new amp ARMv8 Neoverse-N1 testing with a GIGABYTE G242-P36-00 MP32-AR2-00 v01000100 (F31k SCP: 2.10.20220531 BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2402068-NE-NEWAMP18865&grr&sor .
new amp Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Compiler File-System Screen Resolution a b c ARMv8 Neoverse-N1 @ 3.00GHz (128 Cores) GIGABYTE G242-P36-00 MP32-AR2-00 v01000100 (F31k SCP: 2.10.20220531 BIOS) Ampere Computing LLC Altra PCI Root Complex A 16 x 32GB DDR4-3200MT/s Samsung M393A4K40DB3-CWE 800GB Micron_7450_MTFDKBA800TFS ASPEED VGA HDMI 2 x Intel I350 Ubuntu 23.10 6.5.0-13-generic (aarch64) GCC 13.2.0 ext4 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -v Processor Details - Scaling Governor: cppc_cpufreq performance (Boost: Disabled) Python Details - Python 3.11.6 Security Details - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of CSV2 BHB + srbds: Not affected + tsx_async_abort: Not affected
new amp llamafile: mistral-7b-instruct-v0.2.Q8_0 - CPU llamafile: wizardcoder-python-34b-v1.0.Q6_K - CPU onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standard onnx: Faster R-CNN R-50-FPN-int8 - CPU - Standard onnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallel onnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallel onnx: fcn-resnet101-11 - CPU - Standard onnx: fcn-resnet101-11 - CPU - Standard onnx: GPT-2 - CPU - Standard onnx: GPT-2 - CPU - Standard onnx: GPT-2 - CPU - Parallel onnx: GPT-2 - CPU - Parallel onnx: fcn-resnet101-11 - CPU - Parallel onnx: fcn-resnet101-11 - CPU - Parallel onnx: yolov4 - CPU - Parallel onnx: yolov4 - CPU - Parallel onnx: bertsquad-12 - CPU - Parallel onnx: bertsquad-12 - CPU - Parallel onnx: bertsquad-12 - CPU - Standard onnx: bertsquad-12 - CPU - Standard onnx: yolov4 - CPU - Standard onnx: yolov4 - CPU - Standard onnx: T5 Encoder - CPU - Standard onnx: T5 Encoder - CPU - Standard onnx: T5 Encoder - CPU - Parallel onnx: T5 Encoder - CPU - Parallel 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: CaffeNet 12-int8 - CPU - Standard onnx: CaffeNet 12-int8 - CPU - Standard onnx: CaffeNet 12-int8 - CPU - Parallel onnx: CaffeNet 12-int8 - CPU - Parallel onnx: ResNet50 v1-12-int8 - CPU - Standard onnx: ResNet50 v1-12-int8 - CPU - Standard onnx: ResNet50 v1-12-int8 - CPU - Parallel onnx: ResNet50 v1-12-int8 - CPU - Parallel onnx: super-resolution-10 - CPU - Parallel onnx: super-resolution-10 - CPU - Parallel onnx: super-resolution-10 - CPU - Standard onnx: super-resolution-10 - CPU - Standard llamafile: llava-v1.5-7b-q4 - CPU compress-lz4: 9 - Decompression Speed compress-lz4: 9 - Compression Speed compress-lz4: 1 - Decompression Speed compress-lz4: 1 - Compression Speed compress-lz4: 3 - Decompression Speed compress-lz4: 3 - Compression Speed a b c 3.15 1.78 39.4206 25.3641 40.2226 24.8599 830.466 1.20414 5.58525 178.736 6.47235 154.293 888.584 1.12538 164.181 6.09066 91.5067 10.9277 45.0965 22.1724 140.095 7.13777 3.86227 258.637 3.98962 250.556 101.907 9.81261 90.885 11.0025 1.42343 701.371 1.73248 576.593 5.87533 170.121 7.60357 131.488 13.2062 75.7142 12.576 79.4944 3.31 2511.8 27.59 2815.2 519.83 2492.2 80.97 2.89 1.74 39.8855 25.0685 40.2552 24.8398 803.571 1.24444 5.65511 176.523 6.44697 154.899 871.395 1.14758 162.26 6.16283 85.0699 11.7545 45.2911 22.0769 140.568 7.11377 3.8592 258.855 3.97869 251.252 101.733 9.82943 93.0332 10.7484 1.42955 698.343 1.76282 566.725 5.95823 167.736 7.57392 132 13.2144 75.6672 12.5723 79.5166 3.02 2511 27.68 2827.7 520.41 2493.1 80.95 2.83 1.77 39.2789 25.4554 40.2202 24.8612 794.456 1.25872 5.62585 177.439 6.45507 154.703 884 1.13122 161.272 6.20055 90.0129 11.1091 45.4499 21.9998 140.335 7.12556 3.93918 253.597 3.9752 251.457 101.936 9.80991 91.0258 10.9854 1.42532 700.482 1.73356 576.227 5.85706 170.632 7.64929 130.705 13.2191 75.6401 12.5774 79.4851 3.31 2512 27.64 2841.8 521.15 2491.6 80.99 OpenBenchmarking.org
Llamafile Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.6 Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU a b c 0.7088 1.4176 2.1264 2.8352 3.544 3.15 2.89 2.83
Llamafile Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.6 Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU a c b 0.4005 0.801 1.2015 1.602 2.0025 1.78 1.77 1.74
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 c a b 9 18 27 36 45 39.28 39.42 39.89 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 c a b 6 12 18 24 30 25.46 25.36 25.07 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 c a b 9 18 27 36 45 40.22 40.22 40.26 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 Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel c a b 6 12 18 24 30 24.86 24.86 24.84 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: 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 c b a 200 400 600 800 1000 794.46 803.57 830.47 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 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard c b a 0.2832 0.5664 0.8496 1.1328 1.416 1.25872 1.24444 1.20414 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 c b 1.2724 2.5448 3.8172 5.0896 6.362 5.58525 5.62585 5.65511 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 c b 40 80 120 160 200 178.74 177.44 176.52 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: 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 b c a 2 4 6 8 10 6.44697 6.45507 6.47235 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 b c a 30 60 90 120 150 154.90 154.70 154.29 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 b c a 200 400 600 800 1000 871.40 884.00 888.58 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: 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 b c a 0.2582 0.5164 0.7746 1.0328 1.291 1.14758 1.13122 1.12538 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 c b a 40 80 120 160 200 161.27 162.26 164.18 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 1.17 Model: yolov4 - Device: CPU - Executor: Parallel c b a 2 4 6 8 10 6.20055 6.16283 6.09066 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 b c a 20 40 60 80 100 85.07 90.01 91.51 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 b c a 3 6 9 12 15 11.75 11.11 10.93 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 10 20 30 40 50 45.10 45.29 45.45 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: 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 5 10 15 20 25 22.17 22.08 22.00 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: 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 c b 30 60 90 120 150 140.10 140.34 140.57 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Standard a c b 2 4 6 8 10 7.13777 7.12556 7.11377 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 b a c 0.8863 1.7726 2.6589 3.5452 4.4315 3.85920 3.86227 3.93918 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 b a c 60 120 180 240 300 258.86 258.64 253.60 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 c b a 0.8977 1.7954 2.6931 3.5908 4.4885 3.97520 3.97869 3.98962 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 c b a 50 100 150 200 250 251.46 251.25 250.56 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 b a c 20 40 60 80 100 101.73 101.91 101.94 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: 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 b a c 3 6 9 12 15 9.82943 9.81261 9.80991 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 c b 20 40 60 80 100 90.89 91.03 93.03 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 c b 3 6 9 12 15 11.00 10.99 10.75 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 c b 0.3216 0.6432 0.9648 1.2864 1.608 1.42343 1.42532 1.42955 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 c b 150 300 450 600 750 701.37 700.48 698.34 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: 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 c b 0.3966 0.7932 1.1898 1.5864 1.983 1.73248 1.73356 1.76282 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 c b 120 240 360 480 600 576.59 576.23 566.73 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 c a b 1.3406 2.6812 4.0218 5.3624 6.703 5.85706 5.87533 5.95823 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 c a b 40 80 120 160 200 170.63 170.12 167.74 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: Parallel OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel b a c 2 4 6 8 10 7.57392 7.60357 7.64929 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 b a c 30 60 90 120 150 132.00 131.49 130.71 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 3 6 9 12 15 13.21 13.21 13.22 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: 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 20 40 60 80 100 75.71 75.67 75.64 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: 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 b a c 3 6 9 12 15 12.57 12.58 12.58 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: 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 b a c 20 40 60 80 100 79.52 79.49 79.49 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Llamafile Test: llava-v1.5-7b-q4 - Acceleration: CPU OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.6 Test: llava-v1.5-7b-q4 - Acceleration: CPU c a b 0.7448 1.4896 2.2344 2.9792 3.724 3.31 3.31 3.02
LZ4 Compression Compression Level: 9 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.4 Compression Level: 9 - Decompression Speed c a b 500 1000 1500 2000 2500 2512.0 2511.8 2511.0 1. (CC) gcc options: -O3
LZ4 Compression Compression Level: 9 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.4 Compression Level: 9 - Compression Speed b c a 7 14 21 28 35 27.68 27.64 27.59 1. (CC) gcc options: -O3
LZ4 Compression Compression Level: 1 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.4 Compression Level: 1 - Decompression Speed c b a 600 1200 1800 2400 3000 2841.8 2827.7 2815.2 1. (CC) gcc options: -O3
LZ4 Compression Compression Level: 1 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.4 Compression Level: 1 - Compression Speed c b a 110 220 330 440 550 521.15 520.41 519.83 1. (CC) gcc options: -O3
LZ4 Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.4 Compression Level: 3 - Decompression Speed b a c 500 1000 1500 2000 2500 2493.1 2492.2 2491.6 1. (CC) gcc options: -O3
LZ4 Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.4 Compression Level: 3 - Compression Speed c a b 20 40 60 80 100 80.99 80.97 80.95 1. (CC) gcc options: -O3
Phoronix Test Suite v10.8.4