10900K sysbench onednn

Intel Core i9-10900K testing with a Gigabyte Z490 AORUS MASTER (F3 BIOS) and Gigabyte AMD Radeon RX 5500/5500M / Pro 5500M 8GB on Ubuntu 20.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2103134-PTS-10900KSY85&grr&rdt.

10900K sysbench onednnProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen Resolution1234Intel Core i9-10900K @ 5.30GHz (10 Cores / 20 Threads)Gigabyte Z490 AORUS MASTER (F3 BIOS)Intel Comet Lake PCH16GBSamsung SSD 970 EVO 250GBGigabyte AMD Radeon RX 5500/5500M / Pro 5500M 8GB (1900/875MHz)Realtek ALC1220ASUS MG28UIntel + Intel Wi-Fi 6 AX201Ubuntu 20.105.11.0-051100rc2daily20210106-generic (x86_64) 20210105GNOME Shell 3.38.1X Server 1.20.94.6 Mesa 20.2.1 (LLVM 11.0.0)1.2.131GCC 10.2.0ext43840x2160OpenBenchmarking.orgKernel Details- 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: intel_pstate powersave - CPU Microcode: 0xe0 - Thermald 2.3Security Details- itlb_multihit: KVM: Mitigation of VMX disabled + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

10900K sysbench onednnonednn: Deconvolution Batch shapes_1d - f32 - CPUsysbench: CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUsysbench: RAM / Memory12346.6772426017.892843.832834.492847.381779.521745.361748.031.491383.304561.172483.948071.9111512.21502.4500321.362117.92804.822703.7651734129.116.8546526029.632837.762836.922837.571732.401729.051742.261.494453.305451.174653.924551.9327612.17852.4276921.333917.65314.813533.7615034243.576.6223926028.922854.282836.902818.431754.381742.271725.151.491963.302281.172583.898271.9131912.16382.4720621.327717.68994.824413.7745334315.676.5974126019.112818.992832.252844.561744.701764.341749.051.492793.300521.174243.897011.9335112.17122.4546821.329817.77914.834583.7497634146.51OpenBenchmarking.org

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 +/- 0.09219, N = 15SE +/- 0.13332, N = 15SE +/- 0.09531, N = 15SE +/- 0.11275, N = 156.677246.854656.622396.59741MIN: 3.45MIN: 3.45MIN: 3.47MIN: 3.471. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Sysbench

Test: CPU

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPU12346K12K18K24K30KSE +/- 2.59, N = 3SE +/- 5.92, N = 3SE +/- 1.44, N = 3SE +/- 1.33, N = 326017.8926029.6326028.9226019.111. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm

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: CPU12346001200180024003000SE +/- 10.02, N = 3SE +/- 5.58, N = 3SE +/- 23.35, N = 3SE +/- 16.37, N = 32843.832837.762854.282818.99MIN: 2768.24MIN: 2798.07MIN: 2775.53MIN: 2765.731. (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: CPU12346001200180024003000SE +/- 12.24, N = 3SE +/- 0.84, N = 3SE +/- 6.62, N = 3SE +/- 11.43, N = 32834.492836.922836.902832.25MIN: 2770.1MIN: 2770.47MIN: 2764.69MIN: 2770.761. (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: CPU12346001200180024003000SE +/- 3.12, N = 3SE +/- 15.45, N = 3SE +/- 6.65, N = 3SE +/- 5.94, N = 32847.382837.572818.432844.56MIN: 2765.94MIN: 2767.4MIN: 2766.26MIN: 2768.091. (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: CPU1234400800120016002000SE +/- 8.77, N = 3SE +/- 13.35, N = 3SE +/- 19.63, N = 3SE +/- 6.63, N = 31779.521732.401754.381744.70MIN: 1736.71MIN: 1680.02MIN: 1691.38MIN: 1681.331. (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: CPU1234400800120016002000SE +/- 15.68, N = 3SE +/- 21.18, N = 3SE +/- 21.30, N = 3SE +/- 6.63, N = 31745.361729.051742.271764.34MIN: 1705.83MIN: 1683.97MIN: 1683.83MIN: 1689.051. (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: CPU1234400800120016002000SE +/- 14.77, N = 3SE +/- 26.98, N = 3SE +/- 2.77, N = 3SE +/- 27.03, N = 31748.031742.261725.151749.05MIN: 1687.97MIN: 1671.61MIN: 1683.55MIN: 1667.381. (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: CPU12340.33630.67261.00891.34521.6815SE +/- 0.00072, N = 3SE +/- 0.00187, N = 3SE +/- 0.00095, N = 3SE +/- 0.00086, N = 31.491381.494451.491961.49279MIN: 1.48MIN: 1.48MIN: 1.48MIN: 1.481. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: CPU12340.74371.48742.23112.97483.7185SE +/- 0.00272, N = 3SE +/- 0.00232, N = 3SE +/- 0.00348, N = 3SE +/- 0.01635, N = 33.304563.305453.302283.30052MIN: 3.03MIN: 3.03MIN: 3.02MIN: 3.031. (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: CPU12340.26430.52860.79291.05721.3215SE +/- 0.00221, N = 3SE +/- 0.00194, N = 3SE +/- 0.00090, N = 3SE +/- 0.00107, N = 31.172481.174651.172581.17424MIN: 1.16MIN: 1.16MIN: 1.16MIN: 1.161. (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: CPU12340.88831.77662.66493.55324.4415SE +/- 0.01417, N = 3SE +/- 0.00768, N = 3SE +/- 0.00147, N = 3SE +/- 0.00827, N = 33.948073.924553.898273.89701MIN: 3.79MIN: 3.77MIN: 3.76MIN: 3.721. (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: CPU12340.4350.871.3051.742.175SE +/- 0.00175, N = 3SE +/- 0.01672, N = 3SE +/- 0.00284, N = 3SE +/- 0.01806, N = 31.911151.932761.913191.93351MIN: 1.88MIN: 1.88MIN: 1.88MIN: 1.881. (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: CPU12343691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 312.2212.1812.1612.17MIN: 12.1MIN: 12.08MIN: 12.05MIN: 12.061. (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: CPU12340.55621.11241.66862.22482.781SE +/- 0.03980, N = 3SE +/- 0.01028, N = 3SE +/- 0.01612, N = 3SE +/- 0.01102, N = 32.450032.427692.472062.45468MIN: 2.34MIN: 2.31MIN: 2.33MIN: 2.311. (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: CPU1234510152025SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 321.3621.3321.3321.33MIN: 21.29MIN: 21.24MIN: 21.25MIN: 21.241. (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: CPU123448121620SE +/- 0.07, N = 3SE +/- 0.19, N = 3SE +/- 0.13, N = 3SE +/- 0.08, N = 317.9317.6517.6917.78MIN: 17.28MIN: 17.18MIN: 17.18MIN: 17.161. (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: CPU12341.08782.17563.26344.35125.439SE +/- 0.00884, N = 3SE +/- 0.00575, N = 3SE +/- 0.00815, N = 3SE +/- 0.00473, N = 34.822704.813534.824414.83458MIN: 4.79MIN: 4.71MIN: 4.75MIN: 4.731. (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: CPU12340.84931.69862.54793.39724.2465SE +/- 0.00296, N = 3SE +/- 0.00158, N = 3SE +/- 0.00173, N = 3SE +/- 0.00653, N = 33.765173.761503.774533.74976MIN: 3.74MIN: 3.74MIN: 3.75MIN: 3.721. (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 / Memory12347K14K21K28K35KSE +/- 68.06, N = 3SE +/- 99.86, N = 3SE +/- 108.17, N = 3SE +/- 148.70, N = 334129.1134243.5734315.6734146.511. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm


Phoronix Test Suite v10.8.5