oneDNN 2.0 Ryzen 3

AMD Ryzen 3 3200U testing with a MOTILE PF4PU1F (N.1.03 BIOS) and AMD Picasso 512MB on Ubuntu 20.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2012090-HA-ONEDNN20R48.

oneDNN 2.0 Ryzen 3ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen Resolution123AMD Ryzen 3 3200U @ 2.60GHz (2 Cores / 4 Threads)MOTILE PF4PU1F (N.1.03 BIOS)AMD Raven/Raven23584MB128GB BIWIN SSDAMD Picasso 512MB (1200/1200MHz)AMD Raven/Raven2/FenghuangRealtek RTL8111/8168/8411 + Intel Dual Band-AC 3168NGWUbuntu 20.045.4.0-53-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8amdgpu 19.1.04.6 Mesa 20.0.4 (LLVM 9.0.1)GCC 9.3.0ext41920x1080OpenBenchmarking.orgCompiler 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: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8108102 Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + 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 AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

oneDNN 2.0 Ryzen 3onednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU12339.456019.426928.32567.7634548.794651.539162.987769.106152.340052.782812605.012793.912805.412736.616.424112657.912769.627.028840.082818.009428.53657.7667949.548251.983263.438768.963655.323153.347812549.512850.112756.212758.116.323012844.712815.727.031139.601017.930328.39567.8146049.416851.664763.340869.247355.490853.325712602.212787.212661.512803.116.397212605.412808.827.5059OpenBenchmarking.org

oneDNN

Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU123918273645SE +/- 0.40, N = 8SE +/- 0.40, N = 14SE +/- 0.35, N = 1439.4640.0839.60MIN: 32.5MIN: 31.9MIN: 31.791. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU123510152025SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 319.4318.0117.93MIN: 19.27MIN: 17.84MIN: 17.781. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU123714212835SE +/- 0.16, N = 3SE +/- 0.17, N = 3SE +/- 0.17, N = 328.3328.5428.40MIN: 25.26MIN: 24.35MIN: 24.661. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU123246810SE +/- 0.09144, N = 3SE +/- 0.12342, N = 3SE +/- 0.08989, N = 37.763457.766797.81460MIN: 6.34MIN: 6.31MIN: 6.41. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU1231122334455SE +/- 0.27, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 348.7949.5549.42MIN: 46.88MIN: 47.48MIN: 47.41. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU1231224364860SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.14, N = 351.5451.9851.66MIN: 46.07MIN: 45.43MIN: 45.321. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU1231428425670SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 362.9963.4463.34MIN: 59.65MIN: 60.24MIN: 60.641. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU1231530456075SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.19, N = 369.1168.9669.25MIN: 68.74MIN: 68.53MIN: 68.631. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU1231224364860SE +/- 0.29, N = 3SE +/- 0.84, N = 15SE +/- 0.92, N = 1252.3455.3255.49MIN: 47.29MIN: 47.06MIN: 46.561. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU1231224364860SE +/- 0.15, N = 3SE +/- 0.28, N = 3SE +/- 0.68, N = 1552.7853.3553.33MIN: 48.62MIN: 49.25MIN: 47.61. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU1233K6K9K12K15KSE +/- 71.71, N = 3SE +/- 68.31, N = 3SE +/- 102.56, N = 312605.012549.512602.2MIN: 12420.5MIN: 12337.1MIN: 12304.71. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU1233K6K9K12K15KSE +/- 42.78, N = 3SE +/- 19.19, N = 3SE +/- 31.15, N = 312793.912850.112787.2MIN: 12606.8MIN: 12678.4MIN: 12624.41. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU1233K6K9K12K15KSE +/- 125.57, N = 9SE +/- 63.60, N = 3SE +/- 41.66, N = 312805.412756.212661.5MIN: 12372MIN: 12549MIN: 125011. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU1233K6K9K12K15KSE +/- 69.61, N = 3SE +/- 28.97, N = 3SE +/- 28.05, N = 312736.612758.112803.1MIN: 12531.2MIN: 12588MIN: 12650.71. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU12348121620SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 316.4216.3216.40MIN: 15.31MIN: 14.99MIN: 15.071. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU1233K6K9K12K15KSE +/- 33.54, N = 3SE +/- 80.90, N = 3SE +/- 82.68, N = 312657.912844.712605.4MIN: 12498.2MIN: 12586.6MIN: 12362.31. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU1233K6K9K12K15KSE +/- 40.85, N = 3SE +/- 21.50, N = 3SE +/- 15.32, N = 312769.612815.712808.8MIN: 12600MIN: 12666.6MIN: 12660.71. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU123612182430SE +/- 0.22, N = 15SE +/- 0.21, N = 15SE +/- 0.03, N = 327.0327.0327.51MIN: 21.97MIN: 22.25MIN: 23.031. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Phoronix Test Suite v10.8.4