AMD Ryzen 9 5900HX testing with a ASUS G513QY v1.0 (G513QY.311 BIOS) and ASUS AMD Cezanne 512MB on Ubuntu 21.10 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2203307-PTS-5900HXON51 5900HX oneDNN 2.6 - Phoronix Test Suite 5900HX oneDNN 2.6 AMD Ryzen 9 5900HX testing with a ASUS G513QY v1.0 (G513QY.311 BIOS) and ASUS AMD Cezanne 512MB on Ubuntu 21.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2203307-PTS-5900HXON51&sro&grr .
5900HX oneDNN 2.6 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution A B C AMD Ryzen 9 5900HX @ 3.30GHz (8 Cores / 16 Threads) ASUS G513QY v1.0 (G513QY.311 BIOS) AMD Renoir/Cezanne 16GB 512GB SAMSUNG MZVLQ512HBLU-00B00 ASUS AMD Cezanne 512MB (2500/1000MHz) AMD Navi 21 HDMI Audio LQ156M1JW25 Realtek RTL8111/8168/8411 + MEDIATEK Device 7961 Ubuntu 21.10 5.17.0-051700-generic (x86_64) GNOME Shell 40.5 X Server + Wayland 4.6 Mesa 22.0.0-devel (git-9cb9101 2022-01-08 impish-oibaf-ppa) (LLVM 13.0.0 DRM 3.44) 1.2.199 GCC 11.2.0 ext4 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --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: acpi-cpufreq schedutil (Boost: Enabled) - Platform Profile: balanced - CPU Microcode: 0xa50000c - ACPI Profile: balanced Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
5900HX oneDNN 2.6 onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Recurrent Neural Network Training - u8s8f32 - CPU onednn: Recurrent Neural Network Training - f32 - CPU onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onednn: Deconvolution Batch shapes_1d - f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU onednn: IP Shapes 1D - f32 - CPU onednn: IP Shapes 1D - u8s8f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU onednn: IP Shapes 3D - f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: Deconvolution Batch shapes_3d - f32 - CPU onednn: IP Shapes 1D - bf16bf16bf16 - CPU A B C 2841.99 3973.67 3953.61 3940.55 2800.24 2815.85 8.43701 2.42556 1.88996 3.77392 1.29851 6.32732 2.83644 15.6560 3.55750 32.9312 31.3307 6.52829 2802.08 3941.94 3928.54 3926.07 2816.45 2819.76 8.56397 2.37036 1.88868 3.83164 1.29782 6.30537 2.87484 15.1114 3.54426 32.7219 31.2879 6.41569 2823.98 3941.25 3939.75 3935.10 2801.18 2801.28 8.64910 2.36683 1.88893 3.79418 1.30146 6.26398 2.90026 14.3342 3.38402 32.5036 31.2254 6.41738 OpenBenchmarking.org
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU A B C 600 1200 1800 2400 3000 SE +/- 29.06, N = 15 SE +/- 8.65, N = 3 SE +/- 24.07, N = 8 2841.99 2802.08 2823.98 MIN: 2763.48 MIN: 2773.01 MIN: 2764.44 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU A B C 900 1800 2700 3600 4500 SE +/- 32.58, N = 3 SE +/- 1.63, N = 3 SE +/- 5.18, N = 3 3973.67 3941.94 3941.25 MIN: 3914.02 MIN: 3916.45 MIN: 3909.14 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU A B C 800 1600 2400 3200 4000 SE +/- 4.49, N = 3 SE +/- 3.70, N = 3 SE +/- 3.09, N = 3 3953.61 3928.54 3939.75 MIN: 3920.42 MIN: 3905.11 MIN: 3911.82 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU A B C 800 1600 2400 3200 4000 SE +/- 5.81, N = 3 SE +/- 5.66, N = 3 SE +/- 1.40, N = 3 3940.55 3926.07 3935.10 MIN: 3903.19 MIN: 3889.83 MIN: 3909.64 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU A B C 600 1200 1800 2400 3000 SE +/- 7.66, N = 3 SE +/- 7.15, N = 3 SE +/- 0.88, N = 3 2800.24 2816.45 2801.18 MIN: 2777.51 MIN: 2798.14 MIN: 2785 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU A B C 600 1200 1800 2400 3000 SE +/- 8.10, N = 3 SE +/- 6.18, N = 3 SE +/- 5.92, N = 3 2815.85 2819.76 2801.28 MIN: 2783.37 MIN: 2796.92 MIN: 2777.49 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU A B C 2 4 6 8 10 SE +/- 0.10958, N = 3 SE +/- 0.08416, N = 15 SE +/- 0.17417, N = 12 8.43701 8.56397 8.64910 MIN: 5.52 MIN: 5.54 MIN: 5.51 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU A B C 0.5458 1.0916 1.6374 2.1832 2.729 SE +/- 0.04682, N = 14 SE +/- 0.00327, N = 3 SE +/- 0.00822, N = 3 2.42556 2.37036 2.36683 MIN: 2.26 MIN: 2.28 MIN: 2.26 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU A B C 0.4252 0.8504 1.2756 1.7008 2.126 SE +/- 0.00698, N = 3 SE +/- 0.00594, N = 3 SE +/- 0.00266, N = 3 1.88996 1.88868 1.88893 MIN: 1.8 MIN: 1.8 MIN: 1.79 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU A B C 0.8621 1.7242 2.5863 3.4484 4.3105 SE +/- 0.02746, N = 3 SE +/- 0.00208, N = 3 SE +/- 0.01719, N = 3 3.77392 3.83164 3.79418 MIN: 3.51 MIN: 3.58 MIN: 3.53 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU A B C 0.2928 0.5856 0.8784 1.1712 1.464 SE +/- 0.01208, N = 3 SE +/- 0.01165, N = 3 SE +/- 0.00984, N = 3 1.29851 1.29782 1.30146 MIN: 1.25 MIN: 1.25 MIN: 1.25 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU A B C 2 4 6 8 10 SE +/- 0.00610, N = 3 SE +/- 0.00210, N = 3 SE +/- 0.00464, N = 3 6.32732 6.30537 6.26398 MIN: 6.14 MIN: 6.13 MIN: 6.09 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU A B C 0.6526 1.3052 1.9578 2.6104 3.263 SE +/- 0.02338, N = 3 SE +/- 0.03458, N = 15 SE +/- 0.05737, N = 15 2.83644 2.87484 2.90026 MIN: 2.61 MIN: 2.56 MIN: 2.56 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU A B C 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 15.66 15.11 14.33 MIN: 15.44 MIN: 14.83 MIN: 13.92 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU A B C 0.8004 1.6008 2.4012 3.2016 4.002 SE +/- 0.01706, N = 3 SE +/- 0.00555, N = 3 SE +/- 0.00505, N = 3 3.55750 3.54426 3.38402 MIN: 3.45 MIN: 3.47 MIN: 3.31 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU A B C 8 16 24 32 40 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 32.93 32.72 32.50 MIN: 32.45 MIN: 32.02 MIN: 31.51 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU A B C 7 14 21 28 35 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 31.33 31.29 31.23 MIN: 30.93 MIN: 30.93 MIN: 30.75 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU A B C 2 4 6 8 10 SE +/- 0.06187, N = 6 SE +/- 0.00452, N = 3 SE +/- 0.03351, N = 3 6.52829 6.41569 6.41738 MIN: 6.23 MIN: 6.25 MIN: 6.25 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
Phoronix Test Suite v10.8.4