)=6.718444, speed(mflops)=622834.872202 +Max repetitions 3, Elasped time 98.5882, Relative error 0.0462258, Mean 6052.87, Standard Deviation 165.968 +Total Energy 6052.866667 +12831 +Executable: ./dgemmoptimized 12831 12831 12831 1 0 +m=12831, n=12831, k=12831, time(sec)=6.794113, speed(mflops)=621840.136256 +Executable: ./dgemmoptimized 12831 12831 12831 1 0 +m=12831, n=12831, k=12831, time(sec)=6.796715, speed(mflops)=621602.066770 +Executable: ./dgemmoptimized 12831 12831 12831 1 0 +m=12831, n=12831, k=12831, time(sec)=6.834360, speed(mflops)=618178.151070 +Max repetitions 3, Elasped time 99.2111, Relative error 0.0372954, Mean 6039.03, Standard Deviation 133.599 +Total Energy 6039.033333 +12871 +Executable: ./dgemmoptimized 12871 12871 12871 1 0 +m=12871, n=12871, k=12871, time(sec)=6.771522, speed(mflops)=629767.971838 +Executable: ./dgemmoptimized 12871 12871 12871 1 0 +m=12871, n=12871, k=12871, time(sec)=6.768384, speed(mflops)=630059.954836 +Executable: ./dgemmoptimized 12871 12871 12871 1 0 +m=12871, n=12871, k=12871, time(sec)=6.769698, speed(mflops)=629937.667046 +Max repetitions 3, Elasped time 99.4332, Relative error 0.0393148, Mean 6064.67, Standard Deviation 141.431 +Total Energy 6064.666667 +12912 +Executable: ./dgemmoptimized 12912 12912 12912 1 0 +m=12912, n=12912, k=12912, time(sec)=6.922151, speed(mflops)=621970.051488 +Executable: ./dgemmoptimized 12912 12912 12912 1 0 +m=12912, n=12912, k=12912, time(sec)=6.920845, speed(mflops)=622087.425641 +Executable: ./dgemmoptimized 12912 12912 12912 1 0 +m=12912, n=12912, k=12912, time(sec)=6.924728, speed(mflops)=621738.604150 +Max repetitions 3, Elasped time 99.2248, Relative error 0.0926817, Mean 6123.43, Standard Deviation 336.643 +Total Energy 6123.433333 +12953 +Executable: ./dgemmoptimized 12953 12953 12953 1 0 +m=12953, n=12953, k=12953, time(sec)=7.031104, speed(mflops)=618183.742901 +Executable: ./dgemmoptimized 12953 12953 12953 1 0 +m=12953, n=12953, k=12953, time(sec)=7.032384, speed(mflops)=618071.218034 +Executable: ./dgemmoptimized 12953 12953 12953 1 0 +m=12953, n=12953, k=12953, time(sec)=7.014281, speed(mflops)=619666.373930 +Max repetitions 3, Elasped time 98.9384, Relative error 0.00593693, Mean 5867.37, Standard Deviation 20.6626 +Total Energy 5867.366667 +12993 +Executable: ./dgemmoptimized 12993 12993 12993 1 0 +m=12993, n=12993, k=12993, time(sec)=7.194714, speed(mflops)=609740.120180 +Executable: ./dgemmoptimized 12993 12993 12993 1 0 +m=12993, n=12993, k=12993, time(sec)=7.198505, speed(mflops)=609419.020638 +Executable: ./dgemmoptimized 12993 12993 12993 1 0 +m=12993, n=12993, k=12993, time(sec)=7.188171, speed(mflops)=610295.146890 +Max repetitions 3, Elasped time 101.652, Relative error 0.0554697, Mean 5984.73, Standard Deviation 196.916 +Total Energy 5984.733333 +13033 +Executable: ./dgemmoptimized 13033 13033 13033 1 0 +m=13033, n=13033, k=13033, time(sec)=7.099200, speed(mflops)=623668.442564 +Executable: ./dgemmoptimized 13033 13033 13033 1 0 +m=13033, n=13033, k=13033, time(sec)=7.103995, speed(mflops)=623247.477095 +Executable: ./dgemmoptimized 13033 13033 13033 1 0 +m=13033, n=13033, k=13033, time(sec)=7.107308, speed(mflops)=622956.971805 +Max repetitions 3, Elasped time 99.7834, Relative error 0.00534962, Mean 5836.58, Standard Deviation 18.5209 +Total Energy 5836.583333 +13074 +Executable: ./dgemmoptimized 13074 13074 13074 1 0 +m=13074, n=13074, k=13074, time(sec)=6.997282, speed(mflops)=638742.860504 +Executable: ./dgemmoptimized 13074 13074 13074 1 0 +m=13074, n=13074, k=13074, time(sec)=6.995217, speed(mflops)=638931.435086 +Executable: ./dgemmoptimized 13074 13074 13074 1 0 +m=13074, n=13074, k=13074, time(sec)=6.997431, speed(mflops)=638729.258355 +Max repetitions 3, Elasped time 99.809, Relative error 0.0166496, Mean 5845.73, Standard Deviation 57.7327 +Total Energy 5845.733333 +13114 +Executable: ./dgemmoptimized 13114 13114 13114 1 0 +m=13114, n=13114, k=13114, time(sec)=7.209231, speed(mflops)=625671.803914 +Executable: ./dgemmoptimized 13114 13114 13114 1 0 +m=13114, n=13114, k=13114, time(sec)=7.188001, speed(mflops)=627519.765634 +Executable: ./dgemmoptimized 13114 13114 13114 1 0 +m=13114, n=13114, k=13114, time(sec)=7.194087, speed(mflops)=626988.891463 +Max repetitions 3, Elasped time 102.627, Relative error 0.00737068, Mean 6573.8, Standard Deviation 28.7411 +Total Energy 6573.800000 +13154 +Executable: ./dgemmoptimized 13154 13154 13154 1 0 +m=13154, n=13154, k=13154, time(sec)=7.333220, speed(mflops)=620738.659061 +Executable: ./dgemmoptimized 13154 13154 13154 1 0 +m=13154, n=13154, k=13154, time(sec)=7.330703, speed(mflops)=620951.788669 +Executable: ./dgemmoptimized 13154 13154 13154 1 0 +m=13154, n=13154, k=13154, time(sec)=7.329126, speed(mflops)=621085.389750 +Max repetitions 3, Elasped time 101.481, Relative error 0.00765512, Mean 6572.37, Standard Deviation 29.8438 +Total Energy 6572.366667 +13193 +Executable: ./dgemmoptimized 13193 13193 13193 1 0 +m=13193, n=13193, k=13193, time(sec)=7.456177, speed(mflops)=615948.602405 +Executable: ./dgemmoptimized 13193 13193 13193 1 0 +m=13193, n=13193, k=13193, time(sec)=7.423998, speed(mflops)=618618.395029 +Executable: ./dgemmoptimized 13193 13193 13193 1 0 +m=13193, n=13193, k=13193, time(sec)=7.443036, speed(mflops)=617036.099010 +Max repetitions 3, Elasped time 104.038, Relative error 0.0454302, Mean 6656.85, Standard Deviation 179.388 +Total Energy 6656.850000 +13233 +Executable: ./dgemmoptimized 13233 13233 13233 1 0 +m=13233, n=13233, k=13233, time(sec)=7.444670, speed(mflops)=622528.851430 +Executable: ./dgemmoptimized 13233 13233 13233 1 0 +m=13233, n=13233, k=13233, time(sec)=7.442971, speed(mflops)=622670.953064 +Executable: ./dgemmoptimized 13233 13233 13233 1 0 +m=13233, n=13233, k=13233, time(sec)=7.445380, speed(mflops)=622469.485482 +Max repetitions 3, Elasped time 102.507, Relative error 0.00779197, Mean 6528.18, Standard Deviation 30.1731 +Total Energy 6528.183333 +13273 +Executable: ./dgemmoptimized 13273 13273 13273 1 0 +m=13273, n=13273, k=13273, time(sec)=7.503690, speed(mflops)=623250.154540 +Executable: ./dgemmoptimized 13273 13273 13273 1 0 +m=13273, n=13273, k=13273, time(sec)=7.503001, speed(mflops)=623307.390021 +Executable: ./dgemmoptimized 13273 13273 13273 1 0 +m=13273, n=13273, k=13273, time(sec)=7.505120, speed(mflops)=623131.399703 +Max repetitions 3, Elasped time 106.903, Relative error 0.0455259, Mean 6705.53, Standard Deviation 181.08 +Total Energy 6705.533333 +13312 +Executable: ./dgemmoptimized 13312 13312 13312 1 0 +m=13312, n=13312, k=13312, time(sec)=7.891013, speed(mflops)=597898.075658 +Executable: ./dgemmoptimized 13312 13312 13312 1 0 +m=13312, n=13312, k=13312, time(sec)=7.898265, speed(mflops)=597349.119507 +Executable: ./dgemmoptimized 13312 13312 13312 1 0 +m=13312, n=13312, k=13312, time(sec)=7.892592, speed(mflops)=597778.474117 +Max repetitions 3, Elasped time 104.524, Relative error 0.0178327, Mean 6551.52, Standard Deviation 69.301 +Total Energy 6551.516667 +13351 +Executable: ./dgemmoptimized 13351 13351 13351 1 0 +m=13351, n=13351, k=13351, time(sec)=7.752615, speed(mflops)=613936.095171 +Executable: ./dgemmoptimized 13351 13351 13351 1 0 +m=13351, n=13351, k=13351, time(sec)=7.748528, speed(mflops)=614259.916572 +Executable: ./dgemmoptimized 13351 13351 13351 1 0 +m=13351, n=13351, k=13351, time(sec)=7.750837, speed(mflops)=614076.919859 +Max repetitions 3, Elasped time 106.422, Relative error 0.0408794, Mean 6564.35, Standard Deviation 159.175 +Total Energy 6564.350000 +13391 +Executable: ./dgemmoptimized 13391 13391 13391 1 0 +m=13391, n=13391, k=13391, time(sec)=7.881287, speed(mflops)=609357.102624 +Executable: ./dgemmoptimized 13391 13391 13391 1 0 +m=13391, n=13391, k=13391, time(sec)=7.889351, speed(mflops)=608734.253564 +Executable: ./dgemmoptimized 13391 13391 13391 1 0 +m=13391, n=13391, k=13391, time(sec)=7.878167, speed(mflops)=609598.422836 +Max repetitions 3, Elasped time 105.293, Relative error 0.00279372, Mean 6516.15, Standard Deviation 10.7983 +Total Energy 6516.150000 +13430 +Executable: ./dgemmoptimized 13430 13430 13430 1 0 +m=13430, n=13430, k=13430, time(sec)=7.680944, speed(mflops)=630729.925319 +Executable: ./dgemmoptimized 13430 13430 13430 1 0 +m=13430, n=13430, k=13430, time(sec)=7.676587, speed(mflops)=631087.897247 +Executable: ./dgemmoptimized 13430 13430 13430 1 0 +m=13430, n=13430, k=13430, time(sec)=7.745800, speed(mflops)=625448.785477 +Max repetitions 3, Elasped time 104.947, Relative error 0.00381399, Mean 6454.73, Standard Deviation 14.6029 +Total Energy 6454.733333 +13469 +Executable: ./dgemmoptimized 13469 13469 13469 1 0 +m=13469, n=13469, k=13469, time(sec)=7.768817, speed(mflops)=629044.205079 +Executable: ./dgemmoptimized 13469 13469 13469 1 0 +m=13469, n=13469, k=13469, time(sec)=7.767761, speed(mflops)=629129.717871 +Executable: ./dgemmoptimized 13469 13469 13469 1 0 +m=13469, n=13469, k=13469, time(sec)=7.752269, speed(mflops)=630386.956741 +Max repetitions 3, Elasped time 105.774, Relative error 0.0106236, Mean 6396.73, Standard Deviation 40.3099 +Total Energy 6396.733333 +13507 +Executable: ./dgemmoptimized 13507 13507 13507 1 0 +m=13507, n=13507, k=13507, time(sec)=7.864095, speed(mflops)=626697.475914 +Executable: ./dgemmoptimized 13507 13507 13507 1 0 +m=13507, n=13507, k=13507, time(sec)=7.862634, speed(mflops)=626813.928394 +Executable: ./dgemmoptimized 13507 13507 13507 1 0 +m=13507, n=13507, k=13507, time(sec)=7.856576, speed(mflops)=627297.246420 +Max repetitions 3, Elasped time 106.087, Relative error 0.00465581, Mean 6433.88, Standard Deviation 17.7684 +Total Energy 6433.883333 +13546 +Executable: ./dgemmoptimized 13546 13546 13546 1 0 +m=13546, n=13546, k=13546, time(sec)=8.043861, speed(mflops)=618014.470602 +Executable: ./dgemmoptimized 13546 13546 13546 1 0 +m=13546, n=13546, k=13546, time(sec)=8.031194, speed(mflops)=618989.232265 +Executable: ./dgemmoptimized 13546 13546 13546 1 0 +m=13546, n=13546, k=13546, time(sec)=8.031225, speed(mflops)=618986.843438 +Max repetitions 3, Elasped time 106.958, Relative error 0.00905025, Mean 7140.5, Standard Deviation 38.3327 +Total Energy 7140.500000 +13585 +Executable: ./dgemmoptimized 13585 13585 13585 1 0 +m=13585, n=13585, k=13585, time(sec)=8.164941, speed(mflops)=614123.734044 +Executable: ./dgemmoptimized 13585 13585 13585 1 0 +m=13585, n=13585, k=13585, time(sec)=8.166222, speed(mflops)=614027.379444 +Executable: ./dgemmoptimized 13585 13585 13585 1 0 +m=13585, n=13585, k=13585, time(sec)=8.170413, speed(mflops)=613712.420982 +Max repetitions 3, Elasped time 107.73, Relative error 0.00751484, Mean 7157.93, Standard Deviation 31.9071 +Total Energy 7157.933333 +13623 +Executable: ./dgemmoptimized 13623 13623 13623 1 0 +m=13623, n=13623, k=13623, time(sec)=8.114081, speed(mflops)=623173.435090 +Executable: ./dgemmoptimized 13623 13623 13623 1 0 +m=13623, n=13623, k=13623, time(sec)=8.119815, speed(mflops)=622733.368923 +Executable: ./dgemmoptimized 13623 13623 13623 1 0 +m=13623, n=13623, k=13623, time(sec)=8.122342, speed(mflops)=622539.625994 +Max repetitions 3, Elasped time 107.936, Relative error 0.00574696, Mean 7115.75, Standard Deviation 24.2571 +Total Energy 7115.750000 +13662 +Executable: ./dgemmoptimized 13662 13662 13662 1 0 +m=13662, n=13662, k=13662, time(sec)=8.255041, speed(mflops)=617808.117332 +Executable: ./dgemmoptimized 13662 13662 13662 1 0 +m=13662, n=13662, k=13662, time(sec)=8.272599, speed(mflops)=616496.856458 +Executable: ./dgemmoptimized 13662 13662 13662 1 0 +m=13662, n=13662, k=13662, time(sec)=8.274696, speed(mflops)=616340.612178 +Max repetitions 3, Elasped time 108.714, Relative error 0.00743518, Mean 7097.33, Standard Deviation 31.3016 +Total Energy 7097.333333 +13700 +Executable: ./dgemmoptimized 13700 13700 13700 1 0 +m=13700, n=13700, k=13700, time(sec)=8.384512, speed(mflops)=613357.823582 +Executable: ./dgemmoptimized 13700 13700 13700 1 0 +m=13700, n=13700, k=13700, time(sec)=8.393755, speed(mflops)=612682.407940 +Executable: ./dgemmoptimized 13700 13700 13700 1 0 +m=13700, n=13700, k=13700, time(sec)=8.399205, speed(mflops)=612284.855380 +Max repetitions 3, Elasped time 111.539, Relative error 0.0345842, Mean 7155.02, Standard Deviation 146.78 +Total Energy 7155.016667 +13738 +Executable: ./dgemmoptimized 13738 13738 13738 1 0 +m=13738, n=13738, k=13738, time(sec)=8.508655, speed(mflops)=609452.149971 +Executable: ./dgemmoptimized 13738 13738 13738 1 0 +m=13738, n=13738, k=13738, time(sec)=8.513120, speed(mflops)=609132.511410 +Executable: ./dgemmoptimized 13738 13738 13738 1 0 +m=13738, n=13738, k=13738, time(sec)=8.509847, speed(mflops)=609366.792587 +Max repetitions 3, Elasped time 111.968, Relative error 0.0710773, Mean 7199.28, Standard Deviation 303.529 +Total Energy 7199.283333 +13777 +Executable: ./dgemmoptimized 13777 13777 13777 1 0 +m=13777, n=13777, k=13777, time(sec)=8.635517, speed(mflops)=605627.547716 +Executable: ./dgemmoptimized 13777 13777 13777 1 0 +m=13777, n=13777, k=13777, time(sec)=8.621253, speed(mflops)=606629.575609 +Executable: ./dgemmoptimized 13777 13777 13777 1 0 +m=13777, n=13777, k=13777, time(sec)=8.618216, speed(mflops)=606843.362784 +Max repetitions 3, Elasped time 110.762, Relative error 0.000971882, Mean 7023.82, Standard Deviation 4.04918 +Total Energy 7023.816667 +13815 +Executable: ./dgemmoptimized 13815 13815 13815 1 0 +m=13815, n=13815, k=13815, time(sec)=8.325023, speed(mflops)=633427.952977 +Executable: ./dgemmoptimized 13815 13815 13815 1 0 +m=13815, n=13815, k=13815, time(sec)=8.259874, speed(mflops)=638424.044898 +Executable: ./dgemmoptimized 13815 13815 13815 1 0 +m=13815, n=13815, k=13815, time(sec)=8.330845, speed(mflops)=632985.268881 +Max repetitions 3, Elasped time 110.132, Relative error 0.0105701, Mean 7033.57, Standard Deviation 44.0997 +Total Energy 7033.566667 +13852 +Executable: ./dgemmoptimized 13852 13852 13852 1 0 +m=13852, n=13852, k=13852, time(sec)=8.356956, speed(mflops)=636091.113699 +Executable: ./dgemmoptimized 13852 13852 13852 1 0 +m=13852, n=13852, k=13852, time(sec)=8.369276, speed(mflops)=635154.770156 +Executable: ./dgemmoptimized 13852 13852 13852 1 0 +m=13852, n=13852, k=13852, time(sec)=8.368343, speed(mflops)=635225.561316 +Max repetitions 3, Elasped time 110.655, Relative error 0.00606711, Mean 7019.53, Standard Deviation 25.2621 +Total Energy 7019.533333 +13890 +Executable: ./dgemmoptimized 13890 13890 13890 1 0 +m=13890, n=13890, k=13890, time(sec)=8.398075, speed(mflops)=638200.262772 +Executable: ./dgemmoptimized 13890 13890 13890 1 0 +m=13890, n=13890, k=13890, time(sec)=8.391830, speed(mflops)=638675.206571 +Executable: ./dgemmoptimized 13890 13890 13890 1 0 +m=13890, n=13890, k=13890, time(sec)=8.397813, speed(mflops)=638220.193519 +Max repetitions 3, Elasped time 111.196, Relative error 0.00708521, Mean 6994.18, Standard Deviation 29.3947 +Total Energy 6994.183333 +13928 +Executable: ./dgemmoptimized 13928 13928 13928 1 0 +m=13928, n=13928, k=13928, time(sec)=8.598758, speed(mflops)=628435.260145 +Executable: ./dgemmoptimized 13928 13928 13928 1 0 +m=13928, n=13928, k=13928, time(sec)=8.601883, speed(mflops)=628206.957780 +Executable: ./dgemmoptimized 13928 13928 13928 1 0 +m=13928, n=13928, k=13928, time(sec)=8.618301, speed(mflops)=627010.215000 +Max repetitions 3, Elasped time 114.041, Relative error 0.0639206, Mean 7158.73, Standard Deviation 271.429 +Total Energy 7158.733333 +13965 +Executable: ./dgemmoptimized 13965 13965 13965 1 0 +m=13965, n=13965, k=13965, time(sec)=8.695296, speed(mflops)=626424.078431 +Executable: ./dgemmoptimized 13965 13965 13965 1 0 +m=13965, n=13965, k=13965, time(sec)=8.695613, speed(mflops)=626401.235071 +Executable: ./dgemmoptimized 13965 13965 13965 1 0 +m=13965, n=13965, k=13965, time(sec)=8.691932, speed(mflops)=626666.526781 +Max repetitions 3, Elasped time 114.888, Relative error 0.0110763, Mean 7638.93, Standard Deviation 50.1887 +Total Energy 7638.933333 +14003 +Executable: ./dgemmoptimized 14003 14003 14003 1 0 +m=14003, n=14003, k=14003, time(sec)=8.730080, speed(mflops)=629035.321064 +Executable: ./dgemmoptimized 14003 14003 14003 1 0 +m=14003, n=14003, k=14003, time(sec)=8.721784, speed(mflops)=629633.648775 +Executable: ./dgemmoptimized 14003 14003 14003 1 0 +m=14003, n=14003, k=14003, time(sec)=8.704092, speed(mflops)=630913.453098 +Max repetitions 3, Elasped time 113.053, Relative error 0.00439468, Mean 7684.9, Standard Deviation 20.033 +Total Energy 7684.900000 +14040 +Executable: ./dgemmoptimized 14040 14040 14040 1 0 +m=14040, n=14040, k=14040, time(sec)=8.761934, speed(mflops)=631729.764397 +Executable: ./dgemmoptimized 14040 14040 14040 1 0 +m=14040, n=14040, k=14040, time(sec)=8.757015, speed(mflops)=632084.624089 +Executable: ./dgemmoptimized 14040 14040 14040 1 0 +m=14040, n=14040, k=14040, time(sec)=8.761302, speed(mflops)=631775.337911 +Max repetitions 3, Elasped time 113.5, Relative error 0.00405346, Mean 7702.93, Standard Deviation 18.5209 +Total Energy 7702.933333 +14078 +Executable: ./dgemmoptimized 14078 14078 14078 1 0 +m=14078, n=14078, k=14078, time(sec)=8.945295, speed(mflops)=623818.453645 +Executable: ./dgemmoptimized 14078 14078 14078 1 0 +m=14078, n=14078, k=14078, time(sec)=8.937183, speed(mflops)=624384.670817 +Executable: ./dgemmoptimized 14078 14078 14078 1 0 +m=14078, n=14078, k=14078, time(sec)=8.913826, speed(mflops)=626020.747111 +Max repetitions 3, Elasped time 116.281, Relative error 0.039475, Mean 7802.77, Standard Deviation 182.705 +Total Energy 7802.766667 +14115 +Executable: ./dgemmoptimized 14115 14115 14115 1 0 +m=14115, n=14115, k=14115, time(sec)=9.046183, speed(mflops)=621737.795245 +Executable: ./dgemmoptimized 14115 14115 14115 1 0 +m=14115, n=14115, k=14115, time(sec)=9.035662, speed(mflops)=622461.750086 +Executable: ./dgemmoptimized 14115 14115 14115 1 0 +m=14115, n=14115, k=14115, time(sec)=9.051202, speed(mflops)=621393.037656 +Max repetitions 3, Elasped time 118.952, Relative error 0.0374716, Mean 7825.15, Standard Deviation 173.93 +Total Energy 7825.150000 +14152 +Executable: ./dgemmoptimized 14152 14152 14152 1 0 +m=14152, n=14152, k=14152, time(sec)=9.227441, speed(mflops)=614330.653706 +Executable: ./dgemmoptimized 14152 14152 14152 1 0 +m=14152, n=14152, k=14152, time(sec)=9.251819, speed(mflops)=612711.908616 +Executable: ./dgemmoptimized 14152 14152 14152 1 0 +m=14152, n=14152, k=14152, time(sec)=9.243710, speed(mflops)=613249.413325 +Max repetitions 3, Elasped time 115.983, Relative error 0.0101929, Mean 7589.95, Standard Deviation 45.8901 +Total Energy 7589.950000 +14189 +Executable: ./dgemmoptimized 14189 14189 14189 1 0 +m=14189, n=14189, k=14189, time(sec)=9.070918, speed(mflops)=629845.624681 +Executable: ./dgemmoptimized 14189 14189 14189 1 0 +m=14189, n=14189, k=14189, time(sec)=9.063198, speed(mflops)=630382.124506 +Executable: ./dgemmoptimized 14189 14189 14189 1 0 +m=14189, n=14189, k=14189, time(sec)=9.070413, speed(mflops)=629880.706178 +Max repetitions 3, Elasped time 115.789, Relative error 0.00455626, Mean 7576.02, Standard Deviation 20.4752 +Total Energy 7576.016667 +14226 +Executable: ./dgemmoptimized 14226 14226 14226 1 0 +m=14226, n=14226, k=14226, time(sec)=9.017620, speed(mflops)=638537.614942 +Executable: ./dgemmoptimized 14226 14226 14226 1 0 +m=14226, n=14226, k=14226, time(sec)=8.946433, speed(mflops)=643618.459672 +Executable: ./dgemmoptimized 14226 14226 14226 1 0 +m=14226, n=14226, k=14226, time(sec)=8.957662, speed(mflops)=642811.657300 +Max repetitions 3, Elasped time 117.829, Relative error 0.05275, Mean 7777.68, Standard Deviation 243.362 +Total Energy 7777.683333 +14263 +Executable: ./dgemmoptimized 14263 14263 14263 1 0 +m=14263, n=14263, k=14263, time(sec)=9.161797, speed(mflops)=633405.711711 +Executable: ./dgemmoptimized 14263 14263 14263 1 0 +m=14263, n=14263, k=14263, time(sec)=9.161734, speed(mflops)=633410.063305 +Executable: ./dgemmoptimized 14263 14263 14263 1 0 +m=14263, n=14263, k=14263, time(sec)=9.156401, speed(mflops)=633778.995727 +Max repetitions 3, Elasped time 116.87, Relative error 0.00526961, Mean 7558.12, Standard Deviation 23.625 +Total Energy 7558.116667 +14299 +Executable: ./dgemmoptimized 14299 14299 14299 1 0 +m=14299, n=14299, k=14299, time(sec)=9.273007, speed(mflops)=630559.973523 +Executable: ./dgemmoptimized 14299 14299 14299 1 0 +m=14299, n=14299, k=14299, time(sec)=9.273653, speed(mflops)=630516.057333 +Executable: ./dgemmoptimized 14299 14299 14299 1 0 +m=14299, n=14299, k=14299, time(sec)=9.262381, speed(mflops)=631283.370583 +Max repetitions 3, Elasped time 119.303, Relative error 0.042374, Mean 7658.55, Standard Deviation 192.498 +Total Energy 7658.550000 +14336 +Executable: ./dgemmoptimized 14336 14336 14336 1 0 +m=14336, n=14336, k=14336, time(sec)=9.785883, speed(mflops)=602162.846247 +Executable: ./dgemmoptimized 14336 14336 14336 1 0 +m=14336, n=14336, k=14336, time(sec)=9.770750, speed(mflops)=603095.473992 +Executable: ./dgemmoptimized 14336 14336 14336 1 0 +m=14336, n=14336, k=14336, time(sec)=9.794557, speed(mflops)=601629.580251 +Max repetitions 3, Elasped time 119.27, Relative error 0.0142052, Mean 8317.57, Standard Deviation 70.0849 +Total Energy 8317.566667 +14373 +Executable: ./dgemmoptimized 14373 14373 14373 1 0 +m=14373, n=14373, k=14373, time(sec)=9.478031, speed(mflops)=626547.700357 +Executable: ./dgemmoptimized 14373 14373 14373 1 0 +m=14373, n=14373, k=14373, time(sec)=9.487989, speed(mflops)=625890.113178 +Executable: ./dgemmoptimized 14373 14373 14373 1 0 +m=14373, n=14373, k=14373, time(sec)=9.468880, speed(mflops)=627153.228791 +Max repetitions 3, Elasped time 118.705, Relative error 0.0142751, Mean 8304.78, Standard Deviation 70.3213 +Total Energy 8304.783333 +14409 +Executable: ./dgemmoptimized 14409 14409 14409 1 0 +m=14409, n=14409, k=14409, time(sec)=9.514213, speed(mflops)=628866.768727 +Executable: ./dgemmoptimized 14409 14409 14409 1 0 +m=14409, n=14409, k=14409, time(sec)=9.516017, speed(mflops)=628747.543748 +Executable: ./dgemmoptimized 14409 14409 14409 1 0 +m=14409, n=14409, k=14409, time(sec)=9.524405, speed(mflops)=628193.828195 +Max repetitions 3, Elasped time 121.67, Relative error 0.0534888, Mean 8320.28, Standard Deviation 263.986 +Total Energy 8320.283333 +14445 +Executable: ./dgemmoptimized 14445 14445 14445 1 0 +m=14445, n=14445, k=14445, time(sec)=9.617779, speed(mflops)=626769.478890 +Executable: ./dgemmoptimized 14445 14445 14445 1 0 +m=14445, n=14445, k=14445, time(sec)=9.626848, speed(mflops)=626179.031108 +Executable: ./dgemmoptimized 14445 14445 14445 1 0 +m=14445, n=14445, k=14445, time(sec)=9.606875, speed(mflops)=627480.879907 +Max repetitions 3, Elasped time 120.437, Relative error 0.0161199, Mean 8189.47, Standard Deviation 78.3065 +Total Energy 8189.466667 +14482 +Executable: ./dgemmoptimized 14482 14482 14482 1 0 +m=14482, n=14482, k=14482, time(sec)=9.831074, speed(mflops)=617894.970245 +Executable: ./dgemmoptimized 14482 14482 14482 1 0 +m=14482, n=14482, k=14482, time(sec)=9.848587, speed(mflops)=616796.211888 +Executable: ./dgemmoptimized 14482 14482 14482 1 0 +m=14482, n=14482, k=14482, time(sec)=9.834615, speed(mflops)=617672.494672 +Max repetitions 3, Elasped time 121.183, Relative error 0.0109189, Mean 8236.8, Standard Deviation 53.3478 +Total Energy 8236.800000 +14518 +Executable: ./dgemmoptimized 14518 14518 14518 1 0 +m=14518, n=14518, k=14518, time(sec)=9.865013, speed(mflops)=620372.752833 +Executable: ./dgemmoptimized 14518 14518 14518 1 0 +m=14518, n=14518, k=14518, time(sec)=9.854755, speed(mflops)=621018.492932 +Executable: ./dgemmoptimized 14518 14518 14518 1 0 +m=14518, n=14518, k=14518, time(sec)=9.869224, speed(mflops)=620108.055423 +Max repetitions 3, Elasped time 121.22, Relative error 0.00623448, Mean 8191.73, Standard Deviation 30.2939 +Total Energy 8191.733333 +14554 +Executable: ./dgemmoptimized 14554 14554 14554 1 0 +m=14554, n=14554, k=14554, time(sec)=10.012994, speed(mflops)=615762.390584 +Executable: ./dgemmoptimized 14554 14554 14554 1 0 +m=14554, n=14554, k=14554, time(sec)=10.016177, speed(mflops)=615566.687540 +Executable: ./dgemmoptimized 14554 14554 14554 1 0 +m=14554, n=14554, k=14554, time(sec)=9.987616, speed(mflops)=617326.994605 +Max repetitions 3, Elasped time 121.962, Relative error 0.00652568, Mean 8161.35, Standard Deviation 31.5913 +Total Energy 8161.350000 +14590 +Executable: ./dgemmoptimized 14590 14590 14590 1 0 +m=14590, n=14590, k=14590, time(sec)=9.706567, speed(mflops)=639926.673007 +Executable: ./dgemmoptimized 14590 14590 14590 1 0 +m=14590, n=14590, k=14590, time(sec)=9.701638, speed(mflops)=640251.797550 +Executable: ./dgemmoptimized 14590 14590 14590 1 0 +m=14590, n=14590, k=14590, time(sec)=9.700769, speed(mflops)=640309.154001 +Max repetitions 3, Elasped time 121.421, Relative error 0.00125212, Mean 8179.12, Standard Deviation 6.07481 +Total Energy 8179.116667 +14626 +Executable: ./dgemmoptimized 14626 14626 14626 1 0 +m=14626, n=14626, k=14626, time(sec)=9.904198, speed(mflops)=631811.304274 +Executable: ./dgemmoptimized 14626 14626 14626 1 0 +m=14626, n=14626, k=14626, time(sec)=9.840943, speed(mflops)=635872.426250 +Executable: ./dgemmoptimized 14626 14626 14626 1 0 +m=14626, n=14626, k=14626, time(sec)=9.827540, speed(mflops)=636739.638117 +Max repetitions 3, Elasped time 122.234, Relative error 0.00413975, Mean 8142.68, Standard Deviation 19.995 +Total Energy 8142.683333 +14661 +Executable: ./dgemmoptimized 14661 14661 14661 1 0 +m=14661, n=14661, k=14661, time(sec)=9.993945, speed(mflops)=630643.344222 +Executable: ./dgemmoptimized 14661 14661 14661 1 0 +m=14661, n=14661, k=14661, time(sec)=9.987816, speed(mflops)=631030.338704 +Executable: ./dgemmoptimized 14661 14661 14661 1 0 +m=14661, n=14661, k=14661, time(sec)=9.993191, speed(mflops)=630690.934574 +Max repetitions 3, Elasped time 122.916, Relative error 0.00231377, Mean 8181.18, Standard Deviation 11.2283 +Total Energy 8181.183333 +14697 +Executable: ./dgemmoptimized 14697 14697 14697 1 0 +m=14697, n=14697, k=14697, time(sec)=10.151140, speed(mflops)=625462.464365 +Executable: ./dgemmoptimized 14697 14697 14697 1 0 +m=14697, n=14697, k=14697, time(sec)=10.149639, speed(mflops)=625554.967290 +Executable: ./dgemmoptimized 14697 14697 14697 1 0 +m=14697, n=14697, k=14697, time(sec)=10.161021, speed(mflops)=624854.252085 +Max repetitions 3, Elasped time 123.727, Relative error 0.00987217, Mean 8115.83, Standard Deviation 47.5254 +Total Energy 8115.833333 +14733 +Executable: ./dgemmoptimized 14733 14733 14733 1 0 +m=14733, n=14733, k=14733, time(sec)=10.290924, speed(mflops)=621511.542106 +Executable: ./dgemmoptimized 14733 14733 14733 1 0 +m=14733, n=14733, k=14733, time(sec)=10.308737, speed(mflops)=620437.602109 +Executable: ./dgemmoptimized 14733 14733 14733 1 0 +m=14733, n=14733, k=14733, time(sec)=10.293060, speed(mflops)=621382.553071 +Max repetitions 3, Elasped time 126.588, Relative error 0.0784932, Mean 8690.47, Standard Deviation 404.627 +Total Energy 8690.466667 +14768 +Executable: ./dgemmoptimized 14768 14768 14768 1 0 +m=14768, n=14768, k=14768, time(sec)=10.338390, speed(mflops)=623077.589057 +Executable: ./dgemmoptimized 14768 14768 14768 1 0 +m=14768, n=14768, k=14768, time(sec)=10.314798, speed(mflops)=624502.691453 +Executable: ./dgemmoptimized 14768 14768 14768 1 0 +m=14768, n=14768, k=14768, time(sec)=10.328085, speed(mflops)=623699.269598 +Max repetitions 3, Elasped time 124.941, Relative error 0.00422914, Mean 8793.47, Standard Deviation 22.0593 +Total Energy 8793.466667 +14804 +Executable: ./dgemmoptimized 14804 14804 14804 1 0 +m=14804, n=14804, k=14804, time(sec)=10.346966, speed(mflops)=627125.126654 +Executable: ./dgemmoptimized 14804 14804 14804 1 0 +m=14804, n=14804, k=14804, time(sec)=10.358779, speed(mflops)=626409.966853 +Executable: ./dgemmoptimized 14804 14804 14804 1 0 +m=14804, n=14804, k=14804, time(sec)=10.367286, speed(mflops)=625895.943493 +Max repetitions 3, Elasped time 127.381, Relative error 0.0564329, Mean 8949.5, Standard Deviation 299.579 +Total Energy 8949.500000 +14839 +Executable: ./dgemmoptimized 14839 14839 14839 1 0 +m=14839, n=14839, k=14839, time(sec)=10.522859, speed(mflops)=621026.517935 +Executable: ./dgemmoptimized 14839 14839 14839 1 0 +m=14839, n=14839, k=14839, time(sec)=10.521208, speed(mflops)=621123.972999 +Executable: ./dgemmoptimized 14839 14839 14839 1 0 +m=14839, n=14839, k=14839, time(sec)=10.534037, speed(mflops)=620367.526070 +Max repetitions 3, Elasped time 126.22, Relative error 0.00862294, Mean 8807.85, Standard Deviation 45.0511 +Total Energy 8807.850000 +14874 +Executable: ./dgemmoptimized 14874 14874 14874 1 0 +m=14874, n=14874, k=14874, time(sec)=10.629702, speed(mflops)=619144.806014 +Executable: ./dgemmoptimized 14874 14874 14874 1 0 +m=14874, n=14874, k=14874, time(sec)=10.649684, speed(mflops)=617983.112805 +Executable: ./dgemmoptimized 14874 14874 14874 1 0 +m=14874, n=14874, k=14874, time(sec)=10.646085, speed(mflops)=618192.023123 +Max repetitions 3, Elasped time 126.898, Relative error 0.00684353, Mean 8773.48, Standard Deviation 35.6149 +Total Energy 8773.483333 +14910 +Executable: ./dgemmoptimized 14910 14910 14910 1 0 +m=14910, n=14910, k=14910, time(sec)=10.883638, speed(mflops)=609100.339408 +Executable: ./dgemmoptimized 14910 14910 14910 1 0 +m=14910, n=14910, k=14910, time(sec)=10.766546, speed(mflops)=615724.628423 +Executable: ./dgemmoptimized 14910 14910 14910 1 0 +m=14910, n=14910, k=14910, time(sec)=10.890569, speed(mflops)=608712.690702 +Max repetitions 3, Elasped time 129.85, Relative error 0.025006, Mean 8864.37, Standard Deviation 131.483 +Total Energy 8864.366667 +14945 +Executable: ./dgemmoptimized 14945 14945 14945 1 0 +m=14945, n=14945, k=14945, time(sec)=10.704763, speed(mflops)=623649.674205 +Executable: ./dgemmoptimized 14945 14945 14945 1 0 +m=14945, n=14945, k=14945, time(sec)=10.735875, speed(mflops)=621842.359062 +Executable: ./dgemmoptimized 14945 14945 14945 1 0 +m=14945, n=14945, k=14945, time(sec)=10.727102, speed(mflops)=622350.928665 +Max repetitions 3, Elasped time 127.815, Relative error 0.000419553, Mean 8695.05, Standard Deviation 2.16391 +Total Energy 8695.050000 +14980 +Executable: ./dgemmoptimized 14980 14980 14980 1 0 +m=14980, n=14980, k=14980, time(sec)=10.470763, speed(mflops)=642076.991381 +Executable: ./dgemmoptimized 14980 14980 14980 1 0 +m=14980, n=14980, k=14980, time(sec)=10.445598, speed(mflops)=643623.840708 +Executable: ./dgemmoptimized 14980 14980 14980 1 0 +m=14980, n=14980, k=14980, time(sec)=10.452765, speed(mflops)=643182.544691 +Max repetitions 3, Elasped time 127.756, Relative error 0.00436051, Mean 8732, Standard Deviation 22.5856 +Total Energy 8732.000000 +15015 +Executable: ./dgemmoptimized 15015 15015 15015 1 0 +m=15015, n=15015, k=15015, time(sec)=10.597773, speed(mflops)=638838.967496 +Executable: ./dgemmoptimized 15015 15015 15015 1 0 +m=15015, n=15015, k=15015, time(sec)=10.579593, speed(mflops)=639936.743607 +Executable: ./dgemmoptimized 15015 15015 15015 1 0 +m=15015, n=15015, k=15015, time(sec)=10.605814, speed(mflops)=638354.610919 +Max repetitions 3, Elasped time 128.105, Relative error 0.00768821, Mean 8727.57, Standard Deviation 39.8014 +Total Energy 8727.566667 +15050 +Executable: ./dgemmoptimized 15050 15050 15050 1 0 +m=15050, n=15050, k=15050, time(sec)=10.747610, speed(mflops)=634348.040427 +Executable: ./dgemmoptimized 15050 15050 15050 1 0 +m=15050, n=15050, k=15050, time(sec)=10.728046, speed(mflops)=635504.852223 +Executable: ./dgemmoptimized 15050 15050 15050 1 0 +m=15050, n=15050, k=15050, time(sec)=10.635262, speed(mflops)=641049.110215 +Max repetitions 3, Elasped time 128.78, Relative error 0.00474616, Mean 8705.58, Standard Deviation 24.5087 +Total Energy 8705.583333 +15084 +Executable: ./dgemmoptimized 15084 15084 15084 1 0 +m=15084, n=15084, k=15084, time(sec)=10.870508, speed(mflops)=631436.567038 +Executable: ./dgemmoptimized 15084 15084 15084 1 0 +m=15084, n=15084, k=15084, time(sec)=10.888494, speed(mflops)=630393.534323 +Executable: ./dgemmoptimized 15084 15084 15084 1 0 +m=15084, n=15084, k=15084, time(sec)=10.883693, speed(mflops)=630671.614694 +Max repetitions 3, Elasped time 129.629, Relative error 0.00506448, Mean 8655.6, Standard Deviation 26.0023 +Total Energy 8655.600000 +15119 +Executable: ./dgemmoptimized 15119 15119 15119 1 0 +m=15119, n=15119, k=15119, time(sec)=10.998648, speed(mflops)=628434.322602 +Executable: ./dgemmoptimized 15119 15119 15119 1 0 +m=15119, n=15119, k=15119, time(sec)=10.990529, speed(mflops)=628898.570059 +Executable: ./dgemmoptimized 15119 15119 15119 1 0 +m=15119, n=15119, k=15119, time(sec)=11.008142, speed(mflops)=627892.324044 +Max repetitions 3, Elasped time 130.315, Relative error 0.0575571, Mean 8836.7, Standard Deviation 301.696 +Total Energy 8836.700000 +15154 +Executable: ./dgemmoptimized 15154 15154 15154 1 0 +m=15154, n=15154, k=15154, time(sec)=11.024085, speed(mflops)=631348.698437 +Executable: ./dgemmoptimized 15154 15154 15154 1 0 +m=15154, n=15154, k=15154, time(sec)=10.974823, speed(mflops)=634182.596454 +Executable: ./dgemmoptimized 15154 15154 15154 1 0 +m=15154, n=15154, k=15154, time(sec)=10.999615, speed(mflops)=632753.202978 +Max repetitions 3, Elasped time 132.656, Relative error 0.0714892, Mean 9393.03, Standard Deviation 398.314 +Total Energy 9393.033333 +15188 +Executable: ./dgemmoptimized 15188 15188 15188 1 0 +m=15188, n=15188, k=15188, time(sec)=11.085978, speed(mflops)=632059.185906 +Executable: ./dgemmoptimized 15188 15188 15188 1 0 +m=15188, n=15188, k=15188, time(sec)=11.083286, speed(mflops)=632212.704756 +Executable: ./dgemmoptimized 15188 15188 15188 1 0 +m=15188, n=15188, k=15188, time(sec)=11.085097, speed(mflops)=632109.430612 +Max repetitions 3, Elasped time 131.23, Relative error 0.00429178, Mean 9387.67, Standard Deviation 23.8988 +Total Energy 9387.666667 +15223 +Executable: ./dgemmoptimized 15223 15223 15223 1 0 +m=15223, n=15223, k=15223, time(sec)=11.185421, speed(mflops)=630780.709590 +Executable: ./dgemmoptimized 15223 15223 15223 1 0 +m=15223, n=15223, k=15223, time(sec)=11.185985, speed(mflops)=630748.913376 +Executable: ./dgemmoptimized 15223 15223 15223 1 0 +m=15223, n=15223, k=15223, time(sec)=11.187099, speed(mflops)=630686.096707 +Max repetitions 3, Elasped time 131.905, Relative error 0.00169004, Mean 9351.82, Standard Deviation 9.37501 +Total Energy 9351.816667 +15257 +Executable: ./dgemmoptimized 15257 15257 15257 1 0 +m=15257, n=15257, k=15257, time(sec)=11.354306, speed(mflops)=625571.322539 +Executable: ./dgemmoptimized 15257 15257 15257 1 0 +m=15257, n=15257, k=15257, time(sec)=11.355025, speed(mflops)=625531.720627 +Executable: ./dgemmoptimized 15257 15257 15257 1 0 +m=15257, n=15257, k=15257, time(sec)=11.355055, speed(mflops)=625530.078865 +Max repetitions 3, Elasped time 132.728, Relative error 0.0116419, Mean 9334.22, Standard Deviation 64.459 +Total Energy 9334.216667 +15292 +Executable: ./dgemmoptimized 15292 15292 15292 1 0 +m=15292, n=15292, k=15292, time(sec)=11.526987, speed(mflops)=620450.383708 +Executable: ./dgemmoptimized 15292 15292 15292 1 0 +m=15292, n=15292, k=15292, time(sec)=11.542037, speed(mflops)=619641.363813 +Executable: ./dgemmoptimized 15292 15292 15292 1 0 +m=15292, n=15292, k=15292, time(sec)=11.577479, speed(mflops)=617744.469657 +Max repetitions 3, Elasped time 135.587, Relative error 0.0320269, Mean 9407.33, Standard Deviation 178.715 +Total Energy 9407.333333 +15326 +Executable: ./dgemmoptimized 15326 15326 15326 1 0 +m=15326, n=15326, k=15326, time(sec)=11.518296, speed(mflops)=625069.379174 +Executable: ./dgemmoptimized 15326 15326 15326 1 0 +m=15326, n=15326, k=15326, time(sec)=11.538142, speed(mflops)=623994.240429 +Executable: ./dgemmoptimized 15326 15326 15326 1 0 +m=15326, n=15326, k=15326, time(sec)=11.438921, speed(mflops)=629406.755048 +Max repetitions 3, Elasped time 133.834, Relative error 0.00598117, Mean 9328.4, Standard Deviation 33.0958 +Total Energy 9328.400000 +15360 +Executable: ./dgemmoptimized 15360 15360 15360 1 0 +m=15360, n=15360, k=15360, time(sec)=11.612085, speed(mflops)=624156.406631 +Executable: ./dgemmoptimized 15360 15360 15360 1 0 +m=15360, n=15360, k=15360, time(sec)=11.586660, speed(mflops)=625526.011830 +Executable: ./dgemmoptimized 15360 15360 15360 1 0 +m=15360, n=15360, k=15360, time(sec)=11.606389, speed(mflops)=624462.723372 +Max repetitions 3, Elasped time 134.5, Relative error 0.00159373, Mean 9239.97, Standard Deviation 8.73503 +Total Energy 9239.966667 +15394 +Executable: ./dgemmoptimized 15394 15394 15394 1 0 +m=15394, n=15394, k=15394, time(sec)=11.496881, speed(mflops)=634606.338954 +Executable: ./dgemmoptimized 15394 15394 15394 1 0 +m=15394, n=15394, k=15394, time(sec)=11.485309, speed(mflops)=635245.742074 +Executable: ./dgemmoptimized 15394 15394 15394 1 0 +m=15394, n=15394, k=15394, time(sec)=11.466716, speed(mflops)=636275.768359 +Max repetitions 3, Elasped time 136.407, Relative error 0.0508069, Mean 9439.52, Standard Deviation 284.48 +Total Energy 9439.516667 +15428 +Executable: ./dgemmoptimized 15428 15428 15428 1 0 +m=15428, n=15428, k=15428, time(sec)=11.570084, speed(mflops)=634778.736714 +Executable: ./dgemmoptimized 15428 15428 15428 1 0 +m=15428, n=15428, k=15428, time(sec)=11.596663, speed(mflops)=633323.859342 +Executable: ./dgemmoptimized 15428 15428 15428 1 0 +m=15428, n=15428, k=15428, time(sec)=11.566344, speed(mflops)=634983.997628 +Max repetitions 3, Elasped time 137.102, Relative error 0.0334014, Mean 9322.18, Standard Deviation 184.698 +Total Energy 9322.183333 +15462 +Executable: ./dgemmoptimized 15462 15462 15462 1 0 +m=15462, n=15462, k=15462, time(sec)=11.739868, speed(mflops)=629743.641843 +Executable: ./dgemmoptimized 15462 15462 15462 1 0 +m=15462, n=15462, k=15462, time(sec)=11.723588, speed(mflops)=630618.134029 +Executable: ./dgemmoptimized 15462 15462 15462 1 0 +m=15462, n=15462, k=15462, time(sec)=11.747340, speed(mflops)=629343.085751 +Max repetitions 3, Elasped time 135.887, Relative error 0.0117583, Mean 9214.3, Standard Deviation 64.2671 +Total Energy 9214.300000 +15496 +Executable: ./dgemmoptimized 15496 15496 15496 1 0 +m=15496, n=15496, k=15496, time(sec)=11.942307, speed(mflops)=623161.462081 +Executable: ./dgemmoptimized 15496 15496 15496 1 0 +m=15496, n=15496, k=15496, time(sec)=11.931608, speed(mflops)=623720.248921 +Executable: ./dgemmoptimized 15496 15496 15496 1 0 +m=15496, n=15496, k=15496, time(sec)=11.960299, speed(mflops)=622224.032903 +Max repetitions 3, Elasped time 136.849, Relative error 0.00609393, Mean 9949.82, Standard Deviation 35.966 +Total Energy 9949.816667 +15530 +Executable: ./dgemmoptimized 15530 15530 15530 1 0 +m=15530, n=15530, k=15530, time(sec)=11.892463, speed(mflops)=629901.373133 +Executable: ./dgemmoptimized 15530 15530 15530 1 0 +m=15530, n=15530, k=15530, time(sec)=11.865867, speed(mflops)=631313.216888 +Executable: ./dgemmoptimized 15530 15530 15530 1 0 +m=15530, n=15530, k=15530, time(sec)=11.899058, speed(mflops)=629552.245968 +Max repetitions 3, Elasped time 137.028, Relative error 0.00599735, Mean 9953.18, Standard Deviation 35.408 +Total Energy 9953.183333 +15563 +Executable: ./dgemmoptimized 15563 15563 15563 1 0 +m=15563, n=15563, k=15563, time(sec)=11.896475, speed(mflops)=633711.588391 +Executable: ./dgemmoptimized 15563 15563 15563 1 0 +m=15563, n=15563, k=15563, time(sec)=11.890616, speed(mflops)=634023.851672 +Executable: ./dgemmoptimized 15563 15563 15563 1 0 +m=15563, n=15563, k=15563, time(sec)=11.897077, speed(mflops)=633679.534495 +Max repetitions 3, Elasped time 137.567, Relative error 0.00608153, Mean 9955.58, Standard Deviation 35.9137 +Total Energy 9955.583333 +15597 +Executable: ./dgemmoptimized 15597 15597 15597 1 0 +m=15597, n=15597, k=15597, time(sec)=12.009946, speed(mflops)=631847.340932 +Executable: ./dgemmoptimized 15597 15597 15597 1 0 +m=15597, n=15597, k=15597, time(sec)=12.028939, speed(mflops)=630849.683156 +Executable: ./dgemmoptimized 15597 15597 15597 1 0 +m=15597, n=15597, k=15597, time(sec)=12.018081, speed(mflops)=631419.628767 +Max repetitions 3, Elasped time 138.087, Relative error 0.00219207, Mean 9890.42, Standard Deviation 12.8602 +Total Energy 9890.416667 +15631 +Executable: ./dgemmoptimized 15631 15631 15631 1 0 +m=15631, n=15631, k=15631, time(sec)=12.256394, speed(mflops)=623200.174295 +Executable: ./dgemmoptimized 15631 15631 15631 1 0 +m=15631, n=15631, k=15631, time(sec)=12.244106, speed(mflops)=623825.613344 +Executable: ./dgemmoptimized 15631 15631 15631 1 0 +m=15631, n=15631, k=15631, time(sec)=12.309766, speed(mflops)=620498.142335 +Max repetitions 3, Elasped time 139.236, Relative error 0.0073349, Mean 9922.07, Standard Deviation 43.1694 +Total Energy 9922.066667 +15664 +Executable: ./dgemmoptimized 15664 15664 15664 1 0 +m=15664, n=15664, k=15664, time(sec)=12.415826, speed(mflops)=619102.273097 +Executable: ./dgemmoptimized 15664 15664 15664 1 0 +m=15664, n=15664, k=15664, time(sec)=12.410737, speed(mflops)=619356.137074 +Executable: ./dgemmoptimized 15664 15664 15664 1 0 +m=15664, n=15664, k=15664, time(sec)=12.419729, speed(mflops)=618907.719595 +Max repetitions 3, Elasped time 139.969, Relative error 0.00308667, Mean 9857.48, Standard Deviation 18.0483 +Total Energy 9857.483333 +15698 +Executable: ./dgemmoptimized 15698 15698 15698 1 0 +m=15698, n=15698, k=15698, time(sec)=12.486032, speed(mflops)=619638.688346 +Executable: ./dgemmoptimized 15698 15698 15698 1 0 +m=15698, n=15698, k=15698, time(sec)=12.507924, speed(mflops)=618554.161935 +Executable: ./dgemmoptimized 15698 15698 15698 1 0 +m=15698, n=15698, k=15698, time(sec)=12.479999, speed(mflops)=619938.227258 +Max repetitions 3, Elasped time 140.518, Relative error 0.00284366, Mean 9849.65, Standard Deviation 16.6142 +Total Energy 9849.650000 +15731 +Executable: ./dgemmoptimized 15731 15731 15731 1 0 +m=15731, n=15731, k=15731, time(sec)=12.267470, speed(mflops)=634664.168630 +Executable: ./dgemmoptimized 15731 15731 15731 1 0 +m=15731, n=15731, k=15731, time(sec)=12.273626, speed(mflops)=634345.846066 +Executable: ./dgemmoptimized 15731 15731 15731 1 0 +m=15731, n=15731, k=15731, time(sec)=12.325195, speed(mflops)=631691.724065 +Max repetitions 3, Elasped time 144.126, Relative error 0.0466165, Mean 10158.3, Standard Deviation 280.892 +Total Energy 10158.266667 +15764 +Executable: ./dgemmoptimized 15764 15764 15764 1 0 +m=15764, n=15764, k=15764, time(sec)=12.291974, speed(mflops)=637393.512575 +Executable: ./dgemmoptimized 15764 15764 15764 1 0 +m=15764, n=15764, k=15764, time(sec)=12.278932, speed(mflops)=638070.515183 +Executable: ./dgemmoptimized 15764 15764 15764 1 0 +m=15764, n=15764, k=15764, time(sec)=12.282242, speed(mflops)=637898.572711 +Max repetitions 3, Elasped time 140.574, Relative error 0.003092, Mean 9772.22, Standard Deviation 17.9231 +Total Energy 9772.216667 +15798 +Executable: ./dgemmoptimized 15798 15798 15798 1 0 +m=15798, n=15798, k=15798, time(sec)=12.430376, speed(mflops)=634383.760045 +Executable: ./dgemmoptimized 15798 15798 15798 1 0 +m=15798, n=15798, k=15798, time(sec)=12.446501, speed(mflops)=633561.889294 +Executable: ./dgemmoptimized 15798 15798 15798 1 0 +m=15798, n=15798, k=15798, time(sec)=12.432453, speed(mflops)=634277.785065 +Max repetitions 3, Elasped time 141.482, Relative error 0.00543697, Mean 9786.23, Standard Deviation 31.5611 +Total Energy 9786.233333 +15831 +Executable: ./dgemmoptimized 15831 15831 15831 1 0 +m=15831, n=15831, k=15831, time(sec)=12.590611, speed(mflops)=630243.299103 +Executable: ./dgemmoptimized 15831 15831 15831 1 0 +m=15831, n=15831, k=15831, time(sec)=12.564086, speed(mflops)=631573.854827 +Executable: ./dgemmoptimized 15831 15831 15831 1 0 +m=15831, n=15831, k=15831, time(sec)=12.563482, speed(mflops)=631604.213963 +Max repetitions 3, Elasped time 142.119, Relative error 0.00777775, Mean 9786.93, Standard Deviation 45.1524 +Total Energy 9786.933333 +15864 +Executable: ./dgemmoptimized 15864 15864 15864 1 0 +m=15864, n=15864, k=15864, time(sec)=12.784259, speed(mflops)=624586.429568 +Executable: ./dgemmoptimized 15864 15864 15864 1 0 +m=15864, n=15864, k=15864, time(sec)=12.780118, speed(mflops)=624788.800246 +Executable: ./dgemmoptimized 15864 15864 15864 1 0 +m=15864, n=15864, k=15864, time(sec)=12.811785, speed(mflops)=623244.504640 +Max repetitions 3, Elasped time 143.11, Relative error 0.00764368, Mean 10539.9, Standard Deviation 47.7881 +Total Energy 10539.933333 +15897 +Executable: ./dgemmoptimized 15897 15897 15897 1 0 +m=15897, n=15897, k=15897, time(sec)=12.873522, speed(mflops)=624134.436588 +Executable: ./dgemmoptimized 15897 15897 15897 1 0 +m=15897, n=15897, k=15897, time(sec)=12.877424, speed(mflops)=623945.307500 +Executable: ./dgemmoptimized 15897 15897 15897 1 0 +m=15897, n=15897, k=15897, time(sec)=12.882782, speed(mflops)=623685.807111 +Max repetitions 3, Elasped time 143.708, Relative error 0.00329874, Mean 10470.9, Standard Deviation 20.4886 +Total Energy 10470.900000 +15930 +Executable: ./dgemmoptimized 15930 15930 15930 1 0 +m=15930, n=15930, k=15930, time(sec)=12.758163, speed(mflops)=633707.982070 +Executable: ./dgemmoptimized 15930 15930 15930 1 0 +m=15930, n=15930, k=15930, time(sec)=12.770866, speed(mflops)=633077.632752 +Executable: ./dgemmoptimized 15930 15930 15930 1 0 +m=15930, n=15930, k=15930, time(sec)=12.754855, speed(mflops)=633872.338516 +Max repetitions 3, Elasped time 143.891, Relative error 0.00315383, Mean 10486.2, Standard Deviation 19.6171 +Total Energy 10486.166667 +15963 +Executable: ./dgemmoptimized 15963 15963 15963 1 0 +m=15963, n=15963, k=15963, time(sec)=12.942030, speed(mflops)=628595.309409 +Executable: ./dgemmoptimized 15963 15963 15963 1 0 +m=15963, n=15963, k=15963, time(sec)=12.949728, speed(mflops)=628221.636401 +Executable: ./dgemmoptimized 15963 15963 15963 1 0 +m=15963, n=15963, k=15963, time(sec)=12.934854, speed(mflops)=628944.037825 +Max repetitions 3, Elasped time 144.56, Relative error 0.00472041, Mean 10448.2, Standard Deviation 29.2552 +Total Energy 10448.233333 +15995 +Executable: ./dgemmoptimized 15995 15995 15995 1 0 +m=15995, n=15995, k=15995, time(sec)=13.088775, speed(mflops)=625293.222704 +Executable: ./dgemmoptimized 15995 15995 15995 1 0 +m=15995, n=15995, k=15995, time(sec)=13.107701, speed(mflops)=624390.376338 +Executable: ./dgemmoptimized 15995 15995 15995 1 0 +m=15995, n=15995, k=15995, time(sec)=13.132935, speed(mflops)=623190.655430 +Max repetitions 3, Elasped time 145.406, Relative error 0.0142991, Mean 10491.4, Standard Deviation 88.9863 +Total Energy 10491.416667 +16028 +Executable: ./dgemmoptimized 16028 16028 16028 1 0 +m=16028, n=16028, k=16028, time(sec)=13.237752, speed(mflops)=622090.769816 +Executable: ./dgemmoptimized 16028 16028 16028 1 0 +m=16028, n=16028, k=16028, time(sec)=13.242575, speed(mflops)=621864.203247 +Executable: ./dgemmoptimized 16028 16028 16028 1 0 +m=16028, n=16028, k=16028, time(sec)=13.289008, speed(mflops)=619691.354580 +Max repetitions 3, Elasped time 148.183, Relative error 0.0298462, Mean 10553, Standard Deviation 186.828 +Total Energy 10552.950000 +16061 +Executable: ./dgemmoptimized 16061 16061 16061 1 0 +m=16061, n=16061, k=16061, time(sec)=13.450923, speed(mflops)=616021.197274 +Executable: ./dgemmoptimized 16061 16061 16061 1 0 +m=16061, n=16061, k=16061, time(sec)=13.439686, speed(mflops)=616536.251889 +Executable: ./dgemmoptimized 16061 16061 16061 1 0 +m=16061, n=16061, k=16061, time(sec)=13.453133, speed(mflops)=615920.005502 +Max repetitions 3, Elasped time 147.575, Relative error 0.0266901, Mean 10474, Standard Deviation 165.822 +Total Energy 10473.983333 +16093 +Executable: ./dgemmoptimized 16093 16093 16093 1 0 +m=16093, n=16093, k=16093, time(sec)=13.368739, speed(mflops)=623520.276133 +Executable: ./dgemmoptimized 16093 16093 16093 1 0 +m=16093, n=16093, k=16093, time(sec)=13.374768, speed(mflops)=623239.214396 +Executable: ./dgemmoptimized 16093 16093 16093 1 0 +m=16093, n=16093, k=16093, time(sec)=13.364412, speed(mflops)=623722.167364 +Max repetitions 3, Elasped time 147.312, Relative error 0.00167254, Mean 10368.4, Standard Deviation 10.2865 +Total Energy 10368.400000 +16126 +Executable: ./dgemmoptimized 16126 16126 16126 1 0 +m=16126, n=16126, k=16126, time(sec)=12.894198, speed(mflops)=650452.550842 +Executable: ./dgemmoptimized 16126 16126 16126 1 0 +m=16126, n=16126, k=16126, time(sec)=12.906234, speed(mflops)=649845.964352 +Executable: ./dgemmoptimized 16126 16126 16126 1 0 +m=16126, n=16126, k=16126, time(sec)=12.892931, speed(mflops)=650516.481228 +Max repetitions 3, Elasped time 146.109, Relative error 0.00244284, Mean 10435.9, Standard Deviation 15.1218 +Total Energy 10435.900000 +16158 +Executable: ./dgemmoptimized 16158 16158 16158 1 0 +m=16158, n=16158, k=16158, time(sec)=13.148035, speed(mflops)=641699.885488 +Executable: ./dgemmoptimized 16158 16158 16158 1 0 +m=16158, n=16158, k=16158, time(sec)=13.116359, speed(mflops)=643249.581348 +Executable: ./dgemmoptimized 16158 16158 16158 1 0 +m=16158, n=16158, k=16158, time(sec)=13.120983, speed(mflops)=643022.897472 +Max repetitions 3, Elasped time 147.147, Relative error 0.00321323, Mean 10342.9, Standard Deviation 19.7136 +Total Energy 10342.950000 +16191 +Executable: ./dgemmoptimized 16191 16191 16191 1 0 +m=16191, n=16191, k=16191, time(sec)=13.233019, speed(mflops)=641493.225311 +Executable: ./dgemmoptimized 16191 16191 16191 1 0 +m=16191, n=16191, k=16191, time(sec)=13.237961, speed(mflops)=641253.745740 +Executable: ./dgemmoptimized 16191 16191 16191 1 0 +m=16191, n=16191, k=16191, time(sec)=13.226664, speed(mflops)=641801.445110 +Max repetitions 3, Elasped time 149.797, Relative error 0.0274958, Mean 10431.5, Standard Deviation 170.135 +Total Energy 10431.466667 +16223 +Executable: ./dgemmoptimized 16223 16223 16223 1 0 +m=16223, n=16223, k=16223, time(sec)=13.412063, speed(mflops)=636689.839392 +Executable: ./dgemmoptimized 16223 16223 16223 1 0 +m=16223, n=16223, k=16223, time(sec)=13.418372, speed(mflops)=636390.470094 +Executable: ./dgemmoptimized 16223 16223 16223 1 0 +m=16223, n=16223, k=16223, time(sec)=13.412727, speed(mflops)=636658.308806 +Max repetitions 3, Elasped time 150.673, Relative error 0.0244555, Mean 11166.3, Standard Deviation 161.982 +Total Energy 11166.316667 +16255 +Executable: ./dgemmoptimized 16255 16255 16255 1 0 +m=16255, n=16255, k=16255, time(sec)=13.615732, speed(mflops)=630884.596686 +Executable: ./dgemmoptimized 16255 16255 16255 1 0 +m=16255, n=16255, k=16255, time(sec)=13.618397, speed(mflops)=630761.136157 +Executable: ./dgemmoptimized 16255 16255 16255 1 0 +m=16255, n=16255, k=16255, time(sec)=13.647630, speed(mflops)=629410.057108 +Max repetitions 3, Elasped time 150.128, Relative error 0.014115, Mean 11083.8, Standard Deviation 92.8006 +Total Energy 11083.816667 +16288 +Executable: ./dgemmoptimized 16288 16288 16288 1 0 +m=16288, n=16288, k=16288, time(sec)=13.665911, speed(mflops)=632404.109374 +Executable: ./dgemmoptimized 16288 16288 16288 1 0 +m=16288, n=16288, k=16288, time(sec)=13.643147, speed(mflops)=633459.304146 +Executable: ./dgemmoptimized 16288 16288 16288 1 0 +m=16288, n=16288, k=16288, time(sec)=13.640717, speed(mflops)=633572.148811 +Max repetitions 3, Elasped time 150.078, Relative error 0.000712178, Mean 11024.8, Standard Deviation 4.65734 +Total Energy 11024.766667 +16320 +Executable: ./dgemmoptimized 16320 16320 16320 1 0 +m=16320, n=16320, k=16320, time(sec)=13.548257, speed(mflops)=641663.046679 +Executable: ./dgemmoptimized 16320 16320 16320 1 0 +m=16320, n=16320, k=16320, time(sec)=13.560339, speed(mflops)=641091.343857 +Executable: ./dgemmoptimized 16320 16320 16320 1 0 +m=16320, n=16320, k=16320, time(sec)=13.551847, speed(mflops)=641493.070882 +Max repetitions 3, Elasped time 150.111, Relative error 0.00557932, Mean 11065.1, Standard Deviation 36.6199 +Total Energy 11065.116667 +16352 +Executable: ./dgemmoptimized 16352 16352 16352 1 0 +m=16352, n=16352, k=16352, time(sec)=13.782443, speed(mflops)=634477.801515 +Executable: ./dgemmoptimized 16352 16352 16352 1 0 +m=16352, n=16352, k=16352, time(sec)=13.785317, speed(mflops)=634345.517616 +Executable: ./dgemmoptimized 16352 16352 16352 1 0 +m=16352, n=16352, k=16352, time(sec)=13.795307, speed(mflops)=633886.151464 +Max repetitions 3, Elasped time 151.156, Relative error 0.00288818, Mean 11054.5, Standard Deviation 18.9383 +Total Energy 11054.466667 +16384 +Executable: ./dgemmoptimized 16384 16384 16384 1 0 +m=16384, n=16384, k=16384, time(sec)=15.433223, speed(mflops)=569945.306759 +Executable: ./dgemmoptimized 16384 16384 16384 1 0 +m=16384, n=16384, k=16384, time(sec)=15.445528, speed(mflops)=569491.247233 +Executable: ./dgemmoptimized 16384 16384 16384 1 0 +m=16384, n=16384, k=16384, time(sec)=15.468357, speed(mflops)=568650.769360 +Max repetitions 3, Elasped time 158.729, Relative error 0.0389922, Mean 11915.7, Standard Deviation 275.599 +Total Energy 11915.683333 +16416 +Executable: ./dgemmoptimized 16416 16416 16416 1 0 +m=16416, n=16416, k=16416, time(sec)=14.088431, speed(mflops)=628014.097757 +Executable: ./dgemmoptimized 16416 16416 16416 1 0 +m=16416, n=16416, k=16416, time(sec)=14.080546, speed(mflops)=628365.790646 +Executable: ./dgemmoptimized 16416 16416 16416 1 0 +m=16416, n=16416, k=16416, time(sec)=14.119930, speed(mflops)=626613.116387 +Max repetitions 3, Elasped time 154.244, Relative error 0.0421402, Mean 11201.6, Standard Deviation 279.999 +Total Energy 11201.600000 +16448 +Executable: ./dgemmoptimized 16448 16448 16448 1 0 +m=16448, n=16448, k=16448, time(sec)=14.284904, speed(mflops)=623005.615776 +Executable: ./dgemmoptimized 16448 16448 16448 1 0 +m=16448, n=16448, k=16448, time(sec)=14.295471, speed(mflops)=622545.101456 +Executable: ./dgemmoptimized 16448 16448 16448 1 0 +m=16448, n=16448, k=16448, time(sec)=14.275460, speed(mflops)=623417.768099 +Max repetitions 3, Elasped time 153.632, Relative error 0.00234864, Mean 10974.9, Standard Deviation 15.2896 +Total Energy 10974.866667 +16480 +Executable: ./dgemmoptimized 16480 16480 16480 1 0 +m=16480, n=16480, k=16480, time(sec)=14.216808, speed(mflops)=629650.448484 +Executable: ./dgemmoptimized 16480 16480 16480 1 0 +m=16480, n=16480, k=16480, time(sec)=14.215280, speed(mflops)=629718.130683 +Executable: ./dgemmoptimized 16480 16480 16480 1 0 +m=16480, n=16480, k=16480, time(sec)=14.174701, speed(mflops)=631520.876491 +Max repetitions 3, Elasped time 155.753, Relative error 0.021846, Mean 11014.6, Standard Deviation 142.732 +Total Energy 11014.616667 +16512 +Executable: ./dgemmoptimized 16512 16512 16512 1 0 +m=16512, n=16512, k=16512, time(sec)=13.920205, speed(mflops)=646819.952613 +Executable: ./dgemmoptimized 16512 16512 16512 1 0 +m=16512, n=16512, k=16512, time(sec)=13.946985, speed(mflops)=645577.969387 +Executable: ./dgemmoptimized 16512 16512 16512 1 0 +m=16512, n=16512, k=16512, time(sec)=13.919044, speed(mflops)=646873.897945 +Max repetitions 3, Elasped time 155.28, Relative error 0.0424959, Mean 11079.8, Standard Deviation 279.292 +Total Energy 11079.783333 +16543 +Executable: ./dgemmoptimized 16543 16543 16543 1 0 +m=16543, n=16543, k=16543, time(sec)=14.100699, speed(mflops)=642143.608871 +Executable: ./dgemmoptimized 16543 16543 16543 1 0 +m=16543, n=16543, k=16543, time(sec)=14.097293, speed(mflops)=642298.746366 +Executable: ./dgemmoptimized 16543 16543 16543 1 0 +m=16543, n=16543, k=16543, time(sec)=14.108687, speed(mflops)=641780.032812 +Max repetitions 3, Elasped time 154.1, Relative error 0.00995671, Mean 10904.8, Standard Deviation 64.404 +Total Energy 10904.783333 +16575 +Executable: ./dgemmoptimized 16575 16575 16575 1 0 +m=16575, n=16575, k=16575, time(sec)=14.268185, speed(mflops)=638295.629768 +Executable: ./dgemmoptimized 16575 16575 16575 1 0 +m=16575, n=16575, k=16575, time(sec)=14.236442, speed(mflops)=639718.839986 +Executable: ./dgemmoptimized 16575 16575 16575 1 0 +m=16575, n=16575, k=16575, time(sec)=14.249835, speed(mflops)=639117.590455 +Max repetitions 3, Elasped time 156.886, Relative error 0.0380596, Mean 11815, Standard Deviation 266.733 +Total Energy 11814.983333 +16606 +Executable: ./dgemmoptimized 16606 16606 16606 1 0 +m=16606, n=16606, k=16606, time(sec)=14.338684, speed(mflops)=638727.772621 +Executable: ./dgemmoptimized 16606 16606 16606 1 0 +m=16606, n=16606, k=16606, time(sec)=14.321354, speed(mflops)=639500.692608 +Executable: ./dgemmoptimized 16606 16606 16606 1 0 +m=16606, n=16606, k=16606, time(sec)=14.320770, speed(mflops)=639526.766360 +Max repetitions 3, Elasped time 155.44, Relative error 0.00427914, Mean 11651.7, Standard Deviation 29.575 +Total Energy 11651.683333 +16638 +Executable: ./dgemmoptimized 16638 16638 16638 1 0 +m=16638, n=16638, k=16638, time(sec)=14.677607, speed(mflops)=627593.021427 +Executable: ./dgemmoptimized 16638 16638 16638 1 0 +m=16638, n=16638, k=16638, time(sec)=14.711665, speed(mflops)=626140.118424 +Executable: ./dgemmoptimized 16638 16638 16638 1 0 +m=16638, n=16638, k=16638, time(sec)=14.688940, speed(mflops)=627108.803079 +Max repetitions 3, Elasped time 158.906, Relative error 0.021569, Mean 11716.3, Standard Deviation 149.899 +Total Energy 11716.300000 +16670 +Executable: ./dgemmoptimized 16670 16670 16670 1 0 +m=16670, n=16670, k=16670, time(sec)=14.689870, speed(mflops)=630694.202936 +Executable: ./dgemmoptimized 16670 16670 16670 1 0 +m=16670, n=16670, k=16670, time(sec)=14.619512, speed(mflops)=633729.489368 +Executable: ./dgemmoptimized 16670 16670 16670 1 0 +m=16670, n=16670, k=16670, time(sec)=14.678865, speed(mflops)=631167.052346 +Max repetitions 3, Elasped time 159.934, Relative error 0.0312246, Mean 11735.8, Standard Deviation 217.365 +Total Energy 11735.816667 +16701 +Executable: ./dgemmoptimized 16701 16701 16701 1 0 +m=16701, n=16701, k=16701, time(sec)=14.577444, speed(mflops)=639110.628124 +Executable: ./dgemmoptimized 16701 16701 16701 1 0 +m=16701, n=16701, k=16701, time(sec)=14.554419, speed(mflops)=640121.698720 +Executable: ./dgemmoptimized 16701 16701 16701 1 0 +m=16701, n=16701, k=16701, time(sec)=14.564636, speed(mflops)=639672.659536 +Max repetitions 3, Elasped time 157.187, Relative error 0.00892654, Mean 11558.7, Standard Deviation 61.203 +Total Energy 11558.716667 +16732 +Executable: ./dgemmoptimized 16732 16732 16732 1 0 +m=16732, n=16732, k=16732, time(sec)=14.889893, speed(mflops)=629190.251116 +Executable: ./dgemmoptimized 16732 16732 16732 1 0 +m=16732, n=16732, k=16732, time(sec)=14.831769, speed(mflops)=631655.978254 +Executable: ./dgemmoptimized 16732 16732 16732 1 0 +m=16732, n=16732, k=16732, time(sec)=14.867202, speed(mflops)=630150.550380 +Max repetitions 3, Elasped time 160.314, Relative error 0.042815, Mean 11711.2, Standard Deviation 297.425 +Total Energy 11711.216667 +16764 +Executable: ./dgemmoptimized 16764 16764 16764 1 0 +m=16764, n=16764, k=16764, time(sec)=14.961315, speed(mflops)=629786.269189 +Executable: ./dgemmoptimized 16764 16764 16764 1 0 +m=16764, n=16764, k=16764, time(sec)=14.993630, speed(mflops)=628428.922547 +Executable: ./dgemmoptimized 16764 16764 16764 1 0 +m=16764, n=16764, k=16764, time(sec)=15.030470, speed(mflops)=626888.621595 +Max repetitions 3, Elasped time 159.204, Relative error 0.00205255, Mean 11496.1, Standard Deviation 13.9967 +Total Energy 11496.150000 +16795 +Executable: ./dgemmoptimized 16795 16795 16795 1 0 +m=16795, n=16795, k=16795, time(sec)=15.085043, speed(mflops)=628092.289774 +Executable: ./dgemmoptimized 16795 16795 16795 1 0 +m=16795, n=16795, k=16795, time(sec)=15.068621, speed(mflops)=628776.795171 +Executable: ./dgemmoptimized 16795 16795 16795 1 0 +m=16795, n=16795, k=16795, time(sec)=15.076070, speed(mflops)=628466.123837 +Max repetitions 3, Elasped time 161.727, Relative error 0.0165419, Mean 11641.2, Standard Deviation 114.226 +Total Energy 11641.233333 +16826 +Executable: ./dgemmoptimized 16826 16826 16826 1 0 +m=16826, n=16826, k=16826, time(sec)=15.337162, speed(mflops)=621194.560303 +Executable: ./dgemmoptimized 16826 16826 16826 1 0 +m=16826, n=16826, k=16826, time(sec)=15.348643, speed(mflops)=620729.905824 +Executable: ./dgemmoptimized 16826 16826 16826 1 0 +m=16826, n=16826, k=16826, time(sec)=15.188134, speed(mflops)=627289.806910 +Max repetitions 3, Elasped time 162.618, Relative error 0.0370924, Mean 12170.9, Standard Deviation 267.785 +Total Energy 12170.900000 +16857 +Executable: ./dgemmoptimized 16857 16857 16857 1 0 +m=16857, n=16857, k=16857, time(sec)=15.334976, speed(mflops)=624723.375890 +Executable: ./dgemmoptimized 16857 16857 16857 1 0 +m=16857, n=16857, k=16857, time(sec)=15.300001, speed(mflops)=626151.453138 +Executable: ./dgemmoptimized 16857 16857 16857 1 0 +m=16857, n=16857, k=16857, time(sec)=15.294174, speed(mflops)=626390.021272 +Max repetitions 3, Elasped time 161.102, Relative error 0.00574682, Mean 12253.7, Standard Deviation 41.7712 +Total Energy 12253.750000 +16888 +Executable: ./dgemmoptimized 16888 16888 16888 1 0 +m=16888, n=16888, k=16888, time(sec)=15.146310, speed(mflops)=636001.020728 +Executable: ./dgemmoptimized 16888 16888 16888 1 0 +m=16888, n=16888, k=16888, time(sec)=15.052256, speed(mflops)=639975.071475 +Executable: ./dgemmoptimized 16888 16888 16888 1 0 +m=16888, n=16888, k=16888, time(sec)=15.132507, speed(mflops)=636581.144388 +Max repetitions 3, Elasped time 179.302, Relative error 0.252304, Mean 13326.5, Standard Deviation 1994.44 +Total Energy 13326.533333 +16919 +Executable: ./dgemmoptimized 16919 16919 16919 1 0 +m=16919, n=16919, k=16919, time(sec)=15.140921, speed(mflops)=639737.442986 +Executable: ./dgemmoptimized 16919 16919 16919 1 0 +m=16919, n=16919, k=16919, time(sec)=15.175724, speed(mflops)=638270.315160 +Executable: ./dgemmoptimized 16919 16919 16919 1 0 +m=16919, n=16919, k=16919, time(sec)=15.137548, speed(mflops)=639879.997634 +Max repetitions 3, Elasped time 161.289, Relative error 0.00952694, Mean 12288.8, Standard Deviation 69.4452 +Total Energy 12288.783333 +16950 +Executable: ./dgemmoptimized 16950 16950 16950 1 0 +m=16950, n=16950, k=16950, time(sec)=15.303497, speed(mflops)=636426.739693 +Executable: ./dgemmoptimized 16950 16950 16950 1 0 +m=16950, n=16950, k=16950, time(sec)=15.269399, speed(mflops)=637847.946479 +Executable: ./dgemmoptimized 16950 16950 16950 1 0 +m=16950, n=16950, k=16950, time(sec)=15.307143, speed(mflops)=636275.153842 +Max repetitions 3, Elasped time 163.934, Relative error 0.0422587, Mean 12354.1, Standard Deviation 309.676 +Total Energy 12354.116667 +16981 +Executable: ./dgemmoptimized 16981 16981 16981 1 0 +m=16981, n=16981, k=16981, time(sec)=15.495436, speed(mflops)=631998.405072 +Executable: ./dgemmoptimized 16981 16981 16981 1 0 +m=16981, n=16981, k=16981, time(sec)=15.475840, speed(mflops)=632798.655857 +Executable: ./dgemmoptimized 16981 16981 16981 1 0 +m=16981, n=16981, k=16981, time(sec)=15.472291, speed(mflops)=632943.809865 +Max repetitions 3, Elasped time 165.066, Relative error 0.041145, Mean 12297.6, Standard Deviation 300.134 +Total Energy 12297.550000 +17012 +Executable: ./dgemmoptimized 17012 17012 17012 1 0 +m=17012, n=17012, k=17012, time(sec)=15.630294, speed(mflops)=629983.200456 +Executable: ./dgemmoptimized 17012 17012 17012 1 0 +m=17012, n=17012, k=17012, time(sec)=15.609703, speed(mflops)=630814.221840 +Executable: ./dgemmoptimized 17012 17012 17012 1 0 +m=17012, n=17012, k=17012, time(sec)=15.623297, speed(mflops)=630265.347098 +Max repetitions 3, Elasped time 163.775, Relative error 0.00675843, Mean 12181.2, Standard Deviation 48.8335 +Total Energy 12181.250000 +17043 +Executable: ./dgemmoptimized 17043 17043 17043 1 0 +m=17043, n=17043, k=17043, time(sec)=15.792332, speed(mflops)=626934.058783 +Executable: ./dgemmoptimized 17043 17043 17043 1 0 +m=17043, n=17043, k=17043, time(sec)=15.813598, speed(mflops)=626090.963526 +Executable: ./dgemmoptimized 17043 17043 17043 1 0 +m=17043, n=17043, k=17043, time(sec)=15.792970, speed(mflops)=626908.731753 +Max repetitions 3, Elasped time 164.619, Relative error 0.00904518, Mean 12155.2, Standard Deviation 65.2167 +Total Energy 12155.183333 +17073 +Executable: ./dgemmoptimized 17073 17073 17073 1 0 +m=17073, n=17073, k=17073, time(sec)=15.846183, speed(mflops)=628108.756370 +Executable: ./dgemmoptimized 17073 17073 17073 1 0 +m=17073, n=17073, k=17073, time(sec)=15.855981, speed(mflops)=627720.632087 +Executable: ./dgemmoptimized 17073 17073 17073 1 0 +m=17073, n=17073, k=17073, time(sec)=15.851443, speed(mflops)=627900.330790 +Max repetitions 3, Elasped time 165.067, Relative error 0.00456905, Mean 12160.6, Standard Deviation 32.9579 +Total Energy 12160.583333 +17104 +Executable: ./dgemmoptimized 17104 17104 17104 1 0 +m=17104, n=17104, k=17104, time(sec)=15.790865, speed(mflops)=633748.785575 +Executable: ./dgemmoptimized 17104 17104 17104 1 0 +m=17104, n=17104, k=17104, time(sec)=15.801828, speed(mflops)=633309.104508 +Executable: ./dgemmoptimized 17104 17104 17104 1 0 +m=17104, n=17104, k=17104, time(sec)=15.794726, speed(mflops)=633593.868504 +Max repetitions 3, Elasped time 165.231, Relative error 0.00417144, Mean 12104.1, Standard Deviation 29.9503 +Total Energy 12104.150000 +17135 +Executable: ./dgemmoptimized 17135 17135 17135 1 0 +m=17135, n=17135, k=17135, time(sec)=15.938218, speed(mflops)=631309.845778 +Executable: ./dgemmoptimized 17135 17135 17135 1 0 +m=17135, n=17135, k=17135, time(sec)=15.940110, speed(mflops)=631234.909347 +Executable: ./dgemmoptimized 17135 17135 17135 1 0 +m=17135, n=17135, k=17135, time(sec)=15.941254, speed(mflops)=631189.612407 +Max repetitions 3, Elasped time 166.006, Relative error 0.00176684, Mean 12084.2, Standard Deviation 12.6647 +Total Energy 12084.216667 +17165 +Executable: ./dgemmoptimized 17165 17165 17165 1 0 +m=17165, n=17165, k=17165, time(sec)=16.205093, speed(mflops)=624180.055216 +Executable: ./dgemmoptimized 17165 17165 17165 1 0 +m=17165, n=17165, k=17165, time(sec)=16.178148, speed(mflops)=625219.642862 +Executable: ./dgemmoptimized 17165 17165 17165 1 0 +m=17165, n=17165, k=17165, time(sec)=16.186946, speed(mflops)=624879.825214 +Max repetitions 3, Elasped time 171.011, Relative error 0.0337515, Mean 13091.7, Standard Deviation 262.102 +Total Energy 13091.716667 +17196 +Executable: ./dgemmoptimized 17196 17196 17196 1 0 +m=17196, n=17196, k=17196, time(sec)=16.360001, speed(mflops)=621625.722203 +Executable: ./dgemmoptimized 17196 17196 17196 1 0 +m=17196, n=17196, k=17196, time(sec)=16.369980, speed(mflops)=621246.784109 +Executable: ./dgemmoptimized 17196 17196 17196 1 0 +m=17196, n=17196, k=17196, time(sec)=16.361088, speed(mflops)=621584.424445 +Max repetitions 3, Elasped time 167.973, Relative error 0.00860658, Mean 12801.1, Standard Deviation 65.3516 +Total Energy 12801.066667 +17226 +Executable: ./dgemmoptimized 17226 17226 17226 1 0 +m=17226, n=17226, k=17226, time(sec)=16.398936, speed(mflops)=623401.226618 +Executable: ./dgemmoptimized 17226 17226 17226 1 0 +m=17226, n=17226, k=17226, time(sec)=16.450822, speed(mflops)=621435.021003 +Executable: ./dgemmoptimized 17226 17226 17226 1 0 +m=17226, n=17226, k=17226, time(sec)=16.452018, speed(mflops)=621389.839492 +Max repetitions 3, Elasped time 170.492, Relative error 0.0416249, Mean 13050, Standard Deviation 322.212 +Total Energy 13049.966667 +17257 +Executable: ./dgemmoptimized 17257 17257 17257 1 0 +m=17257, n=17257, k=17257, time(sec)=16.175472, speed(mflops)=635431.778051 +Executable: ./dgemmoptimized 17257 17257 17257 1 0 +m=17257, n=17257, k=17257, time(sec)=16.150163, speed(mflops)=636427.569703 +Executable: ./dgemmoptimized 17257 17257 17257 1 0 +m=17257, n=17257, k=17257, time(sec)=16.138838, speed(mflops)=636874.170584 +Max repetitions 3, Elasped time 168.016, Relative error 0.00514451, Mean 12881, Standard Deviation 39.3075 +Total Energy 12881.033333 +17287 +Executable: ./dgemmoptimized 17287 17287 17287 1 0 +m=17287, n=17287, k=17287, time(sec)=15.848042, speed(mflops)=651948.481110 +Executable: ./dgemmoptimized 17287 17287 17287 1 0 +m=17287, n=17287, k=17287, time(sec)=15.833145, speed(mflops)=652561.887167 +Executable: ./dgemmoptimized 17287 17287 17287 1 0 +m=17287, n=17287, k=17287, time(sec)=15.860618, speed(mflops)=651431.542153 +Max repetitions 3, Elasped time 167.445, Relative error 0.00210753, Mean 12869.6, Standard Deviation 16.0886 +Total Energy 12869.616667 +17317 +Executable: ./dgemmoptimized 17317 17317 17317 1 0 +m=17317, n=17317, k=17317, time(sec)=16.040841, speed(mflops)=647471.757971 +Executable: ./dgemmoptimized 17317 17317 17317 1 0 +m=17317, n=17317, k=17317, time(sec)=16.025743, speed(mflops)=648081.750909 +Executable: ./dgemmoptimized 17317 17317 17317 1 0 +m=17317, n=17317, k=17317, time(sec)=16.095265, speed(mflops)=645282.425921 +Max repetitions 3, Elasped time 170.27, Relative error 0.0373207, Mean 13002.5, Standard Deviation 287.843 +Total Energy 13002.450000 +17348 +Executable: ./dgemmoptimized 17348 17348 17348 1 0 +m=17348, n=17348, k=17348, time(sec)=16.215647, speed(mflops)=643937.852609 +Executable: ./dgemmoptimized 17348 17348 17348 1 0 +m=17348, n=17348, k=17348, time(sec)=16.226309, speed(mflops)=643514.730127 +Executable: ./dgemmoptimized 17348 17348 17348 1 0 +m=17348, n=17348, k=17348, time(sec)=16.256649, speed(mflops)=642313.731769 +Max repetitions 3, Elasped time 169.247, Relative error 0.00696718, Mean 12769.1, Standard Deviation 52.7712 +Total Energy 12769.100000 +17378 +Executable: ./dgemmoptimized 17378 17378 17378 1 0 +m=17378, n=17378, k=17378, time(sec)=16.369305, speed(mflops)=641208.292136 +Executable: ./dgemmoptimized 17378 17378 17378 1 0 +m=17378, n=17378, k=17378, time(sec)=16.442550, speed(mflops)=638351.972419 +Executable: ./dgemmoptimized 17378 17378 17378 1 0 +m=17378, n=17378, k=17378, time(sec)=16.418576, speed(mflops)=639284.075973 +Max repetitions 3, Elasped time 170.124, Relative error 0.00864572, Mean 12736.4, Standard Deviation 65.3175 +Total Energy 12736.450000 +17408 +Executable: ./dgemmoptimized 17408 17408 17408 1 0 +m=17408, n=17408, k=17408, time(sec)=17.155028, speed(mflops)=615014.274426 +Executable: ./dgemmoptimized 17408 17408 17408 1 0 +m=17408, n=17408, k=17408, time(sec)=17.160935, speed(mflops)=614802.585563 +Executable: ./dgemmoptimized 17408 17408 17408 1 0 +m=17408, n=17408, k=17408, time(sec)=17.163834, speed(mflops)=614698.738302 +Max repetitions 3, Elasped time 174.74, Relative error 0.019958, Mean 13479.8, Standard Deviation 159.581 +Total Energy 13479.783333 +17438 +Executable: ./dgemmoptimized 17438 17438 17438 1 0 +m=17438, n=17438, k=17438, time(sec)=16.583437, speed(mflops)=639507.248414 +Executable: ./dgemmoptimized 17438 17438 17438 1 0 +m=17438, n=17438, k=17438, time(sec)=16.578692, speed(mflops)=639690.282522 +Executable: ./dgemmoptimized 17438 17438 17438 1 0 +m=17438, n=17438, k=17438, time(sec)=16.590281, speed(mflops)=639243.430365 +Max repetitions 3, Elasped time 173.318, Relative error 0.0250049, Mean 12767.3, Standard Deviation 189.367 +Total Energy 12767.300000 +17468 +Executable: ./dgemmoptimized 17468 17468 17468 1 0 +m=17468, n=17468, k=17468, time(sec)=16.569017, speed(mflops)=643372.949880 +Executable: ./dgemmoptimized 17468 17468 17468 1 0 +m=17468, n=17468, k=17468, time(sec)=16.564526, speed(mflops)=643547.385677 +Executable: ./dgemmoptimized 17468 17468 17468 1 0 +m=17468, n=17468, k=17468, time(sec)=16.603300, speed(mflops)=642044.506020 +Max repetitions 3, Elasped time 171.623, Relative error 0.00489499, Mean 12658.3, Standard Deviation 36.7541 +Total Energy 12658.283333 +17498 +Executable: ./dgemmoptimized 17498 17498 17498 1 0 +m=17498, n=17498, k=17498, time(sec)=16.766873, speed(mflops)=639062.235546 +Executable: ./dgemmoptimized 17498 17498 17498 1 0 +m=17498, n=17498, k=17498, time(sec)=16.709503, speed(mflops)=641256.383353 +Executable: ./dgemmoptimized 17498 17498 17498 1 0 +m=17498, n=17498, k=17498, time(sec)=16.768866, speed(mflops)=638986.293564 +Max repetitions 3, Elasped time 173.031, Relative error 0.0235428, Mean 13096.2, Standard Deviation 182.887 +Total Energy 13096.200000 +17528 +Executable: ./dgemmoptimized 17528 17528 17528 1 0 +m=17528, n=17528, k=17528, time(sec)=16.947101, speed(mflops)=635523.579524 +Executable: ./dgemmoptimized 17528 17528 17528 1 0 +m=17528, n=17528, k=17528, time(sec)=16.956378, speed(mflops)=635175.883354 +Executable: ./dgemmoptimized 17528 17528 17528 1 0 +m=17528, n=17528, k=17528, time(sec)=16.958808, speed(mflops)=635084.871453 +Max repetitions 3, Elasped time 175.419, Relative error 0.0305424, Mean 13475.9, Standard Deviation 244.142 +Total Energy 13475.950000 +17558 +Executable: ./dgemmoptimized 17558 17558 17558 1 0 +m=17558, n=17558, k=17558, time(sec)=17.027738, speed(mflops)=635767.272802 +Executable: ./dgemmoptimized 17558 17558 17558 1 0 +m=17558, n=17558, k=17558, time(sec)=17.018173, speed(mflops)=636124.607698 +Executable: ./dgemmoptimized 17558 17558 17558 1 0 +m=17558, n=17558, k=17558, time(sec)=17.047452, speed(mflops)=635032.063876 +Max repetitions 3, Elasped time 173.982, Relative error 0.00247973, Mean 13393.6, Standard Deviation 19.7008 +Total Energy 13393.650000 +17588 +Executable: ./dgemmoptimized 17588 17588 17588 1 0 +m=17588, n=17588, k=17588, time(sec)=17.283122, speed(mflops)=629589.054771 +Executable: ./dgemmoptimized 17588 17588 17588 1 0 +m=17588, n=17588, k=17588, time(sec)=17.309371, speed(mflops)=628634.309494 +Executable: ./dgemmoptimized 17588 17588 17588 1 0 +m=17588, n=17588, k=17588, time(sec)=17.271852, speed(mflops)=629999.867564 +Max repetitions 3, Elasped time 177.118, Relative error 0.0307626, Mean 13495.9, Standard Deviation 246.266 +Total Energy 13495.883333 +17618 +Executable: ./dgemmoptimized 17618 17618 17618 1 0 +m=17618, n=17618, k=17618, time(sec)=17.306559, speed(mflops)=631959.270614 +Executable: ./dgemmoptimized 17618 17618 17618 1 0 +m=17618, n=17618, k=17618, time(sec)=17.300979, speed(mflops)=632163.082748 +Executable: ./dgemmoptimized 17618 17618 17618 1 0 +m=17618, n=17618, k=17618, time(sec)=17.311705, speed(mflops)=631771.407554 +Max repetitions 3, Elasped time 175.501, Relative error 0.00902601, Mean 13325.4, Standard Deviation 71.3436 +Total Energy 13325.383333 +17647 +Executable: ./dgemmoptimized 17647 17647 17647 1 0 +m=17647, n=17647, k=17647, time(sec)=17.154199, speed(mflops)=640725.790752 +Executable: ./dgemmoptimized 17647 17647 17647 1 0 +m=17647, n=17647, k=17647, time(sec)=17.134585, speed(mflops)=641459.239299 +Executable: ./dgemmoptimized 17647 17647 17647 1 0 +m=17647, n=17647, k=17647, time(sec)=17.130774, speed(mflops)=641601.937220 +Max repetitions 3, Elasped time 175.329, Relative error 0.00568618, Mean 13383, Standard Deviation 45.1392 +Total Energy 13382.983333 +17677 +Executable: ./dgemmoptimized 17677 17677 17677 1 0 +m=17677, n=17677, k=17677, time(sec)=17.072606, speed(mflops)=647076.848101 +Executable: ./dgemmoptimized 17677 17677 17677 1 0 +m=17677, n=17677, k=17677, time(sec)=17.108363, speed(mflops)=645724.444329 +Executable: ./dgemmoptimized 17677 17677 17677 1 0 +m=17677, n=17677, k=17677, time(sec)=17.093233, speed(mflops)=646296.006111 +Max repetitions 3, Elasped time 177.504, Relative error 0.0196793, Mean 13425.5, Standard Deviation 156.718 +Total Energy 13425.500000 +17707 +Executable: ./dgemmoptimized 17707 17707 17707 1 0 +m=17707, n=17707, k=17707, time(sec)=17.199706, speed(mflops)=645570.879782 +Executable: ./dgemmoptimized 17707 17707 17707 1 0 +m=17707, n=17707, k=17707, time(sec)=17.213613, speed(mflops)=645049.320152 +Executable: ./dgemmoptimized 17707 17707 17707 1 0 +m=17707, n=17707, k=17707, time(sec)=17.201880, speed(mflops)=645489.295273 +Max repetitions 3, Elasped time 178.196, Relative error 0.0216173, Mean 13392.6, Standard Deviation 171.73 +Total Energy 13392.600000 +17736 +Executable: ./dgemmoptimized 17736 17736 17736 1 0 +m=17736, n=17736, k=17736, time(sec)=17.409734, speed(mflops)=640921.587984 +Executable: ./dgemmoptimized 17736 17736 17736 1 0 +m=17736, n=17736, k=17736, time(sec)=17.407874, speed(mflops)=640990.074521 +Executable: ./dgemmoptimized 17736 17736 17736 1 0 +m=17736, n=17736, k=17736, time(sec)=17.417082, speed(mflops)=640651.190758 +Max repetitions 3, Elasped time 177.186, Relative error 0.00612078, Mean 13276, Standard Deviation 48.2009 +Total Energy 13276.016667 +17766 +Executable: ./dgemmoptimized 17766 17766 17766 1 0 +m=17766, n=17766, k=17766, time(sec)=17.482526, speed(mflops)=641497.228787 +Executable: ./dgemmoptimized 17766 17766 17766 1 0 +m=17766, n=17766, k=17766, time(sec)=17.614296, speed(mflops)=636698.284620 +Executable: ./dgemmoptimized 17766 17766 17766 1 0 +m=17766, n=17766, k=17766, time(sec)=17.614205, speed(mflops)=636701.576729 +Max repetitions 3, Elasped time 179.874, Relative error 0.0251247, Mean 13352.3, Standard Deviation 198.993 +Total Energy 13352.316667 +17795 +Executable: ./dgemmoptimized 17795 17795 17795 1 0 +m=17795, n=17795, k=17795, time(sec)=17.833890, speed(mflops)=631942.966093 +Executable: ./dgemmoptimized 17795 17795 17795 1 0 +m=17795, n=17795, k=17795, time(sec)=17.934365, speed(mflops)=628402.591802 +Executable: ./dgemmoptimized 17795 17795 17795 1 0 +m=17795, n=17795, k=17795, time(sec)=17.896775, speed(mflops)=629722.475987 +Max repetitions 3, Elasped time 179.256, Relative error 0.00437539, Mean 14000.9, Standard Deviation 36.3373 +Total Energy 14000.900000 +17825 +Executable: ./dgemmoptimized 17825 17825 17825 1 0 +m=17825, n=17825, k=17825, time(sec)=17.800742, speed(mflops)=636327.229389 +Executable: ./dgemmoptimized 17825 17825 17825 1 0 +m=17825, n=17825, k=17825, time(sec)=17.790978, speed(mflops)=636676.446803 +Executable: ./dgemmoptimized 17825 17825 17825 1 0 +m=17825, n=17825, k=17825, time(sec)=17.805665, speed(mflops)=636151.290668 +Max repetitions 3, Elasped time 181.371, Relative error 0.0181835, Mean 14128.8, Standard Deviation 152.393 +Total Energy 14128.833333 +17854 +Executable: ./dgemmoptimized 17854 17854 17854 1 0 +m=17854, n=17854, k=17854, time(sec)=17.667505, speed(mflops)=644260.289558 +Executable: ./dgemmoptimized 17854 17854 17854 1 0 +m=17854, n=17854, k=17854, time(sec)=17.627910, speed(mflops)=645707.393284 +Executable: ./dgemmoptimized 17854 17854 17854 1 0 +m=17854, n=17854, k=17854, time(sec)=17.639296, speed(mflops)=645290.598238 +Max repetitions 3, Elasped time 179.233, Relative error 0.00265773, Mean 13962.4, Standard Deviation 22.0116 +Total Energy 13962.400000 +17883 +Executable: ./dgemmoptimized 17883 17883 17883 1 0 +m=17883, n=17883, k=17883, time(sec)=17.958220, speed(mflops)=636924.327999 +Executable: ./dgemmoptimized 17883 17883 17883 1 0 +m=17883, n=17883, k=17883, time(sec)=17.977048, speed(mflops)=636257.257561 +Executable: ./dgemmoptimized 17883 17883 17883 1 0 +m=17883, n=17883, k=17883, time(sec)=17.948544, speed(mflops)=637267.691049 +Max repetitions 3, Elasped time 182.521, Relative error 0.0201077, Mean 14051.6, Standard Deviation 167.598 +Total Energy 14051.600000 +17913 +Executable: ./dgemmoptimized 17913 17913 17913 1 0 +m=17913, n=17913, k=17913, time(sec)=18.160980, speed(mflops)=632988.315814 +Executable: ./dgemmoptimized 17913 17913 17913 1 0 +m=17913, n=17913, k=17913, time(sec)=18.149369, speed(mflops)=633393.267508 +Executable: ./dgemmoptimized 17913 17913 17913 1 0 +m=17913, n=17913, k=17913, time(sec)=18.190787, speed(mflops)=631951.121028 +Max repetitions 3, Elasped time 183.451, Relative error 0.015859, Mean 14021.1, Standard Deviation 131.898 +Total Energy 14021.083333 +17942 +Executable: ./dgemmoptimized 17942 17942 17942 1 0 +m=17942, n=17942, k=17942, time(sec)=18.394130, speed(mflops)=628005.289029 +Executable: ./dgemmoptimized 17942 17942 17942 1 0 +m=17942, n=17942, k=17942, time(sec)=18.423921, speed(mflops)=626989.816875 +Executable: ./dgemmoptimized 17942 17942 17942 1 0 +m=17942, n=17942, k=17942, time(sec)=18.210783, speed(mflops)=634328.074677 +Max repetitions 3, Elasped time 184.325, Relative error 0.0316949, Mean 14015.3, Standard Deviation 263.495 +Total Energy 14015.316667 +17971 +Executable: ./dgemmoptimized 17971 17971 17971 1 0 +m=17971, n=17971, k=17971, time(sec)=18.496633, speed(mflops)=627558.255931 +Executable: ./dgemmoptimized 17971 17971 17971 1 0 +m=17971, n=17971, k=17971, time(sec)=18.497047, speed(mflops)=627544.213527 +Executable: ./dgemmoptimized 17971 17971 17971 1 0 +m=17971, n=17971, k=17971, time(sec)=18.506622, speed(mflops)=627219.528855 +Max repetitions 3, Elasped time 183.18, Relative error 0.00145941, Mean 13863.1, Standard Deviation 12.001 +Total Energy 13863.083333 +18000 +Executable: ./dgemmoptimized 18000 18000 18000 1 0 +m=18000, n=18000, k=18000, time(sec)=18.722537, speed(mflops)=622992.491597 +Executable: ./dgemmoptimized 18000 18000 18000 1 0 +m=18000, n=18000, k=18000, time(sec)=18.697143, speed(mflops)=623838.623443 +Executable: ./dgemmoptimized 18000 18000 18000 1 0 +m=18000, n=18000, k=18000, time(sec)=18.714625, speed(mflops)=623255.872084 +Max repetitions 3, Elasped time 184.372, Relative error 0.050257, Mean 14096.8, Standard Deviation 420.239 +Total Energy 14096.766667 +18029 +Executable: ./dgemmoptimized 18029 18029 18029 1 0 +m=18029, n=18029, k=18029, time(sec)=18.415447, speed(mflops)=636447.590921 +Executable: ./dgemmoptimized 18029 18029 18029 1 0 +m=18029, n=18029, k=18029, time(sec)=18.395826, speed(mflops)=637126.422713 +Executable: ./dgemmoptimized 18029 18029 18029 1 0 +m=18029, n=18029, k=18029, time(sec)=18.407069, speed(mflops)=636737.271820 +Max repetitions 3, Elasped time 185.656, Relative error 0.0305981, Mean 13970.8, Standard Deviation 253.569 +Total Energy 13970.816667 +18058 +Executable: ./dgemmoptimized 18058 18058 18058 1 0 +m=18058, n=18058, k=18058, time(sec)=18.259471, speed(mflops)=644986.680467 +Executable: ./dgemmoptimized 18058 18058 18058 1 0 +m=18058, n=18058, k=18058, time(sec)=18.306407, speed(mflops)=643332.999121 +Executable: ./dgemmoptimized 18058 18058 18058 1 0 +m=18058, n=18058, k=18058, time(sec)=18.169458, speed(mflops)=648181.998849 +Max repetitions 3, Elasped time 183.369, Relative error 0.00103786, Mean 13835.8, Standard Deviation 8.51768 +Total Energy 13835.783333 +18087 +Executable: ./dgemmoptimized 18087 18087 18087 1 0 +m=18087, n=18087, k=18087, time(sec)=18.545704, speed(mflops)=638096.385469 +Executable: ./dgemmoptimized 18087 18087 18087 1 0 +m=18087, n=18087, k=18087, time(sec)=18.502102, speed(mflops)=639600.129441 +Executable: ./dgemmoptimized 18087 18087 18087 1 0 +m=18087, n=18087, k=18087, time(sec)=18.457695, speed(mflops)=641138.926844 +Max repetitions 3, Elasped time 186.729, Relative error 0.0350172, Mean 14290.9, Standard Deviation 296.838 +Total Energy 14290.850000 +18116 +Executable: ./dgemmoptimized 18116 18116 18116 1 0 +m=18116, n=18116, k=18116, time(sec)=18.637488, speed(mflops)=638013.035282 +Executable: ./dgemmoptimized 18116 18116 18116 1 0 +m=18116, n=18116, k=18116, time(sec)=18.663235, speed(mflops)=637132.865884 +Executable: ./dgemmoptimized 18116 18116 18116 1 0 +m=18116, n=18116, k=18116, time(sec)=18.610650, speed(mflops)=638933.109921 +Max repetitions 3, Elasped time 185.258, Relative error 0.00710366, Mean 14543.2, Standard Deviation 61.2805 +Total Energy 14543.200000 +18145 +Executable: ./dgemmoptimized 18145 18145 18145 1 0 +m=18145, n=18145, k=18145, time(sec)=18.786021, speed(mflops)=636013.171759 +Executable: ./dgemmoptimized 18145 18145 18145 1 0 +m=18145, n=18145, k=18145, time(sec)=18.784400, speed(mflops)=636068.056791 +Executable: ./dgemmoptimized 18145 18145 18145 1 0 +m=18145, n=18145, k=18145, time(sec)=18.784493, speed(mflops)=636064.908254 +Max repetitions 3, Elasped time 185.993, Relative error 0.00118381, Mean 14526, Standard Deviation 10.2002 +Total Energy 14525.966667 +18174 +Executable: ./dgemmoptimized 18174 18174 18174 1 0 +m=18174, n=18174, k=18174, time(sec)=19.006626, speed(mflops)=631650.057883 +Executable: ./dgemmoptimized 18174 18174 18174 1 0 +m=18174, n=18174, k=18174, time(sec)=19.139619, speed(mflops)=627260.993196 +Executable: ./dgemmoptimized 18174 18174 18174 1 0 +m=18174, n=18174, k=18174, time(sec)=19.132122, speed(mflops)=627506.782524 +Max repetitions 3, Elasped time 187.244, Relative error 0.00348782, Mean 14502.8, Standard Deviation 30.0044 +Total Energy 14502.783333 +18203 +Executable: ./dgemmoptimized 18203 18203 18203 1 0 +m=18203, n=18203, k=18203, time(sec)=19.977273, speed(mflops)=603841.140404 +Executable: ./dgemmoptimized 18203 18203 18203 1 0 +m=18203, n=18203, k=18203, time(sec)=19.086396, speed(mflops)=632026.041803 +Executable: ./dgemmoptimized 18203 18203 18203 1 0 +m=18203, n=18203, k=18203, time(sec)=19.095785, speed(mflops)=631715.290280 +Max repetitions 3, Elasped time 188.409, Relative error 0.00437922, Mean 14519.2, Standard Deviation 37.7154 +Total Energy 14519.183333 +18232 +Executable: ./dgemmoptimized 18232 18232 18232 1 0 +m=18232, n=18232, k=18232, time(sec)=19.107053, speed(mflops)=634365.021716 +Executable: ./dgemmoptimized 18232 18232 18232 1 0 +m=18232, n=18232, k=18232, time(sec)=19.109441, speed(mflops)=634285.740736 +Executable: ./dgemmoptimized 18232 18232 18232 1 0 +m=18232, n=18232, k=18232, time(sec)=19.110398, speed(mflops)=634253.976919 +Max repetitions 3, Elasped time 189.953, Relative error 0.0150747, Mean 14582.3, Standard Deviation 130.393 +Total Energy 14582.283333 +18261 +Executable: ./dgemmoptimized 18261 18261 18261 1 0 +m=18261, n=18261, k=18261, time(sec)=19.205344, speed(mflops)=634134.783081 +Executable: ./dgemmoptimized 18261 18261 18261 1 0 +m=18261, n=18261, k=18261, time(sec)=19.242827, speed(mflops)=632899.556079 +Executable: ./dgemmoptimized 18261 18261 18261 1 0 +m=18261, n=18261, k=18261, time(sec)=19.256015, speed(mflops)=632466.101555 +Max repetitions 3, Elasped time 188.902, Relative error 0.00374741, Mean 14440.6, Standard Deviation 32.0993 +Total Energy 14440.583333 +18289 +Executable: ./dgemmoptimized 18289 18289 18289 1 0 +m=18289, n=18289, k=18289, time(sec)=19.347228, speed(mflops)=632384.365935 +Executable: ./dgemmoptimized 18289 18289 18289 1 0 +m=18289, n=18289, k=18289, time(sec)=19.342274, speed(mflops)=632546.337333 +Executable: ./dgemmoptimized 18289 18289 18289 1 0 +m=18289, n=18289, k=18289, time(sec)=19.327782, speed(mflops)=633020.614864 +Max repetitions 3, Elasped time 189.329, Relative error 0.00192814, Mean 14423.6, Standard Deviation 16.4965 +Total Energy 14423.633333 +18318 +Executable: ./dgemmoptimized 18318 18318 18318 1 0 +m=18318, n=18318, k=18318, time(sec)=19.585382, speed(mflops)=627671.072051 +Executable: ./dgemmoptimized 18318 18318 18318 1 0 +m=18318, n=18318, k=18318, time(sec)=19.642522, speed(mflops)=625845.176418 +Executable: ./dgemmoptimized 18318 18318 18318 1 0 +m=18318, n=18318, k=18318, time(sec)=19.588859, speed(mflops)=627559.665700 +Max repetitions 3, Elasped time 192.462, Relative error 0.022071, Mean 14602.1, Standard Deviation 191.168 +Total Energy 14602.083333 +18346 +Executable: ./dgemmoptimized 18346 18346 18346 1 0 +m=18346, n=18346, k=18346, time(sec)=19.532664, speed(mflops)=632255.596736 +Executable: ./dgemmoptimized 18346 18346 18346 1 0 +m=18346, n=18346, k=18346, time(sec)=19.581928, speed(mflops)=630664.976511 +Executable: ./dgemmoptimized 18346 18346 18346 1 0 +m=18346, n=18346, k=18346, time(sec)=19.690686, speed(mflops)=627181.611617 +Max repetitions 3, Elasped time 190.786, Relative error 0.0250143, Mean 15032.8, Standard Deviation 223.053 +Total Energy 15032.816667 +18375 +Executable: ./dgemmoptimized 18375 18375 18375 1 0 +m=18375, n=18375, k=18375, time(sec)=19.894865, speed(mflops)=623693.254264 +Executable: ./dgemmoptimized 18375 18375 18375 1 0 +m=18375, n=18375, k=18375, time(sec)=19.919289, speed(mflops)=622928.504071 +Executable: ./dgemmoptimized 18375 18375 18375 1 0 +m=18375, n=18375, k=18375, time(sec)=19.888853, speed(mflops)=623881.775542 +Max repetitions 3, Elasped time 192.243, Relative error 0.00516082, Mean 15126.1, Standard Deviation 46.3048 +Total Energy 15126.116667 +18404 +Executable: ./dgemmoptimized 18404 18404 18404 1 0 +m=18404, n=18404, k=18404, time(sec)=19.692537, speed(mflops)=633089.343114 +Executable: ./dgemmoptimized 18404 18404 18404 1 0 +m=18404, n=18404, k=18404, time(sec)=19.671230, speed(mflops)=633775.069340 +Executable: ./dgemmoptimized 18404 18404 18404 1 0 +m=18404, n=18404, k=18404, time(sec)=19.691353, speed(mflops)=633127.409028 +Max repetitions 3, Elasped time 191.797, Relative error 0.00458556, Mean 15158.9, Standard Deviation 41.2326 +Total Energy 15158.933333 +18432 +Executable: ./dgemmoptimized 18432 18432 18432 1 0 +m=18432, n=18432, k=18432, time(sec)=19.801112, speed(mflops)=632496.019641 +Executable: ./dgemmoptimized 18432 18432 18432 1 0 +m=18432, n=18432, k=18432, time(sec)=19.818314, speed(mflops)=631947.025738 +Executable: ./dgemmoptimized 18432 18432 18432 1 0 +m=18432, n=18432, k=18432, time(sec)=19.828331, speed(mflops)=631627.777403 +Max repetitions 3, Elasped time 192.458, Relative error 0.00727488, Mean 15061, Standard Deviation 64.9917 +Total Energy 15060.950000 +18460 +Executable: ./dgemmoptimized 18460 18460 18460 1 0 +m=18460, n=18460, k=18460, time(sec)=19.663543, speed(mflops)=639828.106309 +Executable: ./dgemmoptimized 18460 18460 18460 1 0 +m=18460, n=18460, k=18460, time(sec)=19.677505, speed(mflops)=639374.120935 +Executable: ./dgemmoptimized 18460 18460 18460 1 0 +m=18460, n=18460, k=18460, time(sec)=19.673840, speed(mflops)=639493.227689 +Max repetitions 3, Elasped time 192.343, Relative error 0.00242486, Mean 15146.6, Standard Deviation 21.7861 +Total Energy 15146.566667 +18489 +Executable: ./dgemmoptimized 18489 18489 18489 1 0 +m=18489, n=18489, k=18489, time(sec)=19.703311, speed(mflops)=641550.800768 +Executable: ./dgemmoptimized 18489 18489 18489 1 0 +m=18489, n=18489, k=18489, time(sec)=19.753846, speed(mflops)=639909.563589 +Executable: ./dgemmoptimized 18489 18489 18489 1 0 +m=18489, n=18489, k=18489, time(sec)=19.725206, speed(mflops)=640838.680900 +Max repetitions 3, Elasped time 194.863, Relative error 0.0169901, Mean 15238.6, Standard Deviation 153.575 +Total Energy 15238.583333 +18517 +Executable: ./dgemmoptimized 18517 18517 18517 1 0 +m=18517, n=18517, k=18517, time(sec)=19.868150, speed(mflops)=639122.997939 +Executable: ./dgemmoptimized 18517 18517 18517 1 0 +m=18517, n=18517, k=18517, time(sec)=19.860750, speed(mflops)=639361.132608 +Executable: ./dgemmoptimized 18517 18517 18517 1 0 +m=18517, n=18517, k=18517, time(sec)=19.893541, speed(mflops)=638307.253922 +Max repetitions 3, Elasped time 193.617, Relative error 0.00403263, Mean 15076.3, Standard Deviation 36.0631 +Total Energy 15076.300000 +18545 +Executable: ./dgemmoptimized 18545 18545 18545 1 0 +m=18545, n=18545, k=18545, time(sec)=20.097988, speed(mflops)=634684.545318 +Executable: ./dgemmoptimized 18545 18545 18545 1 0 +m=18545, n=18545, k=18545, time(sec)=20.081175, speed(mflops)=635215.944896 +Executable: ./dgemmoptimized 18545 18545 18545 1 0 +m=18545, n=18545, k=18545, time(sec)=20.108479, speed(mflops)=634353.420896 +Max repetitions 3, Elasped time 214.622, Relative error 0.235625, Mean 16417.2, Standard Deviation 2294.57 +Total Energy 16417.216667 +18574 +Executable: ./dgemmoptimized 18574 18574 18574 1 0 +m=18574, n=18574, k=18574, time(sec)=20.111255, speed(mflops)=637246.036551 +Executable: ./dgemmoptimized 18574 18574 18574 1 0 +m=18574, n=18574, k=18574, time(sec)=20.130317, speed(mflops)=636642.615405 +Executable: ./dgemmoptimized 18574 18574 18574 1 0 +m=18574, n=18574, k=18574, time(sec)=20.100713, speed(mflops)=637580.250867 +Max repetitions 3, Elasped time 195.074, Relative error 0.0025437, Mean 15120.8, Standard Deviation 22.815 +Total Energy 15120.766667 +18602 +Executable: ./dgemmoptimized 18602 18602 18602 1 0 +m=18602, n=18602, k=18602, time(sec)=20.340411, speed(mflops)=632920.544204 +Executable: ./dgemmoptimized 18602 18602 18602 1 0 +m=18602, n=18602, k=18602, time(sec)=20.184615, speed(mflops)=637805.768413 +Executable: ./dgemmoptimized 18602 18602 18602 1 0 +m=18602, n=18602, k=18602, time(sec)=20.201196, speed(mflops)=637282.267590 +Max repetitions 3, Elasped time 196.843, Relative error 0.0413326, Mean 15175.8, Standard Deviation 372.069 +Total Energy 15175.750000 +18630 +Executable: ./dgemmoptimized 18630 18630 18630 1 0 +m=18630, n=18630, k=18630, time(sec)=20.176367, speed(mflops)=640952.123121 +Executable: ./dgemmoptimized 18630 18630 18630 1 0 +m=18630, n=18630, k=18630, time(sec)=20.107018, speed(mflops)=643162.765255 +Executable: ./dgemmoptimized 18630 18630 18630 1 0 +m=18630, n=18630, k=18630, time(sec)=20.015907, speed(mflops)=646090.395116 +Max repetitions 3, Elasped time 199.582, Relative error 0.0180479, Mean 15252.8, Standard Deviation 163.289 +Total Energy 15252.833333 +18658 +Executable: ./dgemmoptimized 18658 18658 18658 1 0 +m=18658, n=18658, k=18658, time(sec)=20.458880, speed(mflops)=634955.673324 +Executable: ./dgemmoptimized 18658 18658 18658 1 0 +m=18658, n=18658, k=18658, time(sec)=20.463267, speed(mflops)=634819.544543 +Executable: ./dgemmoptimized 18658 18658 18658 1 0 +m=18658, n=18658, k=18658, time(sec)=20.263036, speed(mflops)=641092.572925 +Max repetitions 3, Elasped time 196.92, Relative error 0.0269933, Mean 15622, Standard Deviation 250.133 +Total Energy 15621.966667 +18686 +Executable: ./dgemmoptimized 18686 18686 18686 1 0 +m=18686, n=18686, k=18686, time(sec)=20.586697, speed(mflops)=633858.552507 +Executable: ./dgemmoptimized 18686 18686 18686 1 0 +m=18686, n=18686, k=18686, time(sec)=20.510098, speed(mflops)=636225.825840 +Executable: ./dgemmoptimized 18686 18686 18686 1 0 +m=18686, n=18686, k=18686, time(sec)=20.526953, speed(mflops)=635703.410886 +Max repetitions 3, Elasped time 201.529, Relative error 0.0187411, Mean 16000.4, Standard Deviation 177.871 +Total Energy 16000.433333 +18714 +Executable: ./dgemmoptimized 18714 18714 18714 1 0 +m=18714, n=18714, k=18714, time(sec)=20.650110, speed(mflops)=634757.003845 +Executable: ./dgemmoptimized 18714 18714 18714 1 0 +m=18714, n=18714, k=18714, time(sec)=20.705108, speed(mflops)=633070.931226 +Executable: ./dgemmoptimized 18714 18714 18714 1 0 +m=18714, n=18714, k=18714, time(sec)=20.665586, speed(mflops)=634281.648729 +Max repetitions 3, Elasped time 198.38, Relative error 0.00146234, Mean 15713.3, Standard Deviation 13.63 +Total Energy 15713.300000 +18742 +Executable: ./dgemmoptimized 18742 18742 18742 1 0 +m=18742, n=18742, k=18742, time(sec)=20.910639, speed(mflops)=629666.365964 +Executable: ./dgemmoptimized 18742 18742 18742 1 0 +m=18742, n=18742, k=18742, time(sec)=20.840136, speed(mflops)=631796.551965 +Executable: ./dgemmoptimized 18742 18742 18742 1 0 +m=18742, n=18742, k=18742, time(sec)=21.049307, speed(mflops)=625518.259649 +Max repetitions 3, Elasped time 200.602, Relative error 0.0185834, Mean 15817.6, Standard Deviation 174.359 +Total Energy 15817.550000 +18770 +Executable: ./dgemmoptimized 18770 18770 18770 1 0 +m=18770, n=18770, k=18770, time(sec)=21.354086, speed(mflops)=619358.101606 +Executable: ./dgemmoptimized 18770 18770 18770 1 0 +m=18770, n=18770, k=18770, time(sec)=21.092338, speed(mflops)=627044.112516 +Executable: ./dgemmoptimized 18770 18770 18770 1 0 +m=18770, n=18770, k=18770, time(sec)=21.360614, speed(mflops)=619168.822957 +Max repetitions 3, Elasped time 200.89, Relative error 0.00140467, Mean 15723.8, Standard Deviation 13.1011 +Total Energy 15723.750000 +18798 +Executable: ./dgemmoptimized 18798 18798 18798 1 0 +m=18798, n=18798, k=18798, time(sec)=20.907070, speed(mflops)=635435.918140 +Executable: ./dgemmoptimized 18798 18798 18798 1 0 +m=18798, n=18798, k=18798, time(sec)=20.809352, speed(mflops)=638419.842269 +Executable: ./dgemmoptimized 18798 18798 18798 1 0 +m=18798, n=18798, k=18798, time(sec)=20.814956, speed(mflops)=638247.959940 +Max repetitions 3, Elasped time 199.909, Relative error 0.000893468, Mean 15691.2, Standard Deviation 8.316 +Total Energy 15691.183333 +18826 +Executable: ./dgemmoptimized 18826 18826 18826 1 0 +m=18826, n=18826, k=18826, time(sec)=20.679373, speed(mflops)=645307.616979 +Executable: ./dgemmoptimized 18826 18826 18826 1 0 +m=18826, n=18826, k=18826, time(sec)=20.582180, speed(mflops)=648354.890857 +Executable: ./dgemmoptimized 18826 18826 18826 1 0 +m=18826, n=18826, k=18826, time(sec)=20.578208, speed(mflops)=648480.030313 +Max repetitions 3, Elasped time 199.554, Relative error 0.0039716, Mean 15713.8, Standard Deviation 37.0191 +Total Energy 15713.783333 +18854 +Executable: ./dgemmoptimized 18854 18854 18854 1 0 +m=18854, n=18854, k=18854, time(sec)=20.832022, speed(mflops)=643441.509298 +Executable: ./dgemmoptimized 18854 18854 18854 1 0 +m=18854, n=18854, k=18854, time(sec)=20.760291, speed(mflops)=645664.732515 +Executable: ./dgemmoptimized 18854 18854 18854 1 0 +m=18854, n=18854, k=18854, time(sec)=20.789406, speed(mflops)=644760.497740 +Max repetitions 3, Elasped time 200.719, Relative error 0.00336009, Mean 15628.2, Standard Deviation 31.1487 +Total Energy 15628.183333 +18882 +Executable: ./dgemmoptimized 18882 18882 18882 1 0 +m=18882, n=18882, k=18882, time(sec)=20.991492, speed(mflops)=641402.534974 +Executable: ./dgemmoptimized 18882 18882 18882 1 0 +m=18882, n=18882, k=18882, time(sec)=20.926092, speed(mflops)=643407.089810 +Executable: ./dgemmoptimized 18882 18882 18882 1 0 +m=18882, n=18882, k=18882, time(sec)=20.977709, speed(mflops)=641823.948205 +Max repetitions 3, Elasped time 201.267, Relative error 0.0128283, Mean 15659.4, Standard Deviation 119.159 +Total Energy 15659.450000 +18909 +Executable: ./dgemmoptimized 18909 18909 18909 1 0 +m=18909, n=18909, k=18909, time(sec)=21.232986, speed(mflops)=636831.604553 +Executable: ./dgemmoptimized 18909 18909 18909 1 0 +m=18909, n=18909, k=18909, time(sec)=21.148615, speed(mflops)=639372.197610 +Executable: ./dgemmoptimized 18909 18909 18909 1 0 +m=18909, n=18909, k=18909, time(sec)=21.220530, speed(mflops)=637205.409373 +Max repetitions 3, Elasped time 210.525, Relative error 0.0912116, Mean 16581.7, Standard Deviation 897.138 +Total Energy 16581.716667 +18937 +Executable: ./dgemmoptimized 18937 18937 18937 1 0 +m=18937, n=18937, k=18937, time(sec)=21.568385, speed(mflops)=629717.711262 +Executable: ./dgemmoptimized 18937 18937 18937 1 0 +m=18937, n=18937, k=18937, time(sec)=21.581371, speed(mflops)=629338.790502 +Executable: ./dgemmoptimized 18937 18937 18937 1 0 +m=18937, n=18937, k=18937, time(sec)=21.568618, speed(mflops)=629710.903529 +Max repetitions 3, Elasped time 203.758, Relative error 0.00435148, Mean 16361.1, Standard Deviation 42.2308 +Total Energy 16361.116667 +18965 +Executable: ./dgemmoptimized 18965 18965 18965 1 0 +m=18965, n=18965, k=18965, time(sec)=21.672171, speed(mflops)=629486.064935 +Executable: ./dgemmoptimized 18965 18965 18965 1 0 +m=18965, n=18965, k=18965, time(sec)=21.638253, speed(mflops)=630472.782665 +Executable: ./dgemmoptimized 18965 18965 18965 1 0 +m=18965, n=18965, k=18965, time(sec)=21.657464, speed(mflops)=629913.527594 +Max repetitions 3, Elasped time 207.516, Relative error 0.0358049, Mean 16423.4, Standard Deviation 348.807 +Total Energy 16423.400000 +18992 +Executable: ./dgemmoptimized 18992 18992 18992 1 0 +m=18992, n=18992, k=18992, time(sec)=21.655791, speed(mflops)=632656.614475 +Executable: ./dgemmoptimized 18992 18992 18992 1 0 +m=18992, n=18992, k=18992, time(sec)=21.653606, speed(mflops)=632720.450083 +Executable: ./dgemmoptimized 18992 18992 18992 1 0 +m=18992, n=18992, k=18992, time(sec)=21.612793, speed(mflops)=633915.260965 +Max repetitions 3, Elasped time 204.683, Relative error 0.00153364, Mean 16245.3, Standard Deviation 14.7784 +Total Energy 16245.250000 +19020 +Executable: ./dgemmoptimized 19020 19020 19020 1 0 +m=19020, n=19020, k=19020, time(sec)=21.678483, speed(mflops)=634793.754253 +Executable: ./dgemmoptimized 19020 19020 19020 1 0 +m=19020, n=19020, k=19020, time(sec)=21.717878, speed(mflops)=633642.271615 +Executable: ./dgemmoptimized 19020 19020 19020 1 0 +m=19020, n=19020, k=19020, time(sec)=21.691546, speed(mflops)=634411.472529 +Max repetitions 3, Elasped time 205.137, Relative error 0.00621034, Mean 16262.3, Standard Deviation 59.9069 +Total Energy 16262.300000 +19048 +Executable: ./dgemmoptimized 19048 19048 19048 1 0 +m=19048, n=19048, k=19048, time(sec)=21.808433, speed(mflops)=633802.116497 +Executable: ./dgemmoptimized 19048 19048 19048 1 0 +m=19048, n=19048, k=19048, time(sec)=21.845521, speed(mflops)=632726.081202 +Executable: ./dgemmoptimized 19048 19048 19048 1 0 +m=19048, n=19048, k=19048, time(sec)=21.858113, speed(mflops)=632361.578755 +Max repetitions 3, Elasped time 205.942, Relative error 0.00209897, Mean 16294.9, Standard Deviation 20.2879 +Total Energy 16294.883333 +19075 +Executable: ./dgemmoptimized 19075 19075 19075 1 0 +m=19075, n=19075, k=19075, time(sec)=22.004375, speed(mflops)=630833.282281 +Executable: ./dgemmoptimized 19075 19075 19075 1 0 +m=19075, n=19075, k=19075, time(sec)=21.979586, speed(mflops)=631544.744072 +Executable: ./dgemmoptimized 19075 19075 19075 1 0 +m=19075, n=19075, k=19075, time(sec)=21.987388, speed(mflops)=631320.646598 +Max repetitions 3, Elasped time 208.735, Relative error 0.0181957, Mean 16352.1, Standard Deviation 176.491 +Total Energy 16352.083333 +19102 +Executable: ./dgemmoptimized 19102 19102 19102 1 0 +m=19102, n=19102, k=19102, time(sec)=21.999447, speed(mflops)=633657.757920 +Executable: ./dgemmoptimized 19102 19102 19102 1 0 +m=19102, n=19102, k=19102, time(sec)=21.981139, speed(mflops)=634185.526671 +Executable: ./dgemmoptimized 19102 19102 19102 1 0 +m=19102, n=19102, k=19102, time(sec)=22.004502, speed(mflops)=633512.184991 +Max repetitions 3, Elasped time 207.076, Relative error 0.00340476, Mean 16266.5, Standard Deviation 32.8518 +Total Energy 16266.466667 +19130 +Executable: ./dgemmoptimized 19130 19130 19130 1 0 +m=19130, n=19130, k=19130, time(sec)=22.333414, speed(mflops)=626931.061469 +Executable: ./dgemmoptimized 19130 19130 19130 1 0 +m=19130, n=19130, k=19130, time(sec)=22.346929, speed(mflops)=626551.912231 +Executable: ./dgemmoptimized 19130 19130 19130 1 0 +m=19130, n=19130, k=19130, time(sec)=22.530569, speed(mflops)=621445.072896 +Max repetitions 3, Elasped time 208.606, Relative error 0.023768, Mean 16731.7, Standard Deviation 235.892 +Total Energy 16731.716667 +19157 +Executable: ./dgemmoptimized 19157 19157 19157 1 0 +m=19157, n=19157, k=19157, time(sec)=22.458170, speed(mflops)=626091.964089 +Executable: ./dgemmoptimized 19157 19157 19157 1 0 +m=19157, n=19157, k=19157, time(sec)=22.400776, speed(mflops)=627696.095572 +Executable: ./dgemmoptimized 19157 19157 19157 1 0 +m=19157, n=19157, k=19157, time(sec)=22.440378, speed(mflops)=626588.364808 +Max repetitions 3, Elasped time 210.973, Relative error 0.0301336, Mean 17094.1, Standard Deviation 305.547 +Total Energy 17094.116667 +19185 +Executable: ./dgemmoptimized 19185 19185 19185 1 0 +m=19185, n=19185, k=19185, time(sec)=22.142922, speed(mflops)=637794.070780 +Executable: ./dgemmoptimized 19185 19185 19185 1 0 +m=19185, n=19185, k=19185, time(sec)=22.202030, speed(mflops)=636096.084422 +Executable: ./dgemmoptimized 19185 19185 19185 1 0 +m=19185, n=19185, k=19185, time(sec)=22.176657, speed(mflops)=636823.861135 +Max repetitions 3, Elasped time 230.021, Relative error 0.237514, Mean 18092.7, Standard Deviation 2549.01 +Total Energy 18092.716667 +19212 +Executable: ./dgemmoptimized 19212 19212 19212 1 0 +m=19212, n=19212, k=19212, time(sec)=22.222390, speed(mflops)=638200.243665 +Executable: ./dgemmoptimized 19212 19212 19212 1 0 +m=19212, n=19212, k=19212, time(sec)=22.203368, speed(mflops)=638747.000236 +Executable: ./dgemmoptimized 19212 19212 19212 1 0 +m=19212, n=19212, k=19212, time(sec)=22.200525, speed(mflops)=638828.795412 +Max repetitions 3, Elasped time 209.047, Relative error 0.00311804, Mean 16946.2, Standard Deviation 31.3426 +Total Energy 16946.250000 +19239 +Executable: ./dgemmoptimized 19239 19239 19239 1 0 +m=19239, n=19239, k=19239, time(sec)=22.276219, speed(mflops)=639346.074279 +Executable: ./dgemmoptimized 19239 19239 19239 1 0 +m=19239, n=19239, k=19239, time(sec)=22.265107, speed(mflops)=639665.149545 +Executable: ./dgemmoptimized 19239 19239 19239 1 0 +m=19239, n=19239, k=19239, time(sec)=22.277091, speed(mflops)=639321.044252 +Max repetitions 3, Elasped time 210.25, Relative error 0.00845341, Mean 16882, Standard Deviation 84.6517 +Total Energy 16881.983333 +19266 +Executable: ./dgemmoptimized 19266 19266 19266 1 0 +m=19266, n=19266, k=19266, time(sec)=22.319216, speed(mflops)=640804.765305 +Executable: ./dgemmoptimized 19266 19266 19266 1 0 +m=19266, n=19266, k=19266, time(sec)=22.310454, speed(mflops)=641056.418787 +Executable: ./dgemmoptimized 19266 19266 19266 1 0 +m=19266, n=19266, k=19266, time(sec)=22.317378, speed(mflops)=640857.532543 +Max repetitions 3, Elasped time 210.051, Relative error 0.00187465, Mean 16952.6, Standard Deviation 18.851 +Total Energy 16952.566667 +19294 +Executable: ./dgemmoptimized 19294 19294 19294 1 0 +m=19294, n=19294, k=19294, time(sec)=22.511834, speed(mflops)=638095.882736 +Executable: ./dgemmoptimized 19294 19294 19294 1 0 +m=19294, n=19294, k=19294, time(sec)=22.515395, speed(mflops)=637994.961915 +Executable: ./dgemmoptimized 19294 19294 19294 1 0 +m=19294, n=19294, k=19294, time(sec)=22.506523, speed(mflops)=638246.458419 +Max repetitions 3, Elasped time 211.022, Relative error 0.0041519, Mean 16885.3, Standard Deviation 41.5849 +Total Energy 16885.283333 +19321 +Executable: ./dgemmoptimized 19321 19321 19321 1 0 +m=19321, n=19321, k=19321, time(sec)=22.933340, speed(mflops)=629001.224008 +Executable: ./dgemmoptimized 19321 19321 19321 1 0 +m=19321, n=19321, k=19321, time(sec)=22.908640, speed(mflops)=629679.408483 +Executable: ./dgemmoptimized 19321 19321 19321 1 0 +m=19321, n=19321, k=19321, time(sec)=22.912623, speed(mflops)=629569.948027 +Max repetitions 3, Elasped time 215.701, Relative error 0.0592902, Mean 17221.5, Standard Deviation 605.666 +Total Energy 17221.466667 +19348 +Executable: ./dgemmoptimized 19348 19348 19348 1 0 +m=19348, n=19348, k=19348, time(sec)=23.133755, speed(mflops)=626169.775033 +Executable: ./dgemmoptimized 19348 19348 19348 1 0 +m=19348, n=19348, k=19348, time(sec)=23.132170, speed(mflops)=626212.679927 +Executable: ./dgemmoptimized 19348 19348 19348 1 0 +m=19348, n=19348, k=19348, time(sec)=23.114253, speed(mflops)=626698.092564 +Max repetitions 3, Elasped time 213.505, Relative error 0.00194514, Mean 16814.5, Standard Deviation 19.4006 +Total Energy 16814.500000 +19375 +Executable: ./dgemmoptimized 19375 19375 19375 1 0 +m=19375, n=19375, k=19375, time(sec)=22.991445, speed(mflops)=632686.926721 +Executable: ./dgemmoptimized 19375 19375 19375 1 0 +m=19375, n=19375, k=19375, time(sec)=22.963760, speed(mflops)=633449.689058 +Executable: ./dgemmoptimized 19375 19375 19375 1 0 +m=19375, n=19375, k=19375, time(sec)=23.007626, speed(mflops)=632241.965465 +Max repetitions 3, Elasped time 214.76, Relative error 0.0360107, Mean 17197.8, Standard Deviation 367.355 +Total Energy 17197.850000 +19402 +Executable: ./dgemmoptimized 19402 19402 19402 1 0 +m=19402, n=19402, k=19402, time(sec)=22.859562, speed(mflops)=639001.081326 +Executable: ./dgemmoptimized 19402 19402 19402 1 0 +m=19402, n=19402, k=19402, time(sec)=22.965418, speed(mflops)=636055.686937 +Executable: ./dgemmoptimized 19402 19402 19402 1 0 +m=19402, n=19402, k=19402, time(sec)=23.030937, speed(mflops)=634246.223385 +Max repetitions 3, Elasped time 213.642, Relative error 0.00113414, Mean 16738.6, Standard Deviation 11.2607 +Total Energy 16738.633333 +19429 +Executable: ./dgemmoptimized 19429 19429 19429 1 0 +m=19429, n=19429, k=19429, time(sec)=23.156325, speed(mflops)=633449.069171 +Executable: ./dgemmoptimized 19429 19429 19429 1 0 +m=19429, n=19429, k=19429, time(sec)=23.137411, speed(mflops)=633966.890533 +Executable: ./dgemmoptimized 19429 19429 19429 1 0 +m=19429, n=19429, k=19429, time(sec)=23.134084, speed(mflops)=634058.067303 +Max repetitions 3, Elasped time 214.548, Relative error 0.000970407, Mean 17159.7, Standard Deviation 9.87742 +Total Energy 17159.683333 +19456 +Executable: ./dgemmoptimized 19456 19456 19456 1 0 +m=19456, n=19456, k=19456, time(sec)=24.175032, speed(mflops)=609289.385938 +Executable: ./dgemmoptimized 19456 19456 19456 1 0 +m=19456, n=19456, k=19456, time(sec)=24.213273, speed(mflops)=608327.106880 +Executable: ./dgemmoptimized 19456 19456 19456 1 0 +m=19456, n=19456, k=19456, time(sec)=24.209862, speed(mflops)=608412.817281 +Max repetitions 3, Elasped time 218.047, Relative error 0.00355701, Mean 17398.2, Standard Deviation 36.7086 +Total Energy 17398.166667 +19483 +Executable: ./dgemmoptimized 19483 19483 19483 1 0 +m=19483, n=19483, k=19483, time(sec)=23.505939, speed(mflops)=629245.157953 +Executable: ./dgemmoptimized 19483 19483 19483 1 0 +m=19483, n=19483, k=19483, time(sec)=23.540721, speed(mflops)=628315.434396 +Executable: ./dgemmoptimized 19483 19483 19483 1 0 +m=19483, n=19483, k=19483, time(sec)=23.519964, speed(mflops)=628869.938573 +Max repetitions 3, Elasped time 216.363, Relative error 0.00258637, Mean 17551.3, Standard Deviation 26.9266 +Total Energy 17551.350000 +19510 +Executable: ./dgemmoptimized 19510 19510 19510 1 0 +m=19510, n=19510, k=19510, time(sec)=23.608739, speed(mflops)=629113.514508 +Executable: ./dgemmoptimized 19510 19510 19510 1 0 +m=19510, n=19510, k=19510, time(sec)=23.624777, speed(mflops)=628686.433843 +Executable: ./dgemmoptimized 19510 19510 19510 1 0 +m=19510, n=19510, k=19510, time(sec)=23.599300, speed(mflops)=629365.140496 +Max repetitions 3, Elasped time 216.968, Relative error 0.0020325, Mean 17482.8, Standard Deviation 21.0776 +Total Energy 17482.783333 +19537 +Executable: ./dgemmoptimized 19537 19537 19537 1 0 +m=19537, n=19537, k=19537, time(sec)=23.948564, speed(mflops)=622764.934467 +Executable: ./dgemmoptimized 19537 19537 19537 1 0 +m=19537, n=19537, k=19537, time(sec)=23.934841, speed(mflops)=623121.986776 +Executable: ./dgemmoptimized 19537 19537 19537 1 0 +m=19537, n=19537, k=19537, time(sec)=23.980676, speed(mflops)=621931.000372 +Max repetitions 3, Elasped time 218.358, Relative error 0.0031986, Mean 17432.9, Standard Deviation 33.0756 +Total Energy 17432.850000 +19563 +Executable: ./dgemmoptimized 19563 19563 19563 1 0 +m=19563, n=19563, k=19563, time(sec)=23.480802, speed(mflops)=637710.308507 +Executable: ./dgemmoptimized 19563 19563 19563 1 0 +m=19563, n=19563, k=19563, time(sec)=23.459482, speed(mflops)=638289.856617 +Executable: ./dgemmoptimized 19563 19563 19563 1 0 +m=19563, n=19563, k=19563, time(sec)=23.462725, speed(mflops)=638201.633508 +Max repetitions 3, Elasped time 217.208, Relative error 0.00928242, Mean 17466.8, Standard Deviation 96.1731 +Total Energy 17466.750000 +19590 +Executable: ./dgemmoptimized 19590 19590 19590 1 0 +m=19590, n=19590, k=19590, time(sec)=23.194106, speed(mflops)=648269.611766 +Executable: ./dgemmoptimized 19590 19590 19590 1 0 +m=19590, n=19590, k=19590, time(sec)=23.087937, speed(mflops)=651250.654489 +Executable: ./dgemmoptimized 19590 19590 19590 1 0 +m=19590, n=19590, k=19590, time(sec)=23.162682, speed(mflops)=649149.097733 +Max repetitions 3, Elasped time 220.358, Relative error 0.0179732, Mean 17703.9, Standard Deviation 188.744 +Total Energy 17703.866667 +19617 +Executable: ./dgemmoptimized 19617 19617 19617 1 0 +m=19617, n=19617, k=19617, time(sec)=23.367484, speed(mflops)=646123.915451 +Executable: ./dgemmoptimized 19617 19617 19617 1 0 +m=19617, n=19617, k=19617, time(sec)=23.377687, speed(mflops)=645841.923148 +Executable: ./dgemmoptimized 19617 19617 19617 1 0 +m=19617, n=19617, k=19617, time(sec)=23.347759, speed(mflops)=646669.785772 +Max repetitions 3, Elasped time 219.478, Relative error 0.0200007, Mean 17588.2, Standard Deviation 208.664 +Total Energy 17588.233333 +19644 +Executable: ./dgemmoptimized 19644 19644 19644 1 0 +m=19644, n=19644, k=19644, time(sec)=23.614934, speed(mflops)=641997.055964 +Executable: ./dgemmoptimized 19644 19644 19644 1 0 +m=19644, n=19644, k=19644, time(sec)=23.635705, speed(mflops)=641432.869791 +Executable: ./dgemmoptimized 19644 19644 19644 1 0 +m=19644, n=19644, k=19644, time(sec)=23.581979, speed(mflops)=642894.222771 +Max repetitions 3, Elasped time 218.674, Relative error 0.00292161, Mean 17457.2, Standard Deviation 30.2535 +Total Energy 17457.166667 +19670 +Executable: ./dgemmoptimized 19670 19670 19670 1 0 +m=19670, n=19670, k=19670, time(sec)=23.571472, speed(mflops)=645738.041794 +Executable: ./dgemmoptimized 19670 19670 19670 1 0 +m=19670, n=19670, k=19670, time(sec)=23.540390, speed(mflops)=646590.658468 +Executable: ./dgemmoptimized 19670 19670 19670 1 0 +m=19670, n=19670, k=19670, time(sec)=23.743065, speed(mflops)=641071.243443 +Max repetitions 3, Elasped time 219.01, Relative error 0.00202549, Mean 17411.6, Standard Deviation 20.9194 +Total Energy 17411.633333 +19697 +Executable: ./dgemmoptimized 19697 19697 19697 1 0 +m=19697, n=19697, k=19697, time(sec)=23.931133, speed(mflops)=638655.989393 +Executable: ./dgemmoptimized 19697 19697 19697 1 0 +m=19697, n=19697, k=19697, time(sec)=23.941206, speed(mflops)=638387.283311 +Executable: ./dgemmoptimized 19697 19697 19697 1 0 +m=19697, n=19697, k=19697, time(sec)=24.006779, speed(mflops)=636643.569389 +Max repetitions 3, Elasped time 222.381, Relative error 0.0518354, Mean 17685.3, Standard Deviation 543.774 +Total Energy 17685.266667 +19724 +Executable: ./dgemmoptimized 19724 19724 19724 1 0 +m=19724, n=19724, k=19724, time(sec)=24.264772, speed(mflops)=632468.294327 +Executable: ./dgemmoptimized 19724 19724 19724 1 0 +m=19724, n=19724, k=19724, time(sec)=24.181780, speed(mflops)=634638.930942 +Executable: ./dgemmoptimized 19724 19724 19724 1 0 +m=19724, n=19724, k=19724, time(sec)=24.341607, speed(mflops)=630471.891675 +Max repetitions 3, Elasped time 221.633, Relative error 0.00461386, Mean 18167.2, Standard Deviation 49.7201 +Total Energy 18167.183333 +19750 +Executable: ./dgemmoptimized 19750 19750 19750 1 0 +m=19750, n=19750, k=19750, time(sec)=23.986793, speed(mflops)=642331.333060 +Executable: ./dgemmoptimized 19750 19750 19750 1 0 +m=19750, n=19750, k=19750, time(sec)=24.170501, speed(mflops)=637449.292176 +Executable: ./dgemmoptimized 19750 19750 19750 1 0 +m=19750, n=19750, k=19750, time(sec)=24.178198, speed(mflops)=637246.367110 +Max repetitions 3, Elasped time 223.505, Relative error 0.0131936, Mean 18169.3, Standard Deviation 142.195 +Total Energy 18169.350000 +19777 +Executable: ./dgemmoptimized 19777 19777 19777 1 0 +m=19777, n=19777, k=19777, time(sec)=24.071555, speed(mflops)=642698.205928 +Executable: ./dgemmoptimized 19777 19777 19777 1 0 +m=19777, n=19777, k=19777, time(sec)=24.095151, speed(mflops)=642068.826816 +Executable: ./dgemmoptimized 19777 19777 19777 1 0 +m=19777, n=19777, k=19777, time(sec)=24.115887, speed(mflops)=641516.745700 +Max repetitions 3, Elasped time 224.111, Relative error 0.017367, Mean 18073.8, Standard Deviation 186.19 +Total Energy 18073.850000 +19803 +Executable: ./dgemmoptimized 19803 19803 19803 1 0 +m=19803, n=19803, k=19803, time(sec)=24.320530, speed(mflops)=638630.894516 +Executable: ./dgemmoptimized 19803 19803 19803 1 0 +m=19803, n=19803, k=19803, time(sec)=24.339119, speed(mflops)=638143.139707 +Executable: ./dgemmoptimized 19803 19803 19803 1 0 +m=19803, n=19803, k=19803, time(sec)=24.305671, speed(mflops)=639021.313346 +Max repetitions 3, Elasped time 225.502, Relative error 0.0186049, Mean 18117.5, Standard Deviation 199.943 +Total Energy 18117.450000 +19830 +Executable: ./dgemmoptimized 19830 19830 19830 1 0 +m=19830, n=19830, k=19830, time(sec)=24.278166, speed(mflops)=642365.578118 +Executable: ./dgemmoptimized 19830 19830 19830 1 0 +m=19830, n=19830, k=19830, time(sec)=24.519110, speed(mflops)=636053.192659 +Executable: ./dgemmoptimized 19830 19830 19830 1 0 +m=19830, n=19830, k=19830, time(sec)=24.510254, speed(mflops)=636283.011741 +Max repetitions 3, Elasped time 223.518, Relative error 0.000272121, Mean 18036.4, Standard Deviation 2.91133 +Total Energy 18036.366667 +19856 +Executable: ./dgemmoptimized 19856 19856 19856 1 0 +m=19856, n=19856, k=19856, time(sec)=24.735298, speed(mflops)=632977.304289 +Executable: ./dgemmoptimized 19856 19856 19856 1 0 +m=19856, n=19856, k=19856, time(sec)=24.724077, speed(mflops)=633264.584830 +Executable: ./dgemmoptimized 19856 19856 19856 1 0 +m=19856, n=19856, k=19856, time(sec)=24.739065, speed(mflops)=632880.927034 +Max repetitions 3, Elasped time 228.704, Relative error 0.0289432, Mean 18292.2, Standard Deviation 314.045 +Total Energy 18292.233333 +19882 +Executable: ./dgemmoptimized 19882 19882 19882 1 0 +m=19882, n=19882, k=19882, time(sec)=24.691260, speed(mflops)=636600.468442 +Executable: ./dgemmoptimized 19882 19882 19882 1 0 +m=19882, n=19882, k=19882, time(sec)=24.832773, speed(mflops)=632972.709604 +Executable: ./dgemmoptimized 19882 19882 19882 1 0 +m=19882, n=19882, k=19882, time(sec)=24.897742, speed(mflops)=631321.007869 +Max repetitions 3, Elasped time 225.31, Relative error 0.000308681, Mean 17975.2, Standard Deviation 3.29128 +Total Energy 17975.250000 +19909 +Executable: ./dgemmoptimized 19909 19909 19909 1 0 +m=19909, n=19909, k=19909, time(sec)=25.072340, speed(mflops)=629482.218475 +Executable: ./dgemmoptimized 19909 19909 19909 1 0 +m=19909, n=19909, k=19909, time(sec)=24.985701, speed(mflops)=631664.973487 +Executable: ./dgemmoptimized 19909 19909 19909 1 0 +m=19909, n=19909, k=19909, time(sec)=24.992933, speed(mflops)=631482.195020 +Max repetitions 3, Elasped time 230.15, Relative error 0.0300632, Mean 18291.5, Standard Deviation 326.184 +Total Energy 18291.466667 +19935 +Executable: ./dgemmoptimized 19935 19935 19935 1 0 +m=19935, n=19935, k=19935, time(sec)=24.929435, speed(mflops)=635574.229476 +Executable: ./dgemmoptimized 19935 19935 19935 1 0 +m=19935, n=19935, k=19935, time(sec)=25.007927, speed(mflops)=633579.364183 +Executable: ./dgemmoptimized 19935 19935 19935 1 0 +m=19935, n=19935, k=19935, time(sec)=24.931126, speed(mflops)=635531.117846 +Max repetitions 3, Elasped time 226.405, Relative error 0.0203458, Mean 18115.1, Standard Deviation 218.623 +Total Energy 18115.066667 +19961 +Executable: ./dgemmoptimized 19961 19961 19961 1 0 +m=19961, n=19961, k=19961, time(sec)=24.575958, speed(mflops)=647241.606895 +Executable: ./dgemmoptimized 19961 19961 19961 1 0 +m=19961, n=19961, k=19961, time(sec)=24.696664, speed(mflops)=644078.177531 +Executable: ./dgemmoptimized 19961 19961 19961 1 0 +m=19961, n=19961, k=19961, time(sec)=24.662707, speed(mflops)=644964.986887 +Max repetitions 3, Elasped time 225.78, Relative error 0.00165206, Mean 18031, Standard Deviation 17.6695 +Total Energy 18030.966667 +19988 +Executable: ./dgemmoptimized 19988 19988 19988 1 0 +m=19988, n=19988, k=19988, time(sec)=24.853121, speed(mflops)=642624.216194 +Executable: ./dgemmoptimized 19988 19988 19988 1 0 +m=19988, n=19988, k=19988, time(sec)=24.817770, speed(mflops)=643539.579656 +Executable: ./dgemmoptimized 19988 19988 19988 1 0 +m=19988, n=19988, k=19988, time(sec)=24.843216, speed(mflops)=642880.427139 +Max repetitions 3, Elasped time 228.711, Relative error 0.0285723, Mean 18676.2, Standard Deviation 316.53 +Total Energy 18676.216667 +20014 +Executable: ./dgemmoptimized 20014 20014 20014 1 0 +m=20014, n=20014, k=20014, time(sec)=25.046083, speed(mflops)=640164.912911 +Executable: ./dgemmoptimized 20014 20014 20014 1 0 +m=20014, n=20014, k=20014, time(sec)=24.712335, speed(mflops)=648810.541550 +Executable: ./dgemmoptimized 20014 20014 20014 1 0 +m=20014, n=20014, k=20014, time(sec)=24.742617, speed(mflops)=648016.480858 +Max repetitions 3, Elasped time 227.043, Relative error 0.0162392, Mean 18598.6, Standard Deviation 179.153 +Total Energy 18598.566667 +20040 +Executable: ./dgemmoptimized 20040 20040 20040 1 0 +m=20040, n=20040, k=20040, time(sec)=25.179036, speed(mflops)=639269.596764 +Executable: ./dgemmoptimized 20040 20040 20040 1 0 +m=20040, n=20040, k=20040, time(sec)=25.137694, speed(mflops)=640320.947932 +Executable: ./dgemmoptimized 20040 20040 20040 1 0 +m=20040, n=20040, k=20040, time(sec)=25.168860, speed(mflops)=639528.057864 +Max repetitions 3, Elasped time 228.34, Relative error 0.0035036, Mean 18728.2, Standard Deviation 38.9216 +Total Energy 18728.216667 +20066 +Executable: ./dgemmoptimized 20066 20066 20066 1 0 +m=20066, n=20066, k=20066, time(sec)=25.449494, speed(mflops)=634940.850611 +Executable: ./dgemmoptimized 20066 20066 20066 1 0 +m=20066, n=20066, k=20066, time(sec)=25.137506, speed(mflops)=642821.260381 +Executable: ./dgemmoptimized 20066 20066 20066 1 0 +m=20066, n=20066, k=20066, time(sec)=25.261805, speed(mflops)=639658.300672 +Max repetitions 3, Elasped time 229.104, Relative error 0.00757128, Mean 18740.8, Standard Deviation 84.1661 +Total Energy 18740.800000 +20092 +Executable: ./dgemmoptimized 20092 20092 20092 1 0 +m=20092, n=20092, k=20092, time(sec)=25.708880, speed(mflops)=630981.095653 +Executable: ./dgemmoptimized 20092 20092 20092 1 0 +m=20092, n=20092, k=20092, time(sec)=25.678086, speed(mflops)=631737.786476 +Executable: ./dgemmoptimized 20092 20092 20092 1 0 +m=20092, n=20092, k=20092, time(sec)=25.707910, speed(mflops)=631004.906638 +Max repetitions 3, Elasped time 232.508, Relative error 0.0186797, Mean 18756.3, Standard Deviation 207.825 +Total Energy 18756.300000 +20118 +Executable: ./dgemmoptimized 20118 20118 20118 1 0 +m=20118, n=20118, k=20118, time(sec)=25.613654, speed(mflops)=635788.789806 +Executable: ./dgemmoptimized 20118 20118 20118 1 0 +m=20118, n=20118, k=20118, time(sec)=25.497453, speed(mflops)=638686.310451 +Executable: ./dgemmoptimized 20118 20118 20118 1 0 +m=20118, n=20118, k=20118, time(sec)=25.758602, speed(mflops)=632211.098882 +Max repetitions 3, Elasped time 234.04, Relative error 0.0228788, Mean 18933.4, Standard Deviation 256.945 +Total Energy 18933.383333 +20144 +Executable: ./dgemmoptimized 20144 20144 20144 1 0 +m=20144, n=20144, k=20144, time(sec)=25.774796, speed(mflops)=634266.679985 +Executable: ./dgemmoptimized 20144 20144 20144 1 0 +m=20144, n=20144, k=20144, time(sec)=25.741630, speed(mflops)=635083.885296 +Executable: ./dgemmoptimized 20144 20144 20144 1 0 +m=20144, n=20144, k=20144, time(sec)=25.869739, speed(mflops)=631938.894196 +Max repetitions 3, Elasped time 235.48, Relative error 0.0228941, Mean 18954.1, Standard Deviation 257.4 +Total Energy 18954.133333 +20170 +Executable: ./dgemmoptimized 20170 20170 20170 1 0 +m=20170, n=20170, k=20170, time(sec)=25.533747, speed(mflops)=642736.761398 +Executable: ./dgemmoptimized 20170 20170 20170 1 0 +m=20170, n=20170, k=20170, time(sec)=25.611109, speed(mflops)=640795.282011 +Executable: ./dgemmoptimized 20170 20170 20170 1 0 +m=20170, n=20170, k=20170, time(sec)=25.732781, speed(mflops)=637765.419466 +Max repetitions 3, Elasped time 231.428, Relative error 0.00574969, Mean 18638.2, Standard Deviation 63.5664 +Total Energy 18638.166667 +20196 +Executable: ./dgemmoptimized 20196 20196 20196 1 0 +m=20196, n=20196, k=20196, time(sec)=25.993835, speed(mflops)=633805.092499 +Executable: ./dgemmoptimized 20196 20196 20196 1 0 +m=20196, n=20196, k=20196, time(sec)=25.991018, speed(mflops)=633873.790328 +Executable: ./dgemmoptimized 20196 20196 20196 1 0 +m=20196, n=20196, k=20196, time(sec)=25.973383, speed(mflops)=634304.164802 +Max repetitions 3, Elasped time 235.137, Relative error 0.0161657, Mean 19415.3, Standard Deviation 186.173 +Total Energy 19415.300000 +20222 +Executable: ./dgemmoptimized 20222 20222 20222 1 0 +m=20222, n=20222, k=20222, time(sec)=25.961162, speed(mflops)=637056.848860 +Executable: ./dgemmoptimized 20222 20222 20222 1 0 +m=20222, n=20222, k=20222, time(sec)=26.118913, speed(mflops)=633209.194124 +Executable: ./dgemmoptimized 20222 20222 20222 1 0 +m=20222, n=20222, k=20222, time(sec)=26.044170, speed(mflops)=635026.419495 +Max repetitions 3, Elasped time 233.322, Relative error 0.0110428, Mean 19371, Standard Deviation 126.885 +Total Energy 19370.983333 +20248 +Executable: ./dgemmoptimized 20248 20248 20248 1 0 +m=20248, n=20248, k=20248, time(sec)=26.245572, speed(mflops)=632587.124752 +Executable: ./dgemmoptimized 20248 20248 20248 1 0 +m=20248, n=20248, k=20248, time(sec)=26.278407, speed(mflops)=631796.709573 +Executable: ./dgemmoptimized 20248 20248 20248 1 0 +m=20248, n=20248, k=20248, time(sec)=26.350807, speed(mflops)=630060.812419 +Max repetitions 3, Elasped time 234.416, Relative error 0.00195817, Mean 19259.9, Standard Deviation 22.3709 +Total Energy 19259.883333 +20274 +Executable: ./dgemmoptimized 20274 20274 20274 1 0 +m=20274, n=20274, k=20274, time(sec)=26.290138, speed(mflops)=633950.657000 +Executable: ./dgemmoptimized 20274 20274 20274 1 0 +m=20274, n=20274, k=20274, time(sec)=26.295537, speed(mflops)=633820.494514 +Executable: ./dgemmoptimized 20274 20274 20274 1 0 +m=20274, n=20274, k=20274, time(sec)=26.321346, speed(mflops)=633199.010166 +Max repetitions 3, Elasped time 236.791, Relative error 0.0207695, Mean 19419, Standard Deviation 239.24 +Total Energy 19419.050000 +20300 +Executable: ./dgemmoptimized 20300 20300 20300 1 0 +m=20300, n=20300, k=20300, time(sec)=26.721330, speed(mflops)=626123.551688 +Executable: ./dgemmoptimized 20300 20300 20300 1 0 +m=20300, n=20300, k=20300, time(sec)=26.778673, speed(mflops)=624782.790450 +Executable: ./dgemmoptimized 20300 20300 20300 1 0 +m=20300, n=20300, k=20300, time(sec)=26.727250, speed(mflops)=625984.863310 +Max repetitions 3, Elasped time 236.491, Relative error 0.00418323, Mean 19230.8, Standard Deviation 47.7186 +Total Energy 19230.750000 +20326 +Executable: ./dgemmoptimized 20326 20326 20326 1 0 +m=20326, n=20326, k=20326, time(sec)=26.225966, speed(mflops)=640404.339229 +Executable: ./dgemmoptimized 20326 20326 20326 1 0 +m=20326, n=20326, k=20326, time(sec)=26.256095, speed(mflops)=639669.473130 +Executable: ./dgemmoptimized 20326 20326 20326 1 0 +m=20326, n=20326, k=20326, time(sec)=26.251246, speed(mflops)=639787.628657 +Max repetitions 3, Elasped time 237.266, Relative error 0.0114329, Mean 19323.8, Standard Deviation 131.047 +Total Energy 19323.750000 +20352 +Executable: ./dgemmoptimized 20352 20352 20352 1 0 +m=20352, n=20352, k=20352, time(sec)=26.057865, speed(mflops)=647012.163737 +Executable: ./dgemmoptimized 20352 20352 20352 1 0 +m=20352, n=20352, k=20352, time(sec)=26.148770, speed(mflops)=644762.856833 +Executable: ./dgemmoptimized 20352 20352 20352 1 0 +m=20352, n=20352, k=20352, time(sec)=26.027453, speed(mflops)=647768.175533 +Max repetitions 3, Elasped time 235.128, Relative error 0.00474804, Mean 19284.1, Standard Deviation 54.3117 +Total Energy 19284.116667 +20377 +Executable: ./dgemmoptimized 20377 20377 20377 1 0 +m=20377, n=20377, k=20377, time(sec)=26.463745, speed(mflops)=639439.456615 +Executable: ./dgemmoptimized 20377 20377 20377 1 0 +m=20377, n=20377, k=20377, time(sec)=26.471113, speed(mflops)=639261.472181 +Executable: ./dgemmoptimized 20377 20377 20377 1 0 +m=20377, n=20377, k=20377, time(sec)=26.464577, speed(mflops)=639419.351803 +Max repetitions 3, Elasped time 238.613, Relative error 0.0230364, Mean 19368, Standard Deviation 264.654 +Total Energy 19367.950000 +20403 +Executable: ./dgemmoptimized 20403 20403 20403 1 0 +m=20403, n=20403, k=20403, time(sec)=26.504866, speed(mflops)=640894.394844 +Executable: ./dgemmoptimized 20403 20403 20403 1 0 +m=20403, n=20403, k=20403, time(sec)=26.511574, speed(mflops)=640732.231232 +Executable: ./dgemmoptimized 20403 20403 20403 1 0 +m=20403, n=20403, k=20403, time(sec)=26.482488, speed(mflops)=641435.951259 +Max repetitions 3, Elasped time 237.137, Relative error 0.000709417, Mean 19152.9, Standard Deviation 8.05962 +Total Energy 19152.850000 +20429 +Executable: ./dgemmoptimized 20429 20429 20429 1 0 +m=20429, n=20429, k=20429, time(sec)=26.764358, speed(mflops)=637110.099908 +Executable: ./dgemmoptimized 20429 20429 20429 1 0 +m=20429, n=20429, k=20429, time(sec)=26.748364, speed(mflops)=637491.057218 +Executable: ./dgemmoptimized 20429 20429 20429 1 0 +m=20429, n=20429, k=20429, time(sec)=26.754570, speed(mflops)=637343.183707 +Max repetitions 3, Elasped time 240.228, Relative error 0.0167897, Mean 19284.1, Standard Deviation 192.054 +Total Energy 19284.100000 +20454 +Executable: ./dgemmoptimized 20454 20454 20454 1 0 +m=20454, n=20454, k=20454, time(sec)=26.742425, speed(mflops)=639976.408115 +Executable: ./dgemmoptimized 20454 20454 20454 1 0 +m=20454, n=20454, k=20454, time(sec)=26.809259, speed(mflops)=638380.982966 +Executable: ./dgemmoptimized 20454 20454 20454 1 0 +m=20454, n=20454, k=20454, time(sec)=27.023676, speed(mflops)=633315.799594 +Max repetitions 3, Elasped time 238.826, Relative error 0.0184812, Mean 19759.5, Standard Deviation 216.614 +Total Energy 19759.533333 +20480 +Executable: ./dgemmoptimized 20480 20480 20480 1 0 +m=20480, n=20480, k=20480, time(sec)=30.024564, speed(mflops)=572193.793325 +Executable: ./dgemmoptimized 20480 20480 20480 1 0 +m=20480, n=20480, k=20480, time(sec)=30.037288, speed(mflops)=571951.409605 +Executable: ./dgemmoptimized 20480 20480 20480 1 0 +m=20480, n=20480, k=20480, time(sec)=30.083401, speed(mflops)=571074.700102 +Max repetitions 3, Elasped time 250.617, Relative error 0.025672, Mean 20796.2, Standard Deviation 316.682 +Total Energy 20796.166667 diff --git a/tests/dgemmresultsdvfs3/dgemmse.txt b/tests/dgemmresultsdvfs3/dgemmse.txt new file mode 100644 index 0000000..a384479 --- /dev/null +++ b/tests/dgemmresultsdvfs3/dgemmse.txt @@ -0,0 +1,96 @@ +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=22.726712, speed(mflops)=597954.731283 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=22.678297, speed(mflops)=599231.279770 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=22.676856, speed(mflops)=599269.357951 +Max repetitions 3, Elasped time 316.958, Relative error 0.00346305, Mean 25635.6, Standard Deviation 52.6602 +Total Energy 25635.600000 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=23.657531, speed(mflops)=574427.861757 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=23.720250, speed(mflops)=572909.007523 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=23.727124, speed(mflops)=572743.033411 +Max repetitions 3, Elasped time 330.13, Relative error 0.00497582, Mean 26107.3, Standard Deviation 77.0559 +Total Energy 26107.266667 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=24.826926, speed(mflops)=547371.227668 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=24.780211, speed(mflops)=548403.117933 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=24.755704, speed(mflops)=548946.012627 +Max repetitions 3, Elasped time 344.43, Relative error 0.00377815, Mean 26467.3, Standard Deviation 59.3156 +Total Energy 26467.266667 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=26.029810, speed(mflops)=522076.221866 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=26.032660, speed(mflops)=522019.069742 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=25.889843, speed(mflops)=524898.701270 +Max repetitions 3, Elasped time 360.237, Relative error 0.00107893, Mean 27573, Standard Deviation 17.6464 +Total Energy 27572.983333 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=27.209983, speed(mflops)=499432.318824 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=27.350576, speed(mflops)=496865.038521 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=27.344593, speed(mflops)=496973.750390 +Max repetitions 3, Elasped time 377.717, Relative error 0.0023827, Mean 28531.3, Standard Deviation 40.3248 +Total Energy 28531.333333 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=28.693141, speed(mflops)=473616.498374 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=28.773111, speed(mflops)=472300.159355 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=28.816436, speed(mflops)=471590.069215 +Max repetitions 3, Elasped time 447.764, Relative error 0.305624, Mean 32918.3, Standard Deviation 5967.68 +Total Energy 32918.333333 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=30.376888, speed(mflops)=447364.619561 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=30.432986, speed(mflops)=446539.983197 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=30.369101, speed(mflops)=447479.332543 +Max repetitions 3, Elasped time 420.778, Relative error 0.0174337, Mean 30801.7, Standard Deviation 318.525 +Total Energy 30801.733333 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=32.226582, speed(mflops)=421687.445455 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=32.271329, speed(mflops)=421102.737700 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=32.226369, speed(mflops)=421690.231389 +Max repetitions 3, Elasped time 443.232, Relative error 0.00503743, Mean 32298, Standard Deviation 96.5084 +Total Energy 32298.016667 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=34.364076, speed(mflops)=395457.890382 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=34.352418, speed(mflops)=395592.094315 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=34.364322, speed(mflops)=395455.058910 +Max repetitions 3, Elasped time 471.538, Relative error 0.00723886, Mean 33720.9, Standard Deviation 144.794 +Total Energy 33720.933333 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=36.798286, speed(mflops)=369298.313904 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=36.837242, speed(mflops)=368907.773099 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=36.819896, speed(mflops)=369081.568464 +Max repetitions 3, Elasped time 503.123, Relative error 0.0124473, Mean 35931.5, Standard Deviation 265.296 +Total Energy 35931.483333 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=39.609440, speed(mflops)=343088.541810 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=39.608924, speed(mflops)=343093.010812 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=40.923872, speed(mflops)=332068.895191 +Max repetitions 3, Elasped time 540.767, Relative error 0.00127056, Mean 38327.4, Standard Deviation 28.8858 +Total Energy 38327.350000 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=42.934608, speed(mflops)=316517.271230 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=43.927284, speed(mflops)=309364.561653 +Executable: ./dgemmoptimized 3200 46080 46080 1 0 +m=3200, n=46080, k=46080, time(sec)=42.912248, speed(mflops)=316682.195661 +Max repetitions 3, Elasped time 581.691, Relative error 0.0159571, Mean 40734.6, Standard Deviation 385.565 +Total Energy 40734.583333 -- libgit2 0.22.2