AMD Ryzen 9 7900 12-Core testing with a Gigabyte B650M DS3H (F4h BIOS) and Gigabyte AMD Raphael 512MB on Ubuntu 22.10 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2302113-NE-ONNXRUNTI86 onnx runtime 1.14 amd ryzen 7900 - Phoronix Test Suite onnx runtime 1.14 amd ryzen 7900 AMD Ryzen 9 7900 12-Core testing with a Gigabyte B650M DS3H (F4h BIOS) and Gigabyte AMD Raphael 512MB on Ubuntu 22.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2302113-NE-ONNXRUNTI86&export=pdf&rdt&grs .
onnx runtime 1.14 amd ryzen 7900 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution a b c AMD Ryzen 9 7900 12-Core @ 3.70GHz (12 Cores / 24 Threads) Gigabyte B650M DS3H (F4h BIOS) AMD Device 14d8 32GB 1000GB Sabrent Rocket 4.0 Plus Gigabyte AMD Raphael 512MB (2200/2400MHz) AMD Rembrandt Radeon HD Audio ASUS VP28U Realtek RTL8125 2.5GbE Ubuntu 22.10 6.2.0-060200rc5daily20230129-generic (x86_64) GNOME Shell 43.0 X Server 1.21.1.4 + Wayland 4.6 Mesa 23.0.0-devel (git-e20564c 2022-12-12 kinetic-oibaf-ppa) (LLVM 15.0.5 DRM 3.49) 1.3.235 GCC 12.2.0 ext4 3840x2160 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/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-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: 0xa601203 Python Details - Python 3.10.7 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
onnx runtime 1.14 amd ryzen 7900 onnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallel onnx: fcn-resnet101-11 - CPU - Parallel onnx: ArcFace ResNet-100 - CPU - Parallel onnx: GPT-2 - CPU - Parallel onnx: bertsquad-12 - CPU - Parallel onnx: CaffeNet 12-int8 - CPU - Parallel onnx: super-resolution-10 - CPU - Parallel onnx: ResNet50 v1-12-int8 - CPU - Parallel onnx: GPT-2 - CPU - Standard onnx: yolov4 - CPU - Parallel onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standard onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standard onnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallel onnx: super-resolution-10 - CPU - Standard onnx: super-resolution-10 - CPU - Standard onnx: super-resolution-10 - CPU - Parallel onnx: ResNet50 v1-12-int8 - CPU - Standard onnx: ResNet50 v1-12-int8 - CPU - Standard onnx: ResNet50 v1-12-int8 - CPU - Parallel onnx: ArcFace ResNet-100 - CPU - Standard onnx: ArcFace ResNet-100 - CPU - Standard onnx: ArcFace ResNet-100 - CPU - Parallel onnx: fcn-resnet101-11 - CPU - Standard onnx: fcn-resnet101-11 - CPU - Standard onnx: fcn-resnet101-11 - CPU - Parallel onnx: CaffeNet 12-int8 - CPU - Standard onnx: CaffeNet 12-int8 - CPU - Standard onnx: CaffeNet 12-int8 - CPU - Parallel onnx: bertsquad-12 - CPU - Standard onnx: bertsquad-12 - CPU - Standard onnx: bertsquad-12 - CPU - Parallel onnx: yolov4 - CPU - Standard onnx: yolov4 - CPU - Standard onnx: yolov4 - CPU - Parallel onnx: GPT-2 - CPU - Standard onnx: GPT-2 - CPU - Parallel a b c 46.1584 1.44749 28.5525 117.620 12.7244 747.703 104.954 342.109 139.851 7.89231 17.9581 56.4768 21.6724 7.57906 136.489 9.52804 2.58475 388.919 2.92224 26.0143 39.1002 35.0229 417.423 2.44468 690.920 1.072977 939.153 1.33643 62.7802 16.3127 78.6000 103.9429 9.78495 126.714 7.14936 8.49794 48.7839 1.42497 28.0126 119.305 12.6537 756.209 103.984 343.334 140.464 7.85662 20.6953 48.3156 20.4971 6.14844 162.636 9.61619 2.57769 387.843 2.91195 25.1227 39.802 35.6974 393.062 2.54412 701.765 0.98564 1014.19 1.32121 54.7368 18.2687 79.0267 93.408 10.7055 127.279 7.11735 8.37831 45.5455 1.46501 28.4802 117.987 12.5677 747.942 105.142 339.558 140.869 7.88522 20.7296 48.2353 21.9541 8.53572 117.149 9.51022 2.78527 358.939 2.94418 28.2701 35.3716 35.1112 382.71 2.61293 682.589 0.984378 1015.49 1.33605 55.3673 18.0605 79.5671 96.4742 10.3652 126.818 7.09665 8.47144 OpenBenchmarking.org
ONNX Runtime Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel a b c 11 22 33 44 55 SE +/- 0.57, N = 4 46.16 48.78 45.55 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel a b c 0.3296 0.6592 0.9888 1.3184 1.648 SE +/- 0.01034, N = 3 1.44749 1.42497 1.46501 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel a b c 7 14 21 28 35 SE +/- 0.08, N = 3 28.55 28.01 28.48 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Parallel a b c 30 60 90 120 150 SE +/- 0.23, N = 3 117.62 119.31 117.99 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Parallel a b c 3 6 9 12 15 SE +/- 0.11, N = 3 12.72 12.65 12.57 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel a b c 160 320 480 640 800 SE +/- 0.37, N = 3 747.70 756.21 747.94 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Parallel a b c 20 40 60 80 100 SE +/- 0.64, N = 3 104.95 103.98 105.14 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel a b c 70 140 210 280 350 SE +/- 1.02, N = 3 342.11 343.33 339.56 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard a b c 30 60 90 120 150 SE +/- 1.09, N = 3 139.85 140.46 140.87 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Parallel a b c 2 4 6 8 10 SE +/- 0.05112, N = 3 7.89231 7.85662 7.88522 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard a b c 5 10 15 20 25 SE +/- 0.58, N = 15 17.96 20.70 20.73 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard a b c 13 26 39 52 65 SE +/- 1.75, N = 15 56.48 48.32 48.24 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel a b c 5 10 15 20 25 SE +/- 0.26, N = 4 21.67 20.50 21.95 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Standard a b c 2 4 6 8 10 SE +/- 0.36564, N = 15 7.57906 6.14844 8.53572 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Standard a b c 40 80 120 160 200 SE +/- 6.76, N = 15 136.49 162.64 117.15 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Parallel a b c 3 6 9 12 15 SE +/- 0.05819, N = 3 9.52804 9.61619 9.51022 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard a b c 0.6267 1.2534 1.8801 2.5068 3.1335 SE +/- 0.05054, N = 15 2.58475 2.57769 2.78527 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard a b c 80 160 240 320 400 SE +/- 7.79, N = 15 388.92 387.84 358.94 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel a b c 0.6624 1.3248 1.9872 2.6496 3.312 SE +/- 0.00878, N = 3 2.92224 2.91195 2.94418 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard a b c 7 14 21 28 35 SE +/- 1.04, N = 15 26.01 25.12 28.27 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard a b c 9 18 27 36 45 SE +/- 1.18, N = 15 39.10 39.80 35.37 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel a b c 8 16 24 32 40 SE +/- 0.10, N = 3 35.02 35.70 35.11 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard a b c 90 180 270 360 450 SE +/- 19.24, N = 14 417.42 393.06 382.71 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard a b c 0.5879 1.1758 1.7637 2.3516 2.9395 SE +/- 0.08226, N = 14 2.44468 2.54412 2.61293 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel a b c 150 300 450 600 750 SE +/- 4.93, N = 3 690.92 701.77 682.59 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard a b c 0.2414 0.4828 0.7242 0.9656 1.207 SE +/- 0.029300, N = 12 1.072977 0.985640 0.984378 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard a b c 200 400 600 800 1000 SE +/- 25.25, N = 12 939.15 1014.19 1015.49 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel a b c 0.3007 0.6014 0.9021 1.2028 1.5035 SE +/- 0.00074, N = 3 1.33643 1.32121 1.33605 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Standard a b c 14 28 42 56 70 SE +/- 3.13, N = 12 62.78 54.74 55.37 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Standard a b c 4 8 12 16 20 SE +/- 0.70, N = 12 16.31 18.27 18.06 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Parallel a b c 20 40 60 80 100 SE +/- 0.70, N = 3 78.60 79.03 79.57 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Standard a b c 20 40 60 80 100 SE +/- 3.84, N = 15 103.94 93.41 96.47 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Standard a b c 3 6 9 12 15 SE +/- 0.31791, N = 15 9.78495 10.70550 10.36520 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Parallel a b c 30 60 90 120 150 SE +/- 0.82, N = 3 126.71 127.28 126.82 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard a b c 2 4 6 8 10 SE +/- 0.05608, N = 3 7.14936 7.11735 7.09665 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Parallel a b c 2 4 6 8 10 SE +/- 0.01692, N = 3 8.49794 8.37831 8.47144 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
Phoronix Test Suite v10.8.4