Intel Core i7-1185G7 testing with a Dell XPS 13 9310 0DXP1F (3.7.0 BIOS) and Intel Xe TGL GT2 8GB on Ubuntu 24.04 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 2408221-NE-NEWA6453334 newa - Phoronix Test Suite newa Intel Core i7-1185G7 testing with a Dell XPS 13 9310 0DXP1F (3.7.0 BIOS) and Intel Xe TGL GT2 8GB on Ubuntu 24.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2408221-NE-NEWA6453334&grs .
newa Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution a b c Intel Core i7-1185G7 @ 4.80GHz (4 Cores / 8 Threads) Dell XPS 13 9310 0DXP1F (3.7.0 BIOS) Intel Tiger Lake-LP 8 x 2GB LPDDR4-4267MT/s Micron 2300 NVMe 512GB Intel Xe TGL GT2 8GB Realtek ALC289 Intel Wi-Fi 6 AX201 Ubuntu 24.04 6.10.0-061000rc4daily20240621-generic (x86_64) GNOME Shell 46.0 X Server + Wayland 4.6 Mesa 24.3~git2407210600.0cc23b~oibaf~n (git-0cc23b6 2024-07-21 noble-oibaf-ppa) GCC 13.2.0 ext4 1920x1200 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-backtrace --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-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/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-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 (EPP: balance_performance) - CPU Microcode: 0xb6 - Thermald 2.5.6 Python Details - Python 3.12.3 Security Details - gather_data_sampling: Mitigation of Microcode + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: SW sequence; BHI: SW loop KVM: SW loop + srbds: Not affected + tsx_async_abort: Not affected
newa onnx: ResNet101_DUC_HDC-12 - CPU - Parallel onnx: fcn-resnet101-11 - CPU - Parallel onnx: T5 Encoder - CPU - Parallel onnx: GPT-2 - CPU - Parallel onnx: ResNet50 v1-12-int8 - CPU - Parallel onnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallel onnx: yolov4 - CPU - Parallel onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standard onnx: ResNet101_DUC_HDC-12 - CPU - Standard mnn: nasnet onnx: fcn-resnet101-11 - CPU - Standard svt-av1: Preset 13 - Beauty 4K 10-bit onnx: CaffeNet 12-int8 - CPU - Parallel onnx: bertsquad-12 - CPU - Parallel onnx: ArcFace ResNet-100 - CPU - Parallel mnn: SqueezeNetV1.0 onnx: yolov4 - CPU - Standard svt-av1: Preset 8 - Bosphorus 4K svt-av1: Preset 13 - Bosphorus 4K onnx: T5 Encoder - CPU - Standard mnn: mobilenet-v1-1.0 onnx: ArcFace ResNet-100 - CPU - Standard simdjson: Kostya mnn: squeezenetv1.1 mnn: MobileNetV2_224 onnx: ZFNet-512 - CPU - Parallel onnx: super-resolution-10 - CPU - Standard onnx: super-resolution-10 - CPU - Parallel onnx: ResNet50 v1-12-int8 - CPU - Standard etcpak: Multi-Threaded - ETC2 mnn: mobilenetV3 xnnpack: QU8MobileNetV3Small onnx: CaffeNet 12-int8 - CPU - Standard xnnpack: FP16MobileNetV3Large mnn: resnet-v2-50 onnx: GPT-2 - CPU - Standard simdjson: LargeRand xnnpack: FP32MobileNetV3Large svt-av1: Preset 5 - Bosphorus 4K mnn: inception-v3 xnnpack: QU8MobileNetV3Large svt-av1: Preset 8 - Beauty 4K 10-bit build2: Time To Compile svt-av1: Preset 3 - Beauty 4K 10-bit svt-av1: Preset 5 - Bosphorus 1080p simdjson: PartialTweets xnnpack: FP16MobileNetV2 simdjson: DistinctUserID xnnpack: FP16MobileNetV3Small xnnpack: QU8MobileNetV2 xnnpack: FP32MobileNetV2 svt-av1: Preset 3 - Bosphorus 1080p svt-av1: Preset 3 - Bosphorus 4K simdjson: TopTweet onnx: ZFNet-512 - CPU - Standard y-cruncher: 1B svt-av1: Preset 13 - Bosphorus 1080p xnnpack: FP32MobileNetV3Small svt-av1: Preset 5 - Beauty 4K 10-bit onnx: bertsquad-12 - CPU - Standard y-cruncher: 500M svt-av1: Preset 8 - Bosphorus 1080p onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standard onnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallel onnx: ResNet101_DUC_HDC-12 - CPU - Standard onnx: ResNet101_DUC_HDC-12 - CPU - Parallel 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 - Parallel onnx: ArcFace ResNet-100 - CPU - Standard onnx: ArcFace ResNet-100 - CPU - Parallel onnx: fcn-resnet101-11 - CPU - Standard onnx: fcn-resnet101-11 - CPU - Parallel onnx: CaffeNet 12-int8 - CPU - Standard onnx: CaffeNet 12-int8 - CPU - Parallel onnx: bertsquad-12 - CPU - Standard onnx: bertsquad-12 - CPU - Parallel onnx: T5 Encoder - CPU - Standard onnx: T5 Encoder - CPU - Parallel onnx: ZFNet-512 - CPU - Standard onnx: ZFNet-512 - CPU - Parallel onnx: yolov4 - CPU - Standard onnx: yolov4 - CPU - Parallel onnx: GPT-2 - CPU - Standard onnx: GPT-2 - CPU - Parallel a b c 0.21507 0.49448 89.4618 80.9109 96.3135 21.639 2.92997 33.9052 0.28607 13.789 0.717695 4.098 226.993 3.89915 8.62386 5.716 4.8719 13.418 48.64 145.385 4.307 15.4883 3.54 3.44 3.592 33.8638 43.3931 26.9373 118.017 105.936 1.712 814 327.6 4178 20.204 103.421 1.23 3116 5.9 36.867 2149 1.642 536.821 0.23 20.224 7.42 4696 8.08 1402 2359 2758 5.364 1.451 7.68 52.9115 58.004 219.801 1068 1.145 6.62817 25.727 48.235 29.4904 46.21 3495.65 4649.64 23.0415 37.1209 8.47108 10.3811 64.562 115.956 1393.35 2022.32 3.05091 4.40374 150.865 256.463 6.87576 11.1764 18.8969 29.528 205.255 341.296 9.66051 12.3509 0.196218 0.416435 89.4453 74.5841 99.9967 20.1738 2.92361 35.146 0.302547 13.115 0.732657 4.219 233.891 4.0094 8.8586 5.855 4.77207 13.414 48.4 143.241 4.309 15.2241 3.51 3.495 3.55 33.5469 43.5727 27.2706 117.672 106.997 1.728 814 325.387 4203 20.07 104.102 1.23 3091 5.909 36.66 2161 1.634 538.581 0.23 20.189 7.45 4678 8.1 1403 2361 2757 5.372 1.452 7.7 52.8429 57.944 219.378 1067 1.144 6.6393 25.761 48.27 28.4498 49.5661 3305.27 5096.38 22.946 36.667 8.49614 9.99778 65.6826 112.883 1364.89 2401.33 3.07148 4.27347 150.612 249.411 6.97865 11.1778 18.9216 29.8069 209.549 342.039 9.59821 13.4006 0.266239 0.507355 105.74 76.1926 103.356 20.9705 2.75465 33.0444 0.285666 13.86 0.705358 4.226 233.723 3.91465 8.76598 5.806 4.88278 13.688 49.334 142.735 4.233 15.3047 3.48 3.444 3.539 34.0189 42.972 27.2178 116.643 107.025 1.711 806 328.577 4164 20.248 103.236 1.22 3096 5.945 36.935 2153 1.637 539.224 0.229 20.142 7.44 4685 8.07 1398 2353 2766 5.356 1.455 7.68 52.7814 57.864 219.561 1069 1.146 6.63286 25.751 48.212 30.2589 47.6832 3500.58 3756.02 23.2671 36.7382 8.571 9.67201 65.3365 114.075 1417.72 1971 3.04188 4.2768 150.759 255.447 7.00365 9.45416 18.9432 29.3933 204.798 363.019 9.67918 13.1183 OpenBenchmarking.org
ONNX Runtime Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallel a b c 0.0599 0.1198 0.1797 0.2396 0.2995 0.215070 0.196218 0.266239 1. (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.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel a b c 0.1142 0.2284 0.3426 0.4568 0.571 0.494480 0.416435 0.507355 1. (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.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: T5 Encoder - Device: CPU - Executor: Parallel a b c 20 40 60 80 100 89.46 89.45 105.74 1. (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.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: GPT-2 - Device: CPU - Executor: Parallel a b c 20 40 60 80 100 80.91 74.58 76.19 1. (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.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel a b c 20 40 60 80 100 96.31 100.00 103.36 1. (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.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel a b c 5 10 15 20 25 21.64 20.17 20.97 1. (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.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: yolov4 - Device: CPU - Executor: Parallel a b c 0.6592 1.3184 1.9776 2.6368 3.296 2.92997 2.92361 2.75465 1. (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.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard a b c 8 16 24 32 40 33.91 35.15 33.04 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard a b c 0.0681 0.1362 0.2043 0.2724 0.3405 0.286070 0.302547 0.285666 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Mobile Neural Network Model: nasnet OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.9.b11b7037d Model: nasnet a b c 4 8 12 16 20 13.79 13.12 13.86 MIN: 13.38 / MAX: 39.78 MIN: 12.49 / MAX: 33.2 MIN: 13.38 / MAX: 33.37 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard a b c 0.1648 0.3296 0.4944 0.6592 0.824 0.717695 0.732657 0.705358 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
SVT-AV1 Encoder Mode: Preset 13 - Input: Beauty 4K 10-bit OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.2 Encoder Mode: Preset 13 - Input: Beauty 4K 10-bit a b c 0.9509 1.9018 2.8527 3.8036 4.7545 4.098 4.219 4.226 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel a b c 50 100 150 200 250 226.99 233.89 233.72 1. (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.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: bertsquad-12 - Device: CPU - Executor: Parallel a b c 0.9021 1.8042 2.7063 3.6084 4.5105 3.89915 4.00940 3.91465 1. (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.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel a b c 2 4 6 8 10 8.62386 8.85860 8.76598 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.9.b11b7037d Model: SqueezeNetV1.0 a b c 1.3174 2.6348 3.9522 5.2696 6.587 5.716 5.855 5.806 MIN: 5.38 / MAX: 21.36 MIN: 5.39 / MAX: 21.29 MIN: 5.53 / MAX: 28.76 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: yolov4 - Device: CPU - Executor: Standard a b c 1.0986 2.1972 3.2958 4.3944 5.493 4.87190 4.77207 4.88278 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.2 Encoder Mode: Preset 8 - Input: Bosphorus 4K a b c 4 8 12 16 20 13.42 13.41 13.69 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.2 Encoder Mode: Preset 13 - Input: Bosphorus 4K a b c 11 22 33 44 55 48.64 48.40 49.33 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
ONNX Runtime Model: T5 Encoder - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: T5 Encoder - Device: CPU - Executor: Standard a b c 30 60 90 120 150 145.39 143.24 142.74 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.9.b11b7037d Model: mobilenet-v1-1.0 a b c 0.9695 1.939 2.9085 3.878 4.8475 4.307 4.309 4.233 MIN: 4.12 / MAX: 15.8 MIN: 4.11 / MAX: 20.08 MIN: 4.09 / MAX: 16.18 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard a b c 4 8 12 16 20 15.49 15.22 15.30 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 3.10 Throughput Test: Kostya a b c 0.7965 1.593 2.3895 3.186 3.9825 3.54 3.51 3.48 1. (CXX) g++ options: -O3 -lrt
Mobile Neural Network Model: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.9.b11b7037d Model: squeezenetv1.1 a b c 0.7864 1.5728 2.3592 3.1456 3.932 3.440 3.495 3.444 MIN: 3.29 / MAX: 11.21 MIN: 3.28 / MAX: 12.97 MIN: 3.25 / MAX: 17.71 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.9.b11b7037d Model: MobileNetV2_224 a b c 0.8082 1.6164 2.4246 3.2328 4.041 3.592 3.550 3.539 MIN: 3.44 / MAX: 17.94 MIN: 3.45 / MAX: 14.62 MIN: 3.35 / MAX: 14.3 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl
ONNX Runtime Model: ZFNet-512 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: ZFNet-512 - Device: CPU - Executor: Parallel a b c 8 16 24 32 40 33.86 33.55 34.02 1. (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.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: super-resolution-10 - Device: CPU - Executor: Standard a b c 10 20 30 40 50 43.39 43.57 42.97 1. (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.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: super-resolution-10 - Device: CPU - Executor: Parallel a b c 6 12 18 24 30 26.94 27.27 27.22 1. (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.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard a b c 30 60 90 120 150 118.02 117.67 116.64 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Etcpak Benchmark: Multi-Threaded - Configuration: ETC2 OpenBenchmarking.org Mpx/s, More Is Better Etcpak 2.0 Benchmark: Multi-Threaded - Configuration: ETC2 a b c 20 40 60 80 100 105.94 107.00 107.03 1. (CXX) g++ options: -flto -pthread
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.9.b11b7037d Model: mobilenetV3 a b c 0.3888 0.7776 1.1664 1.5552 1.944 1.712 1.728 1.711 MIN: 1.67 / MAX: 8.57 MIN: 1.69 / MAX: 8.49 MIN: 1.63 / MAX: 10.04 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl
XNNPACK Model: QU8MobileNetV3Small OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: QU8MobileNetV3Small a b c 200 400 600 800 1000 814 814 806 1. (CXX) g++ options: -O3 -lrt -lm
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard a b c 70 140 210 280 350 327.60 325.39 328.58 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
XNNPACK Model: FP16MobileNetV3Large OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: FP16MobileNetV3Large a b c 900 1800 2700 3600 4500 4178 4203 4164 1. (CXX) g++ options: -O3 -lrt -lm
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.9.b11b7037d Model: resnet-v2-50 a b c 5 10 15 20 25 20.20 20.07 20.25 MIN: 19.66 / MAX: 37.22 MIN: 19.47 / MAX: 37.21 MIN: 19.59 / MAX: 38.68 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: GPT-2 - Device: CPU - Executor: Standard a b c 20 40 60 80 100 103.42 104.10 103.24 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 3.10 Throughput Test: LargeRandom a b c 0.2768 0.5536 0.8304 1.1072 1.384 1.23 1.23 1.22 1. (CXX) g++ options: -O3 -lrt
XNNPACK Model: FP32MobileNetV3Large OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: FP32MobileNetV3Large a b c 700 1400 2100 2800 3500 3116 3091 3096 1. (CXX) g++ options: -O3 -lrt -lm
SVT-AV1 Encoder Mode: Preset 5 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.2 Encoder Mode: Preset 5 - Input: Bosphorus 4K a b c 1.3376 2.6752 4.0128 5.3504 6.688 5.900 5.909 5.945 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.9.b11b7037d Model: inception-v3 a b c 8 16 24 32 40 36.87 36.66 36.94 MIN: 36.19 / MAX: 64.27 MIN: 34.95 / MAX: 59.06 MIN: 36.09 / MAX: 57.31 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl
XNNPACK Model: QU8MobileNetV3Large OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: QU8MobileNetV3Large a b c 500 1000 1500 2000 2500 2149 2161 2153 1. (CXX) g++ options: -O3 -lrt -lm
SVT-AV1 Encoder Mode: Preset 8 - Input: Beauty 4K 10-bit OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.2 Encoder Mode: Preset 8 - Input: Beauty 4K 10-bit a b c 0.3695 0.739 1.1085 1.478 1.8475 1.642 1.634 1.637 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.17 Time To Compile a b c 120 240 360 480 600 536.82 538.58 539.22
SVT-AV1 Encoder Mode: Preset 3 - Input: Beauty 4K 10-bit OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.2 Encoder Mode: Preset 3 - Input: Beauty 4K 10-bit a b c 0.0518 0.1036 0.1554 0.2072 0.259 0.230 0.230 0.229 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 5 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.2 Encoder Mode: Preset 5 - Input: Bosphorus 1080p a b c 5 10 15 20 25 20.22 20.19 20.14 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 3.10 Throughput Test: PartialTweets a b c 2 4 6 8 10 7.42 7.45 7.44 1. (CXX) g++ options: -O3 -lrt
XNNPACK Model: FP16MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: FP16MobileNetV2 a b c 1000 2000 3000 4000 5000 4696 4678 4685 1. (CXX) g++ options: -O3 -lrt -lm
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 3.10 Throughput Test: DistinctUserID a b c 2 4 6 8 10 8.08 8.10 8.07 1. (CXX) g++ options: -O3 -lrt
XNNPACK Model: FP16MobileNetV3Small OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: FP16MobileNetV3Small a b c 300 600 900 1200 1500 1402 1403 1398 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: QU8MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: QU8MobileNetV2 a b c 500 1000 1500 2000 2500 2359 2361 2353 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP32MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: FP32MobileNetV2 a b c 600 1200 1800 2400 3000 2758 2757 2766 1. (CXX) g++ options: -O3 -lrt -lm
SVT-AV1 Encoder Mode: Preset 3 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.2 Encoder Mode: Preset 3 - Input: Bosphorus 1080p a b c 1.2087 2.4174 3.6261 4.8348 6.0435 5.364 5.372 5.356 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 3 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.2 Encoder Mode: Preset 3 - Input: Bosphorus 4K a b c 0.3274 0.6548 0.9822 1.3096 1.637 1.451 1.452 1.455 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
simdjson Throughput Test: TopTweet OpenBenchmarking.org GB/s, More Is Better simdjson 3.10 Throughput Test: TopTweet a b c 2 4 6 8 10 7.68 7.70 7.68 1. (CXX) g++ options: -O3 -lrt
ONNX Runtime Model: ZFNet-512 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: ZFNet-512 - Device: CPU - Executor: Standard a b c 12 24 36 48 60 52.91 52.84 52.78 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Y-Cruncher Pi Digits To Calculate: 1B OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.8.5 Pi Digits To Calculate: 1B a b c 13 26 39 52 65 58.00 57.94 57.86
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.2 Encoder Mode: Preset 13 - Input: Bosphorus 1080p a b c 50 100 150 200 250 219.80 219.38 219.56 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
XNNPACK Model: FP32MobileNetV3Small OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: FP32MobileNetV3Small a b c 200 400 600 800 1000 1068 1067 1069 1. (CXX) g++ options: -O3 -lrt -lm
SVT-AV1 Encoder Mode: Preset 5 - Input: Beauty 4K 10-bit OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.2 Encoder Mode: Preset 5 - Input: Beauty 4K 10-bit a b c 0.2579 0.5158 0.7737 1.0316 1.2895 1.145 1.144 1.146 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: bertsquad-12 - Device: CPU - Executor: Standard a b c 2 4 6 8 10 6.62817 6.63930 6.63286 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Y-Cruncher Pi Digits To Calculate: 500M OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.8.5 Pi Digits To Calculate: 500M a b c 6 12 18 24 30 25.73 25.76 25.75
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.2 Encoder Mode: Preset 8 - Input: Bosphorus 1080p a b c 11 22 33 44 55 48.24 48.27 48.21 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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 1.19 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard a b c 7 14 21 28 35 29.49 28.45 30.26 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel a b c 11 22 33 44 55 46.21 49.57 47.68 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standard a b c 800 1600 2400 3200 4000 3495.65 3305.27 3500.58 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallel a b c 1100 2200 3300 4400 5500 4649.64 5096.38 3756.02 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: super-resolution-10 - Device: CPU - Executor: Standard a b c 6 12 18 24 30 23.04 22.95 23.27 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: super-resolution-10 - Device: CPU - Executor: Parallel a b c 9 18 27 36 45 37.12 36.67 36.74 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard a b c 2 4 6 8 10 8.47108 8.49614 8.57100 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel a b c 3 6 9 12 15 10.38110 9.99778 9.67201 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard a b c 15 30 45 60 75 64.56 65.68 65.34 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel a b c 30 60 90 120 150 115.96 112.88 114.08 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard a b c 300 600 900 1200 1500 1393.35 1364.89 1417.72 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel a b c 500 1000 1500 2000 2500 2022.32 2401.33 1971.00 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard a b c 0.6911 1.3822 2.0733 2.7644 3.4555 3.05091 3.07148 3.04188 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel a b c 0.9908 1.9816 2.9724 3.9632 4.954 4.40374 4.27347 4.27680 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: bertsquad-12 - Device: CPU - Executor: Standard a b c 30 60 90 120 150 150.87 150.61 150.76 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: bertsquad-12 - Device: CPU - Executor: Parallel a b c 60 120 180 240 300 256.46 249.41 255.45 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: T5 Encoder - Device: CPU - Executor: Standard a b c 2 4 6 8 10 6.87576 6.97865 7.00365 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: T5 Encoder - Device: CPU - Executor: Parallel a b c 3 6 9 12 15 11.17640 11.17780 9.45416 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ZFNet-512 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: ZFNet-512 - Device: CPU - Executor: Standard a b c 5 10 15 20 25 18.90 18.92 18.94 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ZFNet-512 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: ZFNet-512 - Device: CPU - Executor: Parallel a b c 7 14 21 28 35 29.53 29.81 29.39 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: yolov4 - Device: CPU - Executor: Standard a b c 50 100 150 200 250 205.26 209.55 204.80 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: yolov4 - Device: CPU - Executor: Parallel a b c 80 160 240 320 400 341.30 342.04 363.02 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: GPT-2 - Device: CPU - Executor: Standard a b c 3 6 9 12 15 9.66051 9.59821 9.67918 1. (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.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: GPT-2 - Device: CPU - Executor: Parallel a b c 3 6 9 12 15 12.35 13.40 13.12 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Phoronix Test Suite v10.8.4