Xeon E3 oneDNN 2.0 Intel Xeon E3-1280 v5 testing with a MSI Z170A SLI PLUS (MS-7998) v1.0 (2.A0 BIOS) and ASUS AMD Radeon HD 7850 / R7 265 R9 270 1024SP on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2012094-HA-XEONE3ONE76 .
Xeon E3 oneDNN 2.0 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution 1 2 3 Intel Xeon E3-1280 v5 @ 4.00GHz (4 Cores / 8 Threads) MSI Z170A SLI PLUS (MS-7998) v1.0 (2.A0 BIOS) Intel Xeon E3-1200 v5/E3-1500 32GB 256GB TOSHIBA RD400 ASUS AMD Radeon HD 7850 / R7 265 R9 270 1024SP Realtek ALC1150 VA2431 Intel I219-V Ubuntu 20.04 5.9.0-050900rc2daily20200826-generic (x86_64) 20200825 GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 4.5 Mesa 20.0.8 (LLVM 10.0.0) GCC 9.3.0 ext4 1920x1080 OpenBenchmarking.org Compiler Details - --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --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=auto --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: intel_pstate powersave - CPU Microcode: 0xe2 - Thermald 1.9.1 Security Details - itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable
Xeon E3 oneDNN 2.0 onednn: IP Shapes 1D - f32 - CPU onednn: IP Shapes 3D - f32 - CPU onednn: IP Shapes 1D - u8s8f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: Deconvolution Batch shapes_1d - f32 - CPU onednn: Deconvolution Batch shapes_3d - f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU onednn: Recurrent Neural Network Training - f32 - CPU onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Recurrent Neural Network Training - u8s8f32 - CPU onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU 1 2 3 8.11023 12.2717 3.66378 3.23290 20.9101 10.5999 14.3985 20.6333 11.3253 7.43783 7402.18 3950.40 7403.96 3952.60 5.38679 7397.77 3951.82 6.90131 8.13349 12.2502 3.66363 3.23315 20.8975 10.5924 14.3965 20.5155 11.0758 7.44242 7401.84 3954.92 7400.59 3953.55 5.38858 7401.56 3954.41 6.90507 8.10394 12.2610 3.66143 3.22697 20.9165 10.5889 14.4297 20.4948 11.3119 7.43292 7402.39 3949.85 7406.71 3949.87 5.37225 7397.07 3949.09 6.90071 OpenBenchmarking.org
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU 1 2 3 2 4 6 8 10 SE +/- 0.01358, N = 3 SE +/- 0.00686, N = 3 SE +/- 0.01643, N = 3 8.11023 8.13349 8.10394 MIN: 7.93 MIN: 7.97 MIN: 7.95 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU 1 2 3 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 12.27 12.25 12.26 MIN: 12.09 MIN: 12.07 MIN: 12.05 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU 1 2 3 0.8244 1.6488 2.4732 3.2976 4.122 SE +/- 0.00042, N = 3 SE +/- 0.00342, N = 3 SE +/- 0.00315, N = 3 3.66378 3.66363 3.66143 MIN: 3.63 MIN: 3.63 MIN: 3.63 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU 1 2 3 0.7275 1.455 2.1825 2.91 3.6375 SE +/- 0.00893, N = 3 SE +/- 0.00755, N = 3 SE +/- 0.00705, N = 3 3.23290 3.23315 3.22697 MIN: 3.16 MIN: 3.16 MIN: 3.16 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU 1 2 3 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 20.91 20.90 20.92 MIN: 20.84 MIN: 20.83 MIN: 20.82 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU 1 2 3 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 10.60 10.59 10.59 MIN: 10.5 MIN: 10.5 MIN: 10.5 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU 1 2 3 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 14.40 14.40 14.43 MIN: 14.2 MIN: 14.23 MIN: 14.25 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU 1 2 3 5 10 15 20 25 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 20.63 20.52 20.49 MIN: 20.4 MIN: 20.38 MIN: 20.39 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU 1 2 3 3 6 9 12 15 SE +/- 0.09, N = 3 SE +/- 0.01, N = 3 SE +/- 0.12, N = 3 11.33 11.08 11.31 MIN: 11.07 MIN: 10.98 MIN: 10.99 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU 1 2 3 2 4 6 8 10 SE +/- 0.00700, N = 3 SE +/- 0.00268, N = 3 SE +/- 0.01275, N = 3 7.43783 7.44242 7.43292 MIN: 7.39 MIN: 7.4 MIN: 7.37 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU 1 2 3 1600 3200 4800 6400 8000 SE +/- 1.79, N = 3 SE +/- 2.29, N = 3 SE +/- 2.88, N = 3 7402.18 7401.84 7402.39 MIN: 7383.43 MIN: 7388.05 MIN: 7389.3 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU 1 2 3 800 1600 2400 3200 4000 SE +/- 0.48, N = 3 SE +/- 2.81, N = 3 SE +/- 1.24, N = 3 3950.40 3954.92 3949.85 MIN: 3942.05 MIN: 3944.12 MIN: 3940.26 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU 1 2 3 1600 3200 4800 6400 8000 SE +/- 1.28, N = 3 SE +/- 2.41, N = 3 SE +/- 7.65, N = 3 7403.96 7400.59 7406.71 MIN: 7391.29 MIN: 7384.55 MIN: 7379.88 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU 1 2 3 800 1600 2400 3200 4000 SE +/- 1.74, N = 3 SE +/- 1.94, N = 3 SE +/- 0.92, N = 3 3952.60 3953.55 3949.87 MIN: 3942.3 MIN: 3943.31 MIN: 3944.88 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU 1 2 3 1.2124 2.4248 3.6372 4.8496 6.062 SE +/- 0.00577, N = 3 SE +/- 0.00794, N = 3 SE +/- 0.01548, N = 3 5.38679 5.38858 5.37225 MIN: 5.31 MIN: 5.32 MIN: 5.29 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU 1 2 3 1600 3200 4800 6400 8000 SE +/- 2.95, N = 3 SE +/- 2.59, N = 3 SE +/- 5.25, N = 3 7397.77 7401.56 7397.07 MIN: 7386.84 MIN: 7390.11 MIN: 7383.82 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU 1 2 3 800 1600 2400 3200 4000 SE +/- 3.51, N = 3 SE +/- 2.44, N = 3 SE +/- 1.54, N = 3 3951.82 3954.41 3949.09 MIN: 3942.06 MIN: 3941.1 MIN: 3941.43 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU 1 2 3 2 4 6 8 10 SE +/- 0.00304, N = 3 SE +/- 0.00574, N = 3 SE +/- 0.00762, N = 3 6.90131 6.90507 6.90071 MIN: 6.85 MIN: 6.85 MIN: 6.86 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Phoronix Test Suite v10.8.4