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&sor .
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 etcpak: Multi-Threaded - ETC2 simdjson: Kostya simdjson: TopTweet simdjson: LargeRand simdjson: PartialTweets simdjson: DistinctUserID svt-av1: Preset 3 - Bosphorus 4K svt-av1: Preset 5 - Bosphorus 4K svt-av1: Preset 8 - Bosphorus 4K svt-av1: Preset 13 - Bosphorus 4K svt-av1: Preset 3 - Bosphorus 1080p svt-av1: Preset 5 - Bosphorus 1080p svt-av1: Preset 8 - Bosphorus 1080p svt-av1: Preset 13 - Bosphorus 1080p svt-av1: Preset 3 - Beauty 4K 10-bit svt-av1: Preset 5 - Beauty 4K 10-bit svt-av1: Preset 8 - Beauty 4K 10-bit svt-av1: Preset 13 - Beauty 4K 10-bit build2: Time To Compile y-cruncher: 1B y-cruncher: 500M mnn: nasnet mnn: mobilenetV3 mnn: squeezenetv1.1 mnn: resnet-v2-50 mnn: SqueezeNetV1.0 mnn: MobileNetV2_224 mnn: mobilenet-v1-1.0 mnn: inception-v3 xnnpack: FP32MobileNetV2 xnnpack: FP32MobileNetV3Large xnnpack: FP32MobileNetV3Small xnnpack: FP16MobileNetV2 xnnpack: FP16MobileNetV3Large xnnpack: FP16MobileNetV3Small xnnpack: QU8MobileNetV2 xnnpack: QU8MobileNetV3Large xnnpack: QU8MobileNetV3Small onnx: GPT-2 - CPU - Parallel onnx: GPT-2 - CPU - Parallel onnx: GPT-2 - CPU - Standard onnx: GPT-2 - CPU - Standard onnx: yolov4 - CPU - Parallel onnx: yolov4 - CPU - Parallel onnx: yolov4 - CPU - Standard onnx: yolov4 - CPU - Standard onnx: ZFNet-512 - CPU - Parallel onnx: ZFNet-512 - CPU - Parallel onnx: ZFNet-512 - CPU - Standard onnx: ZFNet-512 - CPU - Standard onnx: T5 Encoder - CPU - Parallel onnx: T5 Encoder - CPU - Parallel onnx: T5 Encoder - CPU - Standard onnx: T5 Encoder - CPU - Standard onnx: bertsquad-12 - CPU - Parallel onnx: bertsquad-12 - CPU - Parallel onnx: bertsquad-12 - CPU - Standard onnx: bertsquad-12 - CPU - Standard onnx: CaffeNet 12-int8 - CPU - Parallel onnx: CaffeNet 12-int8 - CPU - Parallel onnx: CaffeNet 12-int8 - CPU - Standard onnx: CaffeNet 12-int8 - CPU - Standard onnx: fcn-resnet101-11 - CPU - Parallel onnx: fcn-resnet101-11 - CPU - Parallel onnx: fcn-resnet101-11 - CPU - Standard onnx: fcn-resnet101-11 - CPU - Standard onnx: ArcFace ResNet-100 - CPU - Parallel onnx: ArcFace ResNet-100 - CPU - Parallel onnx: ArcFace ResNet-100 - CPU - Standard onnx: ArcFace ResNet-100 - CPU - Standard onnx: ResNet50 v1-12-int8 - CPU - Parallel onnx: ResNet50 v1-12-int8 - CPU - Parallel onnx: ResNet50 v1-12-int8 - CPU - Standard onnx: ResNet50 v1-12-int8 - CPU - Standard onnx: super-resolution-10 - CPU - Parallel onnx: super-resolution-10 - CPU - Parallel onnx: super-resolution-10 - CPU - Standard onnx: super-resolution-10 - CPU - Standard onnx: ResNet101_DUC_HDC-12 - CPU - Parallel onnx: ResNet101_DUC_HDC-12 - CPU - Parallel onnx: ResNet101_DUC_HDC-12 - CPU - Standard onnx: ResNet101_DUC_HDC-12 - CPU - Standard onnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallel onnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallel onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standard onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standard a b c 105.936 3.54 7.68 1.23 7.42 8.08 1.451 5.9 13.418 48.64 5.364 20.224 48.235 219.801 0.23 1.145 1.642 4.098 536.821 58.004 25.727 13.789 1.712 3.44 20.204 5.716 3.592 4.307 36.867 2758 3116 1068 4696 4178 1402 2359 2149 814 80.9109 12.3509 103.421 9.66051 2.92997 341.296 4.8719 205.255 33.8638 29.528 52.9115 18.8969 89.4618 11.1764 145.385 6.87576 3.89915 256.463 6.62817 150.865 226.993 4.40374 327.6 3.05091 0.49448 2022.32 0.717695 1393.35 8.62386 115.956 15.4883 64.562 96.3135 10.3811 118.017 8.47108 26.9373 37.1209 43.3931 23.0415 0.21507 4649.64 0.28607 3495.65 21.639 46.21 33.9052 29.4904 106.997 3.51 7.7 1.23 7.45 8.1 1.452 5.909 13.414 48.4 5.372 20.189 48.27 219.378 0.23 1.144 1.634 4.219 538.581 57.944 25.761 13.115 1.728 3.495 20.07 5.855 3.55 4.309 36.66 2757 3091 1067 4678 4203 1403 2361 2161 814 74.5841 13.4006 104.102 9.59821 2.92361 342.039 4.77207 209.549 33.5469 29.8069 52.8429 18.9216 89.4453 11.1778 143.241 6.97865 4.0094 249.411 6.6393 150.612 233.891 4.27347 325.387 3.07148 0.416435 2401.33 0.732657 1364.89 8.8586 112.883 15.2241 65.6826 99.9967 9.99778 117.672 8.49614 27.2706 36.667 43.5727 22.946 0.196218 5096.38 0.302547 3305.27 20.1738 49.5661 35.146 28.4498 107.025 3.48 7.68 1.22 7.44 8.07 1.455 5.945 13.688 49.334 5.356 20.142 48.212 219.561 0.229 1.146 1.637 4.226 539.224 57.864 25.751 13.86 1.711 3.444 20.248 5.806 3.539 4.233 36.935 2766 3096 1069 4685 4164 1398 2353 2153 806 76.1926 13.1183 103.236 9.67918 2.75465 363.019 4.88278 204.798 34.0189 29.3933 52.7814 18.9432 105.74 9.45416 142.735 7.00365 3.91465 255.447 6.63286 150.759 233.723 4.2768 328.577 3.04188 0.507355 1971 0.705358 1417.72 8.76598 114.075 15.3047 65.3365 103.356 9.67201 116.643 8.571 27.2178 36.7382 42.972 23.2671 0.266239 3756.02 0.285666 3500.58 20.9705 47.6832 33.0444 30.2589 OpenBenchmarking.org
Etcpak Benchmark: Multi-Threaded - Configuration: ETC2 OpenBenchmarking.org Mpx/s, More Is Better Etcpak 2.0 Benchmark: Multi-Threaded - Configuration: ETC2 c b a 20 40 60 80 100 107.03 107.00 105.94 1. (CXX) g++ options: -flto -pthread
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
simdjson Throughput Test: TopTweet OpenBenchmarking.org GB/s, More Is Better simdjson 3.10 Throughput Test: TopTweet b c a 2 4 6 8 10 7.70 7.68 7.68 1. (CXX) g++ options: -O3 -lrt
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 3.10 Throughput Test: LargeRandom b a c 0.2768 0.5536 0.8304 1.1072 1.384 1.23 1.23 1.22 1. (CXX) g++ options: -O3 -lrt
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 3.10 Throughput Test: PartialTweets b c a 2 4 6 8 10 7.45 7.44 7.42 1. (CXX) g++ options: -O3 -lrt
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 3.10 Throughput Test: DistinctUserID b a c 2 4 6 8 10 8.10 8.08 8.07 1. (CXX) g++ options: -O3 -lrt
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 c b a 0.3274 0.6548 0.9822 1.3096 1.637 1.455 1.452 1.451 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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 c b a 1.3376 2.6752 4.0128 5.3504 6.688 5.945 5.909 5.900 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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 c a b 4 8 12 16 20 13.69 13.42 13.41 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 c a b 11 22 33 44 55 49.33 48.64 48.40 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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 b a c 1.2087 2.4174 3.6261 4.8348 6.0435 5.372 5.364 5.356 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
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 b a c 11 22 33 44 55 48.27 48.24 48.21 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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 c b 50 100 150 200 250 219.80 219.56 219.38 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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 b a 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: 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 c a b 0.2579 0.5158 0.7737 1.0316 1.2895 1.146 1.145 1.144 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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 c b 0.3695 0.739 1.1085 1.478 1.8475 1.642 1.637 1.634 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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 c b a 0.9509 1.9018 2.8527 3.8036 4.7545 4.226 4.219 4.098 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
Y-Cruncher Pi Digits To Calculate: 1B OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.8.5 Pi Digits To Calculate: 1B c b a 13 26 39 52 65 57.86 57.94 58.00
Y-Cruncher Pi Digits To Calculate: 500M OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.8.5 Pi Digits To Calculate: 500M a c b 6 12 18 24 30 25.73 25.75 25.76
Mobile Neural Network Model: nasnet OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.9.b11b7037d Model: nasnet b a c 4 8 12 16 20 13.12 13.79 13.86 MIN: 12.49 / MAX: 33.2 MIN: 13.38 / MAX: 39.78 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
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.9.b11b7037d Model: mobilenetV3 c a b 0.3888 0.7776 1.1664 1.5552 1.944 1.711 1.712 1.728 MIN: 1.63 / MAX: 10.04 MIN: 1.67 / MAX: 8.57 MIN: 1.69 / MAX: 8.49 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: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.9.b11b7037d Model: squeezenetv1.1 a c b 0.7864 1.5728 2.3592 3.1456 3.932 3.440 3.444 3.495 MIN: 3.29 / MAX: 11.21 MIN: 3.25 / MAX: 17.71 MIN: 3.28 / MAX: 12.97 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: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.9.b11b7037d Model: resnet-v2-50 b a c 5 10 15 20 25 20.07 20.20 20.25 MIN: 19.47 / MAX: 37.21 MIN: 19.66 / MAX: 37.22 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
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.9.b11b7037d Model: SqueezeNetV1.0 a c b 1.3174 2.6348 3.9522 5.2696 6.587 5.716 5.806 5.855 MIN: 5.38 / MAX: 21.36 MIN: 5.53 / MAX: 28.76 MIN: 5.39 / MAX: 21.29 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 c b a 0.8082 1.6164 2.4246 3.2328 4.041 3.539 3.550 3.592 MIN: 3.35 / MAX: 14.3 MIN: 3.45 / MAX: 14.62 MIN: 3.44 / MAX: 17.94 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: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.9.b11b7037d Model: mobilenet-v1-1.0 c a b 0.9695 1.939 2.9085 3.878 4.8475 4.233 4.307 4.309 MIN: 4.09 / MAX: 16.18 MIN: 4.12 / MAX: 15.8 MIN: 4.11 / MAX: 20.08 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: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.9.b11b7037d Model: inception-v3 b a c 8 16 24 32 40 36.66 36.87 36.94 MIN: 34.95 / MAX: 59.06 MIN: 36.19 / MAX: 64.27 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: FP32MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: FP32MobileNetV2 b a c 600 1200 1800 2400 3000 2757 2758 2766 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP32MobileNetV3Large OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: FP32MobileNetV3Large b c a 700 1400 2100 2800 3500 3091 3096 3116 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP32MobileNetV3Small OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: FP32MobileNetV3Small b a c 200 400 600 800 1000 1067 1068 1069 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP16MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: FP16MobileNetV2 b c a 1000 2000 3000 4000 5000 4678 4685 4696 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP16MobileNetV3Large OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: FP16MobileNetV3Large c a b 900 1800 2700 3600 4500 4164 4178 4203 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP16MobileNetV3Small OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: FP16MobileNetV3Small c a b 300 600 900 1200 1500 1398 1402 1403 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: QU8MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: QU8MobileNetV2 c a b 500 1000 1500 2000 2500 2353 2359 2361 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: QU8MobileNetV3Large OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: QU8MobileNetV3Large a c b 500 1000 1500 2000 2500 2149 2153 2161 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: QU8MobileNetV3Small OpenBenchmarking.org us, Fewer Is Better XNNPACK 2cd86b Model: QU8MobileNetV3Small c a b 200 400 600 800 1000 806 814 814 1. (CXX) g++ options: -O3 -lrt -lm
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 c b 20 40 60 80 100 80.91 76.19 74.58 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: 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 c b 3 6 9 12 15 12.35 13.12 13.40 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 Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: GPT-2 - Device: CPU - Executor: Standard b a c 20 40 60 80 100 104.10 103.42 103.24 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 b a c 3 6 9 12 15 9.59821 9.66051 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: 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: 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: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: yolov4 - Device: CPU - Executor: Standard c a b 1.0986 2.1972 3.2958 4.3944 5.493 4.88278 4.87190 4.77207 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 c a b 50 100 150 200 250 204.80 205.26 209.55 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 Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: ZFNet-512 - Device: CPU - Executor: Parallel c a b 8 16 24 32 40 34.02 33.86 33.55 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 c a b 7 14 21 28 35 29.39 29.53 29.81 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 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
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: 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 c a b 20 40 60 80 100 105.74 89.46 89.45 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: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: T5 Encoder - Device: CPU - Executor: Parallel c a b 3 6 9 12 15 9.45416 11.17640 11.17780 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 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
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: 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 b c a 0.9021 1.8042 2.7063 3.6084 4.5105 4.00940 3.91465 3.89915 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 b c a 60 120 180 240 300 249.41 255.45 256.46 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 Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: bertsquad-12 - Device: CPU - Executor: Standard b c a 2 4 6 8 10 6.63930 6.63286 6.62817 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 b c a 30 60 90 120 150 150.61 150.76 150.87 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 Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel b c a 50 100 150 200 250 233.89 233.72 226.99 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 b c a 0.9908 1.9816 2.9724 3.9632 4.954 4.27347 4.27680 4.40374 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 Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard c a b 70 140 210 280 350 328.58 327.60 325.39 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: 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 c a b 0.6911 1.3822 2.0733 2.7644 3.4555 3.04188 3.05091 3.07148 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 c a b 0.1142 0.2284 0.3426 0.4568 0.571 0.507355 0.494480 0.416435 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 c a b 500 1000 1500 2000 2500 1971.00 2022.32 2401.33 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 Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard b a c 0.1648 0.3296 0.4944 0.6592 0.824 0.732657 0.717695 0.705358 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 b a c 300 600 900 1200 1500 1364.89 1393.35 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: 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 b c a 2 4 6 8 10 8.85860 8.76598 8.62386 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 b c a 30 60 90 120 150 112.88 114.08 115.96 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 Inferences Per Second, More Is Better ONNX Runtime 1.19 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard a c b 4 8 12 16 20 15.49 15.30 15.22 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: 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 c b 15 30 45 60 75 64.56 65.34 65.68 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: 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 c b a 20 40 60 80 100 103.36 100.00 96.31 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 c b a 3 6 9 12 15 9.67201 9.99778 10.38110 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
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: 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 b c a 6 12 18 24 30 27.27 27.22 26.94 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: 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 b c a 9 18 27 36 45 36.67 36.74 37.12 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 b a c 10 20 30 40 50 43.57 43.39 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: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.19 Model: super-resolution-10 - Device: CPU - Executor: Standard b a c 6 12 18 24 30 22.95 23.04 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: 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 c a b 0.0599 0.1198 0.1797 0.2396 0.2995 0.266239 0.215070 0.196218 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 c a b 1100 2200 3300 4400 5500 3756.02 4649.64 5096.38 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 b a c 0.0681 0.1362 0.2043 0.2724 0.3405 0.302547 0.286070 0.285666 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 b a c 800 1600 2400 3200 4000 3305.27 3495.65 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: 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 c b 5 10 15 20 25 21.64 20.97 20.17 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 c b 11 22 33 44 55 46.21 47.68 49.57 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 b a c 8 16 24 32 40 35.15 33.91 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: 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 b a c 7 14 21 28 35 28.45 29.49 30.26 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