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/2412184-NE-HURRICANE48&grw .
hurricane-server Processor Motherboard Chipset Memory Disk Graphics Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Compiler File-System Screen Resolution hurricane-server AMD Eng Sample 100-000000897-03 @ 2.55GHz (32 Cores / 64 Threads) Supermicro Super Server H13SSL-N v2.00 (3.0 BIOS) AMD Device 14a4 32 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/s 512GB INTEL SSDPEKKF512G8L llvmpipe (405/715MHz) 2 x Broadcom NetXtreme BCM5720 PCIe Ubuntu 24.04 6.8.0-50-generic (x86_64) GNOME Shell 46.0 X Server 1.21.1.11 NVIDIA 535.183.01 4.5 Mesa 24.0.9-0ubuntu0.3 (LLVM 17.0.6 256 bits) OpenCL 3.0 CUDA 12.2.148 GCC 13.3.0 ext4 1024x768 OpenBenchmarking.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-server litert: DeepLab V3 litert: SqueezeNet litert: Inception V4 litert: NASNet Mobile litert: Mobilenet Float litert: Mobilenet Quant litert: Inception ResNet V2 litert: Quantized COCO SSD MobileNet v1 openvino-genai: Gemma-7b-int4-ov - CPU openvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU openvino-genai: Falcon-7b-instruct-int4-ov - CPU openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU whisperfile: Tiny whisperfile: Small whisperfile: Medium tensorflow: CPU - 1 - VGG-16 tensorflow: GPU - 1 - VGG-16 tensorflow: CPU - 1 - AlexNet tensorflow: CPU - 16 - VGG-16 tensorflow: CPU - 32 - VGG-16 tensorflow: CPU - 64 - VGG-16 tensorflow: GPU - 1 - AlexNet tensorflow: GPU - 16 - VGG-16 tensorflow: GPU - 32 - VGG-16 tensorflow: GPU - 64 - VGG-16 tensorflow: CPU - 16 - AlexNet tensorflow: CPU - 256 - VGG-16 tensorflow: CPU - 32 - AlexNet tensorflow: CPU - 512 - VGG-16 tensorflow: CPU - 64 - AlexNet tensorflow: GPU - 16 - AlexNet tensorflow: GPU - 256 - VGG-16 tensorflow: GPU - 32 - AlexNet tensorflow: GPU - 512 - VGG-16 tensorflow: GPU - 64 - AlexNet tensorflow: CPU - 1 - GoogLeNet tensorflow: CPU - 1 - ResNet-50 tensorflow: CPU - 256 - AlexNet tensorflow: CPU - 512 - AlexNet tensorflow: GPU - 1 - GoogLeNet tensorflow: GPU - 1 - ResNet-50 tensorflow: GPU - 256 - AlexNet tensorflow: GPU - 512 - AlexNet tensorflow: CPU - 16 - GoogLeNet tensorflow: CPU - 16 - ResNet-50 tensorflow: CPU - 32 - GoogLeNet tensorflow: CPU - 32 - ResNet-50 tensorflow: CPU - 64 - GoogLeNet tensorflow: CPU - 64 - ResNet-50 tensorflow: GPU - 16 - GoogLeNet tensorflow: GPU - 16 - ResNet-50 tensorflow: GPU - 32 - GoogLeNet tensorflow: GPU - 32 - ResNet-50 tensorflow: GPU - 64 - GoogLeNet tensorflow: GPU - 64 - ResNet-50 tensorflow: CPU - 256 - GoogLeNet tensorflow: CPU - 256 - ResNet-50 tensorflow: CPU - 512 - GoogLeNet tensorflow: CPU - 512 - ResNet-50 tensorflow: GPU - 256 - GoogLeNet tensorflow: GPU - 256 - ResNet-50 tensorflow: GPU - 512 - GoogLeNet tensorflow: GPU - 512 - ResNet-50 lczero: BLAS scikit-learn: GLM scikit-learn: SAGA scikit-learn: Tree scikit-learn: Lasso scikit-learn: Sparsify scikit-learn: Plot Ward scikit-learn: MNIST Dataset scikit-learn: Plot Neighbors scikit-learn: SGD Regression scikit-learn: SGDOneClassSVM scikit-learn: Isolation Forest scikit-learn: Text Vectorizers scikit-learn: Plot Hierarchical scikit-learn: Plot OMP vs. LARS scikit-learn: Feature Expansions scikit-learn: LocalOutlierFactor scikit-learn: TSNE MNIST Dataset scikit-learn: Isotonic / Logistic scikit-learn: Plot Incremental PCA scikit-learn: Hist Gradient Boosting scikit-learn: Plot Parallel Pairwise scikit-learn: Isotonic / Pathological scikit-learn: Sample Without Replacement scikit-learn: Covertype Dataset Benchmark scikit-learn: Hist Gradient Boosting Adult scikit-learn: Isotonic / Perturbed Logarithm scikit-learn: Hist Gradient Boosting Threading scikit-learn: Hist Gradient Boosting Higgs Boson scikit-learn: 20 Newsgroups / Logistic Regression scikit-learn: Plot Polynomial Kernel Approximation scikit-learn: Hist Gradient Boosting Categorical Only scikit-learn: Kernel PCA Solvers / Time vs. N Samples scikit-learn: Kernel PCA Solvers / Time vs. N Components scikit-learn: Sparse Rand Projections / 100 Iterations rbenchmark: numpy: deepspeech: CPU rnnoise: 26 Minute Long Talking Sample opencv: DNN - Deep Neural Network pytorch: CPU - 1 - ResNet-50 pytorch: CPU - 1 - ResNet-152 pytorch: CPU - 16 - ResNet-50 pytorch: CPU - 32 - ResNet-50 pytorch: CPU - 64 - ResNet-50 pytorch: CPU - 16 - ResNet-152 pytorch: CPU - 256 - ResNet-50 pytorch: CPU - 32 - ResNet-152 pytorch: CPU - 512 - ResNet-50 pytorch: CPU - 64 - ResNet-152 pytorch: CPU - 256 - ResNet-152 pytorch: CPU - 512 - ResNet-152 pytorch: CPU - 1 - Efficientnet_v2_l pytorch: CPU - 16 - Efficientnet_v2_l pytorch: CPU - 32 - Efficientnet_v2_l pytorch: CPU - 64 - Efficientnet_v2_l pytorch: CPU - 256 - Efficientnet_v2_l pytorch: CPU - 512 - Efficientnet_v2_l tensorflow-lite: SqueezeNet tensorflow-lite: Inception V4 tensorflow-lite: NASNet Mobile tensorflow-lite: Mobilenet Float tensorflow-lite: Mobilenet Quant tensorflow-lite: Inception ResNet V2 whisper-cpp: ggml-base.en - 2016 State of the Union whisper-cpp: ggml-small.en - 2016 State of the Union whisper-cpp: ggml-medium.en - 2016 State of the Union xnnpack: FP32MobileNetV1 xnnpack: FP32MobileNetV2 xnnpack: FP32MobileNetV3Large xnnpack: FP32MobileNetV3Small xnnpack: FP16MobileNetV1 xnnpack: FP16MobileNetV2 xnnpack: FP16MobileNetV3Large xnnpack: FP16MobileNetV3Small xnnpack: QS8MobileNetV2 shoc: OpenCL - S3D shoc: OpenCL - Triad shoc: OpenCL - FFT SP shoc: OpenCL - MD5 Hash shoc: OpenCL - Reduction shoc: OpenCL - GEMM SGEMM_N shoc: OpenCL - Max SP Flops shoc: OpenCL - Bus Speed Download shoc: OpenCL - Bus Speed Readback shoc: OpenCL - Texture Read Bandwidth ncnn: CPU - mobilenet ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU - shufflenet-v2 ncnn: CPU - mnasnet ncnn: CPU - efficientnet-b0 ncnn: CPU - blazeface ncnn: CPU - googlenet ncnn: CPU - vgg16 ncnn: CPU - resnet18 ncnn: CPU - alexnet ncnn: CPU - resnet50 ncnn: CPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3 ncnn: CPU - yolov4-tiny ncnn: CPU - squeezenet_ssd ncnn: CPU - regnety_400m ncnn: CPU - vision_transformer ncnn: CPU - FastestDet ncnn: Vulkan GPU - mobilenet ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3 ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - regnety_400m ncnn: Vulkan GPU - vision_transformer ncnn: Vulkan GPU - FastestDet onednn: IP Shapes 1D - CPU onednn: IP Shapes 3D - CPU onednn: Convolution Batch Shapes Auto - CPU onednn: Deconvolution Batch shapes_1d - CPU onednn: Deconvolution Batch shapes_3d - CPU onednn: Recurrent Neural Network Training - CPU onednn: Recurrent Neural Network Inference - CPU openvino: Face Detection FP16 - CPU openvino: Face Detection FP16 - CPU openvino: Person Detection FP16 - CPU openvino: Person Detection FP16 - CPU openvino: Person Detection FP32 - CPU openvino: Person Detection FP32 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection Retail FP16 - CPU openvino: Face Detection Retail FP16 - CPU openvino: Road Segmentation ADAS FP16 - CPU openvino: Road Segmentation ADAS FP16 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU openvino: Person Re-Identification Retail FP16 - CPU openvino: Person Re-Identification Retail FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino-genai: Gemma-7b-int4-ov - CPU - Time To First Token openvino-genai: Gemma-7b-int4-ov - CPU - Time Per Output Token openvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time To First Token openvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time Per Output Token openvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time To First Token openvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time Per Output Token openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time To First Token openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time Per Output Token hurricane-server 3250.31 2102.34 16671.7 31332.4 1332.51 1404.29 19022.7 2299.81 30.11 65.76 39.37 47.17 48.31755 137.64843 312.21719 15.04 1.61 58.02 29.28 31.76 32.65 15.94 1.76 1.77 1.78 376.93 33.52 465.66 33.71 532.95 30.06 1.79 32.12 1.79 33.24 53.62 17.32 651.72 679.63 14.65 4.72 33.97 34.13 214.21 74.57 241.16 84.65 262.31 90.02 20.15 6.60 20.37 6.73 20.83 6.78 283.28 98.53 288.79 101.60 21.06 6.84 21.10 6.83 281 200.421 1027.768 68.790 536.893 156.750 57.026 78.400 174.500 87.926 330.205 236.890 65.346 197.948 46.717 126.776 25.661 268.062 1974.797 36.502 247.454 123.031 4978.992 135.813 434.505 245.146 2180.917 68.022 77.707 12.941 129.017 44.821 68.494 40.062 659.729 0.1707 513.75 53.37464 11.355 33303 67.94 24.69 51.39 52.12 52.10 19.55 52.12 19.51 52.09 19.69 19.48 19.50 12.47 8.21 8.10 8.21 8.20 8.16 2015.74 16113.8 24134.5 1306.87 2531.33 31730.6 116.86325 243.05902 605.21554 1306 2162 3136 2164 1348 1985 3012 2136 2001 268.847 12.8950 1479.17 14.4889 257.887 5521.35 9437.51 13.2138 13.5433 588.113 15.81 7.41 7.93 9.51 6.91 9.73 3.80 17.39 25.23 9.01 5.51 14.46 15.81 26.58 16.85 24.06 67.87 11.18 15.98 7.43 7.95 9.49 6.89 9.71 3.81 17.41 25.17 8.99 5.52 14.46 15.98 27.01 16.92 24.08 67.71 11.57 0.850385 0.680494 1.14790 5.68471 1.81557 811.253 450.858 20.16 790.62 192.30 83.08 193.19 82.70 1536.16 10.37 38.67 412.40 4791.90 3.29 786.83 20.28 2367.68 6.72 1984.68 16.08 6872.55 4.59 834.81 19.12 233.04 68.60 3835.55 8.29 2176.46 7.31 2638.33 11.90 1092.39 29.25 2734.75 5.82 47505.84 0.58 1160.60 27.52 64559.58 0.41 72.72 33.21 18.24 15.21 59.06 25.40 41.41 21.20 OpenBenchmarking.org
LiteRT Model: DeepLab V3 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: DeepLab V3 hurricane-server 700 1400 2100 2800 3500 SE +/- 8.28, N = 3 3250.31
LiteRT Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: SqueezeNet hurricane-server 500 1000 1500 2000 2500 SE +/- 8.16, N = 3 2102.34
LiteRT Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Inception V4 hurricane-server 4K 8K 12K 16K 20K SE +/- 15.14, N = 3 16671.7
LiteRT Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: NASNet Mobile hurricane-server 7K 14K 21K 28K 35K SE +/- 132.52, N = 3 31332.4
LiteRT Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Mobilenet Float hurricane-server 300 600 900 1200 1500 SE +/- 1.07, N = 3 1332.51
LiteRT Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Mobilenet Quant hurricane-server 300 600 900 1200 1500 SE +/- 16.18, N = 15 1404.29
LiteRT Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Inception ResNet V2 hurricane-server 4K 8K 12K 16K 20K SE +/- 63.82, N = 3 19022.7
LiteRT Model: Quantized COCO SSD MobileNet v1 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Quantized COCO SSD MobileNet v1 hurricane-server 500 1000 1500 2000 2500 SE +/- 11.18, N = 3 2299.81
OpenVINO GenAI Model: Gemma-7b-int4-ov - Device: CPU OpenBenchmarking.org tokens/s, More Is Better OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU hurricane-server 7 14 21 28 35 SE +/- 0.24, N = 3 30.11
OpenVINO GenAI Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU OpenBenchmarking.org tokens/s, More Is Better OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU hurricane-server 15 30 45 60 75 SE +/- 0.16, N = 3 65.76
OpenVINO GenAI Model: Falcon-7b-instruct-int4-ov - Device: CPU OpenBenchmarking.org tokens/s, More Is Better OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU hurricane-server 9 18 27 36 45 SE +/- 0.16, N = 3 39.37
OpenVINO GenAI Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU OpenBenchmarking.org tokens/s, More Is Better OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU hurricane-server 11 22 33 44 55 SE +/- 0.29, N = 3 47.17
Whisperfile Model Size: Tiny OpenBenchmarking.org Seconds, Fewer Is Better Whisperfile 20Aug24 Model Size: Tiny hurricane-server 11 22 33 44 55 SE +/- 0.20, N = 3 48.32
Whisperfile Model Size: Small OpenBenchmarking.org Seconds, Fewer Is Better Whisperfile 20Aug24 Model Size: Small hurricane-server 30 60 90 120 150 SE +/- 0.47, N = 3 137.65
Whisperfile Model Size: Medium OpenBenchmarking.org Seconds, Fewer Is Better Whisperfile 20Aug24 Model Size: Medium hurricane-server 70 140 210 280 350 SE +/- 1.81, N = 3 312.22
TensorFlow Device: CPU - Batch Size: 1 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: VGG-16 hurricane-server 4 8 12 16 20 SE +/- 0.01, N = 3 15.04
TensorFlow Device: GPU - Batch Size: 1 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 1 - Model: VGG-16 hurricane-server 0.3623 0.7246 1.0869 1.4492 1.8115 SE +/- 0.00, N = 3 1.61
TensorFlow Device: CPU - Batch Size: 1 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: AlexNet hurricane-server 13 26 39 52 65 SE +/- 0.18, N = 3 58.02
TensorFlow Device: CPU - Batch Size: 16 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 16 - Model: VGG-16 hurricane-server 7 14 21 28 35 SE +/- 0.29, N = 3 29.28
TensorFlow Device: CPU - Batch Size: 32 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 32 - Model: VGG-16 hurricane-server 7 14 21 28 35 SE +/- 0.04, N = 3 31.76
TensorFlow Device: CPU - Batch Size: 64 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: VGG-16 hurricane-server 8 16 24 32 40 SE +/- 0.01, N = 3 32.65
TensorFlow Device: GPU - Batch Size: 1 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 1 - Model: AlexNet hurricane-server 4 8 12 16 20 SE +/- 0.14, N = 3 15.94
TensorFlow Device: GPU - Batch Size: 16 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 16 - Model: VGG-16 hurricane-server 0.396 0.792 1.188 1.584 1.98 SE +/- 0.00, N = 3 1.76
TensorFlow Device: GPU - Batch Size: 32 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 32 - Model: VGG-16 hurricane-server 0.3983 0.7966 1.1949 1.5932 1.9915 SE +/- 0.00, N = 3 1.77
TensorFlow Device: GPU - Batch Size: 64 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 64 - Model: VGG-16 hurricane-server 0.4005 0.801 1.2015 1.602 2.0025 SE +/- 0.00, N = 3 1.78
TensorFlow Device: CPU - Batch Size: 16 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 16 - Model: AlexNet hurricane-server 80 160 240 320 400 SE +/- 0.72, N = 3 376.93
TensorFlow Device: CPU - Batch Size: 256 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: VGG-16 hurricane-server 8 16 24 32 40 SE +/- 0.01, N = 3 33.52
TensorFlow Device: CPU - Batch Size: 32 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 32 - Model: AlexNet hurricane-server 100 200 300 400 500 SE +/- 0.31, N = 3 465.66
TensorFlow Device: CPU - Batch Size: 512 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: VGG-16 hurricane-server 8 16 24 32 40 SE +/- 0.01, N = 3 33.71
TensorFlow Device: CPU - Batch Size: 64 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: AlexNet hurricane-server 120 240 360 480 600 SE +/- 1.95, N = 3 532.95
TensorFlow Device: GPU - Batch Size: 16 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 16 - Model: AlexNet hurricane-server 7 14 21 28 35 SE +/- 0.01, N = 3 30.06
TensorFlow Device: GPU - Batch Size: 256 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 256 - Model: VGG-16 hurricane-server 0.4028 0.8056 1.2084 1.6112 2.014 SE +/- 0.00, N = 3 1.79
TensorFlow Device: GPU - Batch Size: 32 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 32 - Model: AlexNet hurricane-server 7 14 21 28 35 SE +/- 0.00, N = 3 32.12
TensorFlow Device: GPU - Batch Size: 512 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 512 - Model: VGG-16 hurricane-server 0.4028 0.8056 1.2084 1.6112 2.014 SE +/- 0.00, N = 3 1.79
TensorFlow Device: GPU - Batch Size: 64 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 64 - Model: AlexNet hurricane-server 8 16 24 32 40 SE +/- 0.01, N = 3 33.24
TensorFlow Device: CPU - Batch Size: 1 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: GoogLeNet hurricane-server 12 24 36 48 60 SE +/- 0.66, N = 3 53.62
TensorFlow Device: CPU - Batch Size: 1 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 hurricane-server 4 8 12 16 20 SE +/- 0.05, N = 3 17.32
TensorFlow Device: CPU - Batch Size: 256 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: AlexNet hurricane-server 140 280 420 560 700 SE +/- 0.16, N = 3 651.72
TensorFlow Device: CPU - Batch Size: 512 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: AlexNet hurricane-server 150 300 450 600 750 SE +/- 0.16, N = 3 679.63
TensorFlow Device: GPU - Batch Size: 1 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 1 - Model: GoogLeNet hurricane-server 4 8 12 16 20 SE +/- 0.04, N = 3 14.65
TensorFlow Device: GPU - Batch Size: 1 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 1 - Model: ResNet-50 hurricane-server 1.062 2.124 3.186 4.248 5.31 SE +/- 0.02, N = 3 4.72
TensorFlow Device: GPU - Batch Size: 256 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 256 - Model: AlexNet hurricane-server 8 16 24 32 40 SE +/- 0.00, N = 3 33.97
TensorFlow Device: GPU - Batch Size: 512 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 512 - Model: AlexNet hurricane-server 8 16 24 32 40 SE +/- 0.00, N = 3 34.13
TensorFlow Device: CPU - Batch Size: 16 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 16 - Model: GoogLeNet hurricane-server 50 100 150 200 250 SE +/- 0.53, N = 3 214.21
TensorFlow Device: CPU - Batch Size: 16 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 16 - Model: ResNet-50 hurricane-server 20 40 60 80 100 SE +/- 0.12, N = 3 74.57
TensorFlow Device: CPU - Batch Size: 32 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 32 - Model: GoogLeNet hurricane-server 50 100 150 200 250 SE +/- 1.98, N = 3 241.16
TensorFlow Device: CPU - Batch Size: 32 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 32 - Model: ResNet-50 hurricane-server 20 40 60 80 100 SE +/- 0.02, N = 3 84.65
TensorFlow Device: CPU - Batch Size: 64 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: GoogLeNet hurricane-server 60 120 180 240 300 SE +/- 0.20, N = 3 262.31
TensorFlow Device: CPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: ResNet-50 hurricane-server 20 40 60 80 100 SE +/- 0.12, N = 3 90.02
TensorFlow Device: GPU - Batch Size: 16 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 16 - Model: GoogLeNet hurricane-server 5 10 15 20 25 SE +/- 0.02, N = 3 20.15
TensorFlow Device: GPU - Batch Size: 16 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 16 - Model: ResNet-50 hurricane-server 2 4 6 8 10 SE +/- 0.01, N = 3 6.60
TensorFlow Device: GPU - Batch Size: 32 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 32 - Model: GoogLeNet hurricane-server 5 10 15 20 25 SE +/- 0.20, N = 3 20.37
TensorFlow Device: GPU - Batch Size: 32 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 32 - Model: ResNet-50 hurricane-server 2 4 6 8 10 SE +/- 0.00, N = 3 6.73
TensorFlow Device: GPU - Batch Size: 64 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 64 - Model: GoogLeNet hurricane-server 5 10 15 20 25 SE +/- 0.00, N = 3 20.83
TensorFlow Device: GPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 64 - Model: ResNet-50 hurricane-server 2 4 6 8 10 SE +/- 0.01, N = 3 6.78
TensorFlow Device: CPU - Batch Size: 256 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: GoogLeNet hurricane-server 60 120 180 240 300 SE +/- 0.12, N = 3 283.28
TensorFlow Device: CPU - Batch Size: 256 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 hurricane-server 20 40 60 80 100 SE +/- 0.05, N = 3 98.53
TensorFlow Device: CPU - Batch Size: 512 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: GoogLeNet hurricane-server 60 120 180 240 300 SE +/- 0.32, N = 3 288.79
TensorFlow Device: CPU - Batch Size: 512 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 hurricane-server 20 40 60 80 100 SE +/- 0.05, N = 3 101.60
TensorFlow Device: GPU - Batch Size: 256 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 256 - Model: GoogLeNet hurricane-server 5 10 15 20 25 SE +/- 0.02, N = 3 21.06
TensorFlow Device: GPU - Batch Size: 256 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 256 - Model: ResNet-50 hurricane-server 2 4 6 8 10 SE +/- 0.00, N = 3 6.84
TensorFlow Device: GPU - Batch Size: 512 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 512 - Model: GoogLeNet hurricane-server 5 10 15 20 25 SE +/- 0.01, N = 3 21.10
TensorFlow Device: GPU - Batch Size: 512 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: GPU - Batch Size: 512 - Model: ResNet-50 hurricane-server 2 4 6 8 10 SE +/- 0.00, N = 3 6.83
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.31.1 Backend: BLAS hurricane-server 60 120 180 240 300 SE +/- 2.91, N = 3 281 1. (CXX) g++ options: -flto -pthread
Scikit-Learn Benchmark: GLM OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: GLM hurricane-server 40 80 120 160 200 SE +/- 0.25, N = 3 200.42 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: SAGA OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: SAGA hurricane-server 200 400 600 800 1000 SE +/- 0.84, N = 3 1027.77 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Tree OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Tree hurricane-server 15 30 45 60 75 SE +/- 0.69, N = 15 68.79 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Lasso OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Lasso hurricane-server 120 240 360 480 600 SE +/- 2.40, N = 3 536.89 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Sparsify OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Sparsify hurricane-server 30 60 90 120 150 SE +/- 0.28, N = 3 156.75 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Plot Ward OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Plot Ward hurricane-server 13 26 39 52 65 SE +/- 0.10, N = 3 57.03 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: MNIST Dataset OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: MNIST Dataset hurricane-server 20 40 60 80 100 SE +/- 0.03, N = 3 78.40 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Plot Neighbors OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Plot Neighbors hurricane-server 40 80 120 160 200 SE +/- 0.73, N = 3 174.50 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: SGD Regression OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: SGD Regression hurricane-server 20 40 60 80 100 SE +/- 0.12, N = 3 87.93 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: SGDOneClassSVM OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: SGDOneClassSVM hurricane-server 70 140 210 280 350 SE +/- 0.43, N = 3 330.21 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Isolation Forest OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Isolation Forest hurricane-server 50 100 150 200 250 SE +/- 0.22, N = 3 236.89 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Text Vectorizers OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Text Vectorizers hurricane-server 15 30 45 60 75 SE +/- 0.08, N = 3 65.35 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Plot Hierarchical OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Plot Hierarchical hurricane-server 40 80 120 160 200 SE +/- 0.23, N = 3 197.95 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Plot OMP vs. LARS OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Plot OMP vs. LARS hurricane-server 11 22 33 44 55 SE +/- 0.08, N = 3 46.72 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Feature Expansions OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Feature Expansions hurricane-server 30 60 90 120 150 SE +/- 0.31, N = 3 126.78 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: LocalOutlierFactor OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: LocalOutlierFactor hurricane-server 6 12 18 24 30 SE +/- 0.02, N = 3 25.66 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: TSNE MNIST Dataset OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: TSNE MNIST Dataset hurricane-server 60 120 180 240 300 SE +/- 0.45, N = 3 268.06 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Isotonic / Logistic OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Isotonic / Logistic hurricane-server 400 800 1200 1600 2000 SE +/- 0.59, N = 3 1974.80 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Plot Incremental PCA OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Plot Incremental PCA hurricane-server 8 16 24 32 40 SE +/- 0.08, N = 3 36.50 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Hist Gradient Boosting OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting hurricane-server 50 100 150 200 250 SE +/- 0.79, N = 3 247.45 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Plot Parallel Pairwise OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Plot Parallel Pairwise hurricane-server 30 60 90 120 150 SE +/- 0.39, N = 3 123.03 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Isotonic / Pathological OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Isotonic / Pathological hurricane-server 1100 2200 3300 4400 5500 SE +/- 1.30, N = 3 4978.99 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Sample Without Replacement OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Sample Without Replacement hurricane-server 30 60 90 120 150 SE +/- 0.09, N = 3 135.81 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Covertype Dataset Benchmark OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Covertype Dataset Benchmark hurricane-server 90 180 270 360 450 SE +/- 0.10, N = 3 434.51 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Hist Gradient Boosting Adult OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Adult hurricane-server 50 100 150 200 250 SE +/- 0.15, N = 3 245.15 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Isotonic / Perturbed Logarithm OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Isotonic / Perturbed Logarithm hurricane-server 500 1000 1500 2000 2500 SE +/- 1.48, N = 3 2180.92 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Hist Gradient Boosting Threading OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Threading hurricane-server 15 30 45 60 75 SE +/- 0.19, N = 3 68.02 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Hist Gradient Boosting Higgs Boson OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Higgs Boson hurricane-server 20 40 60 80 100 SE +/- 0.88, N = 3 77.71 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: 20 Newsgroups / Logistic Regression OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: 20 Newsgroups / Logistic Regression hurricane-server 3 6 9 12 15 SE +/- 0.08, N = 3 12.94 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Plot Polynomial Kernel Approximation OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Plot Polynomial Kernel Approximation hurricane-server 30 60 90 120 150 SE +/- 0.10, N = 3 129.02 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Hist Gradient Boosting Categorical Only OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Categorical Only hurricane-server 10 20 30 40 50 SE +/- 0.31, N = 3 44.82 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Kernel PCA Solvers / Time vs. N Samples OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Kernel PCA Solvers / Time vs. N Samples hurricane-server 15 30 45 60 75 SE +/- 0.18, N = 3 68.49 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Kernel PCA Solvers / Time vs. N Components OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Kernel PCA Solvers / Time vs. N Components hurricane-server 9 18 27 36 45 SE +/- 0.57, N = 3 40.06 1. (F9X) gfortran options: -O0
Scikit-Learn Benchmark: Sparse Random Projections / 100 Iterations OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Sparse Random Projections / 100 Iterations hurricane-server 140 280 420 560 700 SE +/- 1.78, N = 3 659.73 1. (F9X) gfortran options: -O0
R Benchmark OpenBenchmarking.org Seconds, Fewer Is Better R Benchmark hurricane-server 0.0384 0.0768 0.1152 0.1536 0.192 SE +/- 0.0004, N = 3 0.1707
Numpy Benchmark OpenBenchmarking.org Score, More Is Better Numpy Benchmark hurricane-server 110 220 330 440 550 SE +/- 1.66, N = 3 513.75
DeepSpeech Acceleration: CPU OpenBenchmarking.org Seconds, Fewer Is Better DeepSpeech 0.6 Acceleration: CPU hurricane-server 12 24 36 48 60 SE +/- 0.09, N = 3 53.37
RNNoise Input: 26 Minute Long Talking Sample OpenBenchmarking.org Seconds, Fewer Is Better RNNoise 0.2 Input: 26 Minute Long Talking Sample hurricane-server 3 6 9 12 15 SE +/- 0.05, N = 3 11.36 1. (CC) gcc options: -O2 -pedantic -fvisibility=hidden
OpenCV Test: DNN - Deep Neural Network OpenBenchmarking.org ms, Fewer Is Better OpenCV 4.7 Test: DNN - Deep Neural Network hurricane-server 7K 14K 21K 28K 35K SE +/- 601.47, N = 15 33303 1. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt
PyTorch Device: CPU - Batch Size: 1 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 hurricane-server 15 30 45 60 75 SE +/- 0.51, N = 3 67.94 MIN: 50.17 / MAX: 69.35
PyTorch Device: CPU - Batch Size: 1 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 1 - Model: ResNet-152 hurricane-server 6 12 18 24 30 SE +/- 0.17, N = 3 24.69 MIN: 19.29 / MAX: 25.17
PyTorch Device: CPU - Batch Size: 16 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 16 - Model: ResNet-50 hurricane-server 12 24 36 48 60 SE +/- 0.34, N = 3 51.39 MIN: 38.88 / MAX: 52.76
PyTorch Device: CPU - Batch Size: 32 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 32 - Model: ResNet-50 hurricane-server 12 24 36 48 60 SE +/- 0.13, N = 3 52.12 MIN: 38.35 / MAX: 52.97
PyTorch Device: CPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 64 - Model: ResNet-50 hurricane-server 12 24 36 48 60 SE +/- 0.19, N = 3 52.10 MIN: 45.33 / MAX: 52.97
PyTorch Device: CPU - Batch Size: 16 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 16 - Model: ResNet-152 hurricane-server 5 10 15 20 25 SE +/- 0.21, N = 3 19.55 MIN: 14.89 / MAX: 19.9
PyTorch Device: CPU - Batch Size: 256 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 hurricane-server 12 24 36 48 60 SE +/- 0.18, N = 3 52.12 MIN: 39.21 / MAX: 53.52
PyTorch Device: CPU - Batch Size: 32 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 32 - Model: ResNet-152 hurricane-server 5 10 15 20 25 SE +/- 0.09, N = 3 19.51 MIN: 16.27 / MAX: 19.75
PyTorch Device: CPU - Batch Size: 512 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 hurricane-server 12 24 36 48 60 SE +/- 0.23, N = 3 52.09 MIN: 45 / MAX: 53.04
PyTorch Device: CPU - Batch Size: 64 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 64 - Model: ResNet-152 hurricane-server 5 10 15 20 25 SE +/- 0.01, N = 3 19.69 MIN: 18.64 / MAX: 19.84
PyTorch Device: CPU - Batch Size: 256 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 256 - Model: ResNet-152 hurricane-server 5 10 15 20 25 SE +/- 0.16, N = 3 19.48 MIN: 15.08 / MAX: 19.95
PyTorch Device: CPU - Batch Size: 512 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 512 - Model: ResNet-152 hurricane-server 5 10 15 20 25 SE +/- 0.11, N = 3 19.50 MIN: 6 / MAX: 19.85
PyTorch Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l hurricane-server 3 6 9 12 15 SE +/- 0.09, N = 3 12.47 MIN: 10.7 / MAX: 12.87
PyTorch Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l hurricane-server 2 4 6 8 10 SE +/- 0.04, N = 3 8.21 MIN: 7 / MAX: 8.84
PyTorch Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l hurricane-server 2 4 6 8 10 SE +/- 0.09, N = 4 8.10 MIN: 2.17 / MAX: 8.79
PyTorch Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_l hurricane-server 2 4 6 8 10 SE +/- 0.03, N = 3 8.21 MIN: 5.85 / MAX: 8.81
PyTorch Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_l hurricane-server 2 4 6 8 10 SE +/- 0.01, N = 3 8.20 MIN: 7.01 / MAX: 8.8
PyTorch Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_l hurricane-server 2 4 6 8 10 SE +/- 0.01, N = 3 8.16 MIN: 3.8 / MAX: 8.81
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: SqueezeNet hurricane-server 400 800 1200 1600 2000 SE +/- 6.84, N = 3 2015.74
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception V4 hurricane-server 3K 6K 9K 12K 15K SE +/- 14.50, N = 3 16113.8
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: NASNet Mobile hurricane-server 5K 10K 15K 20K 25K SE +/- 13.44, N = 3 24134.5
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Float hurricane-server 300 600 900 1200 1500 SE +/- 4.16, N = 3 1306.87
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Quant hurricane-server 500 1000 1500 2000 2500 SE +/- 26.36, N = 4 2531.33
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception ResNet V2 hurricane-server 7K 14K 21K 28K 35K SE +/- 101.48, N = 3 31730.6
Whisper.cpp Model: ggml-base.en - Input: 2016 State of the Union OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.6.2 Model: ggml-base.en - Input: 2016 State of the Union hurricane-server 30 60 90 120 150 SE +/- 0.28, N = 3 116.86 1. (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.org Seconds, Fewer Is Better Whisper.cpp 1.6.2 Model: ggml-small.en - Input: 2016 State of the Union hurricane-server 50 100 150 200 250 SE +/- 0.71, N = 3 243.06 1. (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.org Seconds, Fewer Is Better Whisper.cpp 1.6.2 Model: ggml-medium.en - Input: 2016 State of the Union hurricane-server 130 260 390 520 650 SE +/- 5.80, N = 3 605.22 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni
XNNPACK Model: FP32MobileNetV1 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV1 hurricane-server 300 600 900 1200 1500 SE +/- 2.33, N = 3 1306 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP32MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV2 hurricane-server 500 1000 1500 2000 2500 SE +/- 7.51, N = 3 2162 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP32MobileNetV3Large OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV3Large hurricane-server 700 1400 2100 2800 3500 SE +/- 11.68, N = 3 3136 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP32MobileNetV3Small OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV3Small hurricane-server 500 1000 1500 2000 2500 SE +/- 5.46, N = 3 2164 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP16MobileNetV1 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV1 hurricane-server 300 600 900 1200 1500 SE +/- 3.06, N = 3 1348 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP16MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV2 hurricane-server 400 800 1200 1600 2000 SE +/- 2.91, N = 3 1985 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP16MobileNetV3Large OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV3Large hurricane-server 600 1200 1800 2400 3000 SE +/- 9.07, N = 3 3012 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP16MobileNetV3Small OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV3Small hurricane-server 500 1000 1500 2000 2500 SE +/- 4.84, N = 3 2136 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: QS8MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: QS8MobileNetV2 hurricane-server 400 800 1200 1600 2000 SE +/- 5.33, N = 3 2001 1. (CXX) g++ options: -O3 -lrt -lm
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: S3D OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: S3D hurricane-server 60 120 180 240 300 SE +/- 0.10, N = 3 268.85 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Triad OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Triad hurricane-server 3 6 9 12 15 SE +/- 0.00, N = 3 12.90 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: FFT SP OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: FFT SP hurricane-server 300 600 900 1200 1500 SE +/- 10.08, N = 12 1479.17 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: MD5 Hash OpenBenchmarking.org GHash/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: MD5 Hash hurricane-server 4 8 12 16 20 SE +/- 0.00, N = 3 14.49 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Reduction OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Reduction hurricane-server 60 120 180 240 300 SE +/- 0.04, N = 3 257.89 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: GEMM SGEMM_N OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: GEMM SGEMM_N hurricane-server 1200 2400 3600 4800 6000 SE +/- 0.39, N = 3 5521.35 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Max SP Flops OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Max SP Flops hurricane-server 2K 4K 6K 8K 10K SE +/- 0.57, N = 3 9437.51 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Bus Speed Download OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Download hurricane-server 3 6 9 12 15 SE +/- 0.00, N = 3 13.21 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Bus Speed Readback OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Readback hurricane-server 3 6 9 12 15 SE +/- 0.00, N = 3 13.54 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Texture Read Bandwidth OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Texture Read Bandwidth hurricane-server 130 260 390 520 650 SE +/- 0.03, N = 3 588.11 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mobilenet hurricane-server 4 8 12 16 20 SE +/- 0.13, N = 3 15.81 MIN: 15.42 / MAX: 19.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 hurricane-server 2 4 6 8 10 SE +/- 0.02, N = 3 7.41 MIN: 7.07 / MAX: 11.25 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 hurricane-server 2 4 6 8 10 SE +/- 0.02, N = 3 7.93 MIN: 7.73 / MAX: 12.06 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: shufflenet-v2 hurricane-server 3 6 9 12 15 SE +/- 0.04, N = 3 9.51 MIN: 9.3 / MAX: 13.61 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mnasnet hurricane-server 2 4 6 8 10 SE +/- 0.01, N = 3 6.91 MIN: 6.66 / MAX: 10.95 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: efficientnet-b0 hurricane-server 3 6 9 12 15 SE +/- 0.02, N = 3 9.73 MIN: 9.35 / MAX: 16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: blazeface hurricane-server 0.855 1.71 2.565 3.42 4.275 SE +/- 0.02, N = 3 3.80 MIN: 3.71 / MAX: 6.05 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: googlenet hurricane-server 4 8 12 16 20 SE +/- 0.03, N = 3 17.39 MIN: 17.15 / MAX: 21.41 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vgg16 hurricane-server 6 12 18 24 30 SE +/- 0.22, N = 3 25.23 MIN: 24.68 / MAX: 29.42 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet18 hurricane-server 3 6 9 12 15 SE +/- 0.04, N = 3 9.01 MIN: 8.81 / MAX: 20.83 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: alexnet hurricane-server 1.2398 2.4796 3.7194 4.9592 6.199 SE +/- 0.01, N = 3 5.51 MIN: 5.39 / MAX: 7.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet50 hurricane-server 4 8 12 16 20 SE +/- 0.10, N = 3 14.46 MIN: 14.12 / MAX: 27.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 hurricane-server 4 8 12 16 20 SE +/- 0.13, N = 3 15.81 MIN: 15.42 / MAX: 19.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: yolov4-tiny hurricane-server 6 12 18 24 30 SE +/- 0.41, N = 3 26.58 MIN: 24.96 / MAX: 30.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: squeezenet_ssd hurricane-server 4 8 12 16 20 SE +/- 0.01, N = 3 16.85 MIN: 16.68 / MAX: 22.41 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: regnety_400m hurricane-server 6 12 18 24 30 SE +/- 0.06, N = 3 24.06 MIN: 23.72 / MAX: 36.76 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vision_transformer hurricane-server 15 30 45 60 75 SE +/- 2.57, N = 3 67.87 MIN: 44.97 / MAX: 758 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: FastestDet hurricane-server 3 6 9 12 15 SE +/- 0.44, N = 3 11.18 MIN: 10.06 / MAX: 21.07 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mobilenet hurricane-server 4 8 12 16 20 SE +/- 0.02, N = 3 15.98 MIN: 15.78 / MAX: 20.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 hurricane-server 2 4 6 8 10 SE +/- 0.03, N = 3 7.43 MIN: 7.08 / MAX: 11.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 hurricane-server 2 4 6 8 10 SE +/- 0.02, N = 3 7.95 MIN: 7.73 / MAX: 15.08 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 hurricane-server 3 6 9 12 15 SE +/- 0.01, N = 3 9.49 MIN: 9.27 / MAX: 14.87 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mnasnet hurricane-server 2 4 6 8 10 SE +/- 0.01, N = 3 6.89 MIN: 6.67 / MAX: 7.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 hurricane-server 3 6 9 12 15 SE +/- 0.02, N = 3 9.71 MIN: 9.4 / MAX: 13.08 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: blazeface hurricane-server 0.8573 1.7146 2.5719 3.4292 4.2865 SE +/- 0.00, N = 3 3.81 MIN: 3.74 / MAX: 7.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: googlenet hurricane-server 4 8 12 16 20 SE +/- 0.04, N = 3 17.41 MIN: 17.2 / MAX: 22.8 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vgg16 hurricane-server 6 12 18 24 30 SE +/- 0.25, N = 3 25.17 MIN: 23.53 / MAX: 34.68 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet18 hurricane-server 3 6 9 12 15 SE +/- 0.04, N = 3 8.99 MIN: 8.82 / MAX: 13.05 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: alexnet hurricane-server 1.242 2.484 3.726 4.968 6.21 SE +/- 0.00, N = 3 5.52 MIN: 5.39 / MAX: 9.56 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet50 hurricane-server 4 8 12 16 20 SE +/- 0.11, N = 3 14.46 MIN: 14.13 / MAX: 18.67 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 hurricane-server 4 8 12 16 20 SE +/- 0.02, N = 3 15.98 MIN: 15.78 / MAX: 20.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny hurricane-server 6 12 18 24 30 SE +/- 0.05, N = 3 27.01 MIN: 25.85 / MAX: 31.62 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd hurricane-server 4 8 12 16 20 SE +/- 0.02, N = 3 16.92 MIN: 16.68 / MAX: 29.48 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m hurricane-server 6 12 18 24 30 SE +/- 0.02, N = 3 24.08 MIN: 23.85 / MAX: 28.53 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer hurricane-server 15 30 45 60 75 SE +/- 1.75, N = 3 67.71 MIN: 45.61 / MAX: 933.74 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: FastestDet hurricane-server 3 6 9 12 15 SE +/- 0.42, N = 3 11.57 MIN: 10.54 / MAX: 16.03 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: IP Shapes 1D - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: IP Shapes 1D - Engine: CPU hurricane-server 0.1913 0.3826 0.5739 0.7652 0.9565 SE +/- 0.001043, N = 3 0.850385 MIN: 0.82 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
oneDNN Harness: IP Shapes 3D - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: IP Shapes 3D - Engine: CPU hurricane-server 0.1531 0.3062 0.4593 0.6124 0.7655 SE +/- 0.000710, N = 3 0.680494 MIN: 0.65 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Convolution Batch Shapes Auto - Engine: CPU hurricane-server 0.2583 0.5166 0.7749 1.0332 1.2915 SE +/- 0.00120, N = 3 1.14790 MIN: 1.11 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Deconvolution Batch shapes_1d - Engine: CPU hurricane-server 1.2791 2.5582 3.8373 5.1164 6.3955 SE +/- 0.00716, N = 3 5.68471 MIN: 3.77 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Deconvolution Batch shapes_3d - Engine: CPU hurricane-server 0.4085 0.817 1.2255 1.634 2.0425 SE +/- 0.00663, N = 3 1.81557 MIN: 1.79 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
oneDNN Harness: Recurrent Neural Network Training - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Recurrent Neural Network Training - Engine: CPU hurricane-server 200 400 600 800 1000 SE +/- 0.33, N = 3 811.25 MIN: 807.44 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
oneDNN Harness: Recurrent Neural Network Inference - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Recurrent Neural Network Inference - Engine: CPU hurricane-server 100 200 300 400 500 SE +/- 0.21, N = 3 450.86 MIN: 447.46 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU hurricane-server 5 10 15 20 25 SE +/- 0.01, N = 3 20.16 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU hurricane-server 200 400 600 800 1000 SE +/- 0.52, N = 3 790.62 MIN: 405.74 / MAX: 865.84 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU hurricane-server 40 80 120 160 200 SE +/- 0.15, N = 3 192.30 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU hurricane-server 20 40 60 80 100 SE +/- 0.07, N = 3 83.08 MIN: 40.18 / MAX: 109.43 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Person Detection FP32 - Device: CPU hurricane-server 40 80 120 160 200 SE +/- 0.60, N = 3 193.19 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Detection FP32 - Device: CPU hurricane-server 20 40 60 80 100 SE +/- 0.26, N = 3 82.70 MIN: 39.41 / MAX: 109.65 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU hurricane-server 300 600 900 1200 1500 SE +/- 0.45, N = 3 1536.16 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU hurricane-server 3 6 9 12 15 SE +/- 0.00, N = 3 10.37 MIN: 5.46 / MAX: 41.76 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU hurricane-server 9 18 27 36 45 SE +/- 0.04, N = 3 38.67 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU hurricane-server 90 180 270 360 450 SE +/- 0.40, N = 3 412.40 MIN: 344.16 / MAX: 498.39 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU hurricane-server 1000 2000 3000 4000 5000 SE +/- 12.23, N = 3 4791.90 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU hurricane-server 0.7403 1.4806 2.2209 2.9612 3.7015 SE +/- 0.01, N = 3 3.29 MIN: 1.9 / MAX: 35.77 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU hurricane-server 200 400 600 800 1000 SE +/- 0.23, N = 3 786.83 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU hurricane-server 5 10 15 20 25 SE +/- 0.01, N = 3 20.28 MIN: 14.13 / MAX: 39.24 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16-INT8 - Device: CPU hurricane-server 500 1000 1500 2000 2500 SE +/- 3.74, N = 3 2367.68 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16-INT8 - Device: CPU hurricane-server 2 4 6 8 10 SE +/- 0.01, N = 3 6.72 MIN: 4.28 / MAX: 18.93 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16 - Device: CPU hurricane-server 400 800 1200 1600 2000 SE +/- 12.59, N = 3 1984.68 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16 - Device: CPU hurricane-server 4 8 12 16 20 SE +/- 0.11, N = 3 16.08 MIN: 8.51 / MAX: 99.91 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU hurricane-server 1500 3000 4500 6000 7500 SE +/- 3.13, N = 3 6872.55 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU hurricane-server 1.0328 2.0656 3.0984 4.1312 5.164 SE +/- 0.00, N = 3 4.59 MIN: 2.72 / MAX: 18.86 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU hurricane-server 200 400 600 800 1000 SE +/- 0.46, N = 3 834.81 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU hurricane-server 5 10 15 20 25 SE +/- 0.01, N = 3 19.12 MIN: 11.33 / MAX: 35.26 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU hurricane-server 50 100 150 200 250 SE +/- 0.16, N = 3 233.04 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU hurricane-server 15 30 45 60 75 SE +/- 0.05, N = 3 68.60 MIN: 36.93 / MAX: 98.87 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16-INT8 - Device: CPU hurricane-server 800 1600 2400 3200 4000 SE +/- 28.56, N = 3 3835.55 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16-INT8 - Device: CPU hurricane-server 2 4 6 8 10 SE +/- 0.07, N = 3 8.29 MIN: 4.39 / MAX: 59.43 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU hurricane-server 500 1000 1500 2000 2500 SE +/- 2.00, N = 3 2176.46 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU hurricane-server 2 4 6 8 10 SE +/- 0.01, N = 3 7.31 MIN: 4.6 / MAX: 22.02 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU hurricane-server 600 1200 1800 2400 3000 SE +/- 3.23, N = 3 2638.33 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU hurricane-server 3 6 9 12 15 SE +/- 0.01, N = 3 11.90 MIN: 7.82 / MAX: 26.25 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU hurricane-server 200 400 600 800 1000 SE +/- 8.53, N = 3 1092.39 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU hurricane-server 7 14 21 28 35 SE +/- 0.23, N = 3 29.25 MIN: 20.04 / MAX: 50.13 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU hurricane-server 600 1200 1800 2400 3000 SE +/- 2.65, N = 3 2734.75 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU hurricane-server 1.3095 2.619 3.9285 5.238 6.5475 SE +/- 0.01, N = 3 5.82 MIN: 3.76 / MAX: 20.84 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU hurricane-server 10K 20K 30K 40K 50K SE +/- 19.37, N = 3 47505.84 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU hurricane-server 0.1305 0.261 0.3915 0.522 0.6525 SE +/- 0.00, N = 3 0.58 MIN: 0.3 / MAX: 12.74 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU hurricane-server 200 400 600 800 1000 SE +/- 2.64, N = 3 1160.60 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU hurricane-server 6 12 18 24 30 SE +/- 0.06, N = 3 27.52 MIN: 21.34 / MAX: 50.49 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU hurricane-server 14K 28K 42K 56K 70K SE +/- 85.18, N = 3 64559.58 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU hurricane-server 0.0923 0.1846 0.2769 0.3692 0.4615 SE +/- 0.00, N = 3 0.41 MIN: 0.23 / MAX: 11.69 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenVINO GenAI Model: Gemma-7b-int4-ov - Device: CPU - Time To First Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU - Time To First Token hurricane-server 16 32 48 64 80 SE +/- 0.30, N = 3 72.72
OpenVINO GenAI Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Token hurricane-server 8 16 24 32 40 SE +/- 0.27, N = 3 33.21
OpenVINO GenAI Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Token hurricane-server 4 8 12 16 20 SE +/- 0.01, N = 3 18.24
OpenVINO GenAI Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Token hurricane-server 4 8 12 16 20 SE +/- 0.04, N = 3 15.21
OpenVINO GenAI Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Token hurricane-server 13 26 39 52 65 SE +/- 0.06, N = 3 59.06
OpenVINO GenAI Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Token hurricane-server 6 12 18 24 30 SE +/- 0.11, N = 3 25.40
OpenVINO GenAI Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Token hurricane-server 9 18 27 36 45 SE +/- 0.10, N = 3 41.41
OpenVINO GenAI Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Token hurricane-server 5 10 15 20 25 SE +/- 0.13, N = 3 21.20
Phoronix Test Suite v10.8.5