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&grs.

new ampProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelCompilerFile-SystemScreen ResolutionabcARMv8 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 A16 x 32GB DDR4-3200MT/s Samsung M393A4K40DB3-CWE800GB Micron_7450_MTFDKBA800TFSASPEEDVGA HDMI2 x Intel I350Ubuntu 23.106.5.0-13-generic (aarch64)GCC 13.2.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler 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 3.11.6Security 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 ampllamafile: mistral-7b-instruct-v0.2.Q8_0 - CPUllamafile: llava-v1.5-7b-q4 - CPUonnx: bertsquad-12 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardllamafile: wizardcoder-python-34b-v1.0.Q6_K - CPUonnx: T5 Encoder - CPU - Standardonnx: fcn-resnet101-11 - CPU - Parallelonnx: yolov4 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: GPT-2 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Parallelcompress-lz4: 1 - Decompression Speedonnx: bertsquad-12 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Standardonnx: GPT-2 - CPU - Parallelonnx: T5 Encoder - CPU - Parallelonnx: yolov4 - CPU - Standardcompress-lz4: 9 - Compression Speedcompress-lz4: 1 - Compression Speedonnx: ArcFace ResNet-100 - CPU - Parallelonnx: super-resolution-10 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelcompress-lz4: 3 - Decompression Speedcompress-lz4: 3 - Compression Speedcompress-lz4: 9 - Decompression Speedonnx: super-resolution-10 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: super-resolution-10 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: bertsquad-12 - CPU - Parallelonnx: T5 Encoder - CPU - Standardonnx: T5 Encoder - CPU - Parallelonnx: yolov4 - CPU - Standardonnx: yolov4 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: GPT-2 - CPU - Parallelabc3.153.3110.92771.2041411.00251.78258.6371.125386.09066576.593170.12125.3641178.736131.4882815.222.1724701.371154.293250.5567.1377727.59519.839.8126175.714224.85992492.280.972511.879.494439.420640.222612.57613.20625.875337.6035790.885101.907830.466888.5841.423431.7324845.096591.50673.862273.98962140.095164.1815.585256.472352.893.0211.75451.2444410.74841.74258.8551.147586.16283566.725167.73625.0685176.5231322827.722.0769698.343154.899251.2527.1137727.68520.419.8294375.667224.83982493.180.95251179.516639.885540.255212.572313.21445.958237.5739293.0332101.733803.571871.3951.429551.7628245.291185.06993.85923.97869140.568162.265.655116.446972.833.3111.10911.2587210.98541.77253.5971.131226.20055576.227170.63225.4554177.439130.7052841.821.9998700.482154.703251.4577.1255627.64521.159.8099175.640124.86122491.680.99251279.485139.278940.220212.577413.21915.857067.6492991.0258101.936794.4568841.425321.7335645.449990.01293.939183.9752140.335161.2725.625856.45507OpenBenchmarking.org

Llamafile

Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPUabc0.70881.41762.12642.83523.5443.152.892.83

Llamafile

Test: llava-v1.5-7b-q4 - Acceleration: CPU

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: llava-v1.5-7b-q4 - Acceleration: CPUabc0.74481.48962.23442.97923.7243.313.023.31

ONNX Runtime

Model: bertsquad-12 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: Parallelabc369121510.9311.7511.111. (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.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: Standardabc0.28320.56640.84961.13281.4161.204141.244441.258721. (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.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: Standardabc369121511.0010.7510.991. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

Llamafile

Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPUabc0.40050.8011.20151.6022.00251.781.741.77

ONNX Runtime

Model: T5 Encoder - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: Standardabc60120180240300258.64258.86253.601. (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.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: Parallelabc0.25820.51640.77461.03281.2911.125381.147581.131221. (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.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: Parallelabc2468106.090666.162836.200551. (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.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallelabc120240360480600576.59566.73576.231. (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.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standardabc4080120160200170.12167.74170.631. (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.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standardabc61218243025.3625.0725.461. (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.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: Standardabc4080120160200178.74176.52177.441. (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.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallelabc306090120150131.49132.00130.711. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

LZ4 Compression

Compression Level: 1 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.4Compression Level: 1 - Decompression Speedabc60012001800240030002815.22827.72841.81. (CC) gcc options: -O3

ONNX Runtime

Model: bertsquad-12 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: Standardabc51015202522.1722.0822.001. (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.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: Standardabc150300450600750701.37698.34700.481. (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.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: Parallelabc306090120150154.29154.90154.701. (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.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: Parallelabc50100150200250250.56251.25251.461. (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.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: Standardabc2468107.137777.113777.125561. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

LZ4 Compression

Compression Level: 9 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.4Compression Level: 9 - Compression Speedabc71421283527.5927.6827.641. (CC) gcc options: -O3

LZ4 Compression

Compression Level: 1 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.4Compression Level: 1 - Compression Speedabc110220330440550519.83520.41521.151. (CC) gcc options: -O3

ONNX Runtime

Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallelabc36912159.812619.829439.809911. (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.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: Parallelabc2040608010075.7175.6775.641. (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.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallelabc61218243024.8624.8424.861. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

LZ4 Compression

Compression Level: 3 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.4Compression Level: 3 - Decompression Speedabc50010001500200025002492.22493.12491.61. (CC) gcc options: -O3

LZ4 Compression

Compression Level: 3 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.4Compression Level: 3 - Compression Speedabc2040608010080.9780.9580.991. (CC) gcc options: -O3

LZ4 Compression

Compression Level: 9 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.4Compression Level: 9 - Decompression Speedabc50010001500200025002511.82511.02512.01. (CC) gcc options: -O3

ONNX Runtime

Model: super-resolution-10 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: Standardabc2040608010079.4979.5279.491. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standardabc91827364539.4239.8939.281. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallelabc91827364540.2240.2640.221. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: Standardabc369121512.5812.5712.581. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: Parallelabc369121513.2113.2113.221. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standardabc1.34062.68124.02185.36246.7035.875335.958235.857061. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallelabc2468107.603577.573927.649291. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: Standardabc2040608010090.8993.0391.031. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallelabc20406080100101.91101.73101.941. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: Standardabc2004006008001000830.47803.57794.461. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: Parallelabc2004006008001000888.58871.40884.001. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: Standardabc0.32160.64320.96481.28641.6081.423431.429551.425321. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallelabc0.39660.79321.18981.58641.9831.732481.762821.733561. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: Standardabc102030405045.1045.2945.451. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: Parallelabc2040608010091.5185.0790.011. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: Standardabc0.88631.77262.65893.54524.43153.862273.859203.939181. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: Parallelabc0.89771.79542.69313.59084.48853.989623.978693.975201. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: Standardabc306090120150140.10140.57140.341. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: Parallelabc4080120160200164.18162.26161.271. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: Standardabc1.27242.54483.81725.08966.3625.585255.655115.625851. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: Parallelabc2468106.472356.446976.455071. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt


Phoronix Test Suite v10.8.5