3400g onednn

AMD Ryzen 5 3400G testing with a ASUS PRIME B450M-A (2006 BIOS) and ASUS AMD Picasso 2GB on Ubuntu 19.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2103136-HA-3400GONED26.

3400g onednnProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverVulkanCompilerFile-SystemScreen Resolution123AMD Ryzen 5 3400G @ 3.70GHz (4 Cores / 8 Threads)ASUS PRIME B450M-A (2006 BIOS)AMD Raven/Raven22 x 8192 MB DDR4-3000MT/s CRUCIAL29GB INTEL MEMPEK1W032GA + 4 x 6001GB Seagate ST6000VN0033-2EEASUS AMD Picasso 2GB (1400/1500MHz)AMD Raven/Raven2/FenghuangSyncMasterRealtek RTL8111/8168/8411Ubuntu 19.105.3.0-46-generic (x86_64)GNOME Shell 3.34.1X Serverasus1.1.107GCC 9.2.1 20191008ext41280x800OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-offload-targets=nvptx-none,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: 0x8108109Security 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 + tsx_async_abort: Not affected

3400g onednnonednn: 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 - CPU12313.999711.483615.18213.1617319.787318.072225.747329.628213.677519.136713604.36892.5713646.36903.606.6286113611.76939.548.1436213.927911.480615.20533.1627919.765718.130325.491529.723613.693718.738113556.26898.0313664.56937.576.6415713619.96935.678.1515013.845011.548315.52543.1616819.846618.101725.715329.687513.683018.794913648.76949.0113702.26937.506.6676413654.66974.268.18932OpenBenchmarking.org

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU12348121620SE +/- 0.13, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 314.0013.9313.85MIN: 13.34MIN: 13.34MIN: 13.391. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU1233691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 311.4811.4811.55MIN: 11.33MIN: 11.33MIN: 11.331. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU12348121620SE +/- 0.15, N = 3SE +/- 0.19, N = 3SE +/- 0.19, N = 315.1815.2115.53MIN: 14.69MIN: 14.73MIN: 14.911. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU1230.71161.42322.13482.84643.558SE +/- 0.00440, N = 3SE +/- 0.00884, N = 3SE +/- 0.00413, N = 33.161733.162793.16168MIN: 2.96MIN: 2.94MIN: 2.951. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU123510152025SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 319.7919.7719.85MIN: 19.64MIN: 19.64MIN: 19.641. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU12348121620SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 318.0718.1318.10MIN: 17.49MIN: 17.58MIN: 17.551. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU123612182430SE +/- 0.31, N = 3SE +/- 0.06, N = 3SE +/- 0.27, N = 325.7525.4925.72MIN: 24.86MIN: 24.96MIN: 24.91. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU123714212835SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 329.6329.7229.69MIN: 29.38MIN: 29.45MIN: 29.41. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU12348121620SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 313.6813.6913.68MIN: 13.53MIN: 13.52MIN: 13.541. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU123510152025SE +/- 0.20, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 319.1418.7418.79MIN: 18.3MIN: 18.26MIN: 18.271. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU1233K6K9K12K15KSE +/- 41.87, N = 3SE +/- 110.56, N = 3SE +/- 65.94, N = 313604.313556.213648.7MIN: 13398.3MIN: 13358.8MIN: 13478.71. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU12315003000450060007500SE +/- 21.53, N = 3SE +/- 21.07, N = 3SE +/- 29.16, N = 36892.576898.036949.01MIN: 6812.75MIN: 6827.85MIN: 6863.791. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU1233K6K9K12K15KSE +/- 16.46, N = 3SE +/- 54.95, N = 3SE +/- 69.27, N = 313646.313664.513702.2MIN: 13326.6MIN: 13454.7MIN: 13493.11. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU12315003000450060007500SE +/- 13.13, N = 3SE +/- 23.53, N = 3SE +/- 15.77, N = 36903.606937.576937.50MIN: 6855.26MIN: 6872.44MIN: 6870.871. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU123246810SE +/- 0.01550, N = 3SE +/- 0.02363, N = 3SE +/- 0.04632, N = 36.628616.641576.66764MIN: 6.51MIN: 6.52MIN: 6.521. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU1233K6K9K12K15KSE +/- 91.56, N = 3SE +/- 80.68, N = 3SE +/- 83.29, N = 313611.713619.913654.6MIN: 13395.3MIN: 13417.5MIN: 13461.21. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU12315003000450060007500SE +/- 8.25, N = 3SE +/- 24.12, N = 3SE +/- 24.06, N = 36939.546935.676974.26MIN: 6878.17MIN: 6837.84MIN: 6882.621. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU123246810SE +/- 0.00679, N = 3SE +/- 0.01428, N = 3SE +/- 0.03126, N = 38.143628.151508.18932MIN: 8.06MIN: 8.07MIN: 8.071. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Phoronix Test Suite v10.8.4