feb compute AMD Ryzen 7 PRO 6850U testing with a LENOVO ThinkPad X13 Gen 3 21CM0001US (R22ET51W 1.21 BIOS) and AMD Radeon 680M 1GB on Fedora Linux 39 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2402179-NE-FEBCOMPUT81&grs .
feb compute Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution a b c AMD Ryzen 7 PRO 6850U @ 4.77GHz (8 Cores / 16 Threads) LENOVO ThinkPad X13 Gen 3 21CM0001US (R22ET51W 1.21 BIOS) AMD 17h-19h PCIe Root Complex 4 x 4GB DRAM-6400MT/s Micron MT62F1G32D4DR-031 WT 512GB Micron MTFDKBA512TFK AMD Radeon 680M 1GB AMD Rembrandt Radeon HD Audio Qualcomm QCNFA765 Fedora Linux 39 6.5.7-300.fc39.x86_64 (x86_64) GNOME Shell 45.0 X Server 1.20.14 + Wayland 4.6 Mesa 23.2.1 (LLVM 16.0.6 DRM 3.54) GCC 13.2.1 20230918 btrfs 1920x1200 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,m2,lto --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-multilib --enable-offload-defaulted --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-libstdcxx-zoneinfo=/usr/share/zoneinfo --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver Processor Details - Scaling Governor: amd-pstate-epp powersave (EPP: performance) - Platform Profile: balanced - CPU Microcode: 0xa404102 - ACPI Profile: balanced Python Details - Python 3.12.0 Security Details - SELinux + gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
feb compute onnx: fcn-resnet101-11 - CPU - Standard onnx: ArcFace ResNet-100 - CPU - Standard onnx: super-resolution-10 - CPU - Standard onnx: yolov4 - CPU - Standard onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standard onnx: fcn-resnet101-11 - CPU - Parallel onnx: GPT-2 - CPU - Standard onnx: ArcFace ResNet-100 - CPU - Parallel onnx: ResNet50 v1-12-int8 - CPU - Standard onnx: T5 Encoder - CPU - Standard namd: STMV with 1,066,628 Atoms dav1d: Chimera 1080p dav1d: Summer Nature 1080p dav1d: Chimera 1080p 10-bit onnx: yolov4 - CPU - Parallel onnx: CaffeNet 12-int8 - CPU - Parallel onnx: bertsquad-12 - CPU - Parallel dav1d: Summer Nature 4K onnx: super-resolution-10 - CPU - Parallel namd: ATPase with 327,506 Atoms onnx: bertsquad-12 - CPU - Standard onnx: GPT-2 - CPU - Parallel onnx: CaffeNet 12-int8 - CPU - Standard onnx: ResNet50 v1-12-int8 - CPU - Parallel onnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallel onnx: T5 Encoder - CPU - Parallel gromacs: MPI CPU - water_GMX50_bare oidn: RTLightmap.hdr.4096x4096 - CPU-Only oidn: RT.ldr_alb_nrm.3840x2160 - CPU-Only oidn: RT.hdr_alb_nrm.3840x2160 - CPU-Only 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 - 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: yolov4 - CPU - Standard onnx: yolov4 - CPU - Parallel onnx: GPT-2 - CPU - Standard onnx: GPT-2 - CPU - Parallel a b c 0.992048 14.9126 67.7988 4.42743 23.6834 0.666164 76.7556 15.2624 105.615 95.5162 0.10784 440.16 611.34 366.39 4.56321 260.159 6.79852 148.44 47.9894 0.37418 10.0687 74.9963 309.703 102.93 22.925 96.2635 0.726 0.12 0.25 0.25 42.2148 43.617 14.7446 20.835 9.46487 9.71292 67.0522 65.5167 1008.01 1501.12 3.22604 3.84125 99.3082 147.085 10.4632 10.385 225.857 219.138 13.0146 13.326 0.646323 14.9098 66.6421 4.43764 28.387 0.65216 86.4107 15.6843 113.151 101.07 0.11155 440.37 614.45 360.2 4.47998 266.714 6.82285 148.55 48.411 0.37699 10.0992 75.0269 308.325 102.729 22.9837 96.4204 0.725 0.12 0.25 0.25 35.2194 43.5057 15.0008 20.6536 8.8344 9.73161 67.0649 63.7541 1547.21 1533.36 3.24057 3.74602 99.0097 146.562 9.88722 10.3681 225.337 223.209 11.5617 13.321 0.645364 22.3931 47.8397 6.25362 23.6855 0.581199 86.172 14.4464 112.961 100.848 0.11332 458.1 628.79 357.16 4.59463 263.443 6.70092 150.79 48.1098 0.37550 10.0457 74.6672 308.766 102.52 22.8968 96.3188 0.725 0.12 0.25 0.25 42.2114 43.6706 20.8967 20.7828 8.84917 9.75122 44.6524 69.2185 1549.5 1720.57 3.2361 3.7935 99.536 149.227 9.91203 10.3789 159.899 217.639 11.592 13.3848 OpenBenchmarking.org
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard a b c 0.2232 0.4464 0.6696 0.8928 1.116 0.992048 0.646323 0.645364 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 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard a b c 5 10 15 20 25 14.91 14.91 22.39 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Standard a b c 15 30 45 60 75 67.80 66.64 47.84 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 1.17 Model: yolov4 - Device: CPU - Executor: Standard a b c 2 4 6 8 10 4.42743 4.43764 6.25362 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 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard a b c 7 14 21 28 35 23.68 28.39 23.69 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 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel a b c 0.1499 0.2998 0.4497 0.5996 0.7495 0.666164 0.652160 0.581199 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 1.17 Model: GPT-2 - Device: CPU - Executor: Standard a b c 20 40 60 80 100 76.76 86.41 86.17 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel a b c 4 8 12 16 20 15.26 15.68 14.45 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard a b c 30 60 90 120 150 105.62 113.15 112.96 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: T5 Encoder - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Standard a b c 20 40 60 80 100 95.52 101.07 100.85 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
NAMD Input: STMV with 1,066,628 Atoms OpenBenchmarking.org ns/day, More Is Better NAMD 3.0b6 Input: STMV with 1,066,628 Atoms a b c 0.0255 0.051 0.0765 0.102 0.1275 0.10784 0.11155 0.11332
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better dav1d 1.4 Video Input: Chimera 1080p a b c 100 200 300 400 500 440.16 440.37 458.10 1. (CC) gcc options: -pthread
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 1.4 Video Input: Summer Nature 1080p a b c 140 280 420 560 700 611.34 614.45 628.79 1. (CC) gcc options: -pthread
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 1.4 Video Input: Chimera 1080p 10-bit a b c 80 160 240 320 400 366.39 360.20 357.16 1. (CC) gcc options: -pthread
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Parallel a b c 1.0338 2.0676 3.1014 4.1352 5.169 4.56321 4.47998 4.59463 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 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel a b c 60 120 180 240 300 260.16 266.71 263.44 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 1.17 Model: bertsquad-12 - Device: CPU - Executor: Parallel a b c 2 4 6 8 10 6.79852 6.82285 6.70092 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 1.4 Video Input: Summer Nature 4K a b c 30 60 90 120 150 148.44 148.55 150.79 1. (CC) gcc options: -pthread
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Parallel a b c 11 22 33 44 55 47.99 48.41 48.11 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
NAMD Input: ATPase with 327,506 Atoms OpenBenchmarking.org ns/day, More Is Better NAMD 3.0b6 Input: ATPase with 327,506 Atoms a b c 0.0848 0.1696 0.2544 0.3392 0.424 0.37418 0.37699 0.37550
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Standard a b c 3 6 9 12 15 10.07 10.10 10.05 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 1.17 Model: GPT-2 - Device: CPU - Executor: Parallel a b c 20 40 60 80 100 75.00 75.03 74.67 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 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard a b c 70 140 210 280 350 309.70 308.33 308.77 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 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel a b c 20 40 60 80 100 102.93 102.73 102.52 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 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel a b c 6 12 18 24 30 22.93 22.98 22.90 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 1.17 Model: T5 Encoder - Device: CPU - Executor: Parallel a b c 20 40 60 80 100 96.26 96.42 96.32 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2024 Implementation: MPI CPU - Input: water_GMX50_bare a b c 0.1634 0.3268 0.4902 0.6536 0.817 0.726 0.725 0.725 1. (CXX) g++ options: -O3 -lm
Intel Open Image Denoise Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.2 Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only a b c 0.027 0.054 0.081 0.108 0.135 0.12 0.12 0.12
Intel Open Image Denoise Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.2 Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only a b c 0.0563 0.1126 0.1689 0.2252 0.2815 0.25 0.25 0.25
Intel Open Image Denoise Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.2 Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only a b c 0.0563 0.1126 0.1689 0.2252 0.2815 0.25 0.25 0.25
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 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard a b c 10 20 30 40 50 42.21 35.22 42.21 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 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel a b c 10 20 30 40 50 43.62 43.51 43.67 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 1.17 Model: super-resolution-10 - Device: CPU - Executor: Standard a b c 5 10 15 20 25 14.74 15.00 20.90 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 1.17 Model: super-resolution-10 - Device: CPU - Executor: Parallel a b c 5 10 15 20 25 20.84 20.65 20.78 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard a b c 3 6 9 12 15 9.46487 8.83440 8.84917 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 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel a b c 3 6 9 12 15 9.71292 9.73161 9.75122 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 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard a b c 15 30 45 60 75 67.05 67.06 44.65 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 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel a b c 15 30 45 60 75 65.52 63.75 69.22 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard a b c 300 600 900 1200 1500 1008.01 1547.21 1549.50 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 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel a b c 400 800 1200 1600 2000 1501.12 1533.36 1720.57 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard a b c 0.7291 1.4582 2.1873 2.9164 3.6455 3.22604 3.24057 3.23610 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 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel a b c 0.8643 1.7286 2.5929 3.4572 4.3215 3.84125 3.74602 3.79350 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 1.17 Model: bertsquad-12 - Device: CPU - Executor: Standard a b c 20 40 60 80 100 99.31 99.01 99.54 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 1.17 Model: bertsquad-12 - Device: CPU - Executor: Parallel a b c 30 60 90 120 150 147.09 146.56 149.23 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 1.17 Model: T5 Encoder - Device: CPU - Executor: Standard a b c 3 6 9 12 15 10.46320 9.88722 9.91203 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 1.17 Model: T5 Encoder - Device: CPU - Executor: Parallel a b c 3 6 9 12 15 10.39 10.37 10.38 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Standard a b c 50 100 150 200 250 225.86 225.34 159.90 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 1.17 Model: yolov4 - Device: CPU - Executor: Parallel a b c 50 100 150 200 250 219.14 223.21 217.64 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Standard OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Standard a b c 3 6 9 12 15 13.01 11.56 11.59 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 1.17 Model: GPT-2 - Device: CPU - Executor: Parallel a b c 3 6 9 12 15 13.33 13.32 13.38 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