GETRF (LU Factorization) using an external BLAS
Single Precision
Double Precision
Complex Single Precision
Complex Double Precision
Raw Results from Benchmarks
$shell> make BLAS_FUNCTIONS=getrf clean
rm -f sgetrf_openBLAS dgetrf_openBLAS cgetrf_openBLAS zgetrf_openBLAS sgetrf_MKL dgetrf_MKL cgetrf_MKL zgetrf_MKL
$shell> make BLAS_FUNCTIONS=getrf
g++-5.3 -DTYPE="float" -DTYPE_P=int32_t -DBLAS_LIB=\"openBLAS\" -DNDEBUG -std=c++11 -O3 -Wall -m64 -march=native -mfpmath=sse -mavx -DUSE_AVX -DUSE_GCCVEC -I ../../FLENS/ -DUSE_EXTERNAL_BLAS -o sgetrf_openBLAS getrf.cc /home/numerik/lehn/work//OpenBLAS-v0.2.15-0/libopenblas_sandybridge-r0.2.15.a
g++-5.3 -DTYPE="double" -DTYPE_P=int32_t -DBLAS_LIB=\"openBLAS\" -DNDEBUG -std=c++11 -O3 -Wall -m64 -march=native -mfpmath=sse -mavx -DUSE_AVX -DUSE_GCCVEC -I ../../FLENS/ -DUSE_EXTERNAL_BLAS -o dgetrf_openBLAS getrf.cc /home/numerik/lehn/work//OpenBLAS-v0.2.15-0/libopenblas_sandybridge-r0.2.15.a
g++-5.3 -DTYPE="std::complex" -DTYPE_P=int32_t -DBLAS_LIB=\"openBLAS\" -DNDEBUG -std=c++11 -O3 -Wall -m64 -march=native -mfpmath=sse -mavx -DUSE_AVX -DUSE_GCCVEC -I ../../FLENS/ -DUSE_EXTERNAL_BLAS -o cgetrf_openBLAS getrf.cc /home/numerik/lehn/work//OpenBLAS-v0.2.15-0/libopenblas_sandybridge-r0.2.15.a
g++-5.3 -DTYPE="std::complex" -DTYPE_P=int32_t -DBLAS_LIB=\"openBLAS\" -DNDEBUG -std=c++11 -O3 -Wall -m64 -march=native -mfpmath=sse -mavx -DUSE_AVX -DUSE_GCCVEC -I ../../FLENS/ -DUSE_EXTERNAL_BLAS -o zgetrf_openBLAS getrf.cc /home/numerik/lehn/work//OpenBLAS-v0.2.15-0/libopenblas_sandybridge-r0.2.15.a
g++-5.3 -DTYPE="float" -DTYPE_P=int64_t -DBLAS_LIB=\"MKL\" -DNDEBUG -std=c++11 -O3 -Wall -m64 -march=native -mfpmath=sse -mavx -DUSE_AVX -DUSE_GCCVEC -I ../../FLENS/ -DUSE_EXTERNAL_BLAS -o sgetrf_MKL getrf.cc -L /opt/intel/compilers_and_libraries/linux/mkl/lib/intel64 -lmkl_intel_ilp64 -Wl,-rpath /opt/intel/compilers_and_libraries/linux/mkl/lib/intel64 -lmkl_intel_ilp64 -lmkl_core -lmkl_sequential -lm -lpthread
g++-5.3 -DTYPE="double" -DTYPE_P=int64_t -DBLAS_LIB=\"MKL\" -DNDEBUG -std=c++11 -O3 -Wall -m64 -march=native -mfpmath=sse -mavx -DUSE_AVX -DUSE_GCCVEC -I ../../FLENS/ -DUSE_EXTERNAL_BLAS -o dgetrf_MKL getrf.cc -L /opt/intel/compilers_and_libraries/linux/mkl/lib/intel64 -lmkl_intel_ilp64 -Wl,-rpath /opt/intel/compilers_and_libraries/linux/mkl/lib/intel64 -lmkl_intel_ilp64 -lmkl_core -lmkl_sequential -lm -lpthread
g++-5.3 -DTYPE="std::complex" -DTYPE_P=int64_t -DBLAS_LIB=\"MKL\" -DNDEBUG -std=c++11 -O3 -Wall -m64 -march=native -mfpmath=sse -mavx -DUSE_AVX -DUSE_GCCVEC -I ../../FLENS/ -DUSE_EXTERNAL_BLAS -o cgetrf_MKL getrf.cc -L /opt/intel/compilers_and_libraries/linux/mkl/lib/intel64 -lmkl_intel_ilp64 -Wl,-rpath /opt/intel/compilers_and_libraries/linux/mkl/lib/intel64 -lmkl_intel_ilp64 -lmkl_core -lmkl_sequential -lm -lpthread
g++-5.3 -DTYPE="std::complex" -DTYPE_P=int64_t -DBLAS_LIB=\"MKL\" -DNDEBUG -std=c++11 -O3 -Wall -m64 -march=native -mfpmath=sse -mavx -DUSE_AVX -DUSE_GCCVEC -I ../../FLENS/ -DUSE_EXTERNAL_BLAS -o zgetrf_MKL getrf.cc -L /opt/intel/compilers_and_libraries/linux/mkl/lib/intel64 -lmkl_intel_ilp64 -Wl,-rpath /opt/intel/compilers_and_libraries/linux/mkl/lib/intel64 -lmkl_intel_ilp64 -lmkl_core -lmkl_sequential -lm -lpthread
$shell> ./sgetrf_MKL > report.sgetrf_MKL
$shell> ./dgetrf_MKL > report.dgetrf_MKL
$shell> ./cgetrf_MKL > report.cgetrf_MKL
$shell> ./zgetrf_MKL > report.zgetrf_MKL
$shell> ./sgetrf_openBLAS > report.sgetrf_openBLAS
$shell> ./dgetrf_openBLAS > report.dgetrf_openBLAS
$shell> ./cgetrf_openBLAS > report.cgetrf_openBLAS
$shell> ./zgetrf_openBLAS > report.zgetrf_openBLAS
$shell> gnuplot plot.sgetrf.mflops
$shell> gnuplot plot.dgetrf.mflops
$shell> gnuplot plot.cgetrf.mflops
$shell> gnuplot plot.zgetrf.mflops
$shell>
Single Precision
$shell> cat report.sgetrf_MKL
# m n info FLENS/ulmBLAS: t MFLOPS MKL: t MFLOPS Residual
50 50 0 0.0032 25.40 2.1e-02
100 100 0 0.0003 2484.04 2.0e-02
150 150 0 0.0005 4709.93 1.8e-02
200 200 0 0.0007 7155.70 1.5e-02
250 250 0 0.0012 8438.10 1.5e-02
300 300 0 0.0008 21308.77 1.7e-02
350 350 0 0.0013 22645.87 1.7e-02
400 400 0 0.0015 27753.92 1.6e-02
450 450 0 0.0021 28273.90 1.6e-02
500 500 0 0.0027 30273.85 1.5e-02
550 550 0 0.0037 29938.14 1.3e-02
600 600 0 0.0044 32765.29 1.2e-02
650 650 0 0.0055 33239.83 1.2e-02
700 700 0 0.0067 34213.18 1.2e-02
750 750 0 0.0082 34312.53 1.2e-02
800 800 0 0.0093 36863.78 1.1e-02
850 850 0 0.0111 36709.88 1.1e-02
900 900 0 0.0130 37372.87 1.1e-02
950 950 0 0.0153 37448.63 1.1e-02
1000 1000 0 0.0170 39167.92 1.0e-02
1050 1050 0 0.0203 37937.27 1.0e-02
1100 1100 0 0.0230 38502.49 1.0e-02
1150 1150 0 0.0266 38149.85 1.0e-02
1200 1200 0 0.0289 39831.12 1.0e-02
1250 1250 0 0.0328 39685.98 9.6e-03
1300 1300 0 0.0364 40187.39 9.6e-03
1350 1350 0 0.0408 40163.06 9.6e-03
1400 1400 0 0.0439 41685.02 9.2e-03
1450 1450 0 0.0490 41448.80 9.1e-03
1500 1500 0 0.0536 41960.52 9.2e-03
1550 1550 0 0.0598 41525.41 9.0e-03
1600 1600 0 0.0637 42825.92 8.5e-03
1650 1650 0 0.0701 42693.83 8.5e-03
1700 1700 0 0.0760 43062.23 8.5e-03
1750 1750 0 0.0833 42870.08 8.6e-03
1800 1800 0 0.0886 43882.28 8.2e-03
1850 1850 0 0.0966 43688.64 8.2e-03
1900 1900 0 0.1037 44057.43 8.1e-03
1950 1950 0 0.1126 43865.86 8.2e-03
2000 2000 0 0.1191 44759.85 7.8e-03
2050 2050 0 0.1344 42717.15 7.9e-03
2100 2100 0 0.1397 44188.15 7.8e-03
2150 2150 0 0.1506 43979.32 7.8e-03
2200 2200 0 0.1584 44806.76 7.5e-03
2250 2250 0 0.1703 44586.25 7.4e-03
2300 2300 0 0.1806 44900.43 7.6e-03
2350 2350 0 0.1931 44795.64 7.4e-03
2400 2400 0 0.2025 45491.10 7.3e-03
2450 2450 0 0.2162 45333.75 7.2e-03
2500 2500 0 0.2280 45675.50 7.3e-03
2550 2550 0 0.2434 45402.37 7.2e-03
2600 2600 0 0.2539 46134.18 6.8e-03
2650 2650 0 0.2698 45976.39 6.9e-03
2700 2700 0 0.2837 46245.67 7.0e-03
2750 2750 0 0.3011 46034.03 6.9e-03
2800 2800 0 0.3138 46624.51 6.7e-03
2850 2850 0 0.3317 46508.64 6.7e-03
2900 2900 0 0.3477 46743.79 6.7e-03
2950 2950 0 0.3676 46545.48 6.7e-03
3000 3000 0 0.3820 47103.84 6.5e-03
3050 3050 0 0.4034 46877.02 6.5e-03
3100 3100 0 0.4241 46816.09 6.6e-03
3150 3150 0 0.4464 46667.00 6.4e-03
3200 3200 0 0.4622 47255.08 6.3e-03
3250 3250 0 0.4921 46495.43 6.4e-03
3300 3300 0 0.5060 47340.45 6.3e-03
3350 3350 0 0.5314 47153.26 6.4e-03
3400 3400 0 0.5500 47627.95 6.2e-03
3450 3450 0 0.5761 47506.98 6.2e-03
3500 3500 0 0.5982 47769.11 6.1e-03
3550 3550 0 0.6272 47543.56 6.2e-03
3600 3600 0 0.6482 47971.54 6.0e-03
3650 3650 0 0.6771 47870.20 6.0e-03
3700 3700 0 0.7016 48118.73 6.0e-03
3750 3750 0 0.7357 47773.69 6.0e-03
3800 3800 0 0.7571 48306.30 5.9e-03
3850 3850 0 0.7898 48159.87 5.9e-03
3900 3900 0 0.8167 48413.34 5.9e-03
3950 3950 0 0.8529 48163.31 5.9e-03
4000 4000 0 0.8787 48548.09 5.9e-03
4050 4050 0 0.9169 48293.34 5.8e-03
4100 4100 0 0.9706 47332.80 5.8e-03
4150 4150 0 0.9925 47998.71 5.7e-03
4200 4200 0 1.0197 48430.89 5.7e-03
4250 4250 0 1.0584 48344.46 5.7e-03
4300 4300 0 1.0921 48525.51 5.7e-03
4350 4350 0 1.1348 48350.03 5.8e-03
4400 4400 0 1.1651 48735.34 5.6e-03
4450 4450 0 1.2095 48563.48 5.6e-03
4500 4500 0 1.2432 48857.48 5.7e-03
4550 4550 0 1.2912 48627.10 5.6e-03
4600 4600 0 1.3264 48915.65 5.5e-03
4650 4650 0 1.3712 48876.48 5.5e-03
4700 4700 0 1.4099 49085.61 5.5e-03
4750 4750 0 1.4608 48902.20 5.5e-03
4800 4800 0 1.4991 49175.18 5.4e-03
4850 4850 0 1.5485 49106.95 5.4e-03
4900 4900 0 1.5915 49275.59 5.4e-03
4950 4950 0 1.6469 49090.47 5.4e-03
5000 5000 0 1.6862 49414.76 5.3e-03
5050 5050 0 1.7407 49316.02 5.3e-03
5100 5100 0 1.7890 49424.92 5.3e-03
5150 5150 0 1.8574 49018.92 5.3e-03
5200 5200 0 1.8977 49388.90 5.2e-03
5250 5250 0 1.9554 49327.02 5.2e-03
5300 5300 0 2.0033 49537.00 5.2e-03
5350 5350 0 2.0690 49334.04 5.2e-03
5400 5400 0 2.1149 49628.77 5.2e-03
5450 5450 0 2.1839 49410.00 5.1e-03
5500 5500 0 2.2314 49700.35 5.1e-03
5550 5550 0 2.3010 49524.54 5.1e-03
5600 5600 0 2.3488 49838.60 5.0e-03
5650 5650 0 2.4198 49684.53 5.1e-03
5700 5700 0 2.4755 49866.44 5.0e-03
5750 5750 0 2.5502 49690.81 5.0e-03
5800 5800 0 2.6064 49899.11 5.0e-03
5850 5850 0 2.6787 49819.46 5.0e-03
5900 5900 0 2.7328 50095.30 4.9e-03
5950 5950 0 2.8158 49865.08 4.9e-03
6000 6000 0 2.8743 50093.26 4.9e-03
$shell> cat report.sgetrf_openBLAS
# m n info FLENS/ulmBLAS: t MFLOPS openBLAS: t MFLOPS Residual
50 50 0 0.0001 568.61 2.0e-02
100 100 0 0.0003 2456.98 1.4e-02
150 150 0 0.0006 3726.10 1.4e-02
200 200 0 0.0011 4952.76 1.3e-02
250 250 0 0.0017 5996.63 1.3e-02
300 300 0 0.0012 15302.08 1.2e-02
350 350 0 0.0017 16829.29 1.1e-02
400 400 0 0.0023 18696.89 1.3e-02
450 450 0 0.0030 20154.66 1.2e-02
500 500 0 0.0038 21676.04 9.1e-03
550 550 0 0.0050 22017.13 1.3e-02
600 600 0 0.0061 23424.00 1.3e-02
650 650 0 0.0075 24231.61 1.3e-02
700 700 0 0.0090 25358.40 1.3e-02
750 750 0 0.0109 25745.70 1.3e-02
800 800 0 0.0126 26993.65 1.3e-02
850 850 0 0.0149 27407.51 1.4e-02
900 900 0 0.0171 28364.44 1.4e-02
950 950 0 0.0200 28505.20 1.5e-02
1000 1000 0 0.0227 29295.05 1.5e-02
1050 1050 0 0.0266 29015.31 1.5e-02
1100 1100 0 0.0296 29931.68 1.5e-02
1150 1150 0 0.0338 29969.80 1.3e-02
1200 1200 0 0.0373 30855.37 1.4e-02
1250 1250 0 0.0420 31000.77 1.3e-02
1300 1300 0 0.0461 31738.44 1.4e-02
1350 1350 0 0.0519 31589.65 1.3e-02
1400 1400 0 0.0566 32306.96 1.3e-02
1450 1450 0 0.0627 32378.51 1.4e-02
1500 1500 0 0.0679 33099.07 1.3e-02
1550 1550 0 0.0758 32741.14 1.4e-02
1600 1600 0 0.0811 33638.24 1.4e-02
1650 1650 0 0.0889 33654.88 1.4e-02
1700 1700 0 0.0951 34417.91 1.4e-02
1750 1750 0 0.1045 34179.86 1.4e-02
1800 1800 0 0.1123 34617.96 1.4e-02
1850 1850 0 0.1219 34616.34 1.5e-02
1900 1900 0 0.1299 35179.95 1.5e-02
1950 1950 0 0.1412 34990.31 1.5e-02
2000 2000 0 0.1498 35592.15 1.5e-02
2050 2050 0 0.1666 34456.81 1.5e-02
2100 2100 0 0.1729 35695.74 1.5e-02
2150 2150 0 0.1874 35345.02 1.4e-02
2200 2200 0 0.1983 35787.05 1.4e-02
2250 2250 0 0.2123 35754.22 1.4e-02
2300 2300 0 0.2234 36299.02 1.4e-02
2350 2350 0 0.2393 36141.95 1.3e-02
2400 2400 0 0.2520 36555.55 1.3e-02
2450 2450 0 0.2680 36570.06 1.3e-02
2500 2500 0 0.2792 37293.45 1.3e-02
2550 2550 0 0.2991 36943.26 1.3e-02
2600 2600 0 0.3139 37314.59 1.3e-02
2650 2650 0 0.3332 37225.31 1.3e-02
2700 2700 0 0.3475 37748.83 1.3e-02
2750 2750 0 0.3692 37538.28 1.2e-02
2800 2800 0 0.3867 37834.06 1.2e-02
2850 2850 0 0.4087 37746.65 1.2e-02
2900 2900 0 0.4226 38462.54 1.3e-02
2950 2950 0 0.4487 38132.20 1.2e-02
3000 3000 0 0.4683 38427.90 1.2e-02
3050 3050 0 0.4958 38141.87 1.2e-02
3100 3100 0 0.5140 38633.48 1.2e-02
3150 3150 0 0.5409 38517.49 1.2e-02
3200 3200 0 0.5621 38857.96 1.2e-02
3250 3250 0 0.5896 38806.18 1.3e-02
3300 3300 0 0.6078 39411.77 1.3e-02
3350 3350 0 0.6428 38982.43 1.3e-02
3400 3400 0 0.6688 39170.84 1.3e-02
3450 3450 0 0.7038 38890.99 1.3e-02
3500 3500 0 0.7272 39298.53 1.3e-02
3550 3550 0 0.7648 38987.63 1.3e-02
3600 3600 0 0.7809 39822.92 1.3e-02
3650 3650 0 0.8181 39618.24 1.3e-02
3700 3700 0 0.8459 39910.34 1.3e-02
3750 3750 0 0.8916 39423.41 1.3e-02
3800 3800 0 0.9181 39836.32 1.3e-02
3850 3850 0 0.9543 39857.83 1.3e-02
3900 3900 0 0.9877 40029.28 1.3e-02
3950 3950 0 1.0339 39733.70 1.3e-02
4000 4000 0 1.0623 40155.78 1.4e-02
4050 4050 0 1.1103 39878.56 1.3e-02
4100 4100 0 1.1489 39986.65 1.4e-02
4150 4150 0 1.1873 40125.17 1.4e-02
4200 4200 0 1.2284 40201.61 1.3e-02
4250 4250 0 1.2775 40053.69 1.3e-02
4300 4300 0 1.3125 40376.94 1.3e-02
4350 4350 0 1.3618 40288.14 1.3e-02
4400 4400 0 1.4065 40369.99 1.3e-02
4450 4450 0 1.4653 40085.24 1.3e-02
4500 4500 0 1.4952 40623.86 1.3e-02
4550 4550 0 1.5598 40253.97 1.2e-02
4600 4600 0 1.6161 40146.68 1.2e-02
4650 4650 0 1.6388 40893.88 1.2e-02
4700 4700 0 1.6827 41126.71 1.2e-02
4750 4750 0 1.7505 40810.25 1.2e-02
4800 4800 0 1.7930 41113.23 1.2e-02
4850 4850 0 1.8554 40986.02 1.2e-02
4900 4900 0 1.8854 41592.73 1.2e-02
4950 4950 0 1.9627 41190.65 1.2e-02
5000 5000 0 2.0168 41314.28 1.2e-02
5050 5050 0 2.0809 41254.98 1.2e-02
5100 5100 0 2.1249 41612.42 1.2e-02
5150 5150 0 2.2105 41188.07 1.2e-02
5200 5200 0 2.2575 41517.57 1.2e-02
5250 5250 0 2.3291 41412.74 1.2e-02
5300 5300 0 2.3645 41969.54 1.2e-02
5350 5350 0 2.4562 41557.26 1.2e-02
5400 5400 0 2.5123 41779.00 1.2e-02
5450 5450 0 2.5892 41675.19 1.2e-02
5500 5500 0 2.6363 42067.01 1.2e-02
5550 5550 0 2.7262 41799.40 1.2e-02
5600 5600 0 2.7877 41992.71 1.2e-02
5650 5650 0 2.8729 41848.83 1.2e-02
5700 5700 0 2.9162 42331.44 1.2e-02
5750 5750 0 3.0145 42037.20 1.2e-02
5800 5800 0 3.0892 42100.77 1.2e-02
5850 5850 0 3.1705 42091.90 1.2e-02
5900 5900 0 3.2253 42446.63 1.2e-02
5950 5950 0 3.3308 42155.39 1.2e-02
6000 6000 0 3.4010 42335.52 1.2e-02
$shell>
Double Precision
$shell> cat report.dgetrf_MKL
# m n info FLENS/ulmBLAS: t MFLOPS MKL: t MFLOPS Residual
50 50 0 0.0023 35.90 2.1e-02
100 100 0 0.0002 2746.92 1.8e-02
150 150 0 0.0006 3997.48 1.7e-02
200 200 0 0.0010 5465.87 1.6e-02
250 250 0 0.0007 14044.63 1.5e-02
300 300 0 0.0012 15372.55 1.6e-02
350 350 0 0.0018 16058.96 1.6e-02
400 400 0 0.0024 17749.92 1.6e-02
450 450 0 0.0033 18364.55 1.5e-02
500 500 0 0.0045 18642.24 1.4e-02
550 550 0 0.0058 18984.06 1.2e-02
600 600 0 0.0073 19587.01 1.2e-02
650 650 0 0.0092 19960.75 1.2e-02
700 700 0 0.0114 20106.45 1.1e-02
750 750 0 0.0137 20434.98 1.1e-02
800 800 0 0.0168 20340.37 1.1e-02
850 850 0 0.0196 20881.22 1.1e-02
900 900 0 0.0232 20968.65 1.0e-02
950 950 0 0.0271 21064.55 1.0e-02
1000 1000 0 0.0313 21253.73 1.0e-02
1050 1050 0 0.0362 21288.26 1.0e-02
1100 1100 0 0.0415 21344.26 1.0e-02
1150 1150 0 0.0476 21271.80 1.1e-02
1200 1200 0 0.0532 21650.23 1.0e-02
1250 1250 0 0.0593 21948.17 9.9e-03
1300 1300 0 0.0672 21771.01 1.0e-02
1350 1350 0 0.0743 22054.99 9.8e-03
1400 1400 0 0.0832 21969.22 9.7e-03
1450 1450 0 0.0910 22315.67 9.7e-03
1500 1500 0 0.1009 22289.59 9.6e-03
1550 1550 0 0.1108 22399.91 9.5e-03
1600 1600 0 0.1241 21991.28 9.4e-03
1650 1650 0 0.1321 22668.03 9.3e-03
1700 1700 0 0.1450 22584.29 9.1e-03
1750 1750 0 0.1563 22855.08 9.0e-03
1800 1800 0 0.1707 22773.85 8.9e-03
1850 1850 0 0.1832 23028.92 8.9e-03
1900 1900 0 0.2022 22602.51 8.8e-03
1950 1950 0 0.2137 23124.81 8.6e-03
2000 2000 0 0.2307 23108.26 8.6e-03
2050 2050 0 0.2582 22232.39 8.4e-03
2100 2100 0 0.2682 23009.50 8.6e-03
2150 2150 0 0.2891 22912.76 8.6e-03
2200 2200 0 0.3078 23055.42 8.8e-03
2250 2250 0 0.3248 23373.13 8.9e-03
2300 2300 0 0.3572 22701.32 8.9e-03
2350 2350 0 0.3716 23278.22 8.8e-03
2400 2400 0 0.3963 23247.01 8.7e-03
2450 2450 0 0.4188 23403.83 8.8e-03
2500 2500 0 0.4450 23400.82 8.7e-03
2550 2550 0 0.4690 23563.50 8.7e-03
2600 2600 0 0.5011 23377.55 8.8e-03
2650 2650 0 0.5236 23689.76 8.7e-03
2700 2700 0 0.5585 23488.56 8.6e-03
2750 2750 0 0.5831 23769.24 8.6e-03
2800 2800 0 0.6198 23606.49 8.5e-03
2850 2850 0 0.6728 22931.94 8.5e-03
2900 2900 0 0.6887 23602.32 8.4e-03
2950 2950 0 0.7158 23902.79 8.4e-03
3000 3000 0 0.7582 23734.52 8.3e-03
3050 3050 0 0.8087 23383.69 8.3e-03
3100 3100 0 0.8389 23667.63 8.3e-03
3150 3150 0 0.8672 24022.51 8.1e-03
3200 3200 0 0.9348 23363.49 8.1e-03
3250 3250 0 0.9462 24180.24 8.2e-03
3300 3300 0 1.0001 23949.73 8.0e-03
3350 3350 0 1.0336 24242.88 8.0e-03
3400 3400 0 1.0951 23922.39 8.1e-03
3450 3450 0 1.1766 23262.46 7.9e-03
3500 3500 0 1.1873 24069.60 7.9e-03
3550 3550 0 1.2328 24188.22 7.9e-03
3600 3600 0 1.2867 24169.18 7.8e-03
3650 3650 0 1.3336 24304.44 7.7e-03
3700 3700 0 1.3943 24213.66 7.8e-03
3750 3750 0 1.4424 24368.38 7.7e-03
3800 3800 0 1.5351 23825.11 7.7e-03
3850 3850 0 1.6055 23692.17 7.6e-03
3900 3900 0 1.6292 24268.13 7.5e-03
3950 3950 0 1.6830 24408.72 7.6e-03
4000 4000 0 1.7560 24292.75 7.4e-03
4050 4050 0 1.8069 24505.05 7.4e-03
4100 4100 0 1.9740 23271.50 7.3e-03
4150 4150 0 1.9394 24564.19 7.2e-03
4200 4200 0 2.0522 24064.07 7.2e-03
4250 4250 0 2.0884 24501.21 7.1e-03
4300 4300 0 2.1806 24303.50 7.0e-03
4350 4350 0 2.2338 24561.67 6.9e-03
4400 4400 0 2.3313 24355.75 6.8e-03
4450 4450 0 2.3854 24623.65 6.8e-03
4500 4500 0 2.4817 24475.20 6.7e-03
4550 4550 0 2.5672 24457.20 6.7e-03
4600 4600 0 2.7084 23955.54 6.6e-03
4650 4650 0 2.7121 24711.28 6.5e-03
4700 4700 0 2.8257 24491.12 6.5e-03
4750 4750 0 2.9284 24394.79 6.3e-03
4800 4800 0 3.0125 24469.81 6.3e-03
4850 4850 0 3.1369 24241.95 6.3e-03
4900 4900 0 3.1971 24528.64 6.2e-03
4950 4950 0 3.2760 24678.29 6.1e-03
5000 5000 0 3.4032 24482.87 6.2e-03
5050 5050 0 3.5581 24126.61 6.0e-03
5100 5100 0 3.5958 24589.97 6.0e-03
5150 5150 0 3.6830 24721.08 6.0e-03
5200 5200 0 3.8657 24245.16 5.9e-03
5250 5250 0 3.8881 24807.83 5.8e-03
5300 5300 0 4.0157 24712.55 5.8e-03
5350 5350 0 4.2462 24038.48 5.8e-03
5400 5400 0 4.2530 24679.12 5.7e-03
5450 5450 0 4.4169 24429.62 5.7e-03
5500 5500 0 4.4737 24789.89 5.7e-03
5550 5550 0 4.5592 24994.26 5.7e-03
5600 5600 0 4.7131 24837.55 5.6e-03
5650 5650 0 4.9605 24236.52 5.6e-03
5700 5700 0 5.1371 24030.45 5.5e-03
5750 5750 0 5.1621 24548.53 5.5e-03
5800 5800 0 5.2392 24823.83 5.5e-03
5850 5850 0 5.4260 24594.85 5.5e-03
5900 5900 0 5.4972 24903.98 5.4e-03
5950 5950 0 5.7870 24263.43 5.4e-03
6000 6000 0 5.8019 24816.48 5.4e-03
$shell> cat report.dgetrf_openBLAS
# m n info FLENS/ulmBLAS: t MFLOPS openBLAS: t MFLOPS Residual
50 50 0 0.0001 582.12 1.5e-02
100 100 0 0.0003 2476.90 1.4e-02
150 150 0 0.0007 3416.73 1.3e-02
200 200 0 0.0012 4555.38 1.2e-02
250 250 0 0.0020 5283.52 1.3e-02
300 300 0 0.0022 8125.99 1.4e-02
350 350 0 0.0020 14052.08 1.4e-02
400 400 0 0.0028 14974.96 1.3e-02
450 450 0 0.0038 15789.16 1.3e-02
500 500 0 0.0050 16564.60 8.5e-03
550 550 0 0.0066 16680.20 8.8e-03
600 600 0 0.0083 17280.19 8.6e-03
650 650 0 0.0104 17645.14 8.6e-03
700 700 0 0.0126 18075.91 8.6e-03
750 750 0 0.0153 18376.74 8.4e-03
800 800 0 0.0181 18820.79 7.1e-03
850 850 0 0.0214 19076.05 6.9e-03
900 900 0 0.0251 19369.34 6.8e-03
950 950 0 0.0292 19540.46 6.8e-03
1000 1000 0 0.0336 19835.47 6.7e-03
1050 1050 0 0.0393 19614.22 6.0e-03
1100 1100 0 0.0448 19810.26 5.9e-03
1150 1150 0 0.0505 20062.75 5.9e-03
1200 1200 0 0.0569 20232.68 5.9e-03
1250 1250 0 0.0635 20494.54 6.0e-03
1300 1300 0 0.0709 20652.03 5.4e-03
1350 1350 0 0.0787 20828.62 5.2e-03
1400 1400 0 0.0873 20944.93 5.3e-03
1450 1450 0 0.0960 21159.45 5.2e-03
1500 1500 0 0.1054 21332.07 5.2e-03
1550 1550 0 0.1160 21400.21 4.9e-03
1600 1600 0 0.1271 21473.78 4.9e-03
1650 1650 0 0.1381 21667.72 4.9e-03
1700 1700 0 0.1502 21790.26 4.8e-03
1750 1750 0 0.1630 21911.62 4.8e-03
1800 1800 0 0.1772 21928.07 4.5e-03
1850 1850 0 0.1906 22142.62 4.5e-03
1900 1900 0 0.2061 22180.81 4.5e-03
1950 1950 0 0.2217 22289.75 4.5e-03
2000 2000 0 0.2387 22337.70 4.5e-03
2050 2050 0 0.2607 22021.64 4.2e-03
2100 2100 0 0.2778 22217.40 4.3e-03
2150 2150 0 0.2962 22360.27 4.2e-03
2200 2200 0 0.3174 22356.56 4.2e-03
2250 2250 0 0.3364 22566.03 4.1e-03
2300 2300 0 0.3589 22592.25 4.0e-03
2350 2350 0 0.3800 22762.92 4.1e-03
2400 2400 0 0.4053 22731.48 4.0e-03
2450 2450 0 0.4274 22931.99 4.0e-03
2500 2500 0 0.4536 22955.91 4.0e-03
2550 2550 0 0.4796 23042.85 3.8e-03
2600 2600 0 0.5091 23010.02 3.8e-03
2650 2650 0 0.5350 23181.40 3.8e-03
2700 2700 0 0.5656 23193.44 3.8e-03
2750 2750 0 0.5950 23296.99 3.7e-03
2800 2800 0 0.6292 23253.52 3.7e-03
2850 2850 0 0.6587 23423.45 3.6e-03
2900 2900 0 0.6943 23411.54 3.6e-03
2950 2950 0 0.7270 23535.75 3.6e-03
3000 3000 0 0.7682 23425.20 3.6e-03
3050 3050 0 0.7994 23657.08 3.6e-03
3100 3100 0 0.8403 23630.72 3.5e-03
3150 3150 0 0.8794 23690.08 3.4e-03
3200 3200 0 0.9236 23647.48 3.4e-03
3250 3250 0 0.9609 23810.97 3.4e-03
3300 3300 0 1.0063 23802.49 3.4e-03
3350 3350 0 1.0490 23887.03 3.4e-03
3400 3400 0 1.1012 23788.42 3.3e-03
3450 3450 0 1.1420 23967.13 3.3e-03
3500 3500 0 1.1939 23935.58 3.3e-03
3550 3550 0 1.2388 24071.94 3.3e-03
3600 3600 0 1.2969 23978.94 3.2e-03
3650 3650 0 1.3438 24119.42 3.2e-03
3700 3700 0 1.4009 24100.05 3.2e-03
3750 3750 0 1.4533 24185.10 3.2e-03
3800 3800 0 1.5199 24063.55 3.2e-03
3850 3850 0 1.5680 24258.09 3.1e-03
3900 3900 0 1.6305 24249.64 3.2e-03
3950 3950 0 1.6888 24323.90 3.1e-03
4000 4000 0 1.7624 24204.99 3.1e-03
4050 4050 0 1.8143 24404.70 3.1e-03
4100 4100 0 1.9218 23904.59 3.0e-03
4150 4150 0 1.9634 24263.98 3.0e-03
4200 4200 0 2.0469 24126.31 3.0e-03
4250 4250 0 2.1010 24353.83 3.0e-03
4300 4300 0 2.1793 24318.06 3.0e-03
4350 4350 0 2.2535 24347.37 3.0e-03
4400 4400 0 2.3393 24271.92 3.0e-03
4450 4450 0 2.3978 24496.14 2.9e-03
4500 4500 0 2.4866 24426.64 2.9e-03
4550 4550 0 2.5595 24531.36 2.9e-03
4600 4600 0 2.6629 24364.78 2.9e-03
4650 4650 0 2.7268 24577.60 2.8e-03
4700 4700 0 2.8229 24515.63 2.9e-03
4750 4750 0 2.9064 24579.39 2.9e-03
4800 4800 0 3.0137 24460.29 2.8e-03
4850 4850 0 3.0792 24695.83 2.8e-03
4900 4900 0 3.1847 24624.38 2.8e-03
4950 4950 0 3.2763 24676.28 2.8e-03
5000 5000 0 3.3932 24555.30 2.8e-03
5050 5050 0 3.4663 24766.11 2.8e-03
5100 5100 0 3.5704 24765.08 2.7e-03
5150 5150 0 3.6732 24786.87 2.7e-03
5200 5200 0 3.8022 24650.44 2.7e-03
5250 5250 0 3.8811 24852.63 2.7e-03
5300 5300 0 3.9980 24821.80 2.7e-03
5350 5350 0 4.1020 24883.43 2.7e-03
5400 5400 0 4.2418 24744.74 2.6e-03
5450 5450 0 4.3281 24930.94 2.7e-03
5500 5500 0 4.4561 24887.45 2.6e-03
5550 5550 0 4.5679 24946.64 2.6e-03
5600 5600 0 4.7100 24854.02 2.6e-03
5650 5650 0 4.8104 24992.98 2.6e-03
5700 5700 0 4.9469 24954.02 2.6e-03
5750 5750 0 5.0632 25028.31 2.6e-03
5800 5800 0 5.2284 24875.43 2.6e-03
5850 5850 0 5.3199 25085.16 2.6e-03
5900 5900 0 5.4633 25058.48 2.5e-03
5950 5950 0 5.5955 25093.90 2.6e-03
6000 6000 0 5.7729 24941.21 2.5e-03
$shell>
Complex Single Precision
$shell> cat report.cgetrf_MKL
# m n info FLENS/ulmBLAS: t MFLOPS MKL: t MFLOPS Residual
50 50 0 0.0023 35.60 5.8e+03
100 100 0 0.0004 1628.42 2.0e+03
150 150 0 0.0010 2346.17 9.3e+02
200 200 0 0.0008 7036.57 6.1e+02
250 250 0 0.0013 7743.82 4.3e+02
300 300 0 0.0021 8406.04 4.2e+02
350 350 0 0.0032 8895.40 2.4e+02
400 400 0 0.0045 9541.24 2.3e+02
450 450 0 0.0062 9757.14 1.8e+02
500 500 0 0.0082 10123.43 1.5e+02
550 550 0 0.0110 10070.12 1.5e+02
600 600 0 0.0137 10460.79 1.3e+02
650 650 0 0.0173 10546.35 1.0e+02
700 700 0 0.0212 10778.12 8.6e+01
750 750 0 0.0259 10834.70 7.8e+01
800 800 0 0.0308 11063.37 7.3e+01
850 850 0 0.0368 11127.97 6.6e+01
900 900 0 0.0430 11287.96 6.0e+01
950 950 0 0.0504 11321.72 5.4e+01
1000 1000 0 0.0581 11469.35 5.4e+01
1050 1050 0 0.0680 11336.21 4.5e+01
1100 1100 0 0.0774 11451.79 4.5e+01
1150 1150 0 0.0883 11474.32 4.0e+01
1200 1200 0 0.0992 11601.27 3.9e+01
1250 1250 0 0.1119 11633.63 3.8e+01
1300 1300 0 0.1248 11725.03 3.3e+01
1350 1350 0 0.1396 11744.38 3.2e+01
1400 1400 0 0.1540 11873.33 3.0e+01
1450 1450 0 0.1710 11881.49 2.8e+01
1500 1500 0 0.1879 11969.26 2.7e+01
1550 1550 0 0.2084 11909.45 2.3e+01
1600 1600 0 0.2272 12015.77 2.5e+01
1650 1650 0 0.2488 12032.01 2.2e+01
1700 1700 0 0.2705 12103.98 2.2e+01
1750 1750 0 0.2947 12116.94 2.2e+01
1800 1800 0 0.3189 12187.67 1.9e+01
1850 1850 0 0.3465 12176.03 1.9e+01
1900 1900 0 0.3727 12265.16 1.8e+01
1950 1950 0 0.4033 12253.40 1.8e+01
2000 2000 0 0.4320 12339.72 1.7e+01
2050 2050 0 0.4736 12123.62 1.7e+01
2100 2100 0 0.5027 12277.57 1.6e+01
2150 2150 0 0.5388 12291.98 1.4e+01
2200 2200 0 0.5742 12357.79 1.5e+01
2250 2250 0 0.6140 12364.04 1.4e+01
2300 2300 0 0.6541 12397.28 1.2e+01
2350 2350 0 0.6966 12415.87 1.3e+01
2400 2400 0 0.7390 12466.70 1.2e+01
2450 2450 0 0.7866 12460.33 1.2e+01
2500 2500 0 0.8328 12504.81 1.2e+01
2550 2550 0 0.8838 12504.01 1.1e+01
2600 2600 0 0.9364 12510.11 1.1e+01
2650 2650 0 0.9913 12512.22 1.1e+01
2700 2700 0 1.0454 12548.34 1.0e+01
2750 2750 0 1.1040 12555.36 1.0e+01
2800 2800 0 1.1610 12601.43 9.3e+00
2850 2850 0 1.2247 12597.42 9.2e+00
2900 2900 0 1.2889 12611.53 9.4e+00
2950 2950 0 1.3536 12640.37 9.2e+00
3000 3000 0 1.4199 12673.34 8.6e+00
3050 3050 0 1.4904 12688.28 8.5e+00
3100 3100 0 1.5689 12655.83 8.0e+00
3150 3150 0 1.6421 12686.61 8.0e+00
3200 3200 0 1.7200 12698.11 7.8e+00
3250 3250 0 1.7999 12711.70 7.8e+00
3300 3300 0 1.8804 12737.79 7.6e+00
3350 3350 0 1.9650 12751.84 7.1e+00
3400 3400 0 2.0506 12775.00 7.2e+00
3450 3450 0 2.1403 12787.71 6.8e+00
3500 3500 0 2.2330 12797.92 6.9e+00
3550 3550 0 2.3273 12812.90 6.9e+00
3600 3600 0 2.4295 12799.77 6.5e+00
3650 3650 0 2.5282 12820.13 6.3e+00
3700 3700 0 2.6317 12828.80 6.3e+00
3750 3750 0 2.7370 12842.18 6.1e+00
3800 3800 0 2.8455 12853.11 5.9e+00
3850 3850 0 2.9575 12861.02 5.5e+00
3900 3900 0 3.0727 12867.63 5.6e+00
3950 3950 0 3.1869 12889.86 5.7e+00
4000 4000 0 3.3071 12899.22 5.4e+00
4050 4050 0 3.4291 12912.64 5.1e+00
4100 4100 0 3.5946 12779.88 5.1e+00
4150 4150 0 3.6998 12876.46 4.9e+00
4200 4200 0 3.8309 12890.76 4.9e+00
4250 4250 0 3.9647 12905.89 4.8e+00
4300 4300 0 4.1040 12913.21 4.7e+00
4350 4350 0 4.2439 12928.30 4.5e+00
4400 4400 0 4.3869 12943.00 4.4e+00
4450 4450 0 4.5338 12955.59 4.3e+00
4500 4500 0 4.6862 12961.43 4.4e+00
4550 4550 0 4.8386 12976.40 4.4e+00
4600 4600 0 4.9987 12979.48 4.4e+00
4650 4650 0 5.1702 12962.64 4.1e+00
4700 4700 0 5.3389 12962.26 4.2e+00
4750 4750 0 5.5018 12984.30 4.1e+00
4800 4800 0 5.6766 12985.99 3.8e+00
4850 4850 0 5.8492 13000.82 3.9e+00
4900 4900 0 6.0285 13008.39 3.7e+00
4950 4950 0 6.2133 13011.71 3.7e+00
5000 5000 0 6.3927 13033.72 3.7e+00
5050 5050 0 6.5826 13041.23 3.5e+00
5100 5100 0 6.7803 13040.89 3.5e+00
5150 5150 0 6.9900 13025.35 3.3e+00
5200 5200 0 7.1911 13033.44 3.5e+00
5250 5250 0 7.3907 13050.83 3.5e+00
5300 5300 0 7.6048 13049.34 3.5e+00
5350 5350 0 7.8152 13060.83 3.5e+00
5400 5400 0 8.0308 13069.78 3.4e+00
5450 5450 0 8.2567 13068.74 3.5e+00
5500 5500 0 8.4792 13079.23 3.6e+00
5550 5550 0 8.6993 13099.14 3.5e+00
5600 5600 0 8.9354 13100.95 3.4e+00
5650 5650 0 9.1915 13080.03 3.5e+00
5700 5700 0 9.4374 13080.44 3.5e+00
5750 5750 0 9.6709 13103.50 3.6e+00
5800 5800 0 9.9251 13103.88 3.6e+00
5850 5850 0 10.1709 13120.80 3.5e+00
5900 5900 0 10.4403 13112.86 3.6e+00
5950 5950 0 10.6917 13132.81 3.7e+00
6000 6000 0 10.9617 13134.95 3.7e+00
$shell> cat report.cgetrf_openBLAS
# m n info FLENS/ulmBLAS: t MFLOPS openBLAS: t MFLOPS Residual
50 50 0 0.0002 414.42 5.2e+03
100 100 0 0.0005 1244.95 2.0e+03
150 150 0 0.0012 1850.36 1.0e+03
200 200 0 0.0023 2332.72 5.9e+02
250 250 0 0.0017 6012.63 4.8e+02
300 300 0 0.0028 6454.68 3.2e+02
350 350 0 0.0041 6915.98 2.4e+02
400 400 0 0.0058 7384.12 2.4e+02
450 450 0 0.0078 7777.14 1.8e+02
500 500 0 0.0104 8029.66 1.7e+02
550 550 0 0.0136 8127.39 1.4e+02
600 600 0 0.0171 8403.31 1.0e+02
650 650 0 0.0214 8551.05 1.0e+02
700 700 0 0.0263 8674.51 1.0e+02
750 750 0 0.0324 8659.46 7.4e+01
800 800 0 0.0384 8882.01 7.8e+01
850 850 0 0.0455 8988.23 6.4e+01
900 900 0 0.0525 9244.40 6.6e+01
950 950 0 0.0619 9225.59 5.1e+01
1000 1000 0 0.0697 9555.51 4.7e+01
1050 1050 0 0.0827 9328.21 4.6e+01
1100 1100 0 0.0941 9424.06 4.3e+01
1150 1150 0 0.1068 9489.63 4.1e+01
1200 1200 0 0.1187 9698.99 3.8e+01
1250 1250 0 0.1323 9837.50 3.7e+01
1300 1300 0 0.1474 9934.31 3.3e+01
1350 1350 0 0.1633 10036.87 3.1e+01
1400 1400 0 0.1810 10101.75 2.9e+01
1450 1450 0 0.1982 10246.76 3.0e+01
1500 1500 0 0.2192 10261.49 2.6e+01
1550 1550 0 0.2408 10306.17 2.5e+01
1600 1600 0 0.2635 10358.21 2.3e+01
1650 1650 0 0.2863 10453.94 2.3e+01
1700 1700 0 0.3154 10380.86 2.2e+01
1750 1750 0 0.3440 10380.64 1.9e+01
1800 1800 0 0.3661 10615.36 2.1e+01
1850 1850 0 0.3971 10626.06 1.9e+01
1900 1900 0 0.4298 10634.32 1.8e+01
1950 1950 0 0.4631 10670.31 1.7e+01
2000 2000 0 0.4976 10714.00 1.7e+01
2050 2050 0 0.5351 10730.26 1.6e+01
2100 2100 0 0.5763 10709.79 1.4e+01
2150 2150 0 0.6174 10726.88 1.4e+01
2200 2200 0 0.6601 10750.59 1.5e+01
2250 2250 0 0.7056 10758.84 1.5e+01
2300 2300 0 0.7602 10666.42 1.3e+01
2350 2350 0 0.7967 10856.27 1.2e+01
2400 2400 0 0.8468 10879.83 1.2e+01
2450 2450 0 0.8927 10979.44 1.3e+01
2500 2500 0 0.9529 10928.63 1.2e+01
2550 2550 0 1.0076 10967.37 1.1e+01
2600 2600 0 1.0629 11020.68 1.1e+01
2650 2650 0 1.1167 11106.47 1.1e+01
2700 2700 0 1.1854 11066.65 1.0e+01
2750 2750 0 1.2493 11095.12 1.0e+01
2800 2800 0 1.3197 11086.71 9.2e+00
2850 2850 0 1.3758 11214.64 9.0e+00
2900 2900 0 1.4527 11189.55 8.9e+00
2950 2950 0 1.5210 11249.65 8.8e+00
3000 3000 0 1.6006 11242.65 8.7e+00
3050 3050 0 1.6728 11304.50 8.0e+00
3100 3100 0 1.7623 11266.81 8.4e+00
3150 3150 0 1.8425 11306.25 8.0e+00
3200 3200 0 1.9329 11298.91 8.1e+00
3250 3250 0 2.0132 11364.78 7.6e+00
3300 3300 0 2.1201 11297.67 7.3e+00
3350 3350 0 2.2094 11341.64 7.2e+00
3400 3400 0 2.3109 11336.14 7.2e+00
3450 3450 0 2.4009 11400.02 7.2e+00
3500 3500 0 2.5111 11380.16 6.7e+00
3550 3550 0 2.6196 11383.11 6.6e+00
3600 3600 0 2.7187 11438.39 6.5e+00
3650 3650 0 2.8163 11508.58 6.1e+00
3700 3700 0 2.9424 11474.36 6.1e+00
3750 3750 0 3.0616 11480.51 6.2e+00
3800 3800 0 3.1947 11448.25 5.9e+00
3850 3850 0 3.2862 11574.65 5.7e+00
3900 3900 0 3.4329 11517.39 5.6e+00
3950 3950 0 3.5603 11538.08 5.3e+00
4000 4000 0 3.7034 11518.68 5.1e+00
4050 4050 0 3.8433 11520.88 5.2e+00
4100 4100 0 3.9951 11498.86 5.3e+00
4150 4150 0 4.1414 11503.46 5.2e+00
4200 4200 0 4.2987 11487.91 5.0e+00
4250 4250 0 4.4399 11524.47 4.7e+00
4300 4300 0 4.6442 11411.16 4.6e+00
4350 4350 0 4.7858 11464.20 4.7e+00
4400 4400 0 4.9119 11559.58 4.7e+00
4450 4450 0 5.0529 11624.53 4.4e+00
4500 4500 0 5.2393 11593.18 4.3e+00
4550 4550 0 5.4091 11607.62 4.3e+00
4600 4600 0 5.6045 11576.46 4.1e+00
4650 4650 0 5.7375 11680.92 4.0e+00
4700 4700 0 5.9544 11622.30 4.0e+00
4750 4750 0 6.1348 11644.57 4.0e+00
4800 4800 0 6.3543 11600.97 3.9e+00
4850 4850 0 6.5160 11670.32 3.8e+00
4900 4900 0 6.7403 11634.57 3.7e+00
4950 4950 0 6.9204 11682.25 3.6e+00
5000 5000 0 7.1290 11687.55 3.6e+00
5050 5050 0 7.3127 11739.22 3.5e+00
5100 5100 0 7.5644 11689.11 3.6e+00
5150 5150 0 7.7527 11743.91 3.6e+00
5200 5200 0 7.9976 11719.19 3.5e+00
5250 5250 0 8.1857 11783.30 3.5e+00
5300 5300 0 8.4515 11741.99 3.4e+00
5350 5350 0 8.7045 11726.37 3.4e+00
5400 5400 0 8.9366 11745.10 3.6e+00
5450 5450 0 9.1469 11796.85 3.5e+00
5500 5500 0 9.4252 11766.43 3.6e+00
5550 5550 0 9.6664 11788.61 3.6e+00
5600 5600 0 9.9695 11741.96 3.6e+00
5650 5650 0 10.1855 11803.55 3.6e+00
5700 5700 0 10.4892 11768.83 3.5e+00
5750 5750 0 10.7178 11823.56 3.5e+00
5800 5800 0 11.0179 11804.24 3.6e+00
5850 5850 0 11.3131 11796.15 3.5e+00
5900 5900 0 11.5472 11855.86 3.6e+00
5950 5950 0 11.8560 11843.16 3.6e+00
6000 6000 0 12.1474 11852.87 3.7e+00
$shell>
Complex Double Precision
$shell> cat report.zgetrf_MKL
# m n info FLENS/ulmBLAS: t MFLOPS MKL: t MFLOPS Residual
50 50 0 0.0024 34.60 2.2e+15
100 100 0 0.0005 1280.29 2.1e+15
150 150 0 0.0014 1594.73 2.0e+15
200 200 0 0.0027 1943.43 2.0e+15
250 250 0 0.0023 4602.85 1.6e+15
300 300 0 0.0037 4905.84 2.3e+15
350 350 0 0.0056 5070.53 2.4e+15
400 400 0 0.0081 5261.90 1.8e+15
450 450 0 0.0113 5387.69 2.3e+15
500 500 0 0.0152 5462.42 2.2e+15
550 550 0 0.0202 5472.22 2.1e+15
600 600 0 0.0259 5550.77 2.2e+15
650 650 0 0.0328 5569.27 2.3e+15
700 700 0 0.0403 5669.52 2.4e+15
750 750 0 0.0490 5728.83 2.2e+15
800 800 0 0.0593 5752.35 2.3e+15
850 850 0 0.0705 5805.67 2.7e+15
900 900 0 0.0831 5846.87 2.6e+15
950 950 0 0.0970 5887.29 2.7e+15
1000 1000 0 0.1123 5931.21 2.5e+15
1050 1050 0 0.1306 5904.25 2.7e+15
1100 1100 0 0.1495 5932.81 2.6e+15
1150 1150 0 0.1700 5959.18 2.8e+15
1200 1200 0 0.1923 5986.86 2.5e+15
1250 1250 0 0.2159 6028.14 2.7e+15
1300 1300 0 0.2432 6019.23 2.6e+15
1350 1350 0 0.2712 6044.64 2.8e+15
1400 1400 0 0.3010 6074.68 2.7e+15
1450 1450 0 0.3337 6087.08 2.8e+15
1500 1500 0 0.3678 6114.86 2.6e+15
1550 1550 0 0.4057 6116.74 2.8e+15
1600 1600 0 0.4452 6130.35 2.8e+15
1650 1650 0 0.4863 6155.91 3.1e+15
1700 1700 0 0.5307 6168.85 2.8e+15
1750 1750 0 0.5769 6190.63 3.3e+15
1800 1800 0 0.6294 6174.59 3.0e+15
1850 1850 0 0.6789 6215.24 2.8e+15
1900 1900 0 0.7351 6217.60 3.4e+15
1950 1950 0 0.7929 6231.85 3.1e+15
2000 2000 0 0.8540 6243.11 3.1e+15
2050 2050 0 0.9332 6152.13 3.0e+15
2100 2100 0 0.9915 6224.62 3.0e+15
2150 2150 0 1.0594 6252.07 3.1e+15
2200 2200 0 1.1341 6257.12 3.3e+15
2250 2250 0 1.2087 6280.32 3.3e+15
2300 2300 0 1.2967 6253.30 3.0e+15
2350 2350 0 1.3754 6288.47 3.0e+15
2400 2400 0 1.4654 6287.01 2.9e+15
2450 2450 0 1.5562 6297.98 3.1e+15
2500 2500 0 1.6501 6310.90 3.3e+15
2550 2550 0 1.7491 6318.02 3.4e+15
2600 2600 0 1.8553 6313.78 2.9e+15
2650 2650 0 1.9600 6327.96 3.3e+15
2700 2700 0 2.0704 6335.99 3.5e+15
2750 2750 0 2.1822 6351.74 3.2e+15
2800 2800 0 2.2998 6361.70 3.1e+15
2850 2850 0 2.4284 6353.48 3.5e+15
2900 2900 0 2.5623 6344.08 3.5e+15
2950 2950 0 2.6895 6362.00 3.6e+15
3000 3000 0 2.8264 6367.00 3.5e+15
3050 3050 0 2.9615 6385.41 3.4e+15
3100 3100 0 3.1165 6371.21 3.5e+15
3150 3150 0 3.2642 6382.09 3.4e+15
3200 3200 0 3.4449 6339.91 3.5e+15
3250 3250 0 3.5765 6397.30 3.5e+15
3300 3300 0 3.7498 6387.72 3.4e+15
3350 3350 0 3.9144 6401.49 3.5e+15
3400 3400 0 4.0959 6395.84 3.6e+15
3450 3450 0 4.2857 6386.26 3.6e+15
3500 3500 0 4.4704 6392.58 3.6e+15
3550 3550 0 4.6427 6422.87 3.6e+15
3600 3600 0 4.8510 6410.52 3.7e+15
3650 3650 0 5.0541 6412.94 3.6e+15
3700 3700 0 5.2636 6414.24 3.7e+15
3750 3750 0 5.4757 6419.11 3.4e+15
3800 3800 0 5.6886 6429.32 3.2e+15
3850 3850 0 5.9242 6420.59 3.5e+15
3900 3900 0 6.1518 6427.10 4.1e+15
3950 3950 0 6.3717 6447.03 3.8e+15
4000 4000 0 6.6210 6442.95 3.1e+15
4050 4050 0 6.8650 6449.87 4.0e+15
4100 4100 0 7.2377 6347.13 4.0e+15
4150 4150 0 7.3986 6439.10 3.7e+15
4200 4200 0 7.6634 6444.01 3.6e+15
4250 4250 0 7.9388 6445.28 3.3e+15
4300 4300 0 8.2192 6447.78 3.8e+15
4350 4350 0 8.5538 6414.17 3.6e+15
4400 4400 0 8.7952 6455.79 3.6e+15
4450 4450 0 9.1057 6450.60 3.7e+15
4500 4500 0 9.4134 6452.46 3.8e+15
4550 4550 0 9.7130 6464.26 3.7e+15
4600 4600 0 10.0578 6450.70 3.7e+15
4650 4650 0 10.3649 6465.93 4.1e+15
4700 4700 0 10.6976 6469.11 3.8e+15
4750 4750 0 11.0248 6479.66 3.8e+15
4800 4800 0 11.3945 6469.48 3.9e+15
4850 4850 0 11.7304 6482.68 3.9e+15
4900 4900 0 12.1114 6474.94 4.0e+15
4950 4950 0 12.5033 6465.96 3.7e+15
5000 5000 0 12.8522 6483.02 3.9e+15
5050 5050 0 13.2484 6479.72 4.0e+15
5100 5100 0 13.6411 6481.93 4.3e+15
5150 5150 0 14.0330 6488.10 3.8e+15
5200 5200 0 14.4639 6479.93 3.9e+15
5250 5250 0 14.8940 6476.11 3.9e+15
5300 5300 0 15.2852 6492.39 4.1e+15
5350 5350 0 15.6863 6507.11 3.9e+15
5400 5400 0 16.1517 6498.48 4.0e+15
5450 5450 0 16.5984 6500.86 3.9e+15
5500 5500 0 17.1079 6482.49 4.0e+15
5550 5550 0 17.5330 6499.40 3.9e+15
5600 5600 0 18.0103 6499.70 4.1e+15
5650 5650 0 18.5068 6496.28 4.0e+15
5700 5700 0 19.0011 6496.77 4.2e+15
5750 5750 0 19.4727 6507.72 4.2e+15
5800 5800 0 20.0324 6492.36 4.0e+15
5850 5850 0 20.4977 6510.51 4.1e+15
5900 5900 0 21.1107 6484.96 4.1e+15
5950 5950 0 21.5508 6515.41 4.0e+15
6000 6000 0 22.1123 6511.41 4.4e+15
$shell> cat report.zgetrf_openBLAS
# m n info FLENS/ulmBLAS: t MFLOPS openBLAS: t MFLOPS Residual
50 50 0 0.0002 331.17 1.6e+15
100 100 0 0.0008 847.42 1.9e+15
150 150 0 0.0023 969.53 2.5e+15
200 200 0 0.0032 1679.86 2.2e+15
250 250 0 0.0039 2672.04 2.0e+15
300 300 0 0.0065 2745.75 2.5e+15
350 350 0 0.0100 2842.04 2.1e+15
400 400 0 0.0148 2878.58 2.4e+15
450 450 0 0.0207 2931.23 2.4e+15
500 500 0 0.0280 2976.67 2.1e+15
550 550 0 0.0371 2982.67 2.2e+15
600 600 0 0.0476 3018.60 2.2e+15
650 650 0 0.0602 3040.15 2.6e+15
700 700 0 0.0744 3068.29 2.2e+15
750 750 0 0.0911 3085.72 2.3e+15
800 800 0 0.1103 3092.50 2.6e+15
850 850 0 0.1310 3122.67 2.3e+15
900 900 0 0.1548 3137.10 2.5e+15
950 950 0 0.1816 3145.27 2.6e+15
1000 1000 0 0.2108 3160.93 2.4e+15
1050 1050 0 0.2451 3146.46 2.7e+15
1100 1100 0 0.2804 3162.85 3.1e+15
1150 1150 0 0.3194 3172.78 2.4e+15
1200 1200 0 0.3619 3181.03 2.5e+15
1250 1250 0 0.4071 3196.18 2.5e+15
1300 1300 0 0.4571 3202.62 2.6e+15
1350 1350 0 0.5100 3214.22 2.9e+15
1400 1400 0 0.5676 3220.93 2.6e+15
1450 1450 0 0.6306 3221.49 2.8e+15
1500 1500 0 0.6954 3233.79 2.8e+15
1550 1550 0 0.7661 3239.13 3.0e+15
1600 1600 0 0.8437 3234.86 3.0e+15
1650 1650 0 0.9211 3249.86 2.7e+15
1700 1700 0 1.0060 3254.28 2.9e+15
1750 1750 0 1.0954 3260.25 3.0e+15
1800 1800 0 1.1900 3265.80 2.8e+15
1850 1850 0 1.2901 3270.61 3.3e+15
1900 1900 0 1.3964 3273.33 3.1e+15
1950 1950 0 1.5070 3278.86 2.9e+15
2000 2000 0 1.6264 3278.03 3.0e+15
2050 2050 0 1.7824 3221.11 3.0e+15
2100 2100 0 1.8839 3276.14 3.4e+15
2150 2150 0 2.0193 3279.98 3.5e+15
2200 2200 0 2.1601 3285.14 3.3e+15
2250 2250 0 2.3081 3288.92 3.0e+15
2300 2300 0 2.4640 3290.92 3.2e+15
2350 2350 0 2.6246 3295.48 3.1e+15
2400 2400 0 2.7982 3292.56 3.4e+15
2450 2450 0 2.9687 3301.46 3.0e+15
2500 2500 0 3.1534 3302.30 2.8e+15
2550 2550 0 3.3427 3306.03 3.3e+15
2600 2600 0 3.5391 3309.85 3.2e+15
2650 2650 0 3.7456 3311.29 3.5e+15
2700 2700 0 3.9577 3314.68 3.7e+15
2750 2750 0 4.1786 3317.08 3.1e+15
2800 2800 0 4.4089 3318.47 3.4e+15
2850 2850 0 4.6950 3286.17 3.7e+15
2900 2900 0 4.8905 3323.83 3.4e+15
2950 2950 0 5.1440 3326.29 3.3e+15
3000 3000 0 5.4058 3328.96 3.3e+15
3050 3050 0 5.6780 3330.47 3.4e+15
3100 3100 0 5.9629 3329.91 3.5e+15
3150 3150 0 6.2543 3330.90 3.1e+15
3200 3200 0 6.5740 3322.19 3.4e+15
3250 3250 0 6.8603 3335.16 3.7e+15
3300 3300 0 7.1755 3338.09 3.7e+15
3350 3350 0 7.5040 3339.30 3.7e+15
3400 3400 0 7.8371 3342.67 3.5e+15
3450 3450 0 8.2698 3309.62 3.6e+15
3500 3500 0 8.5440 3344.70 3.7e+15
3550 3550 0 8.9107 3346.49 3.4e+15
3600 3600 0 9.2918 3346.76 3.5e+15
3650 3650 0 9.6805 3348.11 3.6e+15
3700 3700 0 10.0759 3350.74 3.5e+15
3750 3750 0 10.4904 3350.60 3.2e+15
3800 3800 0 10.9083 3352.86 3.6e+15
3850 3850 0 11.3434 3353.23 3.8e+15
3900 3900 0 11.7879 3354.14 3.7e+15
3950 3950 0 12.2393 3356.30 3.5e+15
4000 4000 0 12.7102 3356.26 3.7e+15
4050 4050 0 13.1836 3358.61 3.9e+15
4100 4100 0 13.8998 3305.02 4.0e+15
4150 4150 0 14.2018 3354.53 3.6e+15
4200 4200 0 14.7256 3353.56 3.8e+15
4250 4250 0 15.2424 3356.95 3.8e+15
4300 4300 0 15.7778 3358.86 3.8e+15
4350 4350 0 16.3547 3354.75 3.8e+15
4400 4400 0 16.9018 3359.39 3.7e+15
4450 4450 0 17.4766 3360.92 3.9e+15
4500 4500 0 18.0597 3363.29 3.8e+15
4550 4550 0 18.6859 3360.14 4.0e+15
4600 4600 0 19.2745 3366.12 3.9e+15
4650 4650 0 19.9139 3365.44 4.2e+15
4700 4700 0 20.5580 3366.30 4.0e+15
4750 4750 0 21.2201 3366.46 3.7e+15
4800 4800 0 21.9089 3364.68 3.8e+15
4850 4850 0 22.5764 3368.31 4.0e+15
4900 4900 0 23.2692 3370.14 3.6e+15
4950 4950 0 23.9933 3369.52 4.0e+15
5000 5000 0 24.7060 3372.49 3.7e+15
5050 5050 0 25.4633 3371.34 3.8e+15
5100 5100 0 26.2123 3373.26 4.0e+15
5150 5150 0 27.0047 3371.54 4.1e+15
5200 5200 0 27.7879 3372.88 3.8e+15
5250 5250 0 28.5932 3373.35 4.4e+15
5300 5300 0 29.3951 3375.99 4.0e+15
5350 5350 0 30.2383 3375.60 3.8e+15
5400 5400 0 31.0669 3378.57 3.7e+15
5450 5450 0 31.9597 3376.26 4.0e+15
5500 5500 0 32.8235 3378.72 4.2e+15
5550 5550 0 33.7345 3377.96 3.8e+15
5600 5600 0 34.6503 3378.38 3.8e+15
5650 5650 0 35.7694 3361.12 4.1e+15
5700 5700 0 36.7353 3360.41 4.1e+15
5750 5750 0 37.4938 3379.84 4.0e+15
5800 5800 0 38.4607 3381.58 3.9e+15
5850 5850 0 39.5406 3375.03 4.0e+15
5900 5900 0 40.4562 3383.96 4.3e+15
5950 5950 0 41.5171 3382.03 4.1e+15
6000 6000 0 42.5525 3383.63 4.3e+15
$shell>