3990X sysbench onednn

AMD Ryzen Threadripper 3990X 64-Core testing with a System76 Thelio Major (F4c Z5 BIOS) and AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB on Pop 20.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2103132-PTS-3990XSYS94&rdt&grt.

3990X sysbench onednnProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen Resolution1234AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads)System76 Thelio Major (F4c Z5 BIOS)AMD Starship/Matisse126GBSamsung SSD 970 EVO Plus 500GBAMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz)AMD Navi 10 HDMI AudioDELL P2415QIntel I211 + Intel Wi-Fi 6 AX200Pop 20.105.8.0-7630-generic (x86_64)GNOME Shell 3.38.2X Server 1.20.84.6 Mesa 21.1.0-devel (git-96d7555 2021-01-22 groovy-oibaf-ppa) (LLVM 11.0.1)1.2.145GCC 10.2.0 + Clang 11.0.1-1~oibaf~gext43840x2160OpenBenchmarking.orgKernel Details- snd_usb_audio.ignore_ctl_error=1 - Transparent Huge Pages: madviseCompiler 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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/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: 0x8301025Security 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: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

3990X sysbench 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 - CPUsysbench: RAM / Memorysysbench: CPU12341.235085.372211.472431.0021510.9461257.566502.021316.527830.8909760.9479413741.53743.9723780.64743.1970.4119153750.35742.7880.6677057515.51124312.601.257248.442701.489451.026891.025497.624992.035856.636250.8967070.9547593770.99744.4713750.45747.6330.4154203759.67744.7870.6687147520.15123807.731.249538.576651.501431.032521.081297.591922.043026.588480.8954180.9538203747.70746.4503760.17745.8170.4119183747.38743.5810.6671927511.92123768.961.238328.119461.462911.035481.082807.706342.026476.656080.8894030.9540163730.17744.3523721.68747.8140.4171223733.74746.7020.6707357484.70123660.73OpenBenchmarking.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: CPU12340.28290.56580.84871.13161.4145SE +/- 0.00292, N = 3SE +/- 0.00760, N = 3SE +/- 0.00826, N = 3SE +/- 0.00828, N = 31.235081.257241.249531.23832MIN: 1.19MIN: 1.2MIN: 1.2MIN: 1.191. (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: CPU1234246810SE +/- 0.01315, N = 3SE +/- 0.11123, N = 3SE +/- 0.01501, N = 3SE +/- 0.02779, N = 35.372218.442708.576658.11946MIN: 5.17MIN: 8.09MIN: 8.33MIN: 7.821. (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: CPU12340.33780.67561.01341.35121.689SE +/- 0.00777, N = 3SE +/- 0.00450, N = 3SE +/- 0.00467, N = 3SE +/- 0.00627, N = 31.472431.489451.501431.46291MIN: 1.26MIN: 1.28MIN: 1.28MIN: 1.241. (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: CPU12340.2330.4660.6990.9321.165SE +/- 0.001528, N = 3SE +/- 0.002666, N = 3SE +/- 0.002913, N = 3SE +/- 0.002595, N = 31.0021511.0268901.0325201.035480MIN: 0.95MIN: 0.98MIN: 0.98MIN: 0.981. (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: CPU12340.24360.48720.73080.97441.218SE +/- 0.006847, N = 3SE +/- 0.016517, N = 3SE +/- 0.002000, N = 3SE +/- 0.009734, N = 30.9461251.0254901.0812901.082800MIN: 0.85MIN: 0.92MIN: 0.98MIN: 0.981. (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: CPU1234246810SE +/- 0.02931, N = 3SE +/- 0.02617, N = 3SE +/- 0.00967, N = 3SE +/- 0.01670, N = 37.566507.624997.591927.70634MIN: 6.16MIN: 6.17MIN: 6.56MIN: 6.611. (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: CPU12340.45970.91941.37911.83882.2985SE +/- 0.00410, N = 3SE +/- 0.00592, N = 3SE +/- 0.00417, N = 3SE +/- 0.00241, N = 32.021312.035852.043022.02647MIN: 1.93MIN: 1.96MIN: 1.97MIN: 1.961. (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: CPU1234246810SE +/- 0.01403, N = 3SE +/- 0.02161, N = 3SE +/- 0.00793, N = 3SE +/- 0.01940, N = 36.527836.636256.588486.65608MIN: 6.36MIN: 6.5MIN: 6.47MIN: 6.511. (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: CPU12340.20180.40360.60540.80721.009SE +/- 0.001294, N = 3SE +/- 0.002296, N = 3SE +/- 0.002330, N = 3SE +/- 0.000457, N = 30.8909760.8967070.8954180.889403MIN: 0.84MIN: 0.84MIN: 0.84MIN: 0.841. (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: CPU12340.21480.42960.64440.85921.074SE +/- 0.002129, N = 3SE +/- 0.001253, N = 3SE +/- 0.000086, N = 3SE +/- 0.000529, N = 30.9479410.9547590.9538200.954016MIN: 0.9MIN: 0.9MIN: 0.89MIN: 0.91. (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: CPU12348001600240032004000SE +/- 3.42, N = 3SE +/- 3.71, N = 3SE +/- 5.93, N = 3SE +/- 10.20, N = 33741.533770.993747.703730.17MIN: 3720.38MIN: 3740.38MIN: 3723.93MIN: 3690.551. (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: CPU1234160320480640800SE +/- 2.22, N = 3SE +/- 0.50, N = 3SE +/- 1.44, N = 3SE +/- 1.34, N = 3743.97744.47746.45744.35MIN: 733.98MIN: 735.64MIN: 736.4MIN: 734.631. (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: CPU12348001600240032004000SE +/- 10.06, N = 3SE +/- 8.77, N = 3SE +/- 6.98, N = 3SE +/- 13.27, N = 33780.643750.453760.173721.68MIN: 3744.41MIN: 3724.77MIN: 3731.98MIN: 36821. (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: CPU1234160320480640800SE +/- 1.10, N = 3SE +/- 1.00, N = 3SE +/- 0.40, N = 3SE +/- 1.95, N = 3743.20747.63745.82747.81MIN: 734.28MIN: 738.57MIN: 737.38MIN: 737.341. (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: CPU12340.09390.18780.28170.37560.4695SE +/- 0.000765, N = 3SE +/- 0.000908, N = 3SE +/- 0.002080, N = 3SE +/- 0.005514, N = 30.4119150.4154200.4119180.417122MIN: 0.4MIN: 0.4MIN: 0.4MIN: 0.41. (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: CPU12348001600240032004000SE +/- 3.01, N = 3SE +/- 4.29, N = 3SE +/- 2.18, N = 3SE +/- 13.03, N = 33750.353759.673747.383733.74MIN: 3727.41MIN: 3726.65MIN: 3726.51MIN: 3691.911. (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: CPU1234160320480640800SE +/- 0.53, N = 3SE +/- 0.96, N = 3SE +/- 1.75, N = 3SE +/- 0.55, N = 3742.79744.79743.58746.70MIN: 734.92MIN: 736.3MIN: 733.02MIN: 738.991. (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: CPU12340.15090.30180.45270.60360.7545SE +/- 0.001823, N = 3SE +/- 0.000941, N = 3SE +/- 0.000661, N = 3SE +/- 0.001611, N = 30.6677050.6687140.6671920.670735MIN: 0.64MIN: 0.64MIN: 0.64MIN: 0.641. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Sysbench

Test: RAM / Memory

OpenBenchmarking.orgMiB/sec, More Is BetterSysbench 1.0.20Test: RAM / Memory123416003200480064008000SE +/- 11.15, N = 3SE +/- 9.49, N = 3SE +/- 12.72, N = 3SE +/- 8.95, N = 37515.517520.157511.927484.701. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm

Sysbench

Test: CPU

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPU123430K60K90K120K150KSE +/- 312.36, N = 3SE +/- 228.83, N = 3SE +/- 281.49, N = 3SE +/- 209.17, N = 3124312.60123807.73123768.96123660.731. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm

Phoronix Test Suite v10.8.5