NKL DNN UPDATED

Intel Core i7-8086K testing with a ASUS PRIME Z370-A (1802 BIOS) and Intel UHD 630 3GB on Ubuntu 18.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/1904192-PTS-NKLDNNUP40.

NKL DNN UPDATEDProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionIntel Core i7-8086KIntel Core i7-8086K @ 5.00GHz (6 Cores / 12 Threads)ASUS PRIME Z370-A (1802 BIOS)Intel 8th Gen Core8192MB118GB INTEL SSDPEK1W120GAIntel UHD 630 3GB (1200MHz)Realtek ALC1220DELL P2415QIntel I219-VUbuntu 18.104.18.0-17-generic (x86_64)GNOME Shell 3.30.2X Server 1.20.1modesetting 1.20.14.5 Mesa 18.2.21.1.80GCC 8.2.0ext43840x2160OpenBenchmarking.org- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v - Scaling Governor: intel_pstate powersave- KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW STIBP + SSB disabled via prctl and seccomp + PTE Inversion

NKL DNN UPDATEDmkl-dnn: IP Batch 1D - f32mkl-dnn: IP Batch All - f32mkl-dnn: IP Batch 1D - u8s8u8s32mkl-dnn: IP Batch 1D - u8s8f32s32mkl-dnn: IP Batch All - u8s8u8s32mkl-dnn: IP Batch All - u8s8f32s32mkl-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_3d - u8s8f32s32mkl-dnn: Convolution Batch conv_all - u8s8u8s32mkl-dnn: Convolution Batch conv_all - u8s8f32s32mkl-dnn: Convolution Batch conv_googlenet_v3 - f32mkl-dnn: Deconvolution Batch deconv_1d - u8s8u8s32mkl-dnn: Deconvolution Batch deconv_3d - u8s8u8s32mkl-dnn: Convolution Batch conv_alexnet - u8s8u8s32mkl-dnn: Deconvolution Batch deconv_1d - u8s8f32s32mkl-dnn: Deconvolution Batch deconv_3d - u8s8f32s32mkl-dnn: Deconvolution Batch deconv_all - u8s8u8s32mkl-dnn: Convolution Batch conv_alexnet - u8s8f32s32mkl-dnn: Convolution Batch conv_googlenet_v3 - u8s8u8s32mkl-dnn: Convolution Batch conv_googlenet_v3 - u8s8f32s32Intel Core i7-8086K10.12139.896.436.4377.9276.9325.323419.206.998.75447.674061.0123974.0723972.1326742.9726346.83191.668431.3613754.17978.278238.1113484.6025675934.86446.32422.18OpenBenchmarking.org

MKL-DNN

Harness: IP Batch 1D - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch 1D - Data Type: f32Intel Core i7-8086K3691215SE +/- 0.10, N = 310.12MIN: 5.741. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MKL-DNN

Harness: IP Batch All - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch All - Data Type: f32Intel Core i7-8086K306090120150SE +/- 1.41, N = 3139.89MIN: 84.391. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MKL-DNN

Harness: IP Batch 1D - Data Type: u8s8u8s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch 1D - Data Type: u8s8u8s32Intel Core i7-8086K246810SE +/- 0.04, N = 36.43MIN: 3.491. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MKL-DNN

Harness: IP Batch 1D - Data Type: u8s8f32s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch 1D - Data Type: u8s8f32s32Intel Core i7-8086K246810SE +/- 0.04, N = 36.43MIN: 3.421. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MKL-DNN

Harness: IP Batch All - Data Type: u8s8u8s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch All - Data Type: u8s8u8s32Intel Core i7-8086K20406080100SE +/- 0.18, N = 377.92MIN: 42.221. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MKL-DNN

Harness: IP Batch All - Data Type: u8s8f32s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch All - Data Type: u8s8f32s32Intel Core i7-8086K20406080100SE +/- 0.80, N = 376.93MIN: 41.821. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

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: f32Intel Core i7-8086K612182430SE +/- 0.01, N = 325.32MIN: 25.111. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -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: f32Intel Core i7-8086K7001400210028003500SE +/- 0.31, N = 33419.20MIN: 3409.781. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -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: f32Intel Core i7-8086K246810SE +/- 0.02, N = 36.99MIN: 6.821. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -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: f32Intel Core i7-8086K246810SE +/- 0.01, N = 38.75MIN: 8.71. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -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: f32Intel Core i7-8086K100200300400500SE +/- 1.07, N = 3447.67MIN: 445.631. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -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: f32Intel Core i7-8086K9001800270036004500SE +/- 10.01, N = 34061.01MIN: 3789.481. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -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: u8s8u8s32Intel Core i7-8086K5K10K15K20K25KSE +/- 10.94, N = 323974.07MIN: 23869.11. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MKL-DNN

Harness: Convolution Batch conv_3d - Data Type: u8s8f32s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_3d - Data Type: u8s8f32s32Intel Core i7-8086K5K10K15K20K25KSE +/- 7.71, N = 323972.13MIN: 23867.61. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -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: u8s8u8s32Intel Core i7-8086K6K12K18K24K30KSE +/- 7.16, N = 326742.97MIN: 26118.81. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MKL-DNN

Harness: Convolution Batch conv_all - Data Type: u8s8f32s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_all - Data Type: u8s8f32s32Intel Core i7-8086K6K12K18K24K30KSE +/- 16.85, N = 326346.83MIN: 25778.11. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MKL-DNN

Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32Intel Core i7-8086K4080120160200SE +/- 0.09, N = 3191.66MIN: 190.481. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -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: u8s8u8s32Intel Core i7-8086K2K4K6K8K10KSE +/- 0.93, N = 38431.36MIN: 8404.011. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MKL-DNN

Harness: Deconvolution Batch deconv_3d - Data Type: u8s8u8s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_3d - Data Type: u8s8u8s32Intel Core i7-8086K3K6K9K12K15KSE +/- 3.03, N = 313754.17MIN: 13725.51. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -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: u8s8u8s32Intel Core i7-8086K2004006008001000SE +/- 9.64, N = 15978.27MIN: 870.311. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MKL-DNN

Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32s32Intel Core i7-8086K2K4K6K8K10KSE +/- 4.77, N = 38238.11MIN: 8206.651. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MKL-DNN

Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32s32Intel Core i7-8086K3K6K9K12K15KSE +/- 9.28, N = 313484.60MIN: 13453.61. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MKL-DNN

Harness: Deconvolution Batch deconv_all - Data Type: u8s8u8s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_all - Data Type: u8s8u8s32Intel Core i7-8086K5K10K15K20K25KSE +/- 28.36, N = 325675MIN: 25204.71. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MKL-DNN

Harness: Convolution Batch conv_alexnet - Data Type: u8s8f32s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_alexnet - Data Type: u8s8f32s32Intel Core i7-8086K2004006008001000SE +/- 10.58, N = 3934.86MIN: 844.941. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MKL-DNN

Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8u8s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8u8s32Intel Core i7-8086K100200300400500SE +/- 1.82, N = 3446.32MIN: 385.091. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MKL-DNN

Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8f32s32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8f32s32Intel Core i7-8086K90180270360450SE +/- 0.70, N = 3422.18MIN: 364.371. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

Phoronix Test Suite v10.8.4