epyc-75f3-new

2 x AMD EPYC 75F3 32-Core testing with a ASRockRack ROME2D16-2T (P3.30 BIOS) and ASPEED on Ubuntu 21.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2204097-NE-EPYC75F3N46&grs&sor.

epyc-75f3-new ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionAAABC2 x AMD EPYC 75F3 32-Core @ 2.95GHz (64 Cores / 128 Threads)ASRockRack ROME2D16-2T (P3.30 BIOS)AMD Starship/Matisse128GB1000GB Western Digital WD_BLACK SN850 1TBASPEEDAMD Starship/Matisse2 x Intel 10G X550TUbuntu 21.105.17.0-051700rc4daily20220219-generic (x86_64)GNOME Shell 40.5X Server1.1.182GCC 11.2.0ext41024x768OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler 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) - CPU Microcode: 0xa001114 Python Details- Python 3.9.7Security 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

epyc-75f3-new onnx: super-resolution-10 - CPU - Standardonnx: GPT-2 - CPU - Standardonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUperf-bench: Epoll Waitonnx: yolov4 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonnx: fcn-resnet101-11 - CPU - Standardonednn: Deconvolution Batch shapes_3d - f32 - CPUavifenc: 6onnx: ArcFace ResNet-100 - CPU - Standardonnx: GPT-2 - CPU - Parallelavifenc: 2avifenc: 10, Losslessavifenc: 6, Losslessperf-bench: Futex Lock-Pionednn: IP Shapes 3D - f32 - CPUperf-bench: Sched Pipeonednn: Convolution Batch Shapes Auto - f32 - CPUperf-bench: Memcpy 1MBperf-bench: Memset 1MBonnx: super-resolution-10 - CPU - Parallelavifenc: 0onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUperf-bench: Futex Hashonednn: Deconvolution Batch shapes_1d - f32 - CPUonnx: ArcFace ResNet-100 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Parallelperf-bench: Syscall Basiconnx: yolov4 - CPU - Parallelonnx: bertsquad-12 - CPU - Parallelonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 1D - f32 - CPUAAABC23520.8785532.127674.27838.7845.0107.215772.639123459900.70538042.86838962.45507269.460297679211.23611705162111.512141624.2463819.451693.033874.181.683910.8972880.7470844.055692.9415846261323422.906122993555404276.70.9046621702.104074.0931194130838.7285.2297.389772.548113513680.70881242.82982963.415414432069.4111711.61297671211.139512251231705220243459417.55342016.944416.221803.514530.241.075151.247010.8156324.258653.779277621310627.343625722916434464.120.8034261581.946323.9861244122537.5665.1977.514802.566433461330.68479944.14791663.789341424270.3271734.92297913411.217412351231694187943659212.49651801.294623.031810.374336.251.8530.9288930.7578264.772923.180914488909429.101320623165393862.480.8292171521.996394.2151279124239.5734.9717.185772.544043394610.68958342.92648563.185354423370.6461721.12294549411.194212291241692459443659221.67181696.64390.231713.394224.871.237530.784430.743012.558613.85444OpenBenchmarking.org

ONNX Runtime

Model: super-resolution-10 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: StandardBAAC170034005100680085007762462644881. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: GPT-2 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: StandardAABC3K6K9K12K15K132341310690941. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUAABC71421283522.9127.3429.10MIN: 16.94MIN: 19.51MIN: 20.221. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

perf-bench

Benchmark: Epoll Wait

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Epoll WaitBAAAC6001200180024003000SE +/- 23.81, N = 1225722352229920621. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma

ONNX Runtime

Model: yolov4 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: StandardAACB801602403204003553162911. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: bertsquad-12 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: StandardBAAC1402804205607006435405391. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUCAAB100020003000400050003862.484276.704464.12MIN: 3242.51MIN: 3959.8MIN: 4162.921. (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.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUBCAAA0.20350.4070.61050.8141.0175SE +/- 0.011448, N = 120.8034260.8292170.8785530.904662MIN: 0.57MIN: 0.6MIN: 0.65MIN: 0.681. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

ONNX Runtime

Model: fcn-resnet101-11 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: StandardAABC40801201602001701581521. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUBCAAA0.47870.95741.43611.91482.3935SE +/- 0.02508, N = 31.946321.996392.104072.12767MIN: 1.74MIN: 1.73MIN: 1.79MIN: 1.721. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

libavif avifenc

Encoder Speed: 6

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6BAACA0.96261.92522.88783.85044.813SE +/- 0.011, N = 33.9864.0934.2154.2781. (CXX) g++ options: -O3 -fPIC -lm

ONNX Runtime

Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardCBAA300600900120015001279124411941. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: GPT-2 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: ParallelAACB300600900120015001308124212251. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

libavif avifenc

Encoder Speed: 2

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 2BAAAC918273645SE +/- 0.11, N = 337.5738.7338.7839.571. (CXX) g++ options: -O3 -fPIC -lm

libavif avifenc

Encoder Speed: 10, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 10, LosslessCABAA1.17652.3533.52954.7065.8825SE +/- 0.030, N = 34.9715.0105.1975.2291. (CXX) g++ options: -O3 -fPIC -lm

libavif avifenc

Encoder Speed: 6, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, LosslessCAAAB246810SE +/- 0.066, N = 77.1857.2157.3897.5141. (CXX) g++ options: -O3 -fPIC -lm

perf-bench

Benchmark: Futex Lock-Pi

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex Lock-PiBCAAA20406080100SE +/- 0.58, N = 3807777771. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUCAABA0.59381.18761.78142.37522.969SE +/- 0.01578, N = 32.544042.548112.566432.63912MIN: 2.05MIN: 2.06MIN: 2.05MIN: 2.081. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

perf-bench

Benchmark: Sched Pipe

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Sched PipeAABAC80K160K240K320K400KSE +/- 3279.19, N = 33513683461333459903394611. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUBCAAA0.15950.3190.47850.6380.7975SE +/- 0.006925, N = 30.6847990.6895830.7053800.708812MIN: 0.64MIN: 0.64MIN: 0.64MIN: 0.671. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

perf-bench

Benchmark: Memcpy 1MB

OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memcpy 1MBBCAAA1020304050SE +/- 0.17, N = 344.1542.9342.8742.831. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma

perf-bench

Benchmark: Memset 1MB

OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memset 1MBBAACA1428425670SE +/- 0.65, N = 563.7963.4263.1962.461. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma

ONNX Runtime

Model: super-resolution-10 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: ParallelAABC90018002700360045004320424242331. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

libavif avifenc

Encoder Speed: 0

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 0AAABC1632486480SE +/- 0.35, N = 369.4169.4670.3370.651. (CXX) g++ options: -O3 -fPIC -lm

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUAACB4008001200160020001711.611721.121734.92MIN: 1495.43MIN: 1603.97MIN: 1463.541. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

perf-bench

Benchmark: Futex Hash

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex HashBAAAC600K1200K1800K2400K3000KSE +/- 6620.62, N = 329791342976792297671229454941. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUAACBA3691215SE +/- 0.09, N = 311.1411.1911.2211.24MIN: 9MIN: 8.84MIN: 9MIN: 8.61. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

ONNX Runtime

Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelBCAA300600900120015001235122912251. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelCBAA3060901201501241231231. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

perf-bench

Benchmark: Syscall Basic

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Syscall BasicAAABC4M8M12M16M20MSE +/- 7517.61, N = 3170522021705162116941879169245941. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -lnuma

ONNX Runtime

Model: yolov4 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: ParallelCBAA901802703604504364364341. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: bertsquad-12 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: ParallelAACB1302603905206505945925921. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUABAAC510152025SE +/- 1.25, N = 1511.5112.5017.5521.67MIN: 5.15MIN: 8.99MIN: 12.56MIN: 15.661. (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.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUACBAA400800120016002000SE +/- 88.05, N = 121624.251696.601801.292016.94MIN: 827.28MIN: 1543.98MIN: 1534.31MIN: 1858.231. (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.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUACAAB10002000300040005000SE +/- 242.60, N = 123819.454390.234416.224623.03MIN: 1342.54MIN: 3742.53MIN: 4047.45MIN: 4242.041. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUACAAB400800120016002000SE +/- 64.86, N = 121693.031713.391803.511810.37MIN: 1036.24MIN: 1504.13MIN: 1650.67MIN: 1535.851. (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.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUACBAA10002000300040005000SE +/- 239.78, N = 143874.184224.874336.254530.24MIN: 1544.77MIN: 3842.95MIN: 3938.66MIN: 3953.071. (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.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUAACAB0.41690.83381.25071.66762.0845SE +/- 0.09292, N = 151.075151.237531.683911.85300MIN: 0.92MIN: 1.09MIN: 0.87MIN: 1.671. (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.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUCABAA0.28060.56120.84181.12241.403SE +/- 0.048482, N = 150.7844300.8972880.9288931.247010MIN: 0.54MIN: 0.51MIN: 0.54MIN: 0.561. (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.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUCABAA0.18350.3670.55050.7340.9175SE +/- 0.011604, N = 150.7430100.7470840.7578260.815632MIN: 0.61MIN: 0.57MIN: 0.62MIN: 0.621. (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.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUCAAAB1.07392.14783.22174.29565.3695SE +/- 0.14420, N = 152.558614.055694.258654.77292MIN: 1.85MIN: 2.07MIN: 2.63MIN: 2.831. (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.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUABAAC0.86721.73442.60163.46884.336SE +/- 0.19680, N = 152.941583.180913.779203.85444MIN: 1.53MIN: 2.24MIN: 2.55MIN: 2.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

Phoronix Test Suite v10.8.4