onnx tr

AMD Ryzen Threadripper PRO 5965WX 24-Cores testing with a ASUS Pro WS WRX80E-SAGE SE WIFI (1201 BIOS) and ASUS NVIDIA NV106 2GB on Ubuntu 23.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2402040-NE-ONNXTR29358&sor&grs.

onnx trProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUScAMD Ryzen Threadripper PRO 5965WX 24-Cores @ 3.80GHz (24 Cores / 48 Threads)ASUS Pro WS WRX80E-SAGE SE WIFI (1201 BIOS)AMD Starship/Matisse8 x 16GB DDR4-2133MT/s Corsair CMK32GX4M2E3200C162048GB SOLIDIGM SSDPFKKW020X7ASUS NVIDIA NV106 2GBAMD Starship/MatisseVA24312 x Intel X550 + Intel Wi-Fi 6 AX200Ubuntu 23.106.5.0-13-generic (x86_64)GNOME Shell 45.0X Server + Waylandnouveau4.3 Mesa 23.2.1-1ubuntu3GCC 13.2.0ext41920x1080OpenBenchmarking.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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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: 0xa008205Python Details- Python 3.11.6Security Details- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

onnx tronnx: super-resolution-10 - CPU - Standardonnx: GPT-2 - CPU - Parallelonnx: T5 Encoder - CPU - Parallelonnx: yolov4 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: T5 Encoder - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Parallelonnx: bertsquad-12 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: super-resolution-10 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonnx: bertsquad-12 - CPU - Parallelonnx: T5 Encoder - CPU - Standardonnx: T5 Encoder - CPU - Parallelonnx: yolov4 - CPU - Standardonnx: yolov4 - CPU - Standardonnx: yolov4 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: GPT-2 - CPU - Standardonnx: GPT-2 - CPU - ParallelaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUSc99.8424131.026181.5289.5475329.946335.0904201.076121.5691.4919112.531630.7052233.825687.27828.494232.565110.01528.224453.79772263.284.2755234.433929.039233.3916428.9712.33114670.2781.25873794.1331.453376.380213.091879.79534.972625.507396.70710.3402104.7357.26082137.6437.6245695.0154137.542173.7229.1594229.279136.4098197.039119.3331.4481512.728431.137233.757686.13827.462532.113310.5248.378533.93035254.3954.2766130.603232.67434.1523430.1082.32498690.5331.50952662.1931.4557983.94311.912478.56125.074135.75502108.9079.1818109.1736.8871145.1057.26342131.261176.8969.4913430.4140193.937123.1751.4841412.4706236.736692.1808.117623.64067275.5604.2228631.138032.276732.8852347.2322.95286673.7881.31876763.0351.4434375.726513.346280.21035.157645.65170103.64599.70516105.3556.86398146.7807.61116OpenBenchmarking.org

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: StandardaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS2040608010099.8495.021. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: ParallelAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUSca306090120150SE +/- 0.66, N = 3137.54131.26131.031. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: T5 Encoder - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: ParallelacAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS4080120160200SE +/- 0.64, N = 3181.53176.90173.721. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: yolov4 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: ParallelacAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS3691215SE +/- 0.00732, N = 39.547539.491349.159421. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelcaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS714212835SE +/- 0.32, N = 330.4129.9529.281. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUSa81624324036.4135.091. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: T5 Encoder - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: StandardaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUSc4080120160200SE +/- 2.01, N = 5201.08197.04193.941. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: ParallelcaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS306090120150SE +/- 0.59, N = 3123.18121.57119.331. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelacAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS0.33570.67141.00711.34281.6785SE +/- 0.00223, N = 31.491911.484141.448151. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: ParallelAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUSac3691215SE +/- 0.16, N = 312.7312.5312.471. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUSa71421283531.1430.711. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: ParallelcaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS50100150200250SE +/- 0.73, N = 3236.74233.83233.761. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelcaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS150300450600750SE +/- 8.43, N = 3692.18687.28686.141. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUSa71421283527.4628.491. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUSa81624324032.1132.571. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: StandardaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS369121510.0210.521. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: ParallelcaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS246810SE +/- 0.03894, N = 38.117628.224458.378531. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardcaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS0.88431.76862.65293.53724.4215SE +/- 0.06571, N = 123.640673.797723.930351. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardcaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS60120180240300SE +/- 4.77, N = 12275.56263.28254.401. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: ParallelcaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS0.96221.92442.88663.84884.811SE +/- 0.01316, N = 34.222864.275524.276611. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUSca816243240SE +/- 0.59, N = 1530.6031.1434.431. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUSca816243240SE +/- 0.61, N = 1532.6732.2829.041. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelcaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS816243240SE +/- 0.34, N = 332.8933.3934.151. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: StandardcaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS90180270360450SE +/- 15.41, N = 15347.23428.97430.111. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: StandardcaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS0.66441.32881.99322.65763.322SE +/- 0.11743, N = 152.952862.331142.324981. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelacAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS150300450600750SE +/- 1.01, N = 3670.28673.79690.531. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: StandardacAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS0.33960.67921.01881.35841.698SE +/- 0.02979, N = 151.258731.318761.509521. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: StandardacAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS2004006008001000SE +/- 15.86, N = 15794.13763.04662.191. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelcaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS0.32760.65520.98281.31041.638SE +/- 0.01776, N = 31.443431.453301.455791. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: StandardcaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS20406080100SE +/- 2.09, N = 1575.7376.3883.941. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: StandardcaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS3691215SE +/- 0.37, N = 1513.3513.0911.911. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: ParallelAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUSac20406080100SE +/- 1.00, N = 378.5679.8080.211. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: T5 Encoder - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: StandardaAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUSc1.16052.3213.48154.6425.8025SE +/- 0.05411, N = 54.972625.074135.157641. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: T5 Encoder - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: ParallelacAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS1.29492.58983.88475.17966.4745SE +/- 0.02036, N = 35.507305.651705.755021. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: yolov4 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: StandardacAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS20406080100SE +/- 2.14, N = 1596.71103.65108.911. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: yolov4 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: StandardacAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS3691215SE +/- 0.19825, N = 1510.340209.705169.181801. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: yolov4 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: ParallelacAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUS20406080100SE +/- 0.08, N = 3104.74105.36109.171. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: StandardcAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUSa246810SE +/- 0.16982, N = 156.863986.887107.260821. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: StandardcAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUSa306090120150SE +/- 3.42, N = 15146.78145.11137.641. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

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

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: ParallelAMD Ryzen Threadripper PRO 5965WX 24-Cores - ASUSca246810SE +/- 0.03837, N = 37.263427.611167.624561. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt


Phoronix Test Suite v10.8.5