Cascade MKL DNN

2 x Intel Xeon Platinum 8280 testing with a GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS) and ASPEED Family on Ubuntu 18.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/1904181-HV-CASCADEMK90.

Cascade MKL DNNProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen Resolutionskylake-avx512cascadelake2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads)GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS)Intel Sky Lake-E DMI3 Registers386048MBSamsung SSD 970 PRO 512GBASPEED FamilyVE2282 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbEUbuntu 18.045.1.0-999-generic (x86_64) 20190416GNOME Shell 3.28.3X Server 1.20.1modesetting 1.20.1GCC 9.0.1 20190414ext41920x1080OpenBenchmarking.orgEnvironment Details- skylake-avx512: CXXFLAGS=-O3-march=skylake-avx512 CFLAGS=-O3-march=skylake-avx512- cascadelake: CXXFLAGS=-O3-march=cascadelake CFLAGS=-O3-march=cascadelakeCompiler Details- --disable-multilib --enable-checking=releaseProcessor Details- Scaling Governor: intel_pstate powersaveSecurity Details- __user pointer sanitization + Enhanced IBRS IBPB: conditional RSB filling + SSB disabled via prctl and seccomp

Cascade MKL DNNmkl-dnn: Convolution Batch conv_3d - f32mkl-dnn: Convolution Batch conv_all - f32mkl-dnn: Deconvolution Batch deconv_1d - f32mkl-dnn: Deconvolution Batch deconv_3d - f32mkl-dnn: Convolution Batch conv_alexnet - f32mkl-dnn: Deconvolution Batch deconv_all - f32mkl-dnn: Convolution Batch conv_3d - u8s8u8s32mkl-dnn: Convolution Batch conv_all - u8s8u8s32mkl-dnn: Deconvolution Batch deconv_1d - u8s8u8s32mkl-dnn: Convolution Batch conv_alexnet - u8s8u8s32skylake-avx512cascadelake4.993931.362.5055.358364.483891.3156.084.373901.242.3252.168264.453911.3255.11OpenBenchmarking.org

MKL-DNN

Harness: Convolution Batch conv_3d - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_3d - Data Type: f32skylake-avx512cascadelake1.12282.24563.36844.49125.614SE +/- 0.06, N = 3SE +/- 0.08, N = 154.994.37MIN: 4.22-march=cascadelake - MIN: 3.741. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl

MKL-DNN

Harness: Convolution Batch conv_all - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_all - Data Type: f32skylake-avx512cascadelake90180270360450SE +/- 2.13, N = 3SE +/- 0.65, N = 3393390MIN: 382.18-march=cascadelake - MIN: 382.161. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl

MKL-DNN

Harness: Deconvolution Batch deconv_1d - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_1d - Data Type: f32skylake-avx512cascadelake0.3060.6120.9181.2241.53SE +/- 0.05, N = 15SE +/- 0.03, N = 151.361.24MIN: 1.03-march=cascadelake - MIN: 11. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl

MKL-DNN

Harness: Deconvolution Batch deconv_3d - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_3d - Data Type: f32skylake-avx512cascadelake0.56251.1251.68752.252.8125SE +/- 0.12, N = 12SE +/- 0.14, N = 152.502.32MIN: 1.13-march=cascadelake - MIN: 1.121. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl

MKL-DNN

Harness: Convolution Batch conv_alexnet - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_alexnet - Data Type: f32skylake-avx512cascadelake1224364860SE +/- 0.97, N = 12SE +/- 0.51, N = 355.3552.16MIN: 48.37-march=cascadelake - MIN: 48.311. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl

MKL-DNN

Harness: Deconvolution Batch deconv_all - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_all - Data Type: f32skylake-avx512cascadelake2004006008001000SE +/- 8.63, N = 8SE +/- 1.54, N = 3836826MIN: 810.11-march=cascadelake - MIN: 812.241. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl

MKL-DNN

Harness: Convolution Batch conv_3d - Data Type: u8s8u8s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_3d - Data Type: u8s8u8s32skylake-avx512cascadelake1.0082.0163.0244.0325.04SE +/- 0.07, N = 15SE +/- 0.07, N = 154.484.45MIN: 3.62-march=cascadelake - MIN: 3.781. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl

MKL-DNN

Harness: Convolution Batch conv_all - Data Type: u8s8u8s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_all - Data Type: u8s8u8s32skylake-avx512cascadelake80160240320400SE +/- 0.28, N = 3SE +/- 1.39, N = 3389391MIN: 382.25-march=cascadelake - MIN: 382.281. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl

MKL-DNN

Harness: Deconvolution Batch deconv_1d - Data Type: u8s8u8s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_1d - Data Type: u8s8u8s32skylake-avx512cascadelake0.2970.5940.8911.1881.485SE +/- 0.04, N = 15SE +/- 0.04, N = 151.311.32MIN: 1.02-march=cascadelake - MIN: 0.991. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl

MKL-DNN

Harness: Convolution Batch conv_alexnet - Data Type: u8s8u8s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_alexnet - Data Type: u8s8u8s32skylake-avx512cascadelake1326395265SE +/- 1.06, N = 13SE +/- 0.79, N = 1556.0855.11MIN: 48.29-march=cascadelake - MIN: 48.131. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl

Phoronix Test Suite v10.8.5