hurricane-server

AMD Eng Sample 100-000000897-03 testing with a Supermicro Super Server H13SSL-N v2.00 (3.0 BIOS) and llvmpipe on Ubuntu 24.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2412185-NE-HURRICANE76.

hurricane-serverProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen Resolutionhurricane-serverAMD Eng Sample 100-000000897-03 @ 2.55GHz (32 Cores / 64 Threads)Supermicro Super Server H13SSL-N v2.00 (3.0 BIOS)AMD Device 14a432 GB + 32 GB + 32 GB + 16 GB + 16 GB + 16 GB + 32 GB + 32 GB + 32 GB + 16 GB + 16 GB + 16 GB DDR5-4800MT/s512GB INTEL SSDPEKKF512G8Lllvmpipe (405/715MHz)2 x Broadcom NetXtreme BCM5720 PCIeUbuntu 24.046.8.0-50-generic (x86_64)GNOME Shell 46.0X Server 1.21.1.11NVIDIA 535.183.014.5 Mesa 24.0.9-0ubuntu0.3 (LLVM 17.0.6 256 bits)OpenCL 3.0 CUDA 12.2.148GCC 13.3.0ext41024x768OpenBenchmarking.org- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-fG75Ri/gcc-13-13.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-fG75Ri/gcc-13-13.3.0/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-build-config=bootstrap-lto-lean --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 - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101020- BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 86.00.4d.00.01- GPU Compute Cores: 3584- Python 3.12.3- gather_data_sampling: Not affected + 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: Vulnerable: 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 Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

hurricane-servershoc: OpenCL - S3Dshoc: OpenCL - Triadshoc: OpenCL - FFT SPshoc: OpenCL - MD5 Hashshoc: OpenCL - Reductionshoc: OpenCL - GEMM SGEMM_Nshoc: OpenCL - Max SP Flopsshoc: OpenCL - Bus Speed Downloadshoc: OpenCL - Bus Speed Readbackshoc: OpenCL - Texture Read Bandwidthlczero: BLASonednn: IP Shapes 1D - CPUonednn: IP Shapes 3D - CPUonednn: Convolution Batch Shapes Auto - CPUonednn: Deconvolution Batch shapes_1d - CPUonednn: Deconvolution Batch shapes_3d - CPUonednn: Recurrent Neural Network Training - CPUonednn: Recurrent Neural Network Inference - CPUnumpy: deepspeech: CPUrbenchmark: rnnoise: 26 Minute Long Talking Samplelitert: DeepLab V3litert: SqueezeNetlitert: Inception V4litert: NASNet Mobilelitert: Mobilenet Floatlitert: Mobilenet Quantlitert: Inception ResNet V2litert: Quantized COCO SSD MobileNet v1tensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2pytorch: CPU - 1 - ResNet-50pytorch: CPU - 1 - ResNet-152pytorch: CPU - 16 - ResNet-50pytorch: CPU - 32 - ResNet-50pytorch: CPU - 64 - ResNet-50pytorch: CPU - 16 - ResNet-152pytorch: CPU - 256 - ResNet-50pytorch: CPU - 32 - ResNet-152pytorch: CPU - 512 - ResNet-50pytorch: CPU - 64 - ResNet-152pytorch: CPU - 256 - ResNet-152pytorch: CPU - 512 - ResNet-152pytorch: CPU - 1 - Efficientnet_v2_lpytorch: CPU - 16 - Efficientnet_v2_lpytorch: CPU - 32 - Efficientnet_v2_lpytorch: CPU - 64 - Efficientnet_v2_lpytorch: CPU - 256 - Efficientnet_v2_lpytorch: CPU - 512 - Efficientnet_v2_ltensorflow: CPU - 1 - VGG-16tensorflow: GPU - 1 - VGG-16tensorflow: CPU - 1 - AlexNettensorflow: CPU - 16 - VGG-16tensorflow: CPU - 32 - VGG-16tensorflow: CPU - 64 - VGG-16tensorflow: GPU - 1 - AlexNettensorflow: GPU - 16 - VGG-16tensorflow: GPU - 32 - VGG-16tensorflow: GPU - 64 - VGG-16tensorflow: CPU - 16 - AlexNettensorflow: CPU - 256 - VGG-16tensorflow: CPU - 32 - AlexNettensorflow: CPU - 512 - VGG-16tensorflow: CPU - 64 - AlexNettensorflow: GPU - 16 - AlexNettensorflow: GPU - 256 - VGG-16tensorflow: GPU - 32 - AlexNettensorflow: GPU - 512 - VGG-16tensorflow: GPU - 64 - AlexNettensorflow: CPU - 1 - GoogLeNettensorflow: CPU - 1 - ResNet-50tensorflow: CPU - 256 - AlexNettensorflow: CPU - 512 - AlexNettensorflow: GPU - 1 - GoogLeNettensorflow: GPU - 1 - ResNet-50tensorflow: GPU - 256 - AlexNettensorflow: GPU - 512 - AlexNettensorflow: CPU - 16 - GoogLeNettensorflow: CPU - 16 - ResNet-50tensorflow: CPU - 32 - GoogLeNettensorflow: CPU - 32 - ResNet-50tensorflow: CPU - 64 - GoogLeNettensorflow: CPU - 64 - ResNet-50tensorflow: GPU - 16 - GoogLeNettensorflow: GPU - 16 - ResNet-50tensorflow: GPU - 32 - GoogLeNettensorflow: GPU - 32 - ResNet-50tensorflow: GPU - 64 - GoogLeNettensorflow: GPU - 64 - ResNet-50tensorflow: CPU - 256 - GoogLeNettensorflow: CPU - 256 - ResNet-50tensorflow: CPU - 512 - GoogLeNettensorflow: CPU - 512 - ResNet-50tensorflow: GPU - 256 - GoogLeNettensorflow: GPU - 256 - ResNet-50tensorflow: GPU - 512 - GoogLeNettensorflow: GPU - 512 - ResNet-50ncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: CPU - vision_transformerncnn: CPU - FastestDetncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - FastestDetxnnpack: FP32MobileNetV1xnnpack: FP32MobileNetV2xnnpack: FP32MobileNetV3Largexnnpack: FP32MobileNetV3Smallxnnpack: FP16MobileNetV1xnnpack: FP16MobileNetV2xnnpack: FP16MobileNetV3Largexnnpack: FP16MobileNetV3Smallxnnpack: QS8MobileNetV2openvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUscikit-learn: GLMscikit-learn: SAGAscikit-learn: Treescikit-learn: Lassoscikit-learn: Sparsifyscikit-learn: Plot Wardscikit-learn: MNIST Datasetscikit-learn: Plot Neighborsscikit-learn: SGD Regressionscikit-learn: SGDOneClassSVMscikit-learn: Isolation Forestscikit-learn: Text Vectorizersscikit-learn: Plot Hierarchicalscikit-learn: Plot OMP vs. LARSscikit-learn: Feature Expansionsscikit-learn: LocalOutlierFactorscikit-learn: TSNE MNIST Datasetscikit-learn: Isotonic / Logisticscikit-learn: Plot Incremental PCAscikit-learn: Hist Gradient Boostingscikit-learn: Plot Parallel Pairwisescikit-learn: Isotonic / Pathologicalscikit-learn: Sample Without Replacementscikit-learn: Covertype Dataset Benchmarkscikit-learn: Hist Gradient Boosting Adultscikit-learn: Isotonic / Perturbed Logarithmscikit-learn: Hist Gradient Boosting Threadingscikit-learn: Hist Gradient Boosting Higgs Bosonscikit-learn: 20 Newsgroups / Logistic Regressionscikit-learn: Plot Polynomial Kernel Approximationscikit-learn: Hist Gradient Boosting Categorical Onlyscikit-learn: Kernel PCA Solvers / Time vs. N Samplesscikit-learn: Kernel PCA Solvers / Time vs. N Componentsscikit-learn: Sparse Rand Projections / 100 Iterationswhisper-cpp: ggml-base.en - 2016 State of the Unionwhisper-cpp: ggml-small.en - 2016 State of the Unionwhisper-cpp: ggml-medium.en - 2016 State of the Unionwhisperfile: Tinywhisperfile: Smallwhisperfile: Mediumopencv: DNN - Deep Neural Networkopenvino-genai: Gemma-7b-int4-ov - CPUopenvino-genai: Gemma-7b-int4-ov - CPU - Time To First Tokenopenvino-genai: Gemma-7b-int4-ov - CPU - Time Per Output Tokenopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPUopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time To First Tokenopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time Per Output Tokenopenvino-genai: Falcon-7b-instruct-int4-ov - CPUopenvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time To First Tokenopenvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time Per Output Tokenopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPUopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time To First Tokenopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time Per Output Tokenhurricane-server268.84712.89501479.1714.4889257.8875521.359437.5113.213813.5433588.1132810.8503850.6804941.147905.684711.81557811.253450.858513.7553.374640.170711.3553250.312102.3416671.731332.41332.511404.2919022.72299.812015.7416113.824134.51306.872531.3331730.667.9424.6951.3952.1252.1019.5552.1219.5152.0919.6919.4819.5012.478.218.108.218.208.1615.041.6158.0229.2831.7632.6515.941.761.771.78376.9333.52465.6633.71532.9530.061.7932.121.7933.2453.6217.32651.72679.6314.654.7233.9734.13214.2174.57241.1684.65262.3190.0220.156.6020.376.7320.836.78283.2898.53288.79101.6021.066.8421.106.8315.817.417.939.516.919.733.8017.3925.239.015.5114.4615.8126.5816.8524.0667.8711.1815.987.437.959.496.899.713.8117.4125.178.995.5214.4615.9827.0116.9224.0867.7111.5713062162313621641348198530122136200120.16790.62192.3083.08193.1982.701536.1610.3738.67412.404791.903.29786.8320.282367.686.721984.6816.086872.554.59834.8119.12233.0468.603835.558.292176.467.312638.3311.901092.3929.252734.755.8247505.840.581160.6027.5264559.580.41200.4211027.76868.790536.893156.75057.02678.400174.50087.926330.205236.89065.346197.94846.717126.77625.661268.0621974.79736.502247.454123.0314978.992135.813434.505245.1462180.91768.02277.70712.941129.01744.82168.49440.062659.729116.86325243.05902605.2155448.31755137.64843312.217193330330.1172.7233.2165.7618.2415.2139.3759.0625.4047.1741.4121.20OpenBenchmarking.org

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: S3D

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3Dhurricane-server60120180240300SE +/- 0.10, N = 3268.851. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Triad

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Triadhurricane-server3691215SE +/- 0.00, N = 312.901. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: FFT SP

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPhurricane-server30060090012001500SE +/- 10.08, N = 121479.171. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: MD5 Hash

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 Hashhurricane-server48121620SE +/- 0.00, N = 314.491. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Reduction

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Reductionhurricane-server60120180240300SE +/- 0.04, N = 3257.891. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: GEMM SGEMM_N

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_Nhurricane-server12002400360048006000SE +/- 0.39, N = 35521.351. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Max SP Flops

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP Flopshurricane-server2K4K6K8K10KSE +/- 0.57, N = 39437.511. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Download

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed Downloadhurricane-server3691215SE +/- 0.00, N = 313.211. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Readback

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed Readbackhurricane-server3691215SE +/- 0.00, N = 313.541. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Texture Read Bandwidth

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read Bandwidthhurricane-server130260390520650SE +/- 0.03, N = 3588.111. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

LeelaChessZero

Backend: BLAS

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.31.1Backend: BLAShurricane-server60120180240300SE +/- 2.91, N = 32811. (CXX) g++ options: -flto -pthread

oneDNN

Harness: IP Shapes 1D - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: IP Shapes 1D - Engine: CPUhurricane-server0.19130.38260.57390.76520.9565SE +/- 0.001043, N = 30.850385MIN: 0.821. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

oneDNN

Harness: IP Shapes 3D - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: IP Shapes 3D - Engine: CPUhurricane-server0.15310.30620.45930.61240.7655SE +/- 0.000710, N = 30.680494MIN: 0.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

oneDNN

Harness: Convolution Batch Shapes Auto - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Convolution Batch Shapes Auto - Engine: CPUhurricane-server0.25830.51660.77491.03321.2915SE +/- 0.00120, N = 31.14790MIN: 1.111. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Deconvolution Batch shapes_1d - Engine: CPUhurricane-server1.27912.55823.83735.11646.3955SE +/- 0.00716, N = 35.68471MIN: 3.771. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

oneDNN

Harness: Deconvolution Batch shapes_3d - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Deconvolution Batch shapes_3d - Engine: CPUhurricane-server0.40850.8171.22551.6342.0425SE +/- 0.00663, N = 31.81557MIN: 1.791. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

oneDNN

Harness: Recurrent Neural Network Training - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Recurrent Neural Network Training - Engine: CPUhurricane-server2004006008001000SE +/- 0.33, N = 3811.25MIN: 807.441. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Recurrent Neural Network Inference - Engine: CPUhurricane-server100200300400500SE +/- 0.21, N = 3450.86MIN: 447.461. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

Numpy Benchmark

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmarkhurricane-server110220330440550SE +/- 1.66, N = 3513.75

DeepSpeech

Acceleration: CPU

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUhurricane-server1224364860SE +/- 0.09, N = 353.37

R Benchmark

OpenBenchmarking.orgSeconds, Fewer Is BetterR Benchmarkhurricane-server0.03840.07680.11520.15360.192SE +/- 0.0004, N = 30.1707

RNNoise

Input: 26 Minute Long Talking Sample

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 0.2Input: 26 Minute Long Talking Samplehurricane-server3691215SE +/- 0.05, N = 311.361. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

LiteRT

Model: DeepLab V3

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: DeepLab V3hurricane-server7001400210028003500SE +/- 8.28, N = 33250.31

LiteRT

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: SqueezeNethurricane-server5001000150020002500SE +/- 8.16, N = 32102.34

LiteRT

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception V4hurricane-server4K8K12K16K20KSE +/- 15.14, N = 316671.7

LiteRT

Model: NASNet Mobile

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: NASNet Mobilehurricane-server7K14K21K28K35KSE +/- 132.52, N = 331332.4

LiteRT

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet Floathurricane-server30060090012001500SE +/- 1.07, N = 31332.51

LiteRT

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet Quanthurricane-server30060090012001500SE +/- 16.18, N = 151404.29

LiteRT

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception ResNet V2hurricane-server4K8K12K16K20KSE +/- 63.82, N = 319022.7

LiteRT

Model: Quantized COCO SSD MobileNet v1

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Quantized COCO SSD MobileNet v1hurricane-server5001000150020002500SE +/- 11.18, N = 32299.81

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNethurricane-server400800120016002000SE +/- 6.84, N = 32015.74

TensorFlow Lite

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4hurricane-server3K6K9K12K15KSE +/- 14.50, N = 316113.8

TensorFlow Lite

Model: NASNet Mobile

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet Mobilehurricane-server5K10K15K20K25KSE +/- 13.44, N = 324134.5

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Floathurricane-server30060090012001500SE +/- 4.16, N = 31306.87

TensorFlow Lite

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Quanthurricane-server5001000150020002500SE +/- 26.36, N = 42531.33

TensorFlow Lite

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2hurricane-server7K14K21K28K35KSE +/- 101.48, N = 331730.6

PyTorch

Device: CPU - Batch Size: 1 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: ResNet-50hurricane-server1530456075SE +/- 0.51, N = 367.94MIN: 50.17 / MAX: 69.35

PyTorch

Device: CPU - Batch Size: 1 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: ResNet-152hurricane-server612182430SE +/- 0.17, N = 324.69MIN: 19.29 / MAX: 25.17

PyTorch

Device: CPU - Batch Size: 16 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 16 - Model: ResNet-50hurricane-server1224364860SE +/- 0.34, N = 351.39MIN: 38.88 / MAX: 52.76

PyTorch

Device: CPU - Batch Size: 32 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 32 - Model: ResNet-50hurricane-server1224364860SE +/- 0.13, N = 352.12MIN: 38.35 / MAX: 52.97

PyTorch

Device: CPU - Batch Size: 64 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: ResNet-50hurricane-server1224364860SE +/- 0.19, N = 352.10MIN: 45.33 / MAX: 52.97

PyTorch

Device: CPU - Batch Size: 16 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 16 - Model: ResNet-152hurricane-server510152025SE +/- 0.21, N = 319.55MIN: 14.89 / MAX: 19.9

PyTorch

Device: CPU - Batch Size: 256 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 256 - Model: ResNet-50hurricane-server1224364860SE +/- 0.18, N = 352.12MIN: 39.21 / MAX: 53.52

PyTorch

Device: CPU - Batch Size: 32 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 32 - Model: ResNet-152hurricane-server510152025SE +/- 0.09, N = 319.51MIN: 16.27 / MAX: 19.75

PyTorch

Device: CPU - Batch Size: 512 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 512 - Model: ResNet-50hurricane-server1224364860SE +/- 0.23, N = 352.09MIN: 45 / MAX: 53.04

PyTorch

Device: CPU - Batch Size: 64 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: ResNet-152hurricane-server510152025SE +/- 0.01, N = 319.69MIN: 18.64 / MAX: 19.84

PyTorch

Device: CPU - Batch Size: 256 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 256 - Model: ResNet-152hurricane-server510152025SE +/- 0.16, N = 319.48MIN: 15.08 / MAX: 19.95

PyTorch

Device: CPU - Batch Size: 512 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 512 - Model: ResNet-152hurricane-server510152025SE +/- 0.11, N = 319.50MIN: 6 / MAX: 19.85

PyTorch

Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_lhurricane-server3691215SE +/- 0.09, N = 312.47MIN: 10.7 / MAX: 12.87

PyTorch

Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_lhurricane-server246810SE +/- 0.04, N = 38.21MIN: 7 / MAX: 8.84

PyTorch

Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_lhurricane-server246810SE +/- 0.09, N = 48.10MIN: 2.17 / MAX: 8.79

PyTorch

Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_lhurricane-server246810SE +/- 0.03, N = 38.21MIN: 5.85 / MAX: 8.81

PyTorch

Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_lhurricane-server246810SE +/- 0.01, N = 38.20MIN: 7.01 / MAX: 8.8

PyTorch

Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_lhurricane-server246810SE +/- 0.01, N = 38.16MIN: 3.8 / MAX: 8.81

TensorFlow

Device: CPU - Batch Size: 1 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: VGG-16hurricane-server48121620SE +/- 0.01, N = 315.04

TensorFlow

Device: GPU - Batch Size: 1 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 1 - Model: VGG-16hurricane-server0.36230.72461.08691.44921.8115SE +/- 0.00, N = 31.61

TensorFlow

Device: CPU - Batch Size: 1 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: AlexNethurricane-server1326395265SE +/- 0.18, N = 358.02

TensorFlow

Device: CPU - Batch Size: 16 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 16 - Model: VGG-16hurricane-server714212835SE +/- 0.29, N = 329.28

TensorFlow

Device: CPU - Batch Size: 32 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: VGG-16hurricane-server714212835SE +/- 0.04, N = 331.76

TensorFlow

Device: CPU - Batch Size: 64 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: VGG-16hurricane-server816243240SE +/- 0.01, N = 332.65

TensorFlow

Device: GPU - Batch Size: 1 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 1 - Model: AlexNethurricane-server48121620SE +/- 0.14, N = 315.94

TensorFlow

Device: GPU - Batch Size: 16 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 16 - Model: VGG-16hurricane-server0.3960.7921.1881.5841.98SE +/- 0.00, N = 31.76

TensorFlow

Device: GPU - Batch Size: 32 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 32 - Model: VGG-16hurricane-server0.39830.79661.19491.59321.9915SE +/- 0.00, N = 31.77

TensorFlow

Device: GPU - Batch Size: 64 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 64 - Model: VGG-16hurricane-server0.40050.8011.20151.6022.0025SE +/- 0.00, N = 31.78

TensorFlow

Device: CPU - Batch Size: 16 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 16 - Model: AlexNethurricane-server80160240320400SE +/- 0.72, N = 3376.93

TensorFlow

Device: CPU - Batch Size: 256 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: VGG-16hurricane-server816243240SE +/- 0.01, N = 333.52

TensorFlow

Device: CPU - Batch Size: 32 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: AlexNethurricane-server100200300400500SE +/- 0.31, N = 3465.66

TensorFlow

Device: CPU - Batch Size: 512 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: VGG-16hurricane-server816243240SE +/- 0.01, N = 333.71

TensorFlow

Device: CPU - Batch Size: 64 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: AlexNethurricane-server120240360480600SE +/- 1.95, N = 3532.95

TensorFlow

Device: GPU - Batch Size: 16 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 16 - Model: AlexNethurricane-server714212835SE +/- 0.01, N = 330.06

TensorFlow

Device: GPU - Batch Size: 256 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 256 - Model: VGG-16hurricane-server0.40280.80561.20841.61122.014SE +/- 0.00, N = 31.79

TensorFlow

Device: GPU - Batch Size: 32 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 32 - Model: AlexNethurricane-server714212835SE +/- 0.00, N = 332.12

TensorFlow

Device: GPU - Batch Size: 512 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 512 - Model: VGG-16hurricane-server0.40280.80561.20841.61122.014SE +/- 0.00, N = 31.79

TensorFlow

Device: GPU - Batch Size: 64 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 64 - Model: AlexNethurricane-server816243240SE +/- 0.01, N = 333.24

TensorFlow

Device: CPU - Batch Size: 1 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: GoogLeNethurricane-server1224364860SE +/- 0.66, N = 353.62

TensorFlow

Device: CPU - Batch Size: 1 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: ResNet-50hurricane-server48121620SE +/- 0.05, N = 317.32

TensorFlow

Device: CPU - Batch Size: 256 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: AlexNethurricane-server140280420560700SE +/- 0.16, N = 3651.72

TensorFlow

Device: CPU - Batch Size: 512 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: AlexNethurricane-server150300450600750SE +/- 0.16, N = 3679.63

TensorFlow

Device: GPU - Batch Size: 1 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 1 - Model: GoogLeNethurricane-server48121620SE +/- 0.04, N = 314.65

TensorFlow

Device: GPU - Batch Size: 1 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 1 - Model: ResNet-50hurricane-server1.0622.1243.1864.2485.31SE +/- 0.02, N = 34.72

TensorFlow

Device: GPU - Batch Size: 256 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 256 - Model: AlexNethurricane-server816243240SE +/- 0.00, N = 333.97

TensorFlow

Device: GPU - Batch Size: 512 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 512 - Model: AlexNethurricane-server816243240SE +/- 0.00, N = 334.13

TensorFlow

Device: CPU - Batch Size: 16 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 16 - Model: GoogLeNethurricane-server50100150200250SE +/- 0.53, N = 3214.21

TensorFlow

Device: CPU - Batch Size: 16 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 16 - Model: ResNet-50hurricane-server20406080100SE +/- 0.12, N = 374.57

TensorFlow

Device: CPU - Batch Size: 32 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: GoogLeNethurricane-server50100150200250SE +/- 1.98, N = 3241.16

TensorFlow

Device: CPU - Batch Size: 32 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: ResNet-50hurricane-server20406080100SE +/- 0.02, N = 384.65

TensorFlow

Device: CPU - Batch Size: 64 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: GoogLeNethurricane-server60120180240300SE +/- 0.20, N = 3262.31

TensorFlow

Device: CPU - Batch Size: 64 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: ResNet-50hurricane-server20406080100SE +/- 0.12, N = 390.02

TensorFlow

Device: GPU - Batch Size: 16 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 16 - Model: GoogLeNethurricane-server510152025SE +/- 0.02, N = 320.15

TensorFlow

Device: GPU - Batch Size: 16 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 16 - Model: ResNet-50hurricane-server246810SE +/- 0.01, N = 36.60

TensorFlow

Device: GPU - Batch Size: 32 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 32 - Model: GoogLeNethurricane-server510152025SE +/- 0.20, N = 320.37

TensorFlow

Device: GPU - Batch Size: 32 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 32 - Model: ResNet-50hurricane-server246810SE +/- 0.00, N = 36.73

TensorFlow

Device: GPU - Batch Size: 64 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 64 - Model: GoogLeNethurricane-server510152025SE +/- 0.00, N = 320.83

TensorFlow

Device: GPU - Batch Size: 64 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 64 - Model: ResNet-50hurricane-server246810SE +/- 0.01, N = 36.78

TensorFlow

Device: CPU - Batch Size: 256 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: GoogLeNethurricane-server60120180240300SE +/- 0.12, N = 3283.28

TensorFlow

Device: CPU - Batch Size: 256 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: ResNet-50hurricane-server20406080100SE +/- 0.05, N = 398.53

TensorFlow

Device: CPU - Batch Size: 512 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: GoogLeNethurricane-server60120180240300SE +/- 0.32, N = 3288.79

TensorFlow

Device: CPU - Batch Size: 512 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: ResNet-50hurricane-server20406080100SE +/- 0.05, N = 3101.60

TensorFlow

Device: GPU - Batch Size: 256 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 256 - Model: GoogLeNethurricane-server510152025SE +/- 0.02, N = 321.06

TensorFlow

Device: GPU - Batch Size: 256 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 256 - Model: ResNet-50hurricane-server246810SE +/- 0.00, N = 36.84

TensorFlow

Device: GPU - Batch Size: 512 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 512 - Model: GoogLeNethurricane-server510152025SE +/- 0.01, N = 321.10

TensorFlow

Device: GPU - Batch Size: 512 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: GPU - Batch Size: 512 - Model: ResNet-50hurricane-server246810SE +/- 0.00, N = 36.83

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mobilenethurricane-server48121620SE +/- 0.13, N = 315.81MIN: 15.42 / MAX: 19.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v2-v2 - Model: mobilenet-v2hurricane-server246810SE +/- 0.02, N = 37.41MIN: 7.07 / MAX: 11.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3 - Model: mobilenet-v3hurricane-server246810SE +/- 0.02, N = 37.93MIN: 7.73 / MAX: 12.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: shufflenet-v2hurricane-server3691215SE +/- 0.04, N = 39.51MIN: 9.3 / MAX: 13.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mnasnethurricane-server246810SE +/- 0.01, N = 36.91MIN: 6.66 / MAX: 10.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: efficientnet-b0hurricane-server3691215SE +/- 0.02, N = 39.73MIN: 9.35 / MAX: 161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: blazefacehurricane-server0.8551.712.5653.424.275SE +/- 0.02, N = 33.80MIN: 3.71 / MAX: 6.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: googlenethurricane-server48121620SE +/- 0.03, N = 317.39MIN: 17.15 / MAX: 21.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vgg16hurricane-server612182430SE +/- 0.22, N = 325.23MIN: 24.68 / MAX: 29.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet18hurricane-server3691215SE +/- 0.04, N = 39.01MIN: 8.81 / MAX: 20.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: alexnethurricane-server1.23982.47963.71944.95926.199SE +/- 0.01, N = 35.51MIN: 5.39 / MAX: 7.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet50hurricane-server48121620SE +/- 0.10, N = 314.46MIN: 14.12 / MAX: 27.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3hurricane-server48121620SE +/- 0.13, N = 315.81MIN: 15.42 / MAX: 19.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: yolov4-tinyhurricane-server612182430SE +/- 0.41, N = 326.58MIN: 24.96 / MAX: 30.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: squeezenet_ssdhurricane-server48121620SE +/- 0.01, N = 316.85MIN: 16.68 / MAX: 22.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: regnety_400mhurricane-server612182430SE +/- 0.06, N = 324.06MIN: 23.72 / MAX: 36.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vision_transformerhurricane-server1530456075SE +/- 2.57, N = 367.87MIN: 44.97 / MAX: 7581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: FastestDethurricane-server3691215SE +/- 0.44, N = 311.18MIN: 10.06 / MAX: 21.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenethurricane-server48121620SE +/- 0.02, N = 315.98MIN: 15.78 / MAX: 20.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2hurricane-server246810SE +/- 0.03, N = 37.43MIN: 7.08 / MAX: 11.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3hurricane-server246810SE +/- 0.02, N = 37.95MIN: 7.73 / MAX: 15.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v2hurricane-server3691215SE +/- 0.01, N = 39.49MIN: 9.27 / MAX: 14.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnethurricane-server246810SE +/- 0.01, N = 36.89MIN: 6.67 / MAX: 7.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b0hurricane-server3691215SE +/- 0.02, N = 39.71MIN: 9.4 / MAX: 13.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazefacehurricane-server0.85731.71462.57193.42924.2865SE +/- 0.00, N = 33.81MIN: 3.74 / MAX: 7.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenethurricane-server48121620SE +/- 0.04, N = 317.41MIN: 17.2 / MAX: 22.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg16hurricane-server612182430SE +/- 0.25, N = 325.17MIN: 23.53 / MAX: 34.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet18hurricane-server3691215SE +/- 0.04, N = 38.99MIN: 8.82 / MAX: 13.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnethurricane-server1.2422.4843.7264.9686.21SE +/- 0.00, N = 35.52MIN: 5.39 / MAX: 9.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet50hurricane-server48121620SE +/- 0.11, N = 314.46MIN: 14.13 / MAX: 18.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3hurricane-server48121620SE +/- 0.02, N = 315.98MIN: 15.78 / MAX: 20.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tinyhurricane-server612182430SE +/- 0.05, N = 327.01MIN: 25.85 / MAX: 31.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssdhurricane-server48121620SE +/- 0.02, N = 316.92MIN: 16.68 / MAX: 29.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400mhurricane-server612182430SE +/- 0.02, N = 324.08MIN: 23.85 / MAX: 28.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformerhurricane-server1530456075SE +/- 1.75, N = 367.71MIN: 45.61 / MAX: 933.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: FastestDethurricane-server3691215SE +/- 0.42, N = 311.57MIN: 10.54 / MAX: 16.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

XNNPACK

Model: FP32MobileNetV1

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV1hurricane-server30060090012001500SE +/- 2.33, N = 313061. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: FP32MobileNetV2

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV2hurricane-server5001000150020002500SE +/- 7.51, N = 321621. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: FP32MobileNetV3Large

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3Largehurricane-server7001400210028003500SE +/- 11.68, N = 331361. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: FP32MobileNetV3Small

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3Smallhurricane-server5001000150020002500SE +/- 5.46, N = 321641. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: FP16MobileNetV1

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV1hurricane-server30060090012001500SE +/- 3.06, N = 313481. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: FP16MobileNetV2

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV2hurricane-server400800120016002000SE +/- 2.91, N = 319851. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: FP16MobileNetV3Large

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3Largehurricane-server6001200180024003000SE +/- 9.07, N = 330121. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: FP16MobileNetV3Small

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3Smallhurricane-server5001000150020002500SE +/- 4.84, N = 321361. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: QS8MobileNetV2

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: QS8MobileNetV2hurricane-server400800120016002000SE +/- 5.33, N = 320011. (CXX) g++ options: -O3 -lrt -lm

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection FP16 - Device: CPUhurricane-server510152025SE +/- 0.01, N = 320.161. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection FP16 - Device: CPUhurricane-server2004006008001000SE +/- 0.52, N = 3790.62MIN: 405.74 / MAX: 865.841. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Detection FP16 - Device: CPUhurricane-server4080120160200SE +/- 0.15, N = 3192.301. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Detection FP16 - Device: CPUhurricane-server20406080100SE +/- 0.07, N = 383.08MIN: 40.18 / MAX: 109.431. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Detection FP32 - Device: CPUhurricane-server4080120160200SE +/- 0.60, N = 3193.191. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Detection FP32 - Device: CPUhurricane-server20406080100SE +/- 0.26, N = 382.70MIN: 39.41 / MAX: 109.651. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16 - Device: CPUhurricane-server30060090012001500SE +/- 0.45, N = 31536.161. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16 - Device: CPUhurricane-server3691215SE +/- 0.00, N = 310.37MIN: 5.46 / MAX: 41.761. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection FP16-INT8 - Device: CPUhurricane-server918273645SE +/- 0.04, N = 338.671. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection FP16-INT8 - Device: CPUhurricane-server90180270360450SE +/- 0.40, N = 3412.40MIN: 344.16 / MAX: 498.391. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection Retail FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16 - Device: CPUhurricane-server10002000300040005000SE +/- 12.23, N = 34791.901. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection Retail FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16 - Device: CPUhurricane-server0.74031.48062.22092.96123.7015SE +/- 0.01, N = 33.29MIN: 1.9 / MAX: 35.771. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Road Segmentation ADAS FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16 - Device: CPUhurricane-server2004006008001000SE +/- 0.23, N = 3786.831. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Road Segmentation ADAS FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16 - Device: CPUhurricane-server510152025SE +/- 0.01, N = 320.28MIN: 14.13 / MAX: 39.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16-INT8 - Device: CPUhurricane-server5001000150020002500SE +/- 3.74, N = 32367.681. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16-INT8 - Device: CPUhurricane-server246810SE +/- 0.01, N = 36.72MIN: 4.28 / MAX: 18.931. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16 - Device: CPUhurricane-server400800120016002000SE +/- 12.59, N = 31984.681. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16 - Device: CPUhurricane-server48121620SE +/- 0.11, N = 316.08MIN: 8.51 / MAX: 99.911. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection Retail FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16-INT8 - Device: CPUhurricane-server15003000450060007500SE +/- 3.13, N = 36872.551. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection Retail FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16-INT8 - Device: CPUhurricane-server1.03282.06563.09844.13125.164SE +/- 0.00, N = 34.59MIN: 2.72 / MAX: 18.861. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Road Segmentation ADAS FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16-INT8 - Device: CPUhurricane-server2004006008001000SE +/- 0.46, N = 3834.811. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Road Segmentation ADAS FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16-INT8 - Device: CPUhurricane-server510152025SE +/- 0.01, N = 319.12MIN: 11.33 / MAX: 35.261. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Machine Translation EN To DE FP16 - Device: CPUhurricane-server50100150200250SE +/- 0.16, N = 3233.041. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Machine Translation EN To DE FP16 - Device: CPUhurricane-server1530456075SE +/- 0.05, N = 368.60MIN: 36.93 / MAX: 98.871. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16-INT8 - Device: CPUhurricane-server8001600240032004000SE +/- 28.56, N = 33835.551. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16-INT8 - Device: CPUhurricane-server246810SE +/- 0.07, N = 38.29MIN: 4.39 / MAX: 59.431. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Vehicle Bike Detection FP16 - Device: CPUhurricane-server5001000150020002500SE +/- 2.00, N = 32176.461. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Vehicle Bike Detection FP16 - Device: CPUhurricane-server246810SE +/- 0.01, N = 37.31MIN: 4.6 / MAX: 22.021. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Noise Suppression Poconet-Like FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Noise Suppression Poconet-Like FP16 - Device: CPUhurricane-server6001200180024003000SE +/- 3.23, N = 32638.331. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Noise Suppression Poconet-Like FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Noise Suppression Poconet-Like FP16 - Device: CPUhurricane-server3691215SE +/- 0.01, N = 311.90MIN: 7.82 / MAX: 26.251. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Handwritten English Recognition FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16 - Device: CPUhurricane-server2004006008001000SE +/- 8.53, N = 31092.391. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Handwritten English Recognition FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16 - Device: CPUhurricane-server714212835SE +/- 0.23, N = 329.25MIN: 20.04 / MAX: 50.131. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Re-Identification Retail FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Re-Identification Retail FP16 - Device: CPUhurricane-server6001200180024003000SE +/- 2.65, N = 32734.751. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Re-Identification Retail FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Re-Identification Retail FP16 - Device: CPUhurricane-server1.30952.6193.92855.2386.5475SE +/- 0.01, N = 35.82MIN: 3.76 / MAX: 20.841. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUhurricane-server10K20K30K40K50KSE +/- 19.37, N = 347505.841. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUhurricane-server0.13050.2610.39150.5220.6525SE +/- 0.00, N = 30.58MIN: 0.3 / MAX: 12.741. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Handwritten English Recognition FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16-INT8 - Device: CPUhurricane-server2004006008001000SE +/- 2.64, N = 31160.601. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Handwritten English Recognition FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16-INT8 - Device: CPUhurricane-server612182430SE +/- 0.06, N = 327.52MIN: 21.34 / MAX: 50.491. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUhurricane-server14K28K42K56K70KSE +/- 85.18, N = 364559.581. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUhurricane-server0.09230.18460.27690.36920.4615SE +/- 0.00, N = 30.41MIN: 0.23 / MAX: 11.691. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Scikit-Learn

Benchmark: GLM

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: GLMhurricane-server4080120160200SE +/- 0.25, N = 3200.421. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: SAGA

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: SAGAhurricane-server2004006008001000SE +/- 0.84, N = 31027.771. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Tree

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Treehurricane-server1530456075SE +/- 0.69, N = 1568.791. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Lasso

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Lassohurricane-server120240360480600SE +/- 2.40, N = 3536.891. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Sparsify

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Sparsifyhurricane-server306090120150SE +/- 0.28, N = 3156.751. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Plot Ward

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Wardhurricane-server1326395265SE +/- 0.10, N = 357.031. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: MNIST Dataset

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: MNIST Datasethurricane-server20406080100SE +/- 0.03, N = 378.401. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Plot Neighbors

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Neighborshurricane-server4080120160200SE +/- 0.73, N = 3174.501. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: SGD Regression

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: SGD Regressionhurricane-server20406080100SE +/- 0.12, N = 387.931. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: SGDOneClassSVM

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: SGDOneClassSVMhurricane-server70140210280350SE +/- 0.43, N = 3330.211. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Isolation Forest

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Isolation Foresthurricane-server50100150200250SE +/- 0.22, N = 3236.891. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Text Vectorizers

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Text Vectorizershurricane-server1530456075SE +/- 0.08, N = 365.351. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Plot Hierarchical

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Hierarchicalhurricane-server4080120160200SE +/- 0.23, N = 3197.951. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Plot OMP vs. LARS

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot OMP vs. LARShurricane-server1122334455SE +/- 0.08, N = 346.721. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Feature Expansions

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Feature Expansionshurricane-server306090120150SE +/- 0.31, N = 3126.781. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: LocalOutlierFactor

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: LocalOutlierFactorhurricane-server612182430SE +/- 0.02, N = 325.661. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: TSNE MNIST Dataset

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: TSNE MNIST Datasethurricane-server60120180240300SE +/- 0.45, N = 3268.061. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Isotonic / Logistic

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Isotonic / Logistichurricane-server400800120016002000SE +/- 0.59, N = 31974.801. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Plot Incremental PCA

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Incremental PCAhurricane-server816243240SE +/- 0.08, N = 336.501. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Hist Gradient Boosting

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient Boostinghurricane-server50100150200250SE +/- 0.79, N = 3247.451. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Plot Parallel Pairwise

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Parallel Pairwisehurricane-server306090120150SE +/- 0.39, N = 3123.031. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Isotonic / Pathological

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Isotonic / Pathologicalhurricane-server11002200330044005500SE +/- 1.30, N = 34978.991. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Sample Without Replacement

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Sample Without Replacementhurricane-server306090120150SE +/- 0.09, N = 3135.811. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Covertype Dataset Benchmark

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Covertype Dataset Benchmarkhurricane-server90180270360450SE +/- 0.10, N = 3434.511. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Hist Gradient Boosting Adult

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient Boosting Adulthurricane-server50100150200250SE +/- 0.15, N = 3245.151. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Isotonic / Perturbed Logarithm

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Isotonic / Perturbed Logarithmhurricane-server5001000150020002500SE +/- 1.48, N = 32180.921. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Hist Gradient Boosting Threading

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient Boosting Threadinghurricane-server1530456075SE +/- 0.19, N = 368.021. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Hist Gradient Boosting Higgs Boson

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient Boosting Higgs Bosonhurricane-server20406080100SE +/- 0.88, N = 377.711. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: 20 Newsgroups / Logistic Regression

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: 20 Newsgroups / Logistic Regressionhurricane-server3691215SE +/- 0.08, N = 312.941. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Plot Polynomial Kernel Approximation

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Polynomial Kernel Approximationhurricane-server306090120150SE +/- 0.10, N = 3129.021. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Hist Gradient Boosting Categorical Only

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient Boosting Categorical Onlyhurricane-server1020304050SE +/- 0.31, N = 344.821. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Kernel PCA Solvers / Time vs. N Samples

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Kernel PCA Solvers / Time vs. N Sampleshurricane-server1530456075SE +/- 0.18, N = 368.491. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Kernel PCA Solvers / Time vs. N Components

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Kernel PCA Solvers / Time vs. N Componentshurricane-server918273645SE +/- 0.57, N = 340.061. (F9X) gfortran options: -O0

Scikit-Learn

Benchmark: Sparse Random Projections / 100 Iterations

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Sparse Random Projections / 100 Iterationshurricane-server140280420560700SE +/- 1.78, N = 3659.731. (F9X) gfortran options: -O0

Whisper.cpp

Model: ggml-base.en - Input: 2016 State of the Union

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.6.2Model: ggml-base.en - Input: 2016 State of the Unionhurricane-server306090120150SE +/- 0.28, N = 3116.861. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni

Whisper.cpp

Model: ggml-small.en - Input: 2016 State of the Union

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.6.2Model: ggml-small.en - Input: 2016 State of the Unionhurricane-server50100150200250SE +/- 0.71, N = 3243.061. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni

Whisper.cpp

Model: ggml-medium.en - Input: 2016 State of the Union

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.6.2Model: ggml-medium.en - Input: 2016 State of the Unionhurricane-server130260390520650SE +/- 5.80, N = 3605.221. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni

Whisperfile

Model Size: Tiny

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisperfile 20Aug24Model Size: Tinyhurricane-server1122334455SE +/- 0.20, N = 348.32

Whisperfile

Model Size: Small

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisperfile 20Aug24Model Size: Smallhurricane-server306090120150SE +/- 0.47, N = 3137.65

Whisperfile

Model Size: Medium

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisperfile 20Aug24Model Size: Mediumhurricane-server70140210280350SE +/- 1.81, N = 3312.22

OpenCV

Test: DNN - Deep Neural Network

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: DNN - Deep Neural Networkhurricane-server7K14K21K28K35KSE +/- 601.47, N = 15333031. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

OpenVINO GenAI

Model: Gemma-7b-int4-ov - Device: CPU

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPUhurricane-server714212835SE +/- 0.24, N = 330.11

OpenVINO GenAI

Model: Gemma-7b-int4-ov - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPU - Time To First Tokenhurricane-server1632486480SE +/- 0.30, N = 372.72

OpenVINO GenAI

Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Tokenhurricane-server816243240SE +/- 0.27, N = 333.21

OpenVINO GenAI

Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPUhurricane-server1530456075SE +/- 0.16, N = 365.76

OpenVINO GenAI

Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Tokenhurricane-server48121620SE +/- 0.01, N = 318.24

OpenVINO GenAI

Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Tokenhurricane-server48121620SE +/- 0.04, N = 315.21

OpenVINO GenAI

Model: Falcon-7b-instruct-int4-ov - Device: CPU

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Falcon-7b-instruct-int4-ov - Device: CPUhurricane-server918273645SE +/- 0.16, N = 339.37

OpenVINO GenAI

Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Tokenhurricane-server1326395265SE +/- 0.06, N = 359.06

OpenVINO GenAI

Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Tokenhurricane-server612182430SE +/- 0.11, N = 325.40

OpenVINO GenAI

Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPUhurricane-server1122334455SE +/- 0.29, N = 347.17

OpenVINO GenAI

Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Tokenhurricane-server918273645SE +/- 0.10, N = 341.41

OpenVINO GenAI

Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Tokenhurricane-server510152025SE +/- 0.13, N = 321.20


Phoronix Test Suite v10.8.5