Benchmarks for a future article. Intel Core i9-11900K testing with a ASUS ROG MAXIMUS XIII HERO (1402 BIOS) and ASUS Intel RKL GT1 31GB on Ubuntu 22.10 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2210210-NE-AVX512ROC09 AVX-512 Core i9 Intel Rocket Lake - Phoronix Test Suite AVX-512 Core i9 Intel Rocket Lake Benchmarks for a future article. Intel Core i9-11900K testing with a ASUS ROG MAXIMUS XIII HERO (1402 BIOS) and ASUS Intel RKL GT1 31GB on Ubuntu 22.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2210210-NE-AVX512ROC09&grs&sor .
Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution i9-11900K AVX-512 On AVX-512 Off AVX-512 On 512 Intel Core i9-11900K @ 5.10GHz (8 Cores / 16 Threads) ASUS ROG MAXIMUS XIII HERO (1402 BIOS) Intel Tiger Lake-H 32GB 2000GB Corsair Force MP600 + 32GB Flash Drive ASUS Intel RKL GT1 31GB (1300MHz) Intel Tiger Lake-H HD Audio ASUS MG28U 2 x Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 Ubuntu 22.10 5.19.0-21-generic (x86_64) GNOME Shell 43.0 X Server + Wayland 4.6 Mesa 22.2.1 1.3.224 GCC 12.2.0 ext4 3840x2160 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Environment Details - i9-11900K: AVX-512 On: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native" - i9-11900K: AVX-512 Off: CXXFLAGS="-O3 -march=native -mno-avx512f" CFLAGS="-O3 -march=native -mno-avx512f" - i9-11900K: AVX-512 On 512: CXXFLAGS="-O3 -march=native -mprefer-vector-width=512" CFLAGS="-O3 -march=native -mprefer-vector-width=512" Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/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-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 Processor Details - Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x54 - Thermald 2.5.1 Python Details - Python 3.10.7 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
cpuminer-opt: LBC, LBRY Credits cpuminer-opt: Quad SHA-256, Pyrite cpuminer-opt: Myriad-Groestl openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU cpuminer-opt: Blake-2 S cpuminer-opt: Triple SHA-256, Onecoin onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU tensorflow: CPU - 512 - GoogLeNet cpuminer-opt: Garlicoin tensorflow: CPU - 256 - GoogLeNet tensorflow: CPU - 256 - ResNet-50 tensorflow: CPU - 64 - ResNet-50 tensorflow: CPU - 32 - GoogLeNet tensorflow: CPU - 64 - GoogLeNet tensorflow: CPU - 16 - GoogLeNet mnn: resnet-v2-50 onednn: IP Shapes 1D - u8s8f32 - CPU tensorflow: CPU - 32 - ResNet-50 deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream tensorflow: CPU - 16 - ResNet-50 ai-benchmark: Device Training Score tensorflow: CPU - 512 - AlexNet ospray: gravity_spheres_volume/dim_512/scivis/real_time cpuminer-opt: Skeincoin ospray: gravity_spheres_volume/dim_512/ao/real_time openvino: Weld Porosity Detection FP16 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU ncnn: CPU - vision_transformer deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream tensorflow: CPU - 256 - VGG-16 tensorflow: CPU - 64 - VGG-16 tensorflow: CPU - 32 - VGG-16 tensorflow: CPU - 256 - AlexNet deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream simdjson: TopTweet simdjson: DistinctUserID onednn: IP Shapes 3D - u8s8f32 - CPU simdjson: PartialTweets tensorflow: CPU - 16 - VGG-16 tensorflow: CPU - 64 - AlexNet ospray: gravity_spheres_volume/dim_512/pathtracer/real_time openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU openvkl: vklBenchmark ISPC tensorflow: CPU - 32 - AlexNet ai-benchmark: Device AI Score openvino: Weld Porosity Detection FP16 - CPU onednn: IP Shapes 1D - f32 - CPU ncnn: CPU - squeezenet_ssd onednn: Deconvolution Batch shapes_3d - f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream ospray: particle_volume/ao/real_time deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream mnn: squeezenetv1.1 tensorflow: CPU - 16 - AlexNet mnn: inception-v3 mnn: SqueezeNetV1.0 ospray: particle_volume/scivis/real_time openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU deepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Stream simdjson: Kostya onednn: IP Shapes 3D - f32 - CPU deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream ncnn: CPU - yolov4-tiny onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU openvino: Person Detection FP16 - CPU onednn: Recurrent Neural Network Inference - u8s8f32 - CPU deepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream openvino: Person Detection FP16 - CPU deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream onednn: Recurrent Neural Network Inference - f32 - CPU openvino: Person Detection FP32 - CPU openvino: Person Detection FP32 - CPU openvino: Face Detection FP16 - CPU onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Face Detection FP16 - CPU ncnn: CPU-v2-v2 - mobilenet-v2 lczero: Eigen openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream ncnn: CPU - efficientnet-b0 deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream mnn: mobilenet-v1-1.0 ncnn: CPU - mnasnet ncnn: CPU - alexnet ospray-studio: 1 - 1080p - 32 - Path Tracer mnn: MobileNetV2_224 ospray-studio: 1 - 4K - 32 - Path Tracer ospray-studio: 1 - 1080p - 16 - Path Tracer numpy: onnx: super-resolution-10 - CPU - Parallel ospray-studio: 1 - 4K - 16 - Path Tracer onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU ospray-studio: 1 - 1080p - 1 - Path Tracer onednn: Convolution Batch Shapes Auto - f32 - CPU ospray-studio: 1 - 4K - 1 - Path Tracer ospray-studio: 3 - 1080p - 32 - Path Tracer ospray-studio: 3 - 4K - 32 - Path Tracer ospray-studio: 3 - 4K - 16 - Path Tracer ospray-studio: 3 - 1080p - 16 - Path Tracer ncnn: CPU-v3-v3 - mobilenet-v3 ospray-studio: 3 - 1080p - 1 - Path Tracer onnx: ArcFace ResNet-100 - CPU - Parallel dav1d: Summer Nature 4K ospray-studio: 3 - 4K - 1 - Path Tracer simdjson: LargeRand openradioss: Cell Phone Drop Test onnx: super-resolution-10 - CPU - Standard ncnn: CPU - mobilenet onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU dav1d: Chimera 1080p 10-bit onednn: Recurrent Neural Network Training - f32 - CPU openradioss: INIVOL and Fluid Structure Interaction Drop Container ncnn: CPU - googlenet dav1d: Chimera 1080p ncnn: CPU - regnety_400m embree: Pathtracer ISPC - Crown ncnn: CPU - resnet18 ncnn: CPU - resnet50 mnn: nasnet ospray: particle_volume/pathtracer/real_time ncnn: CPU - blazeface ncnn: CPU - FastestDet onednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPU openradioss: Rubber O-Ring Seal Installation embree: Pathtracer ISPC - Asian Dragon ai-benchmark: Device Inference Score onednn: IP Shapes 3D - bf16bf16bf16 - CPU onnx: bertsquad-12 - CPU - Standard tnn: CPU - SqueezeNet v2 onnx: fcn-resnet101-11 - CPU - Standard embree: Pathtracer ISPC - Asian Dragon Obj onednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU dav1d: Summer Nature 1080p mnn: mobilenetV3 lczero: BLAS openfoam: drivaerFastback, Small Mesh Size - Mesh Time ncnn: CPU - vgg16 onnx: yolov4 - CPU - Standard tnn: CPU - MobileNet v2 openradioss: Bird Strike on Windshield onednn: Deconvolution Batch shapes_1d - f32 - CPU onnx: bertsquad-12 - CPU - Parallel openradioss: Bumper Beam xmrig: Wownero - 1M gromacs: MPI CPU - water_GMX50_bare onnx: fcn-resnet101-11 - CPU - Parallel onnx: yolov4 - CPU - Parallel tnn: CPU - SqueezeNet v1.1 cpuminer-opt: Magi xmrig: Monero - 1M openfoam: drivaerFastback, Small Mesh Size - Execution Time tnn: CPU - DenseNet onednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU onnx: GPT-2 - CPU - Parallel onnx: GPT-2 - CPU - Standard onednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPU onednn: IP Shapes 1D - bf16bf16bf16 - CPU ncnn: CPU - shufflenet-v2 oidn: RTLightmap.hdr.4096x4096 oidn: RT.ldr_alb_nrm.3840x2160 oidn: RT.hdr_alb_nrm.3840x2160 onnx: ArcFace ResNet-100 - CPU - Standard openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU cpuminer-opt: Deepcoin cpuminer-opt: Ringcoin cpuminer-opt: x25x onednn: Recurrent Neural Network Training - u8s8f32 - CPU i9-11900K AVX-512 On AVX-512 Off AVX-512 On 512 77083 167500 40573 12.23 326.76 6.43 1240.56 862110 231700 0.840660 6.41 623.17 67.68 4384.38 66.63 22.20 21.86 64.22 65.02 63.34 10.295 0.720702 21.24 22.8900 43.6753 20.46 2069 173.67 4.37042 111730 4.42072 24.92 1.47049 87.29 7.5173 132.9124 25.7285 155.3852 9.42 8.73 8.32 163.87 109.2808 36.5979 8.82 8.78 3.01377 8.52 7.76 136.92 5.36461 108.61 36.80 113 112.10 3445 320.80 4.03554 17.19 4.33063 12.1099 35.3834 28.2567 4.95822 14.5381 68.7607 1.670 80.75 19.580 3.073 4.98037 0.85 9379.27 50.7670 78.7761 4.54 10.6347 49.5682 80.6747 20.99 1814.03 1.78 1817.59 20.1259 49.6651 8.8759 112.6756 97.8481 2235.54 40.8668 8.9135 112.1891 1814.65 1.76 2250.02 2.97 3.26773 13.95 286.43 1346.99 3.73 1186 35.62 112.27 8.9516 446.8814 4.86 8.9588 446.4889 1.972 2.62 6.98 65723 2.131 251261 31054 631.24 4950 127267 3093.58 1958 14.3619 7743 78746 302582 152903 37662 2.68 2358 1388 207.14 9373 1.47 120.62 7356 12.28 1.32134 510.88 3079.96 759.23 10.16 734.61 7.05 14.6252 8.69 15.99 7.468 173.134 0.80 2.98 3.81793 250.33 16.5129 1376 4.81904 1008 47.193 102 14.4298 20.8058 894.73 0.938 1268 45.488465 44.74 529 245.952 309.21 8.55193 519 177.40 4015.0 1.031 73 319 230.819 452.82 2239.5 538.97618 2704.934 17.3084 5548 6954 16.1640 8.55274 2.33 0.21 0.43 0.43 2249 0.34 23074.82 11148.96 2152.94 387.72 3088.89 27270 64663 16150 4.88 817.17 14.98 533.79 393213 106137 1.77832 12.88 310.38 33.92 2381.45 37.37 12.48 12.37 36.49 36.94 36.22 18.043 1.24396 12.32 39.1448 25.5407 12.29 1282 107.72 2.72378 70720 2.82821 15.81 2.31183 110.38 11.6244 85.9777 39.3450 101.6365 6.22 6.11 5.95 117.43 150.7668 26.5261 6.35 6.33 2.18670 6.20 5.69 103.31 4.05745 141.30 28.29 87 87.79 2696 252.69 3.22680 13.89 5.39327 14.8411 28.9677 34.5145 6.02446 17.6640 56.5928 2.023 67.80 23.418 3.694 5.91636 1.00 7956.78 43.2306 92.5054 3.86 11.6771 57.8764 69.1005 18.80 2006.02 1.54 2003.54 23.0354 43.3933 7.8089 128.0523 112.5989 2563.45 35.5207 7.8337 127.6469 2000.12 1.54 2563.87 2.60 3.67360 12.26 325.95 1525.18 3.34 1062 31.70 126.09 8.1213 492.3767 4.35 8.1425 491.1153 1.798 2.37 6.33 72145 1.934 275693 34112 575.79 4515 139519 3271.27 2134 15.6093 8450 85854 329527 166508 40948 2.49 2561 1278 192.71 10148 1.36 128.16 7279 11.43 1.40330 487.09 3271.06 713.35 9.55 691.43 6.70 13.8618 8.24 15.40 7.139 164.963 0.76 2.85 243.47 15.8952 1414 1042 46.360 100 14.0227 879.37 0.942 1240 46.532622 45.68 517 241.314 311.82 8.39772 515 174.60 4076.4 1.020 72 315 228.683 453.39 2256.1 538.29062 2703.558 5557 6954 2.33 0.21 0.43 0.43 1951 0.53 14973.88 9966.10 2130.49 359.01 3270.55 76393 164790 40663 12.17 328.08 6.42 1242.45 895513 230687 0.846376 6.33 630.58 67.67 4392.29 66.49 22.13 21.88 64.42 65.15 63.83 10.368 0.715925 21.29 23.0134 43.4408 20.55 2076 172.66 4.36772 112403 4.46906 24.86 1.46948 70.39 7.4707 133.7435 25.4949 156.8121 9.42 8.69 8.29 163.09 108.4890 36.8617 8.82 8.77 2.75246 8.51 7.76 137.75 5.35301 109.09 36.64 112 113.25 3439 321.51 4.03294 17.34 4.32564 12.0178 35.4238 28.2249 4.95280 14.5355 68.7715 1.675 82.10 19.403 3.114 4.95148 0.84 9460.45 51.3573 77.8730 4.53 9.95113 49.3593 81.0216 22.01 1715.75 1.78 1738.00 19.9939 49.9913 8.9905 111.2249 98.0286 2227.69 40.8021 9.0118 110.9617 1739.49 1.77 2244.25 2.95 3.21742 13.99 285.75 1352.08 3.77 1194 35.55 112.48 9.0886 440.0994 4.79 9.0792 440.5608 1.989 2.58 6.69 65447 2.125 250698 31180 631.86 4626 127540 2986.72 1951 14.2835 7734 78809 303966 153101 37620 2.71 2364 1368 190.82 9376 1.47 118.89 6824 12.28 1.30906 477.09 3062.36 755.60 9.96 727.76 7.10 14.6198 8.64 16.24 7.527 173.739 0.80 2.98 3.66945 240.62 16.4541 1363 4.64814 1012 45.679 103 14.3502 20.2612 902.92 0.963 1273 45.3321 44.59 527 240.410 315.86 8.50891 524 175.69 4075.5 1.035 73 319 228.424 449.42 2252.6 535.10825 2695.646 17.2687 5545 6962 16.1605 8.55374 2.33 0.21 0.43 0.43 2250 0.35 22962.10 11270 2190.91 379.94 3073.17 OpenBenchmarking.org
Cpuminer-Opt Algorithm: LBC, LBRY Credits OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: LBC, LBRY Credits AVX-512 On AVX-512 On 512 AVX-512 Off 17K 34K 51K 68K 85K SE +/- 84.13, N = 3 SE +/- 116.81, N = 3 SE +/- 20.00, N = 3 77083 76393 27270 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Quad SHA-256, Pyrite OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Quad SHA-256, Pyrite AVX-512 On AVX-512 On 512 AVX-512 Off 40K 80K 120K 160K 200K SE +/- 280.42, N = 3 SE +/- 346.55, N = 3 SE +/- 42.56, N = 3 167500 164790 64663 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Myriad-Groestl OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Myriad-Groestl AVX-512 On 512 AVX-512 On AVX-512 Off 9K 18K 27K 36K 45K SE +/- 164.55, N = 3 SE +/- 58.12, N = 3 SE +/- 17.32, N = 3 40663 40573 16150 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU AVX-512 On AVX-512 On 512 AVX-512 Off 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 12.23 12.17 4.88 -ldl -ldl -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU AVX-512 On AVX-512 On 512 AVX-512 Off 200 400 600 800 1000 SE +/- 0.34, N = 3 SE +/- 0.43, N = 3 SE +/- 3.19, N = 3 326.76 328.08 817.17 -ldl - MIN: 183.35 / MAX: 422.57 -ldl - MIN: 193.4 / MAX: 422.42 -mno-avx512f - MIN: 559.45 / MAX: 1507.03 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 6.42 6.43 14.98 -ldl - MIN: 3.32 / MAX: 13.51 -ldl - MIN: 3.29 / MAX: 13.76 -mno-avx512f - MIN: 8.89 / MAX: 192.81 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 300 600 900 1200 1500 SE +/- 4.58, N = 3 SE +/- 5.38, N = 3 SE +/- 2.18, N = 3 1242.45 1240.56 533.79 -ldl -ldl -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
Cpuminer-Opt Algorithm: Blake-2 S OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Blake-2 S AVX-512 On 512 AVX-512 On AVX-512 Off 200K 400K 600K 800K 1000K SE +/- 7851.09, N = 15 SE +/- 9836.24, N = 3 SE +/- 382.81, N = 3 895513 862110 393213 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Triple SHA-256, Onecoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Triple SHA-256, Onecoin AVX-512 On AVX-512 On 512 AVX-512 Off 50K 100K 150K 200K 250K SE +/- 1895.81, N = 3 SE +/- 1461.35, N = 3 SE +/- 627.84, N = 3 231700 230687 106137 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU AVX-512 On AVX-512 On 512 AVX-512 Off 0.4001 0.8002 1.2003 1.6004 2.0005 SE +/- 0.003322, N = 3 SE +/- 0.003829, N = 3 SE +/- 0.003095, N = 3 0.840660 0.846376 1.778320 MIN: 0.82 MIN: 0.81 -mno-avx512f - MIN: 1.73 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 6.33 6.41 12.88 -ldl - MIN: 4.22 / MAX: 15.17 -ldl - MIN: 3.21 / MAX: 14.83 -mno-avx512f - MIN: 7.49 / MAX: 109.79 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 140 280 420 560 700 SE +/- 1.77, N = 3 SE +/- 3.77, N = 3 SE +/- 1.58, N = 3 630.58 623.17 310.38 -ldl -ldl -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
TensorFlow Device: CPU - Batch Size: 512 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: GoogLeNet AVX-512 On AVX-512 On 512 AVX-512 Off 15 30 45 60 75 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 67.68 67.67 33.92
Cpuminer-Opt Algorithm: Garlicoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Garlicoin AVX-512 On 512 AVX-512 On AVX-512 Off 900 1800 2700 3600 4500 SE +/- 10.30, N = 3 SE +/- 25.90, N = 3 SE +/- 6.13, N = 3 4392.29 4384.38 2381.45 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
TensorFlow Device: CPU - Batch Size: 256 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: GoogLeNet AVX-512 On AVX-512 On 512 AVX-512 Off 15 30 45 60 75 SE +/- 0.11, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 66.63 66.49 37.37
TensorFlow Device: CPU - Batch Size: 256 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: ResNet-50 AVX-512 On AVX-512 On 512 AVX-512 Off 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 22.20 22.13 12.48
TensorFlow Device: CPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: ResNet-50 AVX-512 On 512 AVX-512 On AVX-512 Off 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 21.88 21.86 12.37
TensorFlow Device: CPU - Batch Size: 32 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: GoogLeNet AVX-512 On 512 AVX-512 On AVX-512 Off 14 28 42 56 70 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 64.42 64.22 36.49
TensorFlow Device: CPU - Batch Size: 64 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: GoogLeNet AVX-512 On 512 AVX-512 On AVX-512 Off 15 30 45 60 75 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 65.15 65.02 36.94
TensorFlow Device: CPU - Batch Size: 16 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: GoogLeNet AVX-512 On 512 AVX-512 On AVX-512 Off 14 28 42 56 70 SE +/- 0.16, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 63.83 63.34 36.22
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: resnet-v2-50 AVX-512 On AVX-512 On 512 AVX-512 Off 4 8 12 16 20 SE +/- 0.05, N = 15 SE +/- 0.04, N = 15 SE +/- 0.08, N = 3 10.30 10.37 18.04 MIN: 9.74 / MAX: 33.88 MIN: 10.05 / MAX: 22.64 -mno-avx512f - MIN: 17.67 / MAX: 24.46 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 0.2799 0.5598 0.8397 1.1196 1.3995 SE +/- 0.001828, N = 4 SE +/- 0.001991, N = 4 SE +/- 0.000314, N = 4 0.715925 0.720702 1.243960 MIN: 0.66 MIN: 0.67 -mno-avx512f - MIN: 1.22 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
TensorFlow Device: CPU - Batch Size: 32 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: ResNet-50 AVX-512 On 512 AVX-512 On AVX-512 Off 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 21.29 21.24 12.32
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream AVX-512 On AVX-512 On 512 AVX-512 Off 9 18 27 36 45 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 22.89 23.01 39.14
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream AVX-512 On AVX-512 On 512 AVX-512 Off 10 20 30 40 50 SE +/- 0.20, N = 3 SE +/- 0.19, N = 3 SE +/- 0.05, N = 3 43.68 43.44 25.54
TensorFlow Device: CPU - Batch Size: 16 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: ResNet-50 AVX-512 On 512 AVX-512 On AVX-512 Off 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 20.55 20.46 12.29
AI Benchmark Alpha Device Training Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Training Score AVX-512 On 512 AVX-512 On AVX-512 Off 400 800 1200 1600 2000 2076 2069 1282
TensorFlow Device: CPU - Batch Size: 512 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: AlexNet AVX-512 On AVX-512 On 512 AVX-512 Off 40 80 120 160 200 SE +/- 0.14, N = 3 SE +/- 0.21, N = 3 SE +/- 0.09, N = 3 173.67 172.66 107.72
OSPRay Benchmark: gravity_spheres_volume/dim_512/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time AVX-512 On AVX-512 On 512 AVX-512 Off 0.9833 1.9666 2.9499 3.9332 4.9165 SE +/- 0.01025, N = 3 SE +/- 0.02096, N = 3 SE +/- 0.00481, N = 3 4.37042 4.36772 2.72378
Cpuminer-Opt Algorithm: Skeincoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Skeincoin AVX-512 On 512 AVX-512 On AVX-512 Off 20K 40K 60K 80K 100K SE +/- 146.55, N = 3 SE +/- 394.25, N = 3 SE +/- 85.44, N = 3 112403 111730 70720 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OSPRay Benchmark: gravity_spheres_volume/dim_512/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/ao/real_time AVX-512 On 512 AVX-512 On AVX-512 Off 1.0055 2.011 3.0165 4.022 5.0275 SE +/- 0.01309, N = 3 SE +/- 0.02867, N = 3 SE +/- 0.01595, N = 3 4.46906 4.42072 2.82821
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU AVX-512 Off AVX-512 On 512 AVX-512 On 6 12 18 24 30 SE +/- 0.00, N = 3 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 15.81 24.86 24.92 -mno-avx512f - MIN: 7.14 / MAX: 105.25 -ldl - MIN: 12.43 / MAX: 42.38 -ldl - MIN: 12.72 / MAX: 35.46 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 0.5202 1.0404 1.5606 2.0808 2.601 SE +/- 0.00281, N = 9 SE +/- 0.00510, N = 9 SE +/- 0.00997, N = 9 1.46948 1.47049 2.31183 MIN: 1.36 MIN: 1.35 -mno-avx512f - MIN: 2.22 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
NCNN Target: CPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vision_transformer AVX-512 On 512 AVX-512 On AVX-512 Off 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 SE +/- 0.39, N = 3 70.39 87.29 110.38 MIN: 69.62 / MAX: 71.72 MIN: 86.63 / MAX: 92.92 -mno-avx512f - MIN: 109.43 / MAX: 116.1 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 3 6 9 12 15 SE +/- 0.0069, N = 3 SE +/- 0.0274, N = 3 SE +/- 0.0062, N = 3 7.4707 7.5173 11.6244
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.48, N = 3 SE +/- 0.04, N = 3 133.74 132.91 85.98
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 9 18 27 36 45 SE +/- 0.11, N = 3 SE +/- 0.15, N = 3 SE +/- 0.05, N = 3 25.49 25.73 39.35
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 30 60 90 120 150 SE +/- 0.68, N = 3 SE +/- 0.92, N = 3 SE +/- 0.14, N = 3 156.81 155.39 101.64
TensorFlow Device: CPU - Batch Size: 256 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: VGG-16 AVX-512 On 512 AVX-512 On AVX-512 Off 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 9.42 9.42 6.22
TensorFlow Device: CPU - Batch Size: 64 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: VGG-16 AVX-512 On AVX-512 On 512 AVX-512 Off 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 8.73 8.69 6.11
TensorFlow Device: CPU - Batch Size: 32 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: VGG-16 AVX-512 On AVX-512 On 512 AVX-512 Off 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 8.32 8.29 5.95
TensorFlow Device: CPU - Batch Size: 256 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: AlexNet AVX-512 On AVX-512 On 512 AVX-512 Off 40 80 120 160 200 SE +/- 0.42, N = 3 SE +/- 0.22, N = 3 SE +/- 0.05, N = 3 163.87 163.09 117.43
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 30 60 90 120 150 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.85, N = 3 108.49 109.28 150.77
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 8 16 24 32 40 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 36.86 36.60 26.53
simdjson Throughput Test: TopTweet OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: TopTweet AVX-512 On 512 AVX-512 On AVX-512 Off 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 8.82 8.82 6.35 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: DistinctUserID AVX-512 On AVX-512 On 512 AVX-512 Off 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 8.78 8.77 6.33 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU AVX-512 Off AVX-512 On 512 AVX-512 On 0.6781 1.3562 2.0343 2.7124 3.3905 SE +/- 0.00482, N = 5 SE +/- 0.01183, N = 5 SE +/- 0.00593, N = 5 2.18670 2.75246 3.01377 -mno-avx512f - MIN: 2.11 MIN: 2.64 MIN: 2.91 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: PartialTweets AVX-512 On AVX-512 On 512 AVX-512 Off 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 8.52 8.51 6.20 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native
TensorFlow Device: CPU - Batch Size: 16 - Model: VGG-16 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: VGG-16 AVX-512 On 512 AVX-512 On AVX-512 Off 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 7.76 7.76 5.69
TensorFlow Device: CPU - Batch Size: 64 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: AlexNet AVX-512 On 512 AVX-512 On AVX-512 Off 30 60 90 120 150 SE +/- 0.13, N = 3 SE +/- 0.11, N = 3 SE +/- 0.07, N = 3 137.75 136.92 103.31
OSPRay Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time AVX-512 On AVX-512 On 512 AVX-512 Off 1.207 2.414 3.621 4.828 6.035 SE +/- 0.01274, N = 3 SE +/- 0.02156, N = 3 SE +/- 0.01158, N = 3 5.36461 5.35301 4.05745
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU AVX-512 Off AVX-512 On 512 AVX-512 On 30 60 90 120 150 SE +/- 1.44, N = 3 SE +/- 0.25, N = 3 SE +/- 0.12, N = 3 141.30 109.09 108.61 -mno-avx512f -ldl -ldl 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU AVX-512 Off AVX-512 On 512 AVX-512 On 8 16 24 32 40 SE +/- 0.29, N = 3 SE +/- 0.08, N = 3 SE +/- 0.04, N = 3 28.29 36.64 36.80 -mno-avx512f - MIN: 11.7 / MAX: 274.34 -ldl - MIN: 13.62 / MAX: 58.49 -ldl - MIN: 12.79 / MAX: 55.71 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
OpenVKL Benchmark: vklBenchmark ISPC OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.0 Benchmark: vklBenchmark ISPC AVX-512 On AVX-512 On 512 AVX-512 Off 30 60 90 120 150 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.00, N = 3 113 112 87 MIN: 10 / MAX: 1116 MIN: 9 / MAX: 1115 MIN: 7 / MAX: 901
TensorFlow Device: CPU - Batch Size: 32 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: AlexNet AVX-512 On 512 AVX-512 On AVX-512 Off 30 60 90 120 150 SE +/- 0.26, N = 3 SE +/- 0.17, N = 3 SE +/- 0.05, N = 3 113.25 112.10 87.79
Meta Performance Per Watts Performance Per Watts OpenBenchmarking.org Performance Per Watts, More Is Better Meta Performance Per Watts Performance Per Watts AVX-512 On AVX-512 On 512 AVX-512 Off 40 80 120 160 200 170.75 170.21 133.30
AI Benchmark Alpha Device AI Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device AI Score AVX-512 On AVX-512 On 512 AVX-512 Off 700 1400 2100 2800 3500 3445 3439 2696
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 70 140 210 280 350 SE +/- 1.00, N = 3 SE +/- 0.40, N = 3 SE +/- 0.05, N = 3 321.51 320.80 252.69 -ldl -ldl -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU AVX-512 Off AVX-512 On 512 AVX-512 On 0.908 1.816 2.724 3.632 4.54 SE +/- 0.00517, N = 4 SE +/- 0.00488, N = 4 SE +/- 0.00337, N = 4 3.22680 4.03294 4.03554 -mno-avx512f - MIN: 3.09 MIN: 3.89 MIN: 3.9 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: squeezenet_ssd AVX-512 Off AVX-512 On AVX-512 On 512 4 8 12 16 20 SE +/- 0.04, N = 3 SE +/- 0.18, N = 3 SE +/- 0.05, N = 3 13.89 17.19 17.34 -mno-avx512f - MIN: 13.58 / MAX: 15.32 MIN: 16.54 / MAX: 25.09 MIN: 17.03 / MAX: 18.98 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 1.2135 2.427 3.6405 4.854 6.0675 SE +/- 0.00516, N = 9 SE +/- 0.00401, N = 9 SE +/- 0.00507, N = 9 4.32564 4.33063 5.39327 MIN: 4.21 MIN: 4.21 -mno-avx512f - MIN: 5.31 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 4 8 12 16 20 SE +/- 0.00, N = 7 SE +/- 0.01, N = 7 SE +/- 0.01, N = 7 12.02 12.11 14.84 MIN: 11.85 MIN: 11.95 -mno-avx512f - MIN: 14.31 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 8 16 24 32 40 SE +/- 0.11, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 35.42 35.38 28.97
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 8 16 24 32 40 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 28.22 28.26 34.51
OSPRay Benchmark: particle_volume/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: particle_volume/ao/real_time AVX-512 Off AVX-512 On AVX-512 On 512 2 4 6 8 10 SE +/- 0.00177, N = 3 SE +/- 0.01187, N = 3 SE +/- 0.03653, N = 3 6.02446 4.95822 4.95280
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 14.54 14.54 17.66
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 15 30 45 60 75 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 68.77 68.76 56.59
Mobile Neural Network Model: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: squeezenetv1.1 AVX-512 On AVX-512 On 512 AVX-512 Off 0.4552 0.9104 1.3656 1.8208 2.276 SE +/- 0.013, N = 15 SE +/- 0.014, N = 15 SE +/- 0.014, N = 3 1.670 1.675 2.023 MIN: 1.54 / MAX: 11.33 MIN: 1.55 / MAX: 7.76 -mno-avx512f - MIN: 1.97 / MAX: 2.72 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
TensorFlow Device: CPU - Batch Size: 16 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: AlexNet AVX-512 On 512 AVX-512 On AVX-512 Off 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 82.10 80.75 67.80
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: inception-v3 AVX-512 On 512 AVX-512 On AVX-512 Off 6 12 18 24 30 SE +/- 0.27, N = 15 SE +/- 0.26, N = 15 SE +/- 0.02, N = 3 19.40 19.58 23.42 MIN: 17.18 / MAX: 49.2 MIN: 17.25 / MAX: 32.64 -mno-avx512f - MIN: 22.95 / MAX: 30.84 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: SqueezeNetV1.0 AVX-512 On AVX-512 On 512 AVX-512 Off 0.8312 1.6624 2.4936 3.3248 4.156 SE +/- 0.020, N = 15 SE +/- 0.022, N = 15 SE +/- 0.032, N = 3 3.073 3.114 3.694 MIN: 2.89 / MAX: 8.65 MIN: 2.9 / MAX: 9.42 -mno-avx512f - MIN: 3.57 / MAX: 4.37 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OSPRay Benchmark: particle_volume/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: particle_volume/scivis/real_time AVX-512 Off AVX-512 On AVX-512 On 512 1.3312 2.6624 3.9936 5.3248 6.656 SE +/- 0.02016, N = 3 SE +/- 0.04966, N = 3 SE +/- 0.01748, N = 3 5.91636 4.98037 4.95148
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 0.225 0.45 0.675 0.9 1.125 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 0.84 0.85 1.00 -ldl - MIN: 0.48 / MAX: 9.99 -ldl - MIN: 0.45 / MAX: 10.27 -mno-avx512f - MIN: 0.48 / MAX: 89.55 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 2K 4K 6K 8K 10K SE +/- 54.72, N = 3 SE +/- 94.72, N = 3 SE +/- 34.03, N = 3 9460.45 9379.27 7956.78 -ldl -ldl -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
Neural Magic DeepSparse Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 12 24 36 48 60 SE +/- 0.37, N = 3 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 51.36 50.77 43.23
Neural Magic DeepSparse Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 20 40 60 80 100 SE +/- 0.56, N = 3 SE +/- 0.23, N = 3 SE +/- 0.19, N = 3 77.87 78.78 92.51
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: Kostya AVX-512 On AVX-512 On 512 AVX-512 Off 1.0215 2.043 3.0645 4.086 5.1075 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 4.54 4.53 3.86 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 3 6 9 12 15 SE +/- 0.01026, N = 5 SE +/- 0.00598, N = 5 SE +/- 0.00748, N = 5 9.95113 10.63470 11.67710 MIN: 9.83 MIN: 10.54 -mno-avx512f - MIN: 11.41 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 13 26 39 52 65 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 49.36 49.57 57.88
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 20 40 60 80 100 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 81.02 80.67 69.10
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: yolov4-tiny AVX-512 Off AVX-512 On AVX-512 On 512 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.41, N = 3 SE +/- 0.44, N = 3 18.80 20.99 22.01 -mno-avx512f - MIN: 18.51 / MAX: 19.88 MIN: 20.36 / MAX: 37.15 MIN: 21.29 / MAX: 26.71 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 400 800 1200 1600 2000 SE +/- 18.65, N = 5 SE +/- 2.62, N = 3 SE +/- 0.87, N = 3 1715.75 1814.03 2006.02 MIN: 1674.74 MIN: 1799.95 -mno-avx512f - MIN: 1997.88 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 0.4005 0.801 1.2015 1.602 2.0025 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 1.78 1.78 1.54 -ldl -ldl -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 400 800 1200 1600 2000 SE +/- 14.49, N = 3 SE +/- 7.10, N = 3 SE +/- 1.98, N = 3 1738.00 1817.59 2003.54 MIN: 1697.55 MIN: 1801.35 -mno-avx512f - MIN: 1993.54 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Neural Magic DeepSparse Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 19.99 20.13 23.04
Neural Magic DeepSparse Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 11 22 33 44 55 SE +/- 0.04, N = 3 SE +/- 0.15, N = 3 SE +/- 0.01, N = 3 49.99 49.67 43.39
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 3 6 9 12 15 SE +/- 0.0301, N = 3 SE +/- 0.0785, N = 3 SE +/- 0.0071, N = 3 8.9905 8.8759 7.8089
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 30 60 90 120 150 SE +/- 0.37, N = 3 SE +/- 1.00, N = 3 SE +/- 0.12, N = 3 111.22 112.68 128.05
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream AVX-512 On AVX-512 On 512 AVX-512 Off 30 60 90 120 150 SE +/- 0.31, N = 3 SE +/- 0.54, N = 3 SE +/- 0.07, N = 3 97.85 98.03 112.60
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 600 1200 1800 2400 3000 SE +/- 7.01, N = 3 SE +/- 0.33, N = 3 SE +/- 7.35, N = 3 2227.69 2235.54 2563.45 -ldl - MIN: 1807.91 / MAX: 2513.61 -ldl - MIN: 1874.94 / MAX: 2477.63 -mno-avx512f - MIN: 1711.34 / MAX: 3871.27 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream AVX-512 On AVX-512 On 512 AVX-512 Off 9 18 27 36 45 SE +/- 0.12, N = 3 SE +/- 0.22, N = 3 SE +/- 0.02, N = 3 40.87 40.80 35.52
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 3 6 9 12 15 SE +/- 0.0265, N = 3 SE +/- 0.0463, N = 3 SE +/- 0.0041, N = 3 9.0118 8.9135 7.8337
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 30 60 90 120 150 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.07, N = 3 110.96 112.19 127.65
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 400 800 1200 1600 2000 SE +/- 20.46, N = 4 SE +/- 0.41, N = 3 SE +/- 3.47, N = 3 1739.49 1814.65 2000.12 MIN: 1670.86 MIN: 1805.32 -mno-avx512f - MIN: 1987.76 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 0.3983 0.7966 1.1949 1.5932 1.9915 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 1.77 1.76 1.54 -ldl -ldl -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 600 1200 1800 2400 3000 SE +/- 8.02, N = 3 SE +/- 9.13, N = 3 SE +/- 9.17, N = 3 2244.25 2250.02 2563.87 -ldl - MIN: 1760.66 / MAX: 2505.49 -ldl - MIN: 1294.64 / MAX: 2438.65 -mno-avx512f - MIN: 1540.87 / MAX: 3813.98 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU AVX-512 On AVX-512 On 512 AVX-512 Off 0.6683 1.3366 2.0049 2.6732 3.3415 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 2.97 2.95 2.60 -ldl -ldl -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 0.8266 1.6532 2.4798 3.3064 4.133 SE +/- 0.00586, N = 4 SE +/- 0.00624, N = 4 SE +/- 0.03921, N = 4 3.21742 3.26773 3.67360 MIN: 3.14 MIN: 3.18 -mno-avx512f - MIN: 3.39 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU AVX-512 Off AVX-512 On AVX-512 On 512 4 8 12 16 20 SE +/- 0.12, N = 6 SE +/- 0.12, N = 3 SE +/- 0.12, N = 7 12.26 13.95 13.99 -mno-avx512f - MIN: 6.09 / MAX: 23.07 -ldl - MIN: 6.25 / MAX: 52.24 -ldl - MIN: 6.28 / MAX: 24.01 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU AVX-512 Off AVX-512 On AVX-512 On 512 70 140 210 280 350 SE +/- 3.32, N = 6 SE +/- 2.42, N = 3 SE +/- 2.59, N = 7 325.95 286.43 285.75 -mno-avx512f -ldl -ldl 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU AVX-512 On AVX-512 On 512 AVX-512 Off 300 600 900 1200 1500 SE +/- 3.79, N = 3 SE +/- 1.26, N = 3 SE +/- 4.24, N = 3 1346.99 1352.08 1525.18 -ldl - MIN: 1224.1 / MAX: 1502.9 -ldl - MIN: 1184.99 / MAX: 1541.85 -mno-avx512f - MIN: 825.15 / MAX: 2479.54 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v2-v2 - Model: mobilenet-v2 AVX-512 Off AVX-512 On AVX-512 On 512 0.8483 1.6966 2.5449 3.3932 4.2415 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 3.34 3.73 3.77 -mno-avx512f - MIN: 3.16 / MAX: 5.05 MIN: 3.56 / MAX: 5.05 MIN: 3.53 / MAX: 4.4 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: Eigen AVX-512 On 512 AVX-512 On AVX-512 Off 300 600 900 1200 1500 SE +/- 14.97, N = 3 SE +/- 11.35, N = 3 SE +/- 10.84, N = 5 1194 1186 1062 -mno-avx512f 1. (CXX) g++ options: -flto -O3 -march=native -pthread
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU AVX-512 On AVX-512 On 512 AVX-512 Off 8 16 24 32 40 SE +/- 0.27, N = 3 SE +/- 0.18, N = 3 SE +/- 0.04, N = 3 35.62 35.55 31.70 -ldl -ldl -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU AVX-512 On AVX-512 On 512 AVX-512 Off 30 60 90 120 150 SE +/- 0.88, N = 3 SE +/- 0.59, N = 3 SE +/- 0.14, N = 3 112.27 112.48 126.09 -ldl - MIN: 60.98 / MAX: 140.63 -ldl - MIN: 53.91 / MAX: 140.82 -mno-avx512f - MIN: 58.5 / MAX: 136.1 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 3 6 9 12 15 SE +/- 0.0140, N = 3 SE +/- 0.0648, N = 3 SE +/- 0.0060, N = 3 9.0886 8.9516 8.1213
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 110 220 330 440 550 SE +/- 0.68, N = 3 SE +/- 3.25, N = 3 SE +/- 0.40, N = 3 440.10 446.88 492.38
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: efficientnet-b0 AVX-512 Off AVX-512 On 512 AVX-512 On 1.0935 2.187 3.2805 4.374 5.4675 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 4.35 4.79 4.86 -mno-avx512f - MIN: 4.2 / MAX: 5.22 MIN: 4.61 / MAX: 9.9 MIN: 4.6 / MAX: 6.13 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 3 6 9 12 15 SE +/- 0.0265, N = 3 SE +/- 0.0383, N = 3 SE +/- 0.0056, N = 3 9.0792 8.9588 8.1425
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream AVX-512 On 512 AVX-512 On AVX-512 Off 110 220 330 440 550 SE +/- 1.29, N = 3 SE +/- 1.90, N = 3 SE +/- 0.41, N = 3 440.56 446.49 491.12
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenet-v1-1.0 AVX-512 Off AVX-512 On AVX-512 On 512 0.4475 0.895 1.3425 1.79 2.2375 SE +/- 0.007, N = 3 SE +/- 0.005, N = 15 SE +/- 0.007, N = 15 1.798 1.972 1.989 -mno-avx512f - MIN: 1.74 / MAX: 2.69 MIN: 1.8 / MAX: 8.03 MIN: 1.9 / MAX: 8.1 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mnasnet AVX-512 Off AVX-512 On 512 AVX-512 On 0.5895 1.179 1.7685 2.358 2.9475 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 2.37 2.58 2.62 -mno-avx512f - MIN: 2.28 / MAX: 3.27 MIN: 2.48 / MAX: 3.14 MIN: 2.48 / MAX: 3.81 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: alexnet AVX-512 Off AVX-512 On 512 AVX-512 On 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.19, N = 3 SE +/- 0.02, N = 3 6.33 6.69 6.98 -mno-avx512f - MIN: 6.2 / MAX: 7.75 MIN: 6.2 / MAX: 7.35 MIN: 6.82 / MAX: 7.88 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
OSPRay Studio Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer AVX-512 On 512 AVX-512 On AVX-512 Off 15K 30K 45K 60K 75K SE +/- 140.32, N = 3 SE +/- 55.47, N = 3 SE +/- 50.78, N = 3 65447 65723 72145 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ldl
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: MobileNetV2_224 AVX-512 Off AVX-512 On 512 AVX-512 On 0.4795 0.959 1.4385 1.918 2.3975 SE +/- 0.019, N = 3 SE +/- 0.014, N = 15 SE +/- 0.014, N = 15 1.934 2.125 2.131 -mno-avx512f - MIN: 1.84 / MAX: 11.59 MIN: 2.03 / MAX: 8.62 MIN: 2.03 / MAX: 8.46 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OSPRay Studio Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer AVX-512 On 512 AVX-512 On AVX-512 Off 60K 120K 180K 240K 300K SE +/- 784.12, N = 3 SE +/- 259.35, N = 3 SE +/- 100.66, N = 3 250698 251261 275693 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ldl
OSPRay Studio Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer AVX-512 On AVX-512 On 512 AVX-512 Off 7K 14K 21K 28K 35K SE +/- 32.95, N = 3 SE +/- 206.81, N = 3 SE +/- 5.46, N = 3 31054 31180 34112 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ldl
Numpy Benchmark OpenBenchmarking.org Score, More Is Better Numpy Benchmark AVX-512 On 512 AVX-512 On AVX-512 Off 140 280 420 560 700 SE +/- 0.87, N = 3 SE +/- 1.23, N = 3 SE +/- 0.90, N = 3 631.86 631.24 575.79
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Parallel AVX-512 On AVX-512 On 512 AVX-512 Off 1100 2200 3300 4400 5500 SE +/- 5.95, N = 3 SE +/- 25.62, N = 3 SE +/- 8.93, N = 3 4950 4626 4515 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OSPRay Studio Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer AVX-512 On AVX-512 On 512 AVX-512 Off 30K 60K 90K 120K 150K SE +/- 834.11, N = 3 SE +/- 430.68, N = 3 SE +/- 39.26, N = 3 127267 127540 139519 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ldl
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 700 1400 2100 2800 3500 SE +/- 38.98, N = 3 SE +/- 4.17, N = 3 SE +/- 2.45, N = 3 2986.72 3093.58 3271.27 MIN: 2932.85 MIN: 3075.2 -mno-avx512f - MIN: 3259.85 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OSPRay Studio Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer AVX-512 On 512 AVX-512 On AVX-512 Off 500 1000 1500 2000 2500 SE +/- 3.51, N = 3 SE +/- 18.66, N = 3 SE +/- 1.45, N = 3 1951 1958 2134 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 4 8 12 16 20 SE +/- 0.01, N = 7 SE +/- 0.01, N = 7 SE +/- 0.01, N = 7 14.28 14.36 15.61 MIN: 14.09 MIN: 14.18 -mno-avx512f - MIN: 15.43 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OSPRay Studio Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer AVX-512 On 512 AVX-512 On AVX-512 Off 2K 4K 6K 8K 10K SE +/- 11.53, N = 3 SE +/- 26.87, N = 3 SE +/- 2.40, N = 3 7734 7743 8450 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ldl
OSPRay Studio Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer AVX-512 On AVX-512 On 512 AVX-512 Off 20K 40K 60K 80K 100K SE +/- 263.45, N = 3 SE +/- 171.11, N = 3 SE +/- 31.80, N = 3 78746 78809 85854 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ldl
OSPRay Studio Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer AVX-512 On AVX-512 On 512 AVX-512 Off 70K 140K 210K 280K 350K SE +/- 646.03, N = 3 SE +/- 378.84, N = 3 SE +/- 178.71, N = 3 302582 303966 329527 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ldl
OSPRay Studio Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer AVX-512 On AVX-512 On 512 AVX-512 Off 40K 80K 120K 160K 200K SE +/- 313.74, N = 3 SE +/- 494.14, N = 3 SE +/- 189.77, N = 3 152903 153101 166508 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ldl
OSPRay Studio Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer AVX-512 On 512 AVX-512 On AVX-512 Off 9K 18K 27K 36K 45K SE +/- 9.61, N = 3 SE +/- 89.45, N = 3 SE +/- 14.77, N = 3 37620 37662 40948 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ldl
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v3-v3 - Model: mobilenet-v3 AVX-512 Off AVX-512 On AVX-512 On 512 0.6098 1.2196 1.8294 2.4392 3.049 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 2.49 2.68 2.71 -mno-avx512f - MIN: 2.4 / MAX: 3.36 MIN: 2.56 / MAX: 3.63 MIN: 2.55 / MAX: 3.5 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
OSPRay Studio Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer AVX-512 On AVX-512 On 512 AVX-512 Off 500 1000 1500 2000 2500 SE +/- 3.76, N = 3 SE +/- 2.33, N = 3 SE +/- 2.85, N = 3 2358 2364 2561 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ldl
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel AVX-512 On AVX-512 On 512 AVX-512 Off 300 600 900 1200 1500 SE +/- 1.36, N = 3 SE +/- 4.33, N = 3 SE +/- 1.76, N = 3 1388 1368 1278 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 1.0 Video Input: Summer Nature 4K AVX-512 On AVX-512 Off AVX-512 On 512 50 100 150 200 250 SE +/- 0.18, N = 3 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 207.14 192.71 190.82 -mno-avx512f 1. (CC) gcc options: -O3 -march=native -pthread -lm
OSPRay Studio Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer AVX-512 On AVX-512 On 512 AVX-512 Off 2K 4K 6K 8K 10K SE +/- 6.67, N = 3 SE +/- 5.51, N = 3 SE +/- 5.70, N = 3 9373 9376 10148 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ldl
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: LargeRandom AVX-512 On 512 AVX-512 On AVX-512 Off 0.3308 0.6616 0.9924 1.3232 1.654 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.47 1.47 1.36 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native
OpenRadioss Model: Cell Phone Drop Test OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: Cell Phone Drop Test AVX-512 On 512 AVX-512 On AVX-512 Off 30 60 90 120 150 SE +/- 0.31, N = 3 SE +/- 1.35, N = 3 SE +/- 0.52, N = 3 118.89 120.62 128.16
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard AVX-512 On AVX-512 Off AVX-512 On 512 1600 3200 4800 6400 8000 SE +/- 80.51, N = 4 SE +/- 44.00, N = 3 SE +/- 64.19, N = 12 7356 7279 6824 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mobilenet AVX-512 Off AVX-512 On AVX-512 On 512 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.15, N = 3 SE +/- 0.13, N = 3 11.43 12.28 12.28 -mno-avx512f - MIN: 11.21 / MAX: 16.87 MIN: 11.79 / MAX: 13.67 MIN: 11.87 / MAX: 18.86 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 0.3157 0.6314 0.9471 1.2628 1.5785 SE +/- 0.00378, N = 4 SE +/- 0.00334, N = 4 SE +/- 0.00373, N = 4 1.30906 1.32134 1.40330 MIN: 1.24 MIN: 1.26 -mno-avx512f - MIN: 1.31 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 1.0 Video Input: Chimera 1080p 10-bit AVX-512 On AVX-512 Off AVX-512 On 512 110 220 330 440 550 SE +/- 0.34, N = 3 SE +/- 0.38, N = 3 SE +/- 0.21, N = 3 510.88 487.09 477.09 -mno-avx512f 1. (CC) gcc options: -O3 -march=native -pthread -lm
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 700 1400 2100 2800 3500 SE +/- 2.98, N = 3 SE +/- 2.36, N = 3 SE +/- 1.15, N = 3 3062.36 3079.96 3271.06 MIN: 3040.47 MIN: 3061.76 -mno-avx512f - MIN: 3261.78 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenRadioss Model: INIVOL and Fluid Structure Interaction Drop Container OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: INIVOL and Fluid Structure Interaction Drop Container AVX-512 Off AVX-512 On 512 AVX-512 On 160 320 480 640 800 SE +/- 4.20, N = 3 SE +/- 10.28, N = 3 SE +/- 7.20, N = 9 713.35 755.60 759.23
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: googlenet AVX-512 Off AVX-512 On 512 AVX-512 On 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.13, N = 3 SE +/- 0.00, N = 3 9.55 9.96 10.16 -mno-avx512f - MIN: 9.33 / MAX: 10.86 MIN: 9.52 / MAX: 10.98 MIN: 9.92 / MAX: 11.36 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better dav1d 1.0 Video Input: Chimera 1080p AVX-512 On AVX-512 On 512 AVX-512 Off 160 320 480 640 800 SE +/- 0.58, N = 4 SE +/- 0.36, N = 4 SE +/- 0.49, N = 4 734.61 727.76 691.43 -mno-avx512f 1. (CC) gcc options: -O3 -march=native -pthread -lm
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: regnety_400m AVX-512 Off AVX-512 On AVX-512 On 512 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 6.70 7.05 7.10 -mno-avx512f - MIN: 6.54 / MAX: 7.93 MIN: 6.87 / MAX: 8.31 MIN: 6.91 / MAX: 11.12 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown AVX-512 On AVX-512 On 512 AVX-512 Off 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.11, N = 3 14.63 14.62 13.86 MIN: 14.41 / MAX: 15.16 MIN: 14.37 / MAX: 15.18 MIN: 13.49 / MAX: 14.34
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet18 AVX-512 Off AVX-512 On 512 AVX-512 On 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 8.24 8.64 8.69 -mno-avx512f - MIN: 8.06 / MAX: 9.19 MIN: 8.45 / MAX: 9.39 MIN: 8.51 / MAX: 14.15 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet50 AVX-512 Off AVX-512 On AVX-512 On 512 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.42, N = 3 SE +/- 0.42, N = 3 15.40 15.99 16.24 -mno-avx512f - MIN: 15.07 / MAX: 24.51 MIN: 15.25 / MAX: 18.48 MIN: 15.19 / MAX: 17.46 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
Mobile Neural Network Model: nasnet OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: nasnet AVX-512 Off AVX-512 On AVX-512 On 512 2 4 6 8 10 SE +/- 0.056, N = 3 SE +/- 0.077, N = 15 SE +/- 0.087, N = 15 7.139 7.468 7.527 -mno-avx512f - MIN: 6.92 / MAX: 7.99 MIN: 6.73 / MAX: 13.9 MIN: 6.72 / MAX: 17.92 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OSPRay Benchmark: particle_volume/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: particle_volume/pathtracer/real_time AVX-512 On 512 AVX-512 On AVX-512 Off 40 80 120 160 200 SE +/- 0.56, N = 3 SE +/- 0.21, N = 3 SE +/- 0.37, N = 3 173.74 173.13 164.96
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: blazeface AVX-512 Off AVX-512 On AVX-512 On 512 0.18 0.36 0.54 0.72 0.9 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 0.76 0.80 0.80 -mno-avx512f - MIN: 0.73 / MAX: 1.52 MIN: 0.77 / MAX: 1.52 MIN: 0.77 / MAX: 1.28 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: FastestDet AVX-512 Off AVX-512 On AVX-512 On 512 0.6705 1.341 2.0115 2.682 3.3525 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 2.85 2.98 2.98 -mno-avx512f - MIN: 2.78 / MAX: 3.41 MIN: 2.81 / MAX: 3.62 MIN: 2.84 / MAX: 3.6 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU AVX-512 On 512 AVX-512 On 0.859 1.718 2.577 3.436 4.295 SE +/- 0.03397, N = 4 SE +/- 0.04459, N = 4 3.66945 3.81793 MIN: 3.28 MIN: 3.28 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenRadioss Model: Rubber O-Ring Seal Installation OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: Rubber O-Ring Seal Installation AVX-512 On 512 AVX-512 Off AVX-512 On 50 100 150 200 250 SE +/- 2.53, N = 4 SE +/- 2.54, N = 5 SE +/- 2.27, N = 7 240.62 243.47 250.33
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon AVX-512 On AVX-512 On 512 AVX-512 Off 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 16.51 16.45 15.90 MIN: 16.3 / MAX: 17.02 MIN: 16.21 / MAX: 16.89 MIN: 15.66 / MAX: 16.42
AI Benchmark Alpha Device Inference Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Inference Score AVX-512 Off AVX-512 On AVX-512 On 512 300 600 900 1200 1500 1414 1376 1363
oneDNN Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU AVX-512 On 512 AVX-512 On 1.0843 2.1686 3.2529 4.3372 5.4215 SE +/- 0.02954, N = 15 SE +/- 0.03916, N = 9 4.64814 4.81904 MIN: 4.01 MIN: 4.15 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Standard AVX-512 Off AVX-512 On 512 AVX-512 On 200 400 600 800 1000 SE +/- 8.55, N = 9 SE +/- 5.77, N = 3 SE +/- 2.67, N = 3 1042 1012 1008 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
TNN Target: CPU - Model: SqueezeNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 AVX-512 On 512 AVX-512 Off AVX-512 On 11 22 33 44 55 SE +/- 0.11, N = 9 SE +/- 0.17, N = 9 SE +/- 0.07, N = 9 45.68 46.36 47.19 MIN: 45.02 / MAX: 47.45 -mno-avx512f - MIN: 45.49 / MAX: 48.72 MIN: 46.52 / MAX: 48.8 1. (CXX) g++ options: -O3 -march=native -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard AVX-512 On 512 AVX-512 On AVX-512 Off 20 40 60 80 100 SE +/- 0.17, N = 3 SE +/- 0.88, N = 8 SE +/- 0.17, N = 3 103 102 100 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Obj AVX-512 On AVX-512 On 512 AVX-512 Off 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 14.43 14.35 14.02 MIN: 14.31 / MAX: 14.74 MIN: 14.2 / MAX: 14.69 MIN: 13.89 / MAX: 14.33
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU AVX-512 On 512 AVX-512 On 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 20.26 20.81 MIN: 19.82 MIN: 20.45 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 1.0 Video Input: Summer Nature 1080p AVX-512 On 512 AVX-512 On AVX-512 Off 200 400 600 800 1000 SE +/- 0.57, N = 8 SE +/- 0.63, N = 8 SE +/- 0.63, N = 8 902.92 894.73 879.37 -mno-avx512f 1. (CC) gcc options: -O3 -march=native -pthread -lm
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenetV3 AVX-512 On AVX-512 Off AVX-512 On 512 0.2167 0.4334 0.6501 0.8668 1.0835 SE +/- 0.005, N = 15 SE +/- 0.003, N = 3 SE +/- 0.012, N = 15 0.938 0.942 0.963 MIN: 0.89 / MAX: 3.62 -mno-avx512f - MIN: 0.92 / MAX: 1.64 MIN: 0.89 / MAX: 10.54 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: BLAS AVX-512 On 512 AVX-512 On AVX-512 Off 300 600 900 1200 1500 SE +/- 11.26, N = 9 SE +/- 17.53, N = 3 SE +/- 8.35, N = 3 1273 1268 1240 -mno-avx512f 1. (CXX) g++ options: -flto -O3 -march=native -pthread
OpenFOAM Input: drivaerFastback, Small Mesh Size - Mesh Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Mesh Time AVX-512 On 512 AVX-512 On AVX-512 Off 11 22 33 44 55 45.33 45.49 46.53 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vgg16 AVX-512 On 512 AVX-512 On AVX-512 Off 10 20 30 40 50 SE +/- 0.23, N = 3 SE +/- 0.13, N = 3 SE +/- 0.13, N = 3 44.59 44.74 45.68 MIN: 43.87 / MAX: 50.43 MIN: 44.1 / MAX: 49.06 -mno-avx512f - MIN: 44.98 / MAX: 50.56 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Standard AVX-512 On AVX-512 On 512 AVX-512 Off 110 220 330 440 550 SE +/- 0.60, N = 3 SE +/- 1.09, N = 3 SE +/- 0.76, N = 3 529 527 517 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 AVX-512 On 512 AVX-512 Off AVX-512 On 50 100 150 200 250 SE +/- 0.06, N = 3 SE +/- 0.28, N = 3 SE +/- 0.25, N = 3 240.41 241.31 245.95 MIN: 237.96 / MAX: 252.77 -mno-avx512f - MIN: 238.09 / MAX: 252.58 MIN: 242.61 / MAX: 266.39 1. (CXX) g++ options: -O3 -march=native -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
OpenRadioss Model: Bird Strike on Windshield OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: Bird Strike on Windshield AVX-512 On AVX-512 Off AVX-512 On 512 70 140 210 280 350 SE +/- 0.35, N = 3 SE +/- 3.86, N = 4 SE +/- 3.22, N = 5 309.21 311.82 315.86
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU AVX-512 Off AVX-512 On 512 AVX-512 On 2 4 6 8 10 SE +/- 0.04615, N = 3 SE +/- 0.02594, N = 3 SE +/- 0.02566, N = 3 8.39772 8.50891 8.55193 -mno-avx512f - MIN: 4.7 MIN: 4.8 MIN: 4.79 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Parallel AVX-512 On 512 AVX-512 On AVX-512 Off 110 220 330 440 550 SE +/- 0.60, N = 3 SE +/- 0.44, N = 3 SE +/- 2.46, N = 3 524 519 515 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenRadioss Model: Bumper Beam OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: Bumper Beam AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 SE +/- 1.56, N = 7 SE +/- 1.21, N = 3 SE +/- 2.45, N = 3 174.60 175.69 177.40
Xmrig Variant: Wownero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Wownero - Hash Count: 1M AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 SE +/- 5.83, N = 3 SE +/- 21.46, N = 3 SE +/- 44.80, N = 3 4076.4 4075.5 4015.0 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2022.1 Implementation: MPI CPU - Input: water_GMX50_bare AVX-512 On 512 AVX-512 On AVX-512 Off 0.2329 0.4658 0.6987 0.9316 1.1645 SE +/- 0.001, N = 3 SE +/- 0.004, N = 3 SE +/- 0.002, N = 3 1.035 1.031 1.020 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel AVX-512 On 512 AVX-512 On AVX-512 Off 16 32 48 64 80 SE +/- 0.44, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 73 73 72 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Parallel AVX-512 On 512 AVX-512 On AVX-512 Off 70 140 210 280 350 SE +/- 0.33, N = 3 SE +/- 0.29, N = 3 SE +/- 0.33, N = 3 319 319 315 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 AVX-512 On 512 AVX-512 Off AVX-512 On 50 100 150 200 250 SE +/- 0.09, N = 4 SE +/- 0.07, N = 4 SE +/- 0.08, N = 4 228.42 228.68 230.82 MIN: 227.09 / MAX: 230.26 -mno-avx512f - MIN: 227.32 / MAX: 231.38 MIN: 229.65 / MAX: 231.83 1. (CXX) g++ options: -O3 -march=native -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
Cpuminer-Opt Algorithm: Magi OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Magi AVX-512 Off AVX-512 On AVX-512 On 512 100 200 300 400 500 SE +/- 0.84, N = 3 SE +/- 0.67, N = 3 SE +/- 3.36, N = 3 453.39 452.82 449.42 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Xmrig Variant: Monero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Monero - Hash Count: 1M AVX-512 Off AVX-512 On 512 AVX-512 On 500 1000 1500 2000 2500 SE +/- 6.72, N = 3 SE +/- 6.87, N = 3 SE +/- 3.33, N = 3 2256.1 2252.6 2239.5 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenFOAM Input: drivaerFastback, Small Mesh Size - Execution Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Execution Time AVX-512 On 512 AVX-512 Off AVX-512 On 120 240 360 480 600 535.11 538.29 538.98 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
TNN Target: CPU - Model: DenseNet OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet AVX-512 On 512 AVX-512 Off AVX-512 On 600 1200 1800 2400 3000 SE +/- 1.39, N = 3 SE +/- 0.35, N = 3 SE +/- 2.72, N = 3 2695.65 2703.56 2704.93 MIN: 2633.85 / MAX: 2768.47 -mno-avx512f - MIN: 2643.22 / MAX: 2776.22 MIN: 2642.6 / MAX: 2789.25 1. (CXX) g++ options: -O3 -march=native -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU AVX-512 On 512 AVX-512 On 4 8 12 16 20 SE +/- 0.00, N = 9 SE +/- 0.00, N = 9 17.27 17.31 MIN: 16.85 MIN: 16.91 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Parallel AVX-512 Off AVX-512 On AVX-512 On 512 1200 2400 3600 4800 6000 SE +/- 1.76, N = 3 SE +/- 7.10, N = 3 SE +/- 3.18, N = 3 5557 5548 5545 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Standard AVX-512 On 512 AVX-512 Off AVX-512 On 1500 3000 4500 6000 7500 SE +/- 9.16, N = 3 SE +/- 4.16, N = 3 SE +/- 4.94, N = 3 6962 6954 6954 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU AVX-512 On 512 AVX-512 On 4 8 12 16 20 SE +/- 0.00, N = 7 SE +/- 0.00, N = 7 16.16 16.16 MIN: 16.06 MIN: 16.07 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU AVX-512 On AVX-512 On 512 2 4 6 8 10 SE +/- 0.00165, N = 4 SE +/- 0.00438, N = 4 8.55274 8.55374 MIN: 8.4 MIN: 8.33 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: shufflenet-v2 AVX-512 On AVX-512 Off AVX-512 On 512 0.5243 1.0486 1.5729 2.0972 2.6215 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 2.33 2.33 2.33 MIN: 2.26 / MAX: 3.21 -mno-avx512f - MIN: 2.27 / MAX: 3.18 MIN: 2.27 / MAX: 2.81 1. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
Intel Open Image Denoise Run: RTLightmap.hdr.4096x4096 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RTLightmap.hdr.4096x4096 AVX-512 On 512 AVX-512 Off AVX-512 On 0.0473 0.0946 0.1419 0.1892 0.2365 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.21 0.21 0.21
Intel Open Image Denoise Run: RT.ldr_alb_nrm.3840x2160 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.ldr_alb_nrm.3840x2160 AVX-512 On 512 AVX-512 Off AVX-512 On 0.0968 0.1936 0.2904 0.3872 0.484 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.43 0.43 0.43
Intel Open Image Denoise Run: RT.hdr_alb_nrm.3840x2160 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.hdr_alb_nrm.3840x2160 AVX-512 On 512 AVX-512 Off AVX-512 On 0.0968 0.1936 0.2904 0.3872 0.484 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.43 0.43 0.43
CPU Temperature Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Celsius CPU Temperature Monitor Phoronix Test Suite System Monitoring AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 27 / Avg: 72.98 / Max: 95 Min: 29 / Avg: 78.17 / Max: 100 Min: 31 / Avg: 79.47 / Max: 100
CPU Power Consumption Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Watts CPU Power Consumption Monitor Phoronix Test Suite System Monitoring AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 6.36 / Avg: 173.58 / Max: 251.93 Min: 6.37 / Avg: 188.45 / Max: 283.94 Min: 6.3 / Avg: 192.29 / Max: 280.23
CPU Peak Freq (Highest CPU Core Frequency) Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Megahertz CPU Peak Freq (Highest CPU Core Frequency) Monitor Phoronix Test Suite System Monitoring AVX-512 On 512 AVX-512 On AVX-512 Off 1000 2000 3000 4000 5000 Min: 2700 / Avg: 4722.22 / Max: 5323 Min: 3350 / Avg: 4733.96 / Max: 5541 Min: 3500 / Avg: 4781.84 / Max: 5621
GROMACS CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better GROMACS 2022.1 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 31 / Avg: 70.7 / Max: 87 Min: 32 / Avg: 70.87 / Max: 87 Min: 32 / Avg: 71.71 / Max: 89
GROMACS CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better GROMACS 2022.1 CPU Power Consumption Monitor AVX-512 On AVX-512 Off AVX-512 On 512 40 80 120 160 200 Min: 11.96 / Avg: 170.87 / Max: 188.26 Min: 11.7 / Avg: 172.11 / Max: 186.28 Min: 12.08 / Avg: 175.38 / Max: 240.72
GROMACS CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better GROMACS 2022.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 Off AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4784 / Max: 5300 Min: 4700 / Avg: 4781.57 / Max: 5267 Min: 4700 / Avg: 4778.77 / Max: 5300
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day Per Watt, More Is Better GROMACS 2022.1 Implementation: MPI CPU - Input: water_GMX50_bare AVX-512 On 512 AVX-512 Off AVX-512 On 0.0014 0.0028 0.0042 0.0056 0.007 0.006 0.006 0.006
Numpy Benchmark CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Numpy Benchmark CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 14 28 42 56 70 Min: 32 / Avg: 61.15 / Max: 70 Min: 34 / Avg: 62.31 / Max: 71 Min: 34 / Avg: 62.39 / Max: 71
Numpy Benchmark CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Numpy Benchmark CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 13 26 39 52 65 Min: 11.97 / Avg: 59.15 / Max: 65.44 Min: 11.84 / Avg: 61.39 / Max: 67.45 Min: 11.83 / Avg: 61.82 / Max: 67.42
Numpy Benchmark CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Numpy Benchmark CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 5086 / Avg: 5292.12 / Max: 5306 Min: 4905 / Avg: 5065.67 / Max: 5305 Min: 4910 / Avg: 5058.87 / Max: 5300
Numpy Benchmark OpenBenchmarking.org Score Per Watt, More Is Better Numpy Benchmark AVX-512 On 512 AVX-512 On AVX-512 Off 3 6 9 12 15 10.293 10.211 9.735
ONNX Runtime CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better ONNX Runtime 1.11 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 39 / Avg: 74.86 / Max: 84 Min: 40 / Avg: 83.1 / Max: 97 Min: 41 / Avg: 83.51 / Max: 95
ONNX Runtime CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.13 / Avg: 166.02 / Max: 178.1 Min: 12.16 / Avg: 195.75 / Max: 212.83 Min: 12.31 / Avg: 197.92 / Max: 211.73
ONNX Runtime CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better ONNX Runtime 1.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4737.48 / Max: 5298 Min: 4700 / Avg: 4718.39 / Max: 5300 Min: 3850 / Avg: 4692.98 / Max: 5274
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel AVX-512 Off AVX-512 On AVX-512 On 512 2 4 6 8 10 7.698 7.013 6.988
ONNX Runtime CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better ONNX Runtime 1.11 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 38 / Avg: 80.76 / Max: 86 Min: 40 / Avg: 85.67 / Max: 96 Min: 40 / Avg: 86.37 / Max: 96
ONNX Runtime CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.04 / Avg: 197.45 / Max: 208.91 Min: 12.17 / Avg: 215.02 / Max: 242.14 Min: 12.25 / Avg: 215.19 / Max: 242.31
ONNX Runtime CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better ONNX Runtime 1.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4719.81 / Max: 5300 Min: 3587 / Avg: 4590.75 / Max: 5143 Min: 3500 / Avg: 4585.07 / Max: 5300
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard AVX-512 On 512 AVX-512 On AVX-512 Off 3 6 9 12 15 10.464 10.451 9.881
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard AVX-512 On 512 AVX-512 On AVX-512 Off 500 1000 1500 2000 2500 SE +/- 1.92, N = 3 SE +/- 2.02, N = 3 SE +/- 35.14, N = 12 2250 2249 1951 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better ONNX Runtime 1.11 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 14 28 42 56 70 Min: 38 / Avg: 64.71 / Max: 67 Min: 39 / Avg: 70.44 / Max: 74 Min: 40 / Avg: 70.87 / Max: 74
ONNX Runtime CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 30 60 90 120 150 Min: 12.21 / Avg: 151.62 / Max: 159.76 Min: 12.13 / Avg: 174.33 / Max: 184.01 Min: 12.21 / Avg: 175.17 / Max: 183.77
ONNX Runtime CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better ONNX Runtime 1.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4800 / Avg: 4814.2 / Max: 5300 Min: 4700 / Avg: 4718.69 / Max: 5297 Min: 4700 / Avg: 4718.08 / Max: 5307
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Parallel AVX-512 Off AVX-512 On AVX-512 On 512 8 16 24 32 40 36.65 31.82 31.65
ONNX Runtime CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better ONNX Runtime 1.11 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 14 28 42 56 70 Min: 39 / Avg: 63.86 / Max: 67 Min: 39 / Avg: 68.81 / Max: 71 Min: 40 / Avg: 68.89 / Max: 72
ONNX Runtime CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 30 60 90 120 150 Min: 12.04 / Avg: 153.13 / Max: 160.84 Min: 12.13 / Avg: 174.92 / Max: 183.06 Min: 12.2 / Avg: 175.95 / Max: 184.82
ONNX Runtime CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better ONNX Runtime 1.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4800 / Avg: 4816.8 / Max: 5300 Min: 4700 / Avg: 4720.24 / Max: 5300 Min: 4700 / Avg: 4718.55 / Max: 5302
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Standard AVX-512 Off AVX-512 On AVX-512 On 512 10 20 30 40 50 45.41 39.75 39.57
ONNX Runtime CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better ONNX Runtime 1.11 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 40 / Avg: 71.61 / Max: 81 Min: 41 / Avg: 79.02 / Max: 90 Min: 41 / Avg: 80.28 / Max: 91
ONNX Runtime CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.03 / Avg: 167.62 / Max: 180.22 Min: 12.5 / Avg: 199.53 / Max: 210.58 Min: 12.39 / Avg: 199.65 / Max: 210.74
ONNX Runtime CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better ONNX Runtime 1.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4732.41 / Max: 5295 Min: 4700 / Avg: 4718.96 / Max: 5300 Min: 4700 / Avg: 4717.76 / Max: 5300
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Parallel AVX-512 Off AVX-512 On 512 AVX-512 On 0.6912 1.3824 2.0736 2.7648 3.456 3.072 2.626 2.600
ONNX Runtime CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better ONNX Runtime 1.11 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 40 / Avg: 83.73 / Max: 88 Min: 40 / Avg: 85.81 / Max: 95 Min: 40 / Avg: 87.16 / Max: 95
ONNX Runtime CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.1 / Avg: 213.3 / Max: 224.83 Min: 12.28 / Avg: 221.92 / Max: 249.13 Min: 12.1 / Avg: 223.48 / Max: 250.46
ONNX Runtime CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better ONNX Runtime 1.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4717.56 / Max: 5304 Min: 3500 / Avg: 4615.05 / Max: 5300 Min: 3561 / Avg: 4598.1 / Max: 5231
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Standard AVX-512 Off AVX-512 On AVX-512 On 512 1.0991 2.1982 3.2973 4.3964 5.4955 4.885 4.542 4.528
ONNX Runtime CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better ONNX Runtime 1.11 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 40 / Avg: 74.62 / Max: 83 Min: 41 / Avg: 82.41 / Max: 93 Min: 41 / Avg: 83.35 / Max: 93
ONNX Runtime CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.12 / Avg: 171.44 / Max: 185.67 Min: 12.41 / Avg: 205.81 / Max: 220.47 Min: 12.22 / Avg: 210.18 / Max: 224.25
ONNX Runtime CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better ONNX Runtime 1.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4718.23 / Max: 5295 Min: 4700 / Avg: 4715.24 / Max: 5300 Min: 3874 / Avg: 4710.34 / Max: 5302
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Parallel AVX-512 Off AVX-512 On AVX-512 On 512 6 12 18 24 30 26.34 23.55 22.48
ONNX Runtime CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better ONNX Runtime 1.11 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 39 / Avg: 83.06 / Max: 88 Min: 39 / Avg: 87.15 / Max: 95 Min: 39 / Avg: 87.18 / Max: 97
ONNX Runtime CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.22 / Avg: 219.18 / Max: 229.39 Min: 12.18 / Avg: 229.09 / Max: 256.96 Min: 12.22 / Avg: 232.2 / Max: 259.58
ONNX Runtime CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better ONNX Runtime 1.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4716.1 / Max: 5305 Min: 3500 / Avg: 4653.64 / Max: 5308 Min: 3500 / Avg: 4629.79 / Max: 5300
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard AVX-512 Off AVX-512 On AVX-512 On 512 8 16 24 32 40 33.21 31.68 29.78
ONNX Runtime CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better ONNX Runtime 1.11 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 40 / Avg: 75.92 / Max: 88 Min: 41 / Avg: 81.09 / Max: 94 Min: 40 / Avg: 81.63 / Max: 94
ONNX Runtime CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.19 / Avg: 175.09 / Max: 200.07 Min: 12.2 / Avg: 194.83 / Max: 220.39 Min: 12.33 / Avg: 195.17 / Max: 218.64
ONNX Runtime CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better ONNX Runtime 1.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4741.29 / Max: 5300 Min: 4700 / Avg: 4718.48 / Max: 5203 Min: 4361 / Avg: 4716.76 / Max: 5300
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel AVX-512 Off AVX-512 On AVX-512 On 512 0.0925 0.185 0.2775 0.37 0.4625 0.411 0.375 0.374
ONNX Runtime CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better ONNX Runtime 1.11 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 39 / Avg: 81.74 / Max: 92 Min: 39 / Avg: 85.21 / Max: 99 Min: 39 / Avg: 85.21 / Max: 98
ONNX Runtime CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.44 / Avg: 208.04 / Max: 219.8 Min: 12.29 / Avg: 216.9 / Max: 237.78 Min: 12.2 / Avg: 218.3 / Max: 237.54
ONNX Runtime CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better ONNX Runtime 1.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4720.87 / Max: 5300 Min: 3564 / Avg: 4670.77 / Max: 5300 Min: 3500 / Avg: 4662.15 / Max: 5300
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard AVX-512 Off AVX-512 On 512 AVX-512 On 0.1082 0.2164 0.3246 0.4328 0.541 0.481 0.472 0.470
ONNX Runtime CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better ONNX Runtime 1.11 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 40 / Avg: 69.43 / Max: 86 Min: 42 / Avg: 74.76 / Max: 95 Min: 39 / Avg: 75.62 / Max: 94
ONNX Runtime CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.26 / Avg: 158.94 / Max: 171.99 Min: 12.55 / Avg: 182.37 / Max: 194.6 Min: 12.18 / Avg: 182.51 / Max: 195.72
ONNX Runtime CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better ONNX Runtime 1.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4788.45 / Max: 5300 Min: 4700 / Avg: 4721.84 / Max: 5299 Min: 4700 / Avg: 4721.58 / Max: 5306
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Parallel AVX-512 Off AVX-512 On 512 AVX-512 On 0.446 0.892 1.338 1.784 2.23 1.982 1.749 1.748
ONNX Runtime CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better ONNX Runtime 1.11 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 40 / Avg: 74.38 / Max: 87 Min: 41 / Avg: 79.4 / Max: 94 Min: 41 / Avg: 80.11 / Max: 94
ONNX Runtime CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.26 / Avg: 183.13 / Max: 192.75 Min: 12.3 / Avg: 202.2 / Max: 213.09 Min: 12.31 / Avg: 202.83 / Max: 212.6
ONNX Runtime CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better ONNX Runtime 1.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4748.49 / Max: 5300 Min: 4700 / Avg: 4722.26 / Max: 5300 Min: 4700 / Avg: 4716.47 / Max: 5301
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Standard AVX-512 Off AVX-512 On AVX-512 On 512 0.6352 1.2704 1.9056 2.5408 3.176 2.823 2.616 2.598
OpenVINO CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 40 / Avg: 80.98 / Max: 89 Min: 40 / Avg: 84.75 / Max: 97 Min: 40 / Avg: 85.67 / Max: 95
OpenVINO CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.2 / Avg: 207.39 / Max: 228.54 Min: 12.26 / Avg: 219.2 / Max: 255.83 Min: 12.32 / Avg: 220.48 / Max: 255.95
OpenVINO CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4731.38 / Max: 5300 Min: 3403 / Avg: 4632.52 / Max: 5130 Min: 3422 / Avg: 4604.88 / Max: 5300
OpenVINO CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 44 / Avg: 76.67 / Max: 83 Min: 40 / Avg: 80.87 / Max: 89 Min: 40 / Avg: 81.03 / Max: 89
OpenVINO CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.72 / Avg: 193.11 / Max: 217.17 Min: 12.31 / Avg: 213.54 / Max: 244.32 Min: 12.28 / Avg: 214.43 / Max: 245.42
OpenVINO CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4735.41 / Max: 5311 Min: 4700 / Avg: 4733.54 / Max: 5300 Min: 4700 / Avg: 4730.67 / Max: 5300
OpenVINO CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 16 32 48 64 80 Min: 60 / Avg: 73.94 / Max: 80 Min: 40 / Avg: 76.21 / Max: 84 Min: 41 / Avg: 76.53 / Max: 85
OpenVINO CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 55.1 / Avg: 178.79 / Max: 191.55 Min: 12.15 / Avg: 198.06 / Max: 213.93 Min: 12.26 / Avg: 198.22 / Max: 214.69
OpenVINO CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 1000 2000 3000 4000 5000 Min: 4700 / Avg: 4746.45 / Max: 5621 Min: 4700 / Avg: 4730.05 / Max: 5300 Min: 4700 / Avg: 4729.11 / Max: 5314
OpenVINO CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 63 / Avg: 85.86 / Max: 93 Min: 41 / Avg: 87.07 / Max: 99 Min: 41 / Avg: 87.16 / Max: 98
OpenVINO CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 56.17 / Avg: 203.83 / Max: 229.49 Min: 12.3 / Avg: 212.55 / Max: 269.62 Min: 12.25 / Avg: 215.41 / Max: 266.45
OpenVINO CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 3648 / Avg: 4621.73 / Max: 5300 Min: 3451 / Avg: 4568.22 / Max: 5300 Min: 2700 / Avg: 4559.24 / Max: 5300
OpenVINO CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor AVX-512 On AVX-512 Off AVX-512 On 512 20 40 60 80 100 Min: 42 / Avg: 86.73 / Max: 97 Min: 61 / Avg: 86.8 / Max: 92 Min: 40 / Avg: 87.33 / Max: 96
OpenVINO CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor AVX-512 On AVX-512 Off AVX-512 On 512 50 100 150 200 250 Min: 12.39 / Avg: 215.87 / Max: 266.83 Min: 55.78 / Avg: 216.3 / Max: 232.36 Min: 12.36 / Avg: 217.96 / Max: 268.63
OpenVINO CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4007 / Avg: 4734.73 / Max: 5300 Min: 3500 / Avg: 4571.82 / Max: 5303 Min: 3000 / Avg: 4570.85 / Max: 5186
OpenVINO CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor AVX-512 On AVX-512 On 512 AVX-512 Off 20 40 60 80 100 Min: 41 / Avg: 86.74 / Max: 97 Min: 41 / Avg: 87 / Max: 97 Min: 60 / Avg: 87.45 / Max: 94
OpenVINO CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 55.18 / Avg: 209.8 / Max: 238.87 Min: 12.59 / Avg: 216.16 / Max: 260.53 Min: 12.19 / Avg: 217.71 / Max: 260.02
OpenVINO CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 3600 / Avg: 4614.52 / Max: 5300 Min: 3500 / Avg: 4603.65 / Max: 5199 Min: 3500 / Avg: 4589.65 / Max: 5300
OpenVINO CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 59 / Avg: 84.96 / Max: 95 Min: 40 / Avg: 86.02 / Max: 100 Min: 41 / Avg: 86.88 / Max: 100
OpenVINO CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 54.81 / Avg: 199.09 / Max: 231.05 Min: 12.17 / Avg: 206.04 / Max: 269.05 Min: 12.33 / Avg: 207.04 / Max: 270.73
OpenVINO CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4766.42 / Max: 5300 Min: 3400 / Avg: 4584.47 / Max: 5300 Min: 3400 / Avg: 4531.88 / Max: 5300
OpenVINO CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 61 / Avg: 84.05 / Max: 95 Min: 40 / Avg: 86.76 / Max: 97 Min: 41 / Avg: 87.35 / Max: 100
OpenVINO CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 55.69 / Avg: 197.83 / Max: 225.46 Min: 12.41 / Avg: 211.56 / Max: 263.47 Min: 12.5 / Avg: 211.57 / Max: 263.35
OpenVINO CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4762.25 / Max: 5300 Min: 3439 / Avg: 4662.38 / Max: 5300 Min: 3434 / Avg: 4623.02 / Max: 5300
OpenVINO CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 61 / Avg: 85.95 / Max: 90 Min: 41 / Avg: 86.73 / Max: 95 Min: 40 / Avg: 87.04 / Max: 95
OpenVINO CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 55.78 / Avg: 221.82 / Max: 236.18 Min: 12.41 / Avg: 231.67 / Max: 274.84 Min: 12.32 / Avg: 232.01 / Max: 274.61
OpenVINO CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4738.5 / Max: 5300 Min: 3400 / Avg: 4624.71 / Max: 5302 Min: 3408 / Avg: 4610.19 / Max: 5310
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU AVX-512 On AVX-512 On 512 AVX-512 Off 0.1193 0.2386 0.3579 0.4772 0.5965 SE +/- 0.01, N = 15 SE +/- 0.01, N = 15 SE +/- 0.00, N = 3 0.34 0.35 0.53 -ldl - MIN: 0.18 / MAX: 82.47 -ldl - MIN: 0.18 / MAX: 11.28 -mno-avx512f - MIN: 0.28 / MAX: 83.77 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU AVX-512 On AVX-512 On 512 AVX-512 Off 5K 10K 15K 20K 25K SE +/- 411.52, N = 15 SE +/- 387.31, N = 15 SE +/- 47.04, N = 3 23074.82 22962.10 14973.88 -ldl -ldl -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -pie
OpenVINO CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 60 / Avg: 83.29 / Max: 89 Min: 38 / Avg: 85.65 / Max: 96 Min: 39 / Avg: 87.24 / Max: 97
OpenVINO CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 54.99 / Avg: 220.55 / Max: 236.23 Min: 12.26 / Avg: 225.84 / Max: 268.92 Min: 12.23 / Avg: 227.4 / Max: 268.33
OpenVINO CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4741.63 / Max: 5304 Min: 3467 / Avg: 4665.94 / Max: 5302 Min: 3400 / Avg: 4621.94 / Max: 5300
OpenVINO CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor AVX-512 On 512 AVX-512 Off AVX-512 On 20 40 60 80 100 Min: 40 / Avg: 82.79 / Max: 99 Min: 60 / Avg: 84.66 / Max: 94 Min: 40 / Avg: 85.93 / Max: 98
OpenVINO CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor AVX-512 On 512 AVX-512 Off AVX-512 On 50 100 150 200 250 Min: 12.29 / Avg: 198.43 / Max: 264.85 Min: 55.05 / Avg: 200.47 / Max: 228.29 Min: 12.09 / Avg: 210.05 / Max: 263.04
OpenVINO CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 3600 / Avg: 4630.48 / Max: 5300 Min: 3417 / Avg: 4571.49 / Max: 5308 Min: 3486 / Avg: 4562.25 / Max: 5300
OpenVINO CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 61 / Avg: 84.02 / Max: 93 Min: 35 / Avg: 84.78 / Max: 98 Min: 39 / Avg: 86.41 / Max: 99
OpenVINO CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 54.89 / Avg: 202.96 / Max: 226.01 Min: 12.17 / Avg: 216.31 / Max: 263.21 Min: 11.88 / Avg: 218.42 / Max: 263.98
OpenVINO CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 3689 / Avg: 4731.52 / Max: 5300 Min: 3424 / Avg: 4605.82 / Max: 5143 Min: 3429 / Avg: 4599.8 / Max: 5310
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 57 / Avg: 74.26 / Max: 89 Min: 39 / Avg: 81.43 / Max: 100 Min: 39 / Avg: 81.85 / Max: 100
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 54.66 / Avg: 180.33 / Max: 219.82 Min: 12.18 / Avg: 198.72 / Max: 231.12 Min: 12.21 / Avg: 199.88 / Max: 233.13
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4746.31 / Max: 5300 Min: 3424 / Avg: 4724.5 / Max: 5302 Min: 3400 / Avg: 4717.76 / Max: 5300
TensorFlow Device: CPU - Batch Size: 512 - Model: GoogLeNet OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: GoogLeNet AVX-512 On AVX-512 On 512 AVX-512 Off 0.0767 0.1534 0.2301 0.3068 0.3835 0.341 0.339 0.188
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 54 / Avg: 74.43 / Max: 88 Min: 35 / Avg: 76.02 / Max: 93 Min: 35 / Avg: 76.2 / Max: 95
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 52.34 / Avg: 181.46 / Max: 234.98 Min: 12.1 / Avg: 187.51 / Max: 247.19 Min: 12.17 / Avg: 188.69 / Max: 244.78
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On 512 AVX-512 On AVX-512 Off 900 1800 2700 3600 4500 Min: 4700 / Avg: 4746.52 / Max: 5300 Min: 4700 / Avg: 4744.85 / Max: 5300 Min: 4700 / Avg: 4739.57 / Max: 5300
TensorFlow Device: CPU - Batch Size: 512 - Model: AlexNet OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: AlexNet AVX-512 On 512 AVX-512 On AVX-512 Off 0.207 0.414 0.621 0.828 1.035 0.920 0.920 0.594
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 39 / Avg: 73.72 / Max: 88 Min: 39 / Avg: 80.86 / Max: 100 Min: 39 / Avg: 81.3 / Max: 99
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.37 / Avg: 181.53 / Max: 217.34 Min: 12.19 / Avg: 196.37 / Max: 222.3 Min: 12.45 / Avg: 196.85 / Max: 222.31
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4745.56 / Max: 5300 Min: 3500 / Avg: 4736.16 / Max: 5300 Min: 3404 / Avg: 4735.04 / Max: 5312
TensorFlow Device: CPU - Batch Size: 256 - Model: GoogLeNet OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: GoogLeNet AVX-512 On 512 AVX-512 On AVX-512 Off 0.0763 0.1526 0.2289 0.3052 0.3815 0.339 0.338 0.206
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 38 / Avg: 73.1 / Max: 85 Min: 39 / Avg: 75.03 / Max: 94 Min: 39 / Avg: 75.22 / Max: 88
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 On 512 AVX-512 Off AVX-512 On 40 80 120 160 200 Min: 12.27 / Avg: 179.14 / Max: 227.47 Min: 12.56 / Avg: 179.61 / Max: 210.75 Min: 12.49 / Avg: 180.37 / Max: 231.09
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On 512 AVX-512 On AVX-512 Off 900 1800 2700 3600 4500 Min: 4700 / Avg: 4756.54 / Max: 5300 Min: 4700 / Avg: 4754.47 / Max: 5300 Min: 4700 / Avg: 4741.91 / Max: 5300
TensorFlow Device: CPU - Batch Size: 256 - Model: AlexNet OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: AlexNet AVX-512 On 512 AVX-512 On AVX-512 Off 0.2048 0.4096 0.6144 0.8192 1.024 0.910 0.909 0.654
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 71.84 / Max: 89 Min: 39 / Avg: 80.23 / Max: 100 Min: 41 / Avg: 80.63 / Max: 100
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.55 / Avg: 176.58 / Max: 210.64 Min: 12.31 / Avg: 191.97 / Max: 247.16 Min: 6.72 / Avg: 192.97 / Max: 247.42
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4768.97 / Max: 5300 Min: 3350 / Avg: 4727.85 / Max: 5303 Min: 3337 / Avg: 4721.84 / Max: 5300
TensorFlow Device: CPU - Batch Size: 256 - Model: ResNet-50 OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: ResNet-50 AVX-512 On 512 AVX-512 On AVX-512 Off 0.0259 0.0518 0.0777 0.1036 0.1295 0.115 0.115 0.071
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 78.01 / Max: 93 Min: 39 / Avg: 87.38 / Max: 100 Min: 39 / Avg: 87.55 / Max: 100
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.64 / Avg: 193.81 / Max: 251.93 Min: 12.13 / Avg: 217.21 / Max: 270.46 Min: 12.64 / Avg: 218.14 / Max: 271.2
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 3500 / Avg: 4740.8 / Max: 5300 Min: 3412 / Avg: 4593.29 / Max: 5302 Min: 3406 / Avg: 4587.01 / Max: 5298
TensorFlow Device: CPU - Batch Size: 256 - Model: VGG-16 OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: VGG-16 AVX-512 On 512 AVX-512 On AVX-512 Off 0.0097 0.0194 0.0291 0.0388 0.0485 0.043 0.043 0.032
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 72.62 / Max: 84 Min: 39 / Avg: 77.98 / Max: 96 Min: 38 / Avg: 78.31 / Max: 98
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.27 / Avg: 176.8 / Max: 195.47 Min: 12.16 / Avg: 187.24 / Max: 205.18 Min: 12.63 / Avg: 187.75 / Max: 210.7
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 Off AVX-512 On 512 900 1800 2700 3600 4500 Min: 4664 / Avg: 4758.71 / Max: 5300 Min: 4700 / Avg: 4747.96 / Max: 5300 Min: 3529 / Avg: 4743.6 / Max: 5300
TensorFlow Device: CPU - Batch Size: 64 - Model: GoogLeNet OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: GoogLeNet AVX-512 On 512 AVX-512 On AVX-512 Off 0.0783 0.1566 0.2349 0.3132 0.3915 0.348 0.346 0.209
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 On AVX-512 On 512 AVX-512 Off 16 32 48 64 80 Min: 39 / Avg: 69.23 / Max: 83 Min: 39 / Avg: 69.91 / Max: 82 Min: 39 / Avg: 69.97 / Max: 77
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 On 512 AVX-512 On AVX-512 Off 40 80 120 160 200 Min: 12.2 / Avg: 160.45 / Max: 196.55 Min: 12.19 / Avg: 164.43 / Max: 192.71 Min: 6.36 / Avg: 168.19 / Max: 198.49
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On 512 AVX-512 On AVX-512 Off 900 1800 2700 3600 4500 Min: 4700 / Avg: 4801.05 / Max: 5300 Min: 4700 / Avg: 4791.45 / Max: 5300 Min: 4700 / Avg: 4773.18 / Max: 5303
TensorFlow Device: CPU - Batch Size: 64 - Model: AlexNet OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: AlexNet AVX-512 On 512 AVX-512 On AVX-512 Off 0.1933 0.3866 0.5799 0.7732 0.9665 0.859 0.833 0.614
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 71.4 / Max: 84 Min: 39 / Avg: 79.12 / Max: 100 Min: 41 / Avg: 79.73 / Max: 100
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.62 / Avg: 174.55 / Max: 197.59 Min: 12.14 / Avg: 189.26 / Max: 231.43 Min: 12.4 / Avg: 189.43 / Max: 229.65
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 Off AVX-512 On 512 900 1800 2700 3600 4500 Min: 3549 / Avg: 4765.25 / Max: 5310 Min: 4700 / Avg: 4765.23 / Max: 5300 Min: 3424 / Avg: 4756.76 / Max: 5300
TensorFlow Device: CPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: ResNet-50 AVX-512 On 512 AVX-512 On AVX-512 Off 0.0261 0.0522 0.0783 0.1044 0.1305 0.116 0.115 0.071
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 73.93 / Max: 88 Min: 38 / Avg: 86.57 / Max: 100 Min: 40 / Avg: 87.14 / Max: 100
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.51 / Avg: 175.98 / Max: 245.02 Min: 12.02 / Avg: 208.44 / Max: 258.78 Min: 12.6 / Avg: 210.35 / Max: 256.26
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4743.38 / Max: 5300 Min: 3431 / Avg: 4653.57 / Max: 5300 Min: 3448 / Avg: 4638.56 / Max: 5309
TensorFlow Device: CPU - Batch Size: 64 - Model: VGG-16 OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: VGG-16 AVX-512 On 512 AVX-512 On AVX-512 Off 0.0095 0.019 0.0285 0.038 0.0475 0.042 0.042 0.035
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 38 / Avg: 70.7 / Max: 82 Min: 38 / Avg: 76.66 / Max: 93 Min: 39 / Avg: 76.91 / Max: 95
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.6 / Avg: 172.16 / Max: 189.69 Min: 12.39 / Avg: 179.76 / Max: 202.8 Min: 6.52 / Avg: 180.79 / Max: 201.41
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 Off AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4784.96 / Max: 5300 Min: 4700 / Avg: 4768.78 / Max: 5300 Min: 4700 / Avg: 4768.38 / Max: 5300
TensorFlow Device: CPU - Batch Size: 32 - Model: GoogLeNet OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: GoogLeNet AVX-512 On AVX-512 On 512 AVX-512 Off 0.0803 0.1606 0.2409 0.3212 0.4015 0.357 0.356 0.212
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 On AVX-512 Off AVX-512 On 512 15 30 45 60 75 Min: 39 / Avg: 64.95 / Max: 75 Min: 39 / Avg: 65.93 / Max: 74 Min: 39 / Avg: 66.99 / Max: 77
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 On AVX-512 On 512 AVX-512 Off 30 60 90 120 150 Min: 12.33 / Avg: 153.27 / Max: 183.98 Min: 12.25 / Avg: 153.32 / Max: 183.15 Min: 12.42 / Avg: 159.17 / Max: 185.93
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On 512 AVX-512 Off AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4812.35 / Max: 5300 Min: 4700 / Avg: 4812.15 / Max: 5300 Min: 4700 / Avg: 4809.19 / Max: 5302
TensorFlow Device: CPU - Batch Size: 32 - Model: AlexNet OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: AlexNet AVX-512 On 512 AVX-512 On AVX-512 Off 0.1663 0.3326 0.4989 0.6652 0.8315 0.739 0.731 0.552
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 70.59 / Max: 82 Min: 39 / Avg: 77.48 / Max: 95 Min: 40 / Avg: 79.09 / Max: 100
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.39 / Avg: 172.96 / Max: 195.6 Min: 12.15 / Avg: 184.01 / Max: 210.17 Min: 12.27 / Avg: 184.03 / Max: 209.54
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On 512 AVX-512 On AVX-512 Off 900 1800 2700 3600 4500 Min: 4700 / Avg: 4782.96 / Max: 5300 Min: 4700 / Avg: 4773.71 / Max: 5300 Min: 4671 / Avg: 4771.11 / Max: 5300
TensorFlow Device: CPU - Batch Size: 32 - Model: ResNet-50 OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: ResNet-50 AVX-512 On 512 AVX-512 On AVX-512 Off 0.0261 0.0522 0.0783 0.1044 0.1305 0.116 0.115 0.071
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 73.18 / Max: 82 Min: 39 / Avg: 85.46 / Max: 100 Min: 40 / Avg: 85.99 / Max: 100
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.49 / Avg: 174.26 / Max: 233.2 Min: 12.29 / Avg: 202.82 / Max: 256.86 Min: 12.4 / Avg: 203.74 / Max: 255.04
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4747.94 / Max: 5300 Min: 3450 / Avg: 4685.15 / Max: 5302 Min: 3437 / Avg: 4669.85 / Max: 5300
TensorFlow Device: CPU - Batch Size: 32 - Model: VGG-16 OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: VGG-16 AVX-512 On 512 AVX-512 On AVX-512 Off 0.0092 0.0184 0.0276 0.0368 0.046 0.041 0.041 0.034
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 38 / Avg: 69.01 / Max: 78 Min: 39 / Avg: 72.15 / Max: 91 Min: 38 / Avg: 72.19 / Max: 93
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.53 / Avg: 165.22 / Max: 190.81 Min: 12.27 / Avg: 167.07 / Max: 202.74 Min: 12.24 / Avg: 168.34 / Max: 205.66
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 On 512 AVX-512 Off 900 1800 2700 3600 4500 Min: 4700 / Avg: 4808.91 / Max: 5300 Min: 4700 / Avg: 4798.4 / Max: 5298 Min: 4700 / Avg: 4793.76 / Max: 5300
TensorFlow Device: CPU - Batch Size: 16 - Model: GoogLeNet OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: GoogLeNet AVX-512 On 512 AVX-512 On AVX-512 Off 0.0853 0.1706 0.2559 0.3412 0.4265 0.379 0.379 0.219
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 On AVX-512 On 512 AVX-512 Off 14 28 42 56 70 Min: 40 / Avg: 61.85 / Max: 71 Min: 39 / Avg: 62.73 / Max: 74 Min: 39 / Avg: 64.1 / Max: 73
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 On AVX-512 On 512 AVX-512 Off 30 60 90 120 150 Min: 12.38 / Avg: 141.92 / Max: 176.87 Min: 12.22 / Avg: 142.65 / Max: 174.16 Min: 6.49 / Avg: 147.48 / Max: 178.42
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4844.17 / Max: 5301 Min: 4700 / Avg: 4841.61 / Max: 5300 Min: 4700 / Avg: 4830.58 / Max: 5302
TensorFlow Device: CPU - Batch Size: 16 - Model: AlexNet OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: AlexNet AVX-512 On 512 AVX-512 On AVX-512 Off 0.1296 0.2592 0.3888 0.5184 0.648 0.576 0.569 0.460
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 38 / Avg: 69.7 / Max: 81 Min: 39 / Avg: 75.6 / Max: 92 Min: 39 / Avg: 75.99 / Max: 90
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.59 / Avg: 170.59 / Max: 185.9 Min: 12.57 / Avg: 178.26 / Max: 201.79 Min: 12.23 / Avg: 178.47 / Max: 201.45
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4779.37 / Max: 5300 Min: 4700 / Avg: 4778.43 / Max: 5300 Min: 4700 / Avg: 4775.16 / Max: 5300
TensorFlow Device: CPU - Batch Size: 16 - Model: ResNet-50 OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: ResNet-50 AVX-512 On 512 AVX-512 On AVX-512 Off 0.0259 0.0518 0.0777 0.1036 0.1295 0.115 0.115 0.072
TensorFlow CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TensorFlow 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 30 / Avg: 71.96 / Max: 82 Min: 30 / Avg: 81.98 / Max: 100 Min: 31 / Avg: 82.6 / Max: 100
TensorFlow CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 11.86 / Avg: 171.94 / Max: 209.38 Min: 11.63 / Avg: 196.47 / Max: 246.65 Min: 11.91 / Avg: 198.07 / Max: 245.72
TensorFlow CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TensorFlow 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4753.54 / Max: 5300 Min: 3441 / Avg: 4723.13 / Max: 5300 Min: 3436 / Avg: 4719.33 / Max: 5300
TensorFlow Device: CPU - Batch Size: 16 - Model: VGG-16 OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: VGG-16 AVX-512 On 512 AVX-512 On AVX-512 Off 0.0088 0.0176 0.0264 0.0352 0.044 0.039 0.039 0.033
TNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TNN 0.3 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 13 26 39 52 65 Min: 30 / Avg: 44.53 / Max: 64 Min: 30 / Avg: 45.12 / Max: 64 Min: 32 / Avg: 46.23 / Max: 65
TNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TNN 0.3 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 12 24 36 48 60 Min: 11.84 / Avg: 31.17 / Max: 57.74 Min: 11.71 / Avg: 32.45 / Max: 58.4 Min: 11.88 / Avg: 32.54 / Max: 58.56
TNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TNN 0.3 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 On 512 AVX-512 Off 900 1800 2700 3600 4500 Min: 5099 / Avg: 5219.48 / Max: 5310 Min: 5100 / Avg: 5205.02 / Max: 5305 Min: 5100 / Avg: 5198.88 / Max: 5304
TNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TNN 0.3 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 12 24 36 48 60 Min: 31 / Avg: 48.23 / Max: 58 Min: 31 / Avg: 48.98 / Max: 58 Min: 33 / Avg: 50.06 / Max: 61
TNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TNN 0.3 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 10 20 30 40 50 Min: 11.86 / Avg: 40.46 / Max: 48.51 Min: 11.78 / Avg: 41.5 / Max: 49.92 Min: 12 / Avg: 42.41 / Max: 50.81
TNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TNN 0.3 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 On 512 AVX-512 Off 900 1800 2700 3600 4500 Min: 5100 / Avg: 5282.12 / Max: 5304 Min: 5099 / Avg: 5261.41 / Max: 5300 Min: 5100 / Avg: 5253.76 / Max: 5300
TNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TNN 0.3 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 13 26 39 52 65 Min: 33 / Avg: 51.92 / Max: 64 Min: 33 / Avg: 53.27 / Max: 64 Min: 35 / Avg: 53.49 / Max: 67
TNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TNN 0.3 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 15 30 45 60 75 Min: 11.9 / Avg: 60.65 / Max: 74.9 Min: 12.02 / Avg: 61.6 / Max: 74.53 Min: 12.01 / Avg: 62.39 / Max: 76.7
TNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TNN 0.3 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4800 / Avg: 5114.03 / Max: 5304 Min: 4800 / Avg: 5109.16 / Max: 5300 Min: 4800 / Avg: 5072.03 / Max: 5313
TNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better TNN 0.3 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 13 26 39 52 65 Min: 36 / Avg: 57.3 / Max: 67 Min: 36 / Avg: 57.79 / Max: 68 Min: 36 / Avg: 58.88 / Max: 69
TNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better TNN 0.3 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 12.19 / Avg: 81.25 / Max: 91.18 Min: 12.03 / Avg: 81.72 / Max: 91.1 Min: 11.94 / Avg: 82.77 / Max: 92.94
TNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better TNN 0.3 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4800 / Avg: 5120.83 / Max: 5304 Min: 4800 / Avg: 5103.01 / Max: 5306 Min: 4800 / Avg: 5095.33 / Max: 5300
NCNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better NCNN 20220729 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 16 32 48 64 80 Min: 40 / Avg: 65.4 / Max: 71 Min: 40 / Avg: 70.36 / Max: 80 Min: 42 / Avg: 71.88 / Max: 87
NCNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better NCNN 20220729 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.39 / Avg: 148.04 / Max: 172.75 Min: 12.52 / Avg: 163.79 / Max: 200.07 Min: 12.42 / Avg: 165.72 / Max: 234.24
NCNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better NCNN 20220729 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4724 / Avg: 4816.34 / Max: 5306 Min: 4700 / Avg: 4737.32 / Max: 5298 Min: 4700 / Avg: 4729.61 / Max: 5300
Mobile Neural Network CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Mobile Neural Network 2.1 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 38 / Avg: 78.24 / Max: 84 Min: 39 / Avg: 85.37 / Max: 95 Min: 41 / Avg: 86.3 / Max: 95
Mobile Neural Network CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Mobile Neural Network 2.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.53 / Avg: 201.43 / Max: 226.39 Min: 12.33 / Avg: 226.92 / Max: 259.77 Min: 12.18 / Avg: 228.4 / Max: 260.3
Mobile Neural Network CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Mobile Neural Network 2.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4718.12 / Max: 5300 Min: 3483 / Avg: 4653.2 / Max: 5308 Min: 3500 / Avg: 4644.38 / Max: 5300
Xmrig CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Xmrig 6.12.1 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 15 30 45 60 75 Min: 37 / Avg: 64.76 / Max: 67 Min: 38 / Avg: 65.69 / Max: 68 Min: 42 / Avg: 77.84 / Max: 79
Xmrig CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Xmrig 6.12.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.39 / Avg: 150.74 / Max: 154.51 Min: 12.39 / Avg: 154.02 / Max: 158.84 Min: 12.43 / Avg: 198.43 / Max: 204.05
Xmrig CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Xmrig 6.12.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 Off AVX-512 On 512 900 1800 2700 3600 4500 Min: 4800 / Avg: 4806.25 / Max: 5300 Min: 4800 / Avg: 4806.2 / Max: 5300 Min: 4700 / Avg: 4708.31 / Max: 5300
Xmrig Variant: Wownero - Hash Count: 1M OpenBenchmarking.org H/s Per Watt, More Is Better Xmrig 6.12.1 Variant: Wownero - Hash Count: 1M AVX-512 Off AVX-512 On AVX-512 On 512 6 12 18 24 30 27.04 26.07 20.54
Xmrig CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Xmrig 6.12.1 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 14 28 42 56 70 Min: 39 / Avg: 60.56 / Max: 63 Min: 39 / Avg: 61.9 / Max: 64 Min: 39 / Avg: 73.38 / Max: 75
Xmrig CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Xmrig 6.12.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 30 60 90 120 150 Min: 12.34 / Avg: 135.27 / Max: 150.47 Min: 12.42 / Avg: 139.26 / Max: 150.83 Min: 12.29 / Avg: 181.65 / Max: 184.85
Xmrig CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Xmrig 6.12.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 Off AVX-512 On 512 900 1800 2700 3600 4500 Min: 4800 / Avg: 4803.31 / Max: 5300 Min: 4800 / Avg: 4803.2 / Max: 5300 Min: 4700 / Avg: 4704.64 / Max: 5245
Xmrig Variant: Monero - Hash Count: 1M OpenBenchmarking.org H/s Per Watt, More Is Better Xmrig 6.12.1 Variant: Monero - Hash Count: 1M AVX-512 Off AVX-512 On AVX-512 On 512 4 8 12 16 20 16.68 16.08 12.40
Cpuminer-Opt CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 37 / Avg: 68.15 / Max: 76 Min: 39 / Avg: 77.28 / Max: 95 Min: 40 / Avg: 77.84 / Max: 95
Cpuminer-Opt CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.49 / Avg: 164.79 / Max: 203.1 Min: 12.52 / Avg: 194 / Max: 268.78 Min: 12.24 / Avg: 194.14 / Max: 277.39
Cpuminer-Opt CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4769.7 / Max: 5300 Min: 4700 / Avg: 4754.62 / Max: 5300 Min: 4700 / Avg: 4753.32 / Max: 5289
Cpuminer-Opt Algorithm: LBC, LBRY Credits OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: LBC, LBRY Credits AVX-512 On AVX-512 On 512 AVX-512 Off 90 180 270 360 450 397.33 393.49 165.49
Cpuminer-Opt CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 38 / Avg: 65.65 / Max: 71 Min: 41 / Avg: 73.88 / Max: 81 Min: 42 / Avg: 75.17 / Max: 93
Cpuminer-Opt CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 6.67 / Avg: 143.31 / Max: 195.06 Min: 12.55 / Avg: 172.45 / Max: 244.87 Min: 12.36 / Avg: 172.53 / Max: 260.03
Cpuminer-Opt CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4830.72 / Max: 5300 Min: 4700 / Avg: 4759.1 / Max: 5308 Min: 4700 / Avg: 4758.76 / Max: 5300
Cpuminer-Opt Algorithm: Skeincoin OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Skeincoin AVX-512 On 512 AVX-512 On AVX-512 Off 140 280 420 560 700 651.49 647.91 493.49
Cpuminer-Opt CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 38 / Avg: 70.52 / Max: 77 Min: 42 / Avg: 83.16 / Max: 91 Min: 40 / Avg: 84.5 / Max: 93
Cpuminer-Opt CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.31 / Avg: 169.09 / Max: 198.24 Min: 12.34 / Avg: 217.57 / Max: 263.4 Min: 12.44 / Avg: 219.64 / Max: 263.83
Cpuminer-Opt CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4759.57 / Max: 5303 Min: 4600 / Avg: 4719.95 / Max: 5301 Min: 3500 / Avg: 4700.75 / Max: 5100
Cpuminer-Opt Algorithm: Deepcoin OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Deepcoin AVX-512 Off AVX-512 On 512 AVX-512 On 13 26 39 52 65 58.94 51.80 50.76
Cpuminer-Opt Algorithm: Deepcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Deepcoin AVX-512 On 512 AVX-512 On AVX-512 Off 2K 4K 6K 8K 10K SE +/- 25.17, N = 3 SE +/- 226.60, N = 12 SE +/- 3.11, N = 3 11270.00 11148.96 9966.10 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 38 / Avg: 71.45 / Max: 78 Min: 41 / Avg: 85.18 / Max: 96 Min: 40 / Avg: 85.36 / Max: 94
Cpuminer-Opt CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.48 / Avg: 166.37 / Max: 191.48 Min: 12.63 / Avg: 211.76 / Max: 259.97 Min: 12.54 / Avg: 213.04 / Max: 259.5
Cpuminer-Opt CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4750.11 / Max: 5297 Min: 3500 / Avg: 4689.84 / Max: 5300 Min: 3500 / Avg: 4653.7 / Max: 5308
Cpuminer-Opt Algorithm: Ringcoin OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Ringcoin AVX-512 Off AVX-512 On 512 AVX-512 On 3 6 9 12 15 12.81 10.35 10.11
Cpuminer-Opt Algorithm: Ringcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Ringcoin AVX-512 On 512 AVX-512 On AVX-512 Off 500 1000 1500 2000 2500 SE +/- 16.96, N = 15 SE +/- 40.17, N = 13 SE +/- 5.83, N = 3 2190.91 2152.94 2130.49 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 38 / Avg: 70.33 / Max: 78 Min: 39 / Avg: 84.38 / Max: 96 Min: 41 / Avg: 85.1 / Max: 98
Cpuminer-Opt CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.41 / Avg: 174.56 / Max: 204.63 Min: 12.3 / Avg: 220.67 / Max: 279.05 Min: 12.53 / Avg: 225.98 / Max: 278.7
Cpuminer-Opt CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4755.84 / Max: 5300 Min: 4522 / Avg: 4667.89 / Max: 5311 Min: 4500 / Avg: 4645.86 / Max: 5300
Cpuminer-Opt Algorithm: Garlicoin OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Garlicoin AVX-512 On 512 AVX-512 On AVX-512 Off 5 10 15 20 25 19.90 19.40 13.64
Cpuminer-Opt CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 35 / Avg: 67.7 / Max: 74 Min: 39 / Avg: 80.97 / Max: 94 Min: 38 / Avg: 82.81 / Max: 93
Cpuminer-Opt CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.29 / Avg: 156.93 / Max: 187.81 Min: 12.21 / Avg: 205.74 / Max: 250.13 Min: 12.61 / Avg: 210.01 / Max: 243.37
Cpuminer-Opt CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4771.9 / Max: 5294 Min: 4650 / Avg: 4751.77 / Max: 5252 Min: 3500 / Avg: 4605.7 / Max: 5307
Cpuminer-Opt Algorithm: x25x OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: x25x AVX-512 Off AVX-512 On 512 AVX-512 On 0.5148 1.0296 1.5444 2.0592 2.574 2.288 1.847 1.846
Cpuminer-Opt Algorithm: x25x OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: x25x AVX-512 On AVX-512 On 512 AVX-512 Off 80 160 240 320 400 SE +/- 1.89, N = 3 SE +/- 7.53, N = 12 SE +/- 0.48, N = 3 387.72 379.94 359.01 -mno-avx512f 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 38 / Avg: 62.38 / Max: 71 Min: 39 / Avg: 72.79 / Max: 89 Min: 42 / Avg: 74.3 / Max: 93
Cpuminer-Opt CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.46 / Avg: 120.8 / Max: 156.32 Min: 12.3 / Avg: 158.84 / Max: 274.55 Min: 12.31 / Avg: 161.61 / Max: 277.66
Cpuminer-Opt CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4834.2 / Max: 5300 Min: 4700 / Avg: 4757.9 / Max: 5300 Min: 4700 / Avg: 4751.67 / Max: 5305
Cpuminer-Opt Algorithm: Blake-2 S OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Blake-2 S AVX-512 On 512 AVX-512 On AVX-512 Off 1200 2400 3600 4800 6000 5541.06 5427.52 3255.01
Cpuminer-Opt CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 38 / Avg: 71.08 / Max: 78 Min: 39 / Avg: 71.49 / Max: 79 Min: 40 / Avg: 82.2 / Max: 95
Cpuminer-Opt CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.44 / Avg: 165.63 / Max: 188.99 Min: 12.43 / Avg: 166.66 / Max: 190.11 Min: 12.13 / Avg: 212.02 / Max: 259.67
Cpuminer-Opt CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4762.57 / Max: 5300 Min: 4700 / Avg: 4753.83 / Max: 5300 Min: 3555 / Avg: 4644.34 / Max: 5300
Cpuminer-Opt Algorithm: Magi OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Magi AVX-512 Off AVX-512 On AVX-512 On 512 0.6158 1.2316 1.8474 2.4632 3.079 2.737 2.717 2.120
Cpuminer-Opt CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 37 / Avg: 68.83 / Max: 76 Min: 38 / Avg: 79.95 / Max: 97 Min: 39 / Avg: 80.53 / Max: 97
Cpuminer-Opt CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.36 / Avg: 159.39 / Max: 196.52 Min: 12.4 / Avg: 204.6 / Max: 277.24 Min: 12.06 / Avg: 205.9 / Max: 276.24
Cpuminer-Opt CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4766.67 / Max: 5300 Min: 3500 / Avg: 4739.94 / Max: 5312 Min: 3500 / Avg: 4739.52 / Max: 5300
Cpuminer-Opt Algorithm: Myriad-Groestl OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Myriad-Groestl AVX-512 On AVX-512 On 512 AVX-512 Off 40 80 120 160 200 198.30 197.49 101.32
Cpuminer-Opt CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 36 / Avg: 65.33 / Max: 73 Min: 38 / Avg: 73.74 / Max: 92 Min: 39 / Avg: 75.84 / Max: 93
Cpuminer-Opt CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.24 / Avg: 140.46 / Max: 186.51 Min: 12.43 / Avg: 175.6 / Max: 252.11 Min: 12.25 / Avg: 177.02 / Max: 245.52
Cpuminer-Opt CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4831.54 / Max: 5312 Min: 4700 / Avg: 4753.87 / Max: 5290 Min: 4700 / Avg: 4750.65 / Max: 5300
Cpuminer-Opt Algorithm: Quad SHA-256, Pyrite OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Quad SHA-256, Pyrite AVX-512 On AVX-512 On 512 AVX-512 Off 200 400 600 800 1000 953.89 930.90 460.38
Cpuminer-Opt CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 64.76 / Max: 73 Min: 40 / Avg: 74.89 / Max: 92 Min: 42 / Avg: 75.38 / Max: 94
Cpuminer-Opt CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.4 / Avg: 129.38 / Max: 169.44 Min: 12.41 / Avg: 169.42 / Max: 278.89 Min: 12.5 / Avg: 169.58 / Max: 237.02
Cpuminer-Opt CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4834.78 / Max: 5300 Min: 4700 / Avg: 4759.14 / Max: 5300 Min: 4700 / Avg: 4753.44 / Max: 5300
Cpuminer-Opt Algorithm: Triple SHA-256, Onecoin OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Triple SHA-256, Onecoin AVX-512 On AVX-512 On 512 AVX-512 Off 300 600 900 1200 1500 1366.28 1361.66 820.32
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 79.8 / Max: 88 Min: 41 / Avg: 83.69 / Max: 93 Min: 41 / Avg: 85.51 / Max: 95
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.39 / Avg: 211.06 / Max: 238.35 Min: 12.62 / Avg: 222.99 / Max: 258.73 Min: 12.35 / Avg: 223.11 / Max: 259.32
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4729.07 / Max: 5300 Min: 3545 / Avg: 4698.05 / Max: 5302 Min: 3500 / Avg: 4678.88 / Max: 5300
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 40 / Avg: 79.86 / Max: 87 Min: 40 / Avg: 84.09 / Max: 94 Min: 42 / Avg: 84.75 / Max: 94
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.61 / Avg: 210.67 / Max: 238.64 Min: 12.42 / Avg: 220.81 / Max: 258.47 Min: 12.38 / Avg: 222.38 / Max: 260.25
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4725.04 / Max: 5303 Min: 3500 / Avg: 4673.77 / Max: 5300 Min: 3524 / Avg: 4668.41 / Max: 5291
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 40 / Avg: 79.82 / Max: 87 Min: 41 / Avg: 83.26 / Max: 94 Min: 42 / Avg: 85.26 / Max: 95
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.3 / Avg: 210.85 / Max: 239.17 Min: 12.6 / Avg: 221.72 / Max: 257.44 Min: 12.23 / Avg: 222.53 / Max: 259.06
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4732.36 / Max: 5300 Min: 4573 / Avg: 4707.8 / Max: 5300 Min: 3500 / Avg: 4683.06 / Max: 5300
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 40 / Avg: 80.45 / Max: 88 Min: 41 / Avg: 83.9 / Max: 95 Min: 41 / Avg: 84.88 / Max: 94
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.67 / Avg: 214.52 / Max: 239.09 Min: 12.53 / Avg: 222.91 / Max: 259.24 Min: 12.32 / Avg: 225.38 / Max: 259.31
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4729.18 / Max: 5303 Min: 3500 / Avg: 4674.91 / Max: 5181 Min: 3500 / Avg: 4672.78 / Max: 5309
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 80.93 / Max: 87 Min: 40 / Avg: 84.18 / Max: 95 Min: 41 / Avg: 85.38 / Max: 95
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.57 / Avg: 214.65 / Max: 239.45 Min: 6.51 / Avg: 222.96 / Max: 260.16 Min: 12.72 / Avg: 223.66 / Max: 258.29
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4726.9 / Max: 5300 Min: 3500 / Avg: 4678.34 / Max: 5300 Min: 3500 / Avg: 4667.49 / Max: 5300
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU AVX-512 On 512 AVX-512 On AVX-512 Off 700 1400 2100 2800 3500 SE +/- 89.39, N = 15 SE +/- 3.05, N = 3 SE +/- 1.82, N = 3 3073.17 3088.89 3270.55 MIN: 2922.72 MIN: 3071.02 -mno-avx512f - MIN: 3260.73 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 33 / Avg: 78.87 / Max: 87 Min: 38 / Avg: 84.54 / Max: 94 Min: 37 / Avg: 84.81 / Max: 94
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.16 / Avg: 214.34 / Max: 239.55 Min: 12.16 / Avg: 224.81 / Max: 259.66 Min: 12.36 / Avg: 225.11 / Max: 259.84
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4733.47 / Max: 5312 Min: 4649 / Avg: 4725.14 / Max: 5300 Min: 3500 / Avg: 4710.26 / Max: 5301
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 On AVX-512 On 512 15 30 45 60 75 Min: 38 / Avg: 63.03 / Max: 77 Min: 39 / Avg: 64.2 / Max: 78
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.43 / Avg: 143.59 / Max: 212.38 Min: 12.45 / Avg: 147.95 / Max: 221.19
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4826.46 / Max: 5302 Min: 4700 / Avg: 4807.8 / Max: 5221
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 14 28 42 56 70 Min: 36 / Avg: 60.25 / Max: 74 Min: 38 / Avg: 63.12 / Max: 74 Min: 38 / Avg: 64.16 / Max: 75
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.3 / Avg: 141.01 / Max: 214.89 Min: 12.46 / Avg: 151.73 / Max: 216.95 Min: 12.28 / Avg: 152.81 / Max: 217.07
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4857.73 / Max: 5270 Min: 4700 / Avg: 4831.27 / Max: 5300 Min: 4700 / Avg: 4824.57 / Max: 5300
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 15 30 45 60 75 Min: 32 / Avg: 54.62 / Max: 65 Min: 38 / Avg: 62.72 / Max: 76 Min: 39 / Avg: 63.95 / Max: 76
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.06 / Avg: 127.79 / Max: 179.3 Min: 12.37 / Avg: 152.68 / Max: 217.03 Min: 12.48 / Avg: 154.47 / Max: 218.24
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4800 / Avg: 4883.85 / Max: 5307 Min: 4700 / Avg: 4817.98 / Max: 5300 Min: 4700 / Avg: 4805.17 / Max: 5300
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 On AVX-512 On 512 15 30 45 60 75 Min: 37 / Avg: 62.76 / Max: 75 Min: 38 / Avg: 63.8 / Max: 78
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.19 / Avg: 145.98 / Max: 216.11 Min: 12.44 / Avg: 147.87 / Max: 217.33
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4840.23 / Max: 5303 Min: 4700 / Avg: 4825.21 / Max: 5297
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 15 30 45 60 75 Min: 35 / Avg: 56.98 / Max: 70 Min: 38 / Avg: 61.41 / Max: 78 Min: 38 / Avg: 61.88 / Max: 79
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.18 / Avg: 117.33 / Max: 206.36 Min: 12.26 / Avg: 135.98 / Max: 211.15 Min: 12.46 / Avg: 138.07 / Max: 211.6
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4753 / Avg: 4904.44 / Max: 5300 Min: 4700 / Avg: 4847.06 / Max: 5310 Min: 4700 / Avg: 4828.02 / Max: 5149
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 14 28 42 56 70 Min: 34 / Avg: 54.35 / Max: 70 Min: 39 / Avg: 59.67 / Max: 73 Min: 40 / Avg: 59.91 / Max: 74
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 11.99 / Avg: 110.48 / Max: 208.04 Min: 12.27 / Avg: 140.62 / Max: 220.8 Min: 12.41 / Avg: 142.22 / Max: 219.9
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4789 / Avg: 4907.45 / Max: 5306 Min: 4700 / Avg: 4835.06 / Max: 5300 Min: 4700 / Avg: 4834.06 / Max: 5301
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 On AVX-512 On 512 15 30 45 60 75 Min: 39 / Avg: 68.31 / Max: 79 Min: 41 / Avg: 68.97 / Max: 80
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.55 / Avg: 164.37 / Max: 212.69 Min: 12.64 / Avg: 166.08 / Max: 212.18
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4799.03 / Max: 5300 Min: 4700 / Avg: 4796.12 / Max: 5300
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 38 / Avg: 67.95 / Max: 80 Min: 39 / Avg: 75.8 / Max: 90 Min: 40 / Avg: 76.38 / Max: 90
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.34 / Avg: 167.49 / Max: 223.12 Min: 12.39 / Avg: 197.09 / Max: 259.67 Min: 12.45 / Avg: 197.65 / Max: 260.01
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4797.83 / Max: 5306 Min: 4700 / Avg: 4794.07 / Max: 5308 Min: 4700 / Avg: 4792.74 / Max: 5301
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 31 / Avg: 66.53 / Max: 80 Min: 34 / Avg: 71.48 / Max: 87 Min: 35 / Avg: 71.51 / Max: 88
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 11.91 / Avg: 174.01 / Max: 231.27 Min: 12.26 / Avg: 185.14 / Max: 254.54 Min: 12.2 / Avg: 187.14 / Max: 256.22
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4801.83 / Max: 5299 Min: 4700 / Avg: 4798.47 / Max: 5302 Min: 4700 / Avg: 4796.3 / Max: 5300
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 On AVX-512 On 512 14 28 42 56 70 Min: 34 / Avg: 49.81 / Max: 71 Min: 36 / Avg: 53.02 / Max: 71
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.22 / Avg: 97.45 / Max: 213.88 Min: 12.08 / Avg: 97.63 / Max: 215.11
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4987.32 / Max: 5308 Min: 4700 / Avg: 4940.08 / Max: 5300
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 15 30 45 60 75 Min: 35 / Avg: 52.66 / Max: 74 Min: 35 / Avg: 53.89 / Max: 78 Min: 36 / Avg: 55.78 / Max: 79
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.03 / Avg: 101.88 / Max: 232.56 Min: 12.2 / Avg: 108.52 / Max: 242.72 Min: 12.27 / Avg: 108.7 / Max: 242.03
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 On 512 AVX-512 Off 900 1800 2700 3600 4500 Min: 4700 / Avg: 4984.13 / Max: 5309 Min: 4700 / Avg: 4983.09 / Max: 5312 Min: 4700 / Avg: 4953.98 / Max: 5300
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 16 32 48 64 80 Min: 34 / Avg: 51.76 / Max: 71 Min: 39 / Avg: 56.03 / Max: 81 Min: 39 / Avg: 58.3 / Max: 82
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.12 / Avg: 99.49 / Max: 224.72 Min: 12.32 / Avg: 109.91 / Max: 245.61 Min: 12.27 / Avg: 110.93 / Max: 247.56
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 Off AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4987.92 / Max: 5312 Min: 4721 / Avg: 4966.06 / Max: 5300 Min: 4700 / Avg: 4931.38 / Max: 5267
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 74.22 / Max: 90 Min: 39 / Avg: 74.99 / Max: 90
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.48 / Avg: 187.07 / Max: 255.81 Min: 12.43 / Avg: 188.15 / Max: 256.3
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4772.18 / Max: 5298 Min: 4700 / Avg: 4768.42 / Max: 5101
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 37 / Avg: 68.37 / Max: 81 Min: 40 / Avg: 76.51 / Max: 95 Min: 39 / Avg: 76.57 / Max: 97
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.49 / Avg: 157.07 / Max: 224.86 Min: 12.33 / Avg: 182.51 / Max: 273 Min: 12.23 / Avg: 183.19 / Max: 271.84
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4797.64 / Max: 5309 Min: 3426 / Avg: 4750.48 / Max: 5310 Min: 3430 / Avg: 4699.55 / Max: 5139
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 32 / Avg: 63.64 / Max: 79 Min: 36 / Avg: 73.12 / Max: 90 Min: 38 / Avg: 73.45 / Max: 90
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12 / Avg: 154.65 / Max: 222.78 Min: 12.16 / Avg: 185.77 / Max: 260.53 Min: 12.31 / Avg: 186.16 / Max: 260.32
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4788.28 / Max: 5100 Min: 4700 / Avg: 4787.63 / Max: 5228 Min: 4700 / Avg: 4787.19 / Max: 5300
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 On 512 AVX-512 On 15 30 45 60 75 Min: 36 / Avg: 59.45 / Max: 76 Min: 36 / Avg: 59.56 / Max: 76
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.11 / Avg: 126.88 / Max: 209.9 Min: 11.99 / Avg: 128 / Max: 209.14
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4894.72 / Max: 5300 Min: 4700 / Avg: 4872.99 / Max: 5300
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 13 26 39 52 65 Min: 36 / Avg: 50.61 / Max: 60 Min: 38 / Avg: 53.03 / Max: 64 Min: 37 / Avg: 53.8 / Max: 65
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 30 60 90 120 150 Min: 12.03 / Avg: 95.8 / Max: 154.46 Min: 12.34 / Avg: 109.26 / Max: 184.33 Min: 12.31 / Avg: 109.54 / Max: 183.13
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4800 / Avg: 4940.32 / Max: 5300 Min: 4700 / Avg: 4892.18 / Max: 5300 Min: 4700 / Avg: 4884.79 / Max: 5300
oneDNN CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.7 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 13 26 39 52 65 Min: 39 / Avg: 54 / Max: 63 Min: 40 / Avg: 56.59 / Max: 68 Min: 41 / Avg: 57.77 / Max: 69
oneDNN CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 30 60 90 120 150 Min: 12.3 / Avg: 101.38 / Max: 166.77 Min: 12.33 / Avg: 114.74 / Max: 188.88 Min: 12.56 / Avg: 116.37 / Max: 189.01
oneDNN CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.7 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4800 / Avg: 4945.85 / Max: 5300 Min: 4700 / Avg: 4896.54 / Max: 5300 Min: 4700 / Avg: 4879.13 / Max: 5300
OSPRay Studio CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 40 / Avg: 80.67 / Max: 84 Min: 42 / Avg: 88.64 / Max: 93 Min: 43 / Avg: 88.73 / Max: 96
OSPRay Studio CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.35 / Avg: 210.54 / Max: 220.82 Min: 12.63 / Avg: 233.36 / Max: 267.63 Min: 12.76 / Avg: 236.54 / Max: 265.22
OSPRay Studio CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4722.23 / Max: 5309 Min: 4557 / Avg: 4641.27 / Max: 5300 Min: 4550 / Avg: 4626.21 / Max: 5300
OSPRay Studio CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 78.83 / Max: 83 Min: 41 / Avg: 87.07 / Max: 91 Min: 41 / Avg: 87.32 / Max: 93
OSPRay Studio CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.41 / Avg: 203.49 / Max: 220.04 Min: 12.75 / Avg: 230.35 / Max: 267.14 Min: 12.74 / Avg: 232.51 / Max: 265.53
OSPRay Studio CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4740.31 / Max: 5310 Min: 4564 / Avg: 4689.08 / Max: 5307 Min: 3500 / Avg: 4671.61 / Max: 5300
OSPRay Studio CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 40 / Avg: 76.25 / Max: 85 Min: 41 / Avg: 87.29 / Max: 92 Min: 41 / Avg: 87.49 / Max: 93
OSPRay Studio CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.56 / Avg: 187.54 / Max: 219.01 Min: 12.82 / Avg: 227.75 / Max: 264.86 Min: 12.61 / Avg: 232.9 / Max: 264
OSPRay Studio CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4785.08 / Max: 5300 Min: 4564 / Avg: 4690.88 / Max: 5300 Min: 3500 / Avg: 4665.37 / Max: 5300
OSPRay Studio CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 40 / Avg: 76.99 / Max: 83 Min: 41 / Avg: 84.31 / Max: 94 Min: 42 / Avg: 85.88 / Max: 91
OSPRay Studio CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.3 / Avg: 191.08 / Max: 219.81 Min: 12.69 / Avg: 217.88 / Max: 264.37 Min: 12.56 / Avg: 219.94 / Max: 267.67
OSPRay Studio CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4778.13 / Max: 5310 Min: 3465 / Avg: 4730.1 / Max: 5300 Min: 4570 / Avg: 4723.71 / Max: 5300
OSPRay Studio CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 40 / Avg: 78.9 / Max: 84 Min: 42 / Avg: 86.55 / Max: 92 Min: 41 / Avg: 86.58 / Max: 95
OSPRay Studio CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.34 / Avg: 199.23 / Max: 219.6 Min: 6.41 / Avg: 226.74 / Max: 265.64 Min: 12.66 / Avg: 226.89 / Max: 265.02
OSPRay Studio CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4753.09 / Max: 5326 Min: 4561 / Avg: 4700.89 / Max: 5300 Min: 4570 / Avg: 4692.8 / Max: 5300
OSPRay Studio CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 78.14 / Max: 88 Min: 41 / Avg: 86.94 / Max: 91 Min: 42 / Avg: 87.08 / Max: 93
OSPRay Studio CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.47 / Avg: 198.07 / Max: 218.51 Min: 12.48 / Avg: 225.22 / Max: 265.65 Min: 12.71 / Avg: 228.53 / Max: 263.37
OSPRay Studio CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4753.65 / Max: 5300 Min: 4576 / Avg: 4701.44 / Max: 5300 Min: 4571 / Avg: 4680.45 / Max: 5300
OSPRay Studio CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 40 / Avg: 80.21 / Max: 84 Min: 42 / Avg: 88.05 / Max: 96 Min: 41 / Avg: 88.34 / Max: 94
OSPRay Studio CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.51 / Avg: 209.79 / Max: 224.27 Min: 12.78 / Avg: 234.22 / Max: 270.6 Min: 12.53 / Avg: 235.59 / Max: 266.57
OSPRay Studio CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4726.06 / Max: 5300 Min: 4546 / Avg: 4639.07 / Max: 5300 Min: 3450 / Avg: 4627.77 / Max: 5304
OSPRay Studio CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 40 / Avg: 79.03 / Max: 84 Min: 41 / Avg: 86.52 / Max: 93 Min: 42 / Avg: 87.16 / Max: 95
OSPRay Studio CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.44 / Avg: 201.82 / Max: 223.16 Min: 12.72 / Avg: 226.55 / Max: 269.83 Min: 12.63 / Avg: 229.98 / Max: 273.69
OSPRay Studio CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4747.54 / Max: 5300 Min: 3477 / Avg: 4691.4 / Max: 5300 Min: 3446 / Avg: 4670.53 / Max: 5310
OSPRay Studio CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 41 / Avg: 79.36 / Max: 84 Min: 40 / Avg: 87.2 / Max: 96 Min: 41 / Avg: 87.44 / Max: 93
OSPRay Studio CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.21 / Avg: 203.21 / Max: 220.23 Min: 12.57 / Avg: 231.83 / Max: 266.17 Min: 12.49 / Avg: 232 / Max: 270.49
OSPRay Studio CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4745.23 / Max: 5313 Min: 4570 / Avg: 4680.41 / Max: 5300 Min: 3461 / Avg: 4676.99 / Max: 5300
OSPRay Studio CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 40 / Avg: 76.62 / Max: 83 Min: 41 / Avg: 84.26 / Max: 91 Min: 42 / Avg: 84.38 / Max: 94
OSPRay Studio CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.43 / Avg: 187.52 / Max: 220.7 Min: 12.67 / Avg: 212.47 / Max: 268.13 Min: 12.52 / Avg: 215.79 / Max: 268.64
OSPRay Studio CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4791.69 / Max: 5308 Min: 4600 / Avg: 4754.09 / Max: 5300 Min: 3426 / Avg: 4746.5 / Max: 5300
OSPRay Studio CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 40 / Avg: 78.59 / Max: 84 Min: 41 / Avg: 86.12 / Max: 95 Min: 41 / Avg: 86.33 / Max: 94
OSPRay Studio CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.27 / Avg: 197.1 / Max: 221.49 Min: 12.59 / Avg: 223.34 / Max: 269.08 Min: 12.54 / Avg: 224.93 / Max: 265.94
OSPRay Studio CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4759.97 / Max: 5300 Min: 4567 / Avg: 4716.26 / Max: 5300 Min: 3453 / Avg: 4694.88 / Max: 5301
OSPRay Studio CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 38 / Avg: 78.1 / Max: 84 Min: 38 / Avg: 85.39 / Max: 96 Min: 38 / Avg: 86.37 / Max: 93
OSPRay Studio CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.2 / Avg: 196.81 / Max: 219.8 Min: 12.45 / Avg: 224.9 / Max: 263.86 Min: 12.47 / Avg: 227.36 / Max: 267.89
OSPRay Studio CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4759.8 / Max: 5300 Min: 3500 / Avg: 4719.74 / Max: 5310 Min: 4572 / Avg: 4702.26 / Max: 5300
OSPRay CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 81.5 / Max: 88 Min: 40 / Avg: 82.87 / Max: 95 Min: 40 / Avg: 82.89 / Max: 92
OSPRay CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor AVX-512 On AVX-512 On 512 AVX-512 Off 50 100 150 200 250 Min: 12.35 / Avg: 206.8 / Max: 279.53 Min: 12.5 / Avg: 207.18 / Max: 278.74 Min: 12.34 / Avg: 207.64 / Max: 238.67
OSPRay CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4762.5 / Max: 5263 Min: 4500 / Avg: 4677.43 / Max: 5310 Min: 3500 / Avg: 4675.68 / Max: 5300
OSPRay Benchmark: particle_volume/pathtracer/real_time OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: particle_volume/pathtracer/real_time AVX-512 On 512 AVX-512 On AVX-512 Off 0.1888 0.3776 0.5664 0.7552 0.944 0.839 0.837 0.794
OSPRay CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 40 / Avg: 76.45 / Max: 82 Min: 41 / Avg: 81.84 / Max: 91 Min: 41 / Avg: 82.31 / Max: 91
OSPRay CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.9 / Avg: 184.06 / Max: 210.42 Min: 12.49 / Avg: 198.08 / Max: 238.61 Min: 12.55 / Avg: 198.87 / Max: 240.3
OSPRay CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 On 512 AVX-512 Off 900 1800 2700 3600 4500 Min: 4700 / Avg: 4769.71 / Max: 5300 Min: 4700 / Avg: 4769.33 / Max: 5198 Min: 4700 / Avg: 4763.75 / Max: 5305
OSPRay Benchmark: particle_volume/scivis/real_time OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: particle_volume/scivis/real_time AVX-512 Off AVX-512 On 512 AVX-512 On 0.0072 0.0144 0.0216 0.0288 0.036 0.032 0.025 0.025
OSPRay CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 41 / Avg: 79.36 / Max: 82 Min: 41 / Avg: 88.39 / Max: 92 Min: 42 / Avg: 88.47 / Max: 92
OSPRay CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.62 / Avg: 203.23 / Max: 210.28 Min: 12.57 / Avg: 231.69 / Max: 239.43 Min: 12.62 / Avg: 232.11 / Max: 240.01
OSPRay CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4711.34 / Max: 5300 Min: 4656 / Avg: 4708 / Max: 5311 Min: 4652 / Avg: 4706.83 / Max: 5300
OSPRay Benchmark: particle_volume/ao/real_time OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: particle_volume/ao/real_time AVX-512 Off AVX-512 On 512 AVX-512 On 0.0068 0.0136 0.0204 0.0272 0.034 0.030 0.021 0.021
OSPRay CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 40 / Avg: 82.51 / Max: 87 Min: 41 / Avg: 87.66 / Max: 96 Min: 42 / Avg: 87.79 / Max: 94
OSPRay CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.55 / Avg: 216.29 / Max: 232.17 Min: 12.57 / Avg: 236.09 / Max: 283.94 Min: 12.54 / Avg: 237.53 / Max: 280.23
OSPRay CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4729.58 / Max: 5300 Min: 4521 / Avg: 4617.05 / Max: 5300 Min: 3400 / Avg: 4599.64 / Max: 5301
OSPRay Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time AVX-512 On 512 AVX-512 On AVX-512 Off 0.0052 0.0104 0.0156 0.0208 0.026 0.023 0.023 0.019
OSPRay CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 39 / Avg: 77.75 / Max: 82 Min: 41 / Avg: 85.73 / Max: 94 Min: 41 / Avg: 86.81 / Max: 93
OSPRay CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.35 / Avg: 198.29 / Max: 211.32 Min: 12.57 / Avg: 234.34 / Max: 264.33 Min: 12.49 / Avg: 236.7 / Max: 264.63
OSPRay CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4727.24 / Max: 5300 Min: 3500 / Avg: 4674.77 / Max: 5300 Min: 3461 / Avg: 4640.61 / Max: 5300
OSPRay Benchmark: gravity_spheres_volume/dim_512/scivis/real_time OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time AVX-512 On 512 AVX-512 On AVX-512 Off 0.0043 0.0086 0.0129 0.0172 0.0215 0.019 0.018 0.014
OSPRay CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OSPRay 2.10 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 33 / Avg: 77.15 / Max: 82 Min: 32 / Avg: 84.89 / Max: 94 Min: 32 / Avg: 85.49 / Max: 94
OSPRay CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.22 / Avg: 198.05 / Max: 219.36 Min: 12.22 / Avg: 235.26 / Max: 262.25 Min: 12.34 / Avg: 237.72 / Max: 263.57
OSPRay CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OSPRay 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4729.36 / Max: 5300 Min: 3422 / Avg: 4664.09 / Max: 5300 Min: 3419 / Avg: 4650.07 / Max: 5300
OSPRay Benchmark: gravity_spheres_volume/dim_512/ao/real_time OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/ao/real_time AVX-512 On 512 AVX-512 On AVX-512 Off 0.0043 0.0086 0.0129 0.0172 0.0215 0.019 0.019 0.014
Intel Open Image Denoise CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Intel Open Image Denoise 1.4.0 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 33 / Avg: 66.75 / Max: 90 Min: 33 / Avg: 68.63 / Max: 93 Min: 33 / Avg: 68.65 / Max: 93
Intel Open Image Denoise CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Intel Open Image Denoise 1.4.0 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 11.72 / Avg: 146.54 / Max: 222.43 Min: 11.75 / Avg: 152.84 / Max: 237.4 Min: 11.76 / Avg: 152.88 / Max: 234.36
Intel Open Image Denoise CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Intel Open Image Denoise 1.4.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 Off AVX-512 On 512 900 1800 2700 3600 4500 Min: 4119 / Avg: 4870.24 / Max: 5313 Min: 4700 / Avg: 4858.52 / Max: 5300 Min: 3603 / Avg: 4840.9 / Max: 5310
Intel Open Image Denoise Run: RTLightmap.hdr.4096x4096 OpenBenchmarking.org Images / Sec Per Watt, More Is Better Intel Open Image Denoise 1.4.0 Run: RTLightmap.hdr.4096x4096 AVX-512 On 512 AVX-512 Off AVX-512 On 0.0002 0.0004 0.0006 0.0008 0.001 0.001 0.001 0.001
Intel Open Image Denoise CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Intel Open Image Denoise 1.4.0 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 34 / Avg: 66 / Max: 91 Min: 34 / Avg: 67.93 / Max: 95 Min: 34 / Avg: 68.43 / Max: 94
Intel Open Image Denoise CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Intel Open Image Denoise 1.4.0 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 11.88 / Avg: 141.62 / Max: 221.74 Min: 11.99 / Avg: 150.51 / Max: 235.87 Min: 11.99 / Avg: 150.87 / Max: 235.4
Intel Open Image Denoise CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Intel Open Image Denoise 1.4.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 Off AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4882.39 / Max: 5312 Min: 4700 / Avg: 4875.18 / Max: 5300 Min: 4700 / Avg: 4857.45 / Max: 5305
Intel Open Image Denoise Run: RT.ldr_alb_nrm.3840x2160 OpenBenchmarking.org Images / Sec Per Watt, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.ldr_alb_nrm.3840x2160 AVX-512 On 512 AVX-512 Off AVX-512 On 0.0007 0.0014 0.0021 0.0028 0.0035 0.003 0.003 0.003
Intel Open Image Denoise CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Intel Open Image Denoise 1.4.0 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 36 / Avg: 65.5 / Max: 88 Min: 37 / Avg: 69 / Max: 95 Min: 37 / Avg: 69.29 / Max: 95
Intel Open Image Denoise CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Intel Open Image Denoise 1.4.0 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.01 / Avg: 141.33 / Max: 222.42 Min: 12.03 / Avg: 150.73 / Max: 237.19 Min: 12.06 / Avg: 150.88 / Max: 237.41
Intel Open Image Denoise CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Intel Open Image Denoise 1.4.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4865.94 / Max: 5286 Min: 3571 / Avg: 4858.54 / Max: 5310 Min: 4700 / Avg: 4851.22 / Max: 5300
Intel Open Image Denoise Run: RT.hdr_alb_nrm.3840x2160 OpenBenchmarking.org Images / Sec Per Watt, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.hdr_alb_nrm.3840x2160 AVX-512 On 512 AVX-512 Off AVX-512 On 0.0007 0.0014 0.0021 0.0028 0.0035 0.003 0.003 0.003
OpenVKL CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenVKL 1.0 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 40 / Avg: 72.95 / Max: 82 Min: 41 / Avg: 79.44 / Max: 92 Min: 41 / Avg: 79.75 / Max: 95
OpenVKL CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenVKL 1.0 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.4 / Avg: 165.67 / Max: 222.7 Min: 12.58 / Avg: 193.56 / Max: 269.81 Min: 12.63 / Avg: 193.7 / Max: 270.03
OpenVKL CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenVKL 1.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4841.21 / Max: 5326 Min: 3472 / Avg: 4818.52 / Max: 5304 Min: 3451 / Avg: 4805.24 / Max: 5300
OpenVKL Benchmark: vklBenchmark ISPC OpenBenchmarking.org Items / Sec Per Watt, More Is Better OpenVKL 1.0 Benchmark: vklBenchmark ISPC AVX-512 On AVX-512 On 512 AVX-512 Off 0.1314 0.2628 0.3942 0.5256 0.657 0.584 0.578 0.525
Embree CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Embree 3.13 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 39 / Avg: 74.03 / Max: 79 Min: 40 / Avg: 82.5 / Max: 90 Min: 40 / Avg: 82.82 / Max: 90
Embree CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Embree 3.13 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.19 / Avg: 190.79 / Max: 210.6 Min: 12.58 / Avg: 230.62 / Max: 256.43 Min: 12.42 / Avg: 231.69 / Max: 256.24
Embree CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Embree 3.13 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 On 512 AVX-512 Off 900 1800 2700 3600 4500 Min: 4700 / Avg: 4747.38 / Max: 5300 Min: 4700 / Avg: 4741.65 / Max: 5192 Min: 4700 / Avg: 4736.93 / Max: 5274
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown AVX-512 Off AVX-512 On 512 AVX-512 On 0.0164 0.0328 0.0492 0.0656 0.082 0.073 0.063 0.063
Embree CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Embree 3.13 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 16 32 48 64 80 Min: 39 / Avg: 68.47 / Max: 75 Min: 40 / Avg: 74.66 / Max: 84 Min: 40 / Avg: 74.96 / Max: 83
Embree CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Embree 3.13 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.35 / Avg: 158.11 / Max: 203.56 Min: 12.36 / Avg: 186.7 / Max: 237.13 Min: 12.47 / Avg: 188.21 / Max: 237.49
Embree CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Embree 3.13 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 Off AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4808.92 / Max: 5300 Min: 4700 / Avg: 4803.53 / Max: 5224 Min: 4700 / Avg: 4798.01 / Max: 5300
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Obj AVX-512 Off AVX-512 On AVX-512 On 512 0.02 0.04 0.06 0.08 0.1 0.089 0.077 0.076
Embree CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Embree 3.13 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 16 32 48 64 80 Min: 37 / Avg: 69.41 / Max: 75 Min: 38 / Avg: 76.74 / Max: 85 Min: 39 / Avg: 76.82 / Max: 84
Embree CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Embree 3.13 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.16 / Avg: 176.35 / Max: 205.68 Min: 12.42 / Avg: 212.61 / Max: 240.22 Min: 12.6 / Avg: 212.97 / Max: 241.03
Embree CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Embree 3.13 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4765.12 / Max: 5300 Min: 4700 / Avg: 4748.06 / Max: 5300 Min: 4700 / Avg: 4746.84 / Max: 5101
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon AVX-512 Off AVX-512 On AVX-512 On 512 0.0203 0.0406 0.0609 0.0812 0.1015 0.090 0.078 0.077
dav1d CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better dav1d 1.0 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 15 30 45 60 75 Min: 36 / Avg: 62.16 / Max: 72 Min: 38 / Avg: 68.94 / Max: 81 Min: 38 / Avg: 69.14 / Max: 80
dav1d CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better dav1d 1.0 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.37 / Avg: 147.97 / Max: 189.99 Min: 12.44 / Avg: 176.58 / Max: 231.88 Min: 12.28 / Avg: 176.77 / Max: 228.64
dav1d CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better dav1d 1.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4850.01 / Max: 5296 Min: 4700 / Avg: 4794.56 / Max: 5310 Min: 4700 / Avg: 4791.38 / Max: 5299
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS Per Watt, More Is Better dav1d 1.0 Video Input: Chimera 1080p 10-bit AVX-512 Off AVX-512 On AVX-512 On 512 0.7407 1.4814 2.2221 2.9628 3.7035 3.292 2.893 2.699
dav1d CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better dav1d 1.0 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 16 32 48 64 80 Min: 36 / Avg: 62.58 / Max: 73 Min: 39 / Avg: 69.68 / Max: 86 Min: 38 / Avg: 69.91 / Max: 85
dav1d CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better dav1d 1.0 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.15 / Avg: 144.63 / Max: 196.82 Min: 12.51 / Avg: 174.06 / Max: 240.93 Min: 6.61 / Avg: 175.75 / Max: 241.88
dav1d CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better dav1d 1.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4858.22 / Max: 5310 Min: 4700 / Avg: 4821.12 / Max: 5300 Min: 4700 / Avg: 4815.92 / Max: 5300
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS Per Watt, More Is Better dav1d 1.0 Video Input: Chimera 1080p AVX-512 Off AVX-512 On AVX-512 On 512 1.0757 2.1514 3.2271 4.3028 5.3785 4.781 4.220 4.141
dav1d CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better dav1d 1.0 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 16 32 48 64 80 Min: 35 / Avg: 62.8 / Max: 73 Min: 34 / Avg: 70.34 / Max: 86 Min: 36 / Avg: 70.99 / Max: 85
dav1d CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better dav1d 1.0 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 6.5 / Avg: 155.12 / Max: 197.33 Min: 12.1 / Avg: 189.54 / Max: 242.47 Min: 12.01 / Avg: 189.65 / Max: 246.19
dav1d CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better dav1d 1.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4854.52 / Max: 5304 Min: 4700 / Avg: 4792.86 / Max: 5300 Min: 4700 / Avg: 4790.25 / Max: 5300
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS Per Watt, More Is Better dav1d 1.0 Video Input: Summer Nature 4K AVX-512 Off AVX-512 On AVX-512 On 512 0.2795 0.559 0.8385 1.118 1.3975 1.242 1.092 1.007
dav1d CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better dav1d 1.0 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 15 30 45 60 75 Min: 30 / Avg: 49.97 / Max: 70 Min: 31 / Avg: 55.32 / Max: 80 Min: 32 / Avg: 56.14 / Max: 79
dav1d CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better dav1d 1.0 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 11.76 / Avg: 104.25 / Max: 203.56 Min: 12.01 / Avg: 122.85 / Max: 243.48 Min: 12.1 / Avg: 122.86 / Max: 243.01
dav1d CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better dav1d 1.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4777 / Avg: 4979.34 / Max: 5300 Min: 4700 / Avg: 4954.03 / Max: 5302 Min: 4700 / Avg: 4943.85 / Max: 5300
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS Per Watt, More Is Better dav1d 1.0 Video Input: Summer Nature 1080p AVX-512 Off AVX-512 On 512 AVX-512 On 2 4 6 8 10 8.435 7.349 7.283
simdjson CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better simdjson 2.0 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 13 26 39 52 65 Min: 31 / Avg: 59.16 / Max: 64 Min: 31 / Avg: 61.48 / Max: 66 Min: 32 / Avg: 62.1 / Max: 66
simdjson CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 13 26 39 52 65 Min: 11.88 / Avg: 58.68 / Max: 62.89 Min: 11.74 / Avg: 63.23 / Max: 67.46 Min: 11.88 / Avg: 63.33 / Max: 67.43
simdjson CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better simdjson 2.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 5100 / Avg: 5288.44 / Max: 5300 Min: 4928 / Avg: 5001.48 / Max: 5300 Min: 4901 / Avg: 4998.59 / Max: 5300
simdjson Throughput Test: TopTweet OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: TopTweet AVX-512 On 512 AVX-512 On AVX-512 Off 0.0313 0.0626 0.0939 0.1252 0.1565 0.139 0.139 0.108
simdjson CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better simdjson 2.0 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 13 26 39 52 65 Min: 31 / Avg: 60.86 / Max: 64 Min: 32 / Avg: 61.85 / Max: 66 Min: 32 / Avg: 62.56 / Max: 67
simdjson CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 13 26 39 52 65 Min: 11.88 / Avg: 59.01 / Max: 62.7 Min: 11.77 / Avg: 63.39 / Max: 67.58 Min: 11.84 / Avg: 63.44 / Max: 67.76
simdjson CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better simdjson 2.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 5100 / Avg: 5291.72 / Max: 5319 Min: 4901 / Avg: 5003.41 / Max: 5303 Min: 4900 / Avg: 4999.18 / Max: 5300
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: DistinctUserID AVX-512 On 512 AVX-512 On AVX-512 Off 0.0311 0.0622 0.0933 0.1244 0.1555 0.138 0.138 0.107
simdjson CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better simdjson 2.0 CPU Temperature Monitor AVX-512 On AVX-512 Off AVX-512 On 512 12 24 36 48 60 Min: 32 / Avg: 56.14 / Max: 63 Min: 31 / Avg: 56.21 / Max: 61 Min: 32 / Avg: 56.59 / Max: 63
simdjson CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 12 24 36 48 60 Min: 11.78 / Avg: 55.55 / Max: 59.77 Min: 11.9 / Avg: 56.95 / Max: 60.96 Min: 11.79 / Avg: 57.11 / Max: 61.15
simdjson CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better simdjson 2.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 1000 2000 3000 4000 5000 Min: 5100 / Avg: 5288.13 / Max: 5498 Min: 4976 / Avg: 5227.59 / Max: 5300 Min: 4966 / Avg: 5223.47 / Max: 5300
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: Kostya AVX-512 On AVX-512 On 512 AVX-512 Off 0.018 0.036 0.054 0.072 0.09 0.080 0.079 0.069
simdjson CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better simdjson 2.0 CPU Temperature Monitor AVX-512 On AVX-512 Off AVX-512 On 512 12 24 36 48 60 Min: 32 / Avg: 58.29 / Max: 63 Min: 32 / Avg: 58.34 / Max: 63 Min: 32 / Avg: 58.34 / Max: 63
simdjson CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 12 24 36 48 60 Min: 11.95 / Avg: 55.09 / Max: 59.62 Min: 11.88 / Avg: 55.9 / Max: 60.31 Min: 11.92 / Avg: 56.3 / Max: 60.48
simdjson CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better simdjson 2.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 1000 2000 3000 4000 5000 Min: 5100 / Avg: 5283.99 / Max: 5300 Min: 4975 / Avg: 5256.72 / Max: 5541 Min: 4994 / Avg: 5238.51 / Max: 5310
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: LargeRandom AVX-512 On 512 AVX-512 On AVX-512 Off 0.0059 0.0118 0.0177 0.0236 0.0295 0.026 0.026 0.025
simdjson CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better simdjson 2.0 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 14 28 42 56 70 Min: 34 / Avg: 62.29 / Max: 70 Min: 33 / Avg: 63.44 / Max: 67 Min: 34 / Avg: 63.86 / Max: 68
simdjson CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 13 26 39 52 65 Min: 11.94 / Avg: 59.59 / Max: 65.08 Min: 12.12 / Avg: 62.94 / Max: 67.82 Min: 11.91 / Avg: 63.23 / Max: 67.98
simdjson CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better simdjson 2.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 5100 / Avg: 5289.95 / Max: 5318 Min: 4901 / Avg: 4982.12 / Max: 5233 Min: 4810 / Avg: 4978.7 / Max: 5258
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: PartialTweets AVX-512 On 512 AVX-512 On AVX-512 Off 0.0304 0.0608 0.0912 0.1216 0.152 0.135 0.135 0.104
LeelaChessZero CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better LeelaChessZero 0.28 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 39 / Avg: 72.12 / Max: 84 Min: 39 / Avg: 81.97 / Max: 94 Min: 39 / Avg: 82.03 / Max: 93
LeelaChessZero CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better LeelaChessZero 0.28 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.39 / Avg: 168.69 / Max: 185.14 Min: 12.13 / Avg: 206.92 / Max: 228.93 Min: 12.29 / Avg: 208.24 / Max: 229.04
LeelaChessZero CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better LeelaChessZero 0.28 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4742.26 / Max: 5300 Min: 4700 / Avg: 4716.16 / Max: 5309 Min: 4700 / Avg: 4714.46 / Max: 5300
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second Per Watt, More Is Better LeelaChessZero 0.28 Backend: Eigen AVX-512 Off AVX-512 On 512 AVX-512 On 2 4 6 8 10 6.296 5.734 5.732
LeelaChessZero CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better LeelaChessZero 0.28 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 38 / Avg: 72.81 / Max: 86 Min: 37 / Avg: 81.96 / Max: 92 Min: 38 / Avg: 82.27 / Max: 94
LeelaChessZero CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better LeelaChessZero 0.28 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.26 / Avg: 169.99 / Max: 187.33 Min: 12.29 / Avg: 208.54 / Max: 230.94 Min: 12.35 / Avg: 210.02 / Max: 231.6
LeelaChessZero CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better LeelaChessZero 0.28 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4730.95 / Max: 5300 Min: 4700 / Avg: 4715.02 / Max: 5309 Min: 4700 / Avg: 4714.39 / Max: 5302
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second Per Watt, More Is Better LeelaChessZero 0.28 Backend: BLAS AVX-512 Off AVX-512 On AVX-512 On 512 2 4 6 8 10 7.295 6.080 6.061
OpenFOAM CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenFOAM 10 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 14 28 42 56 70 Min: 38 / Avg: 60.32 / Max: 71 Min: 38 / Avg: 61.09 / Max: 71 Min: 38 / Avg: 61.46 / Max: 73
OpenFOAM CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenFOAM 10 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 30 60 90 120 150 Min: 12.27 / Avg: 134.48 / Max: 185.27 Min: 12.47 / Avg: 137.27 / Max: 176.06 Min: 12.28 / Avg: 137.66 / Max: 174.47
OpenFOAM CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenFOAM 10 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On 512 AVX-512 Off AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4808.62 / Max: 5301 Min: 4731 / Avg: 4807.69 / Max: 5300 Min: 4700 / Avg: 4805.98 / Max: 5300
OpenRadioss CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenRadioss 2022.10.13 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 15 30 45 60 75 Min: 38 / Avg: 69.5 / Max: 75 Min: 38 / Avg: 69.98 / Max: 76 Min: 39 / Avg: 70.02 / Max: 75
OpenRadioss CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenRadioss 2022.10.13 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 30 60 90 120 150 Min: 12.5 / Avg: 163.73 / Max: 168.75 Min: 12.49 / Avg: 165.47 / Max: 171.6 Min: 12.33 / Avg: 166.01 / Max: 172.07
OpenRadioss CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenRadioss 2022.10.13 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4796.02 / Max: 5300 Min: 4700 / Avg: 4786.9 / Max: 5311 Min: 4700 / Avg: 4786.28 / Max: 5301
OpenRadioss CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenRadioss 2022.10.13 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 15 30 45 60 75 Min: 39 / Avg: 72.15 / Max: 77 Min: 39 / Avg: 72.17 / Max: 77 Min: 39 / Avg: 72.25 / Max: 77
OpenRadioss CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenRadioss 2022.10.13 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.52 / Avg: 170 / Max: 193.93 Min: 12.46 / Avg: 170.68 / Max: 195.05 Min: 12.18 / Avg: 171.5 / Max: 195.54
OpenRadioss CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenRadioss 2022.10.13 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On AVX-512 Off AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4728.36 / Max: 5300 Min: 4700 / Avg: 4725.71 / Max: 5303 Min: 4700 / Avg: 4723.82 / Max: 5299
OpenRadioss CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenRadioss 2022.10.13 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 15 30 45 60 75 Min: 39 / Avg: 69.57 / Max: 75 Min: 39 / Avg: 69.64 / Max: 75 Min: 39 / Avg: 69.91 / Max: 76
OpenRadioss CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenRadioss 2022.10.13 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 30 60 90 120 150 Min: 12.35 / Avg: 164.91 / Max: 183.91 Min: 12.46 / Avg: 165.44 / Max: 186 Min: 12.38 / Avg: 166.68 / Max: 187.69
OpenRadioss CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenRadioss 2022.10.13 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On 512 AVX-512 Off AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4779.74 / Max: 5300 Min: 4700 / Avg: 4779.68 / Max: 5309 Min: 4700 / Avg: 4776.23 / Max: 5300
OpenRadioss CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenRadioss 2022.10.13 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 14 28 42 56 70 Min: 38 / Avg: 69.59 / Max: 73 Min: 38 / Avg: 70.17 / Max: 75 Min: 38 / Avg: 70.36 / Max: 75
OpenRadioss CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenRadioss 2022.10.13 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 30 60 90 120 150 Min: 12.42 / Avg: 166.23 / Max: 179.39 Min: 12.59 / Avg: 167.03 / Max: 184.87 Min: 12.45 / Avg: 168.45 / Max: 185.36
OpenRadioss CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenRadioss 2022.10.13 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4789.33 / Max: 5302 Min: 4700 / Avg: 4746.34 / Max: 5300 Min: 4700 / Avg: 4744.78 / Max: 5300
OpenRadioss CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better OpenRadioss 2022.10.13 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 14 28 42 56 70 Min: 38 / Avg: 70.2 / Max: 74 Min: 40 / Avg: 70.47 / Max: 75 Min: 39 / Avg: 70.71 / Max: 75
OpenRadioss CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenRadioss 2022.10.13 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 30 60 90 120 150 Min: 12.24 / Avg: 164.06 / Max: 177.04 Min: 12.55 / Avg: 164.63 / Max: 179.72 Min: 12.45 / Avg: 165.14 / Max: 181.24
OpenRadioss CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better OpenRadioss 2022.10.13 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4764.39 / Max: 5301 Min: 4700 / Avg: 4752.2 / Max: 5302 Min: 4700 / Avg: 4738.14 / Max: 5300
Neural Magic DeepSparse CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 72.53 / Max: 86 Min: 39 / Avg: 77.07 / Max: 96 Min: 40 / Avg: 78.84 / Max: 95
Neural Magic DeepSparse CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.4 / Avg: 167.72 / Max: 220.91 Min: 12.69 / Avg: 185.26 / Max: 260.57 Min: 12.54 / Avg: 189.06 / Max: 260.04
Neural Magic DeepSparse CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Neural Magic DeepSparse 1.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4864.76 / Max: 5300 Min: 3500 / Avg: 4792.63 / Max: 5301 Min: 3500 / Avg: 4712.83 / Max: 5302
Neural Magic DeepSparse CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 38 / Avg: 71.94 / Max: 85 Min: 38 / Avg: 79.14 / Max: 93 Min: 39 / Avg: 79.22 / Max: 92
Neural Magic DeepSparse CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.27 / Avg: 168.07 / Max: 217.66 Min: 12.46 / Avg: 191.4 / Max: 257.39 Min: 12.35 / Avg: 194.31 / Max: 256.42
Neural Magic DeepSparse CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Neural Magic DeepSparse 1.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4854.95 / Max: 5363 Min: 4587 / Avg: 4805.51 / Max: 5300 Min: 3500 / Avg: 4768.23 / Max: 5302
Neural Magic DeepSparse CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 74.07 / Max: 85 Min: 40 / Avg: 80.82 / Max: 93 Min: 39 / Avg: 80.84 / Max: 95
Neural Magic DeepSparse CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.46 / Avg: 181.5 / Max: 215.22 Min: 12.65 / Avg: 200.79 / Max: 239.52 Min: 12.46 / Avg: 204.1 / Max: 244.9
Neural Magic DeepSparse CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Neural Magic DeepSparse 1.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4785.41 / Max: 5300 Min: 4700 / Avg: 4783.64 / Max: 5301 Min: 3578 / Avg: 4752.98 / Max: 5300
Neural Magic DeepSparse CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 38 / Avg: 73.22 / Max: 82 Min: 39 / Avg: 80.23 / Max: 93 Min: 39 / Avg: 80.25 / Max: 92
Neural Magic DeepSparse CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.46 / Avg: 178.55 / Max: 211.42 Min: 12.29 / Avg: 195.66 / Max: 239.75 Min: 12.46 / Avg: 200.45 / Max: 240.26
Neural Magic DeepSparse CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Neural Magic DeepSparse 1.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 On 512 AVX-512 Off AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4796.86 / Max: 5302 Min: 4700 / Avg: 4792.9 / Max: 5300 Min: 4700 / Avg: 4785.87 / Max: 5309
Neural Magic DeepSparse CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 39 / Avg: 65.01 / Max: 75 Min: 37 / Avg: 73.66 / Max: 88 Min: 40 / Avg: 74.99 / Max: 88
Neural Magic DeepSparse CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.57 / Avg: 151.3 / Max: 208.63 Min: 12.39 / Avg: 185.33 / Max: 241.17 Min: 12.58 / Avg: 186.84 / Max: 241.51
Neural Magic DeepSparse CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Neural Magic DeepSparse 1.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4899.77 / Max: 5314 Min: 4700 / Avg: 4813.34 / Max: 5300 Min: 4700 / Avg: 4803.42 / Max: 5300
Neural Magic DeepSparse CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 38 / Avg: 64.6 / Max: 73 Min: 38 / Avg: 73.65 / Max: 89 Min: 39 / Avg: 75.07 / Max: 90
Neural Magic DeepSparse CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 12.29 / Avg: 152.74 / Max: 206.29 Min: 12.27 / Avg: 178.55 / Max: 250.04 Min: 12.24 / Avg: 188.78 / Max: 249.74
Neural Magic DeepSparse CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Neural Magic DeepSparse 1.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4884.74 / Max: 5310 Min: 4700 / Avg: 4865.03 / Max: 5312 Min: 4700 / Avg: 4810.87 / Max: 5300
Neural Magic DeepSparse CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 72.83 / Max: 87 Min: 41 / Avg: 76.64 / Max: 95 Min: 40 / Avg: 78.69 / Max: 92
Neural Magic DeepSparse CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.43 / Avg: 168.83 / Max: 221.42 Min: 12.5 / Avg: 186.42 / Max: 260.13 Min: 12.39 / Avg: 189.75 / Max: 259.61
Neural Magic DeepSparse CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Neural Magic DeepSparse 1.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4862.17 / Max: 5301 Min: 4389 / Avg: 4809.78 / Max: 5300 Min: 3500 / Avg: 4711.32 / Max: 5304
Neural Magic DeepSparse CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 38 / Avg: 71.71 / Max: 85 Min: 39 / Avg: 78.7 / Max: 94 Min: 39 / Avg: 79.14 / Max: 92
Neural Magic DeepSparse CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.38 / Avg: 167.69 / Max: 217.29 Min: 12.46 / Avg: 192.59 / Max: 258.71 Min: 12.38 / Avg: 193.85 / Max: 256.16
Neural Magic DeepSparse CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Neural Magic DeepSparse 1.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4847.56 / Max: 5310 Min: 4575 / Avg: 4802.05 / Max: 5300 Min: 3500 / Avg: 4747.88 / Max: 5310
Neural Magic DeepSparse CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 40 / Avg: 78.22 / Max: 86 Min: 40 / Avg: 82.42 / Max: 94 Min: 41 / Avg: 82.64 / Max: 96
Neural Magic DeepSparse CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.46 / Avg: 198.19 / Max: 227.43 Min: 12.48 / Avg: 211.14 / Max: 256.86 Min: 12.31 / Avg: 211.91 / Max: 258.7
Neural Magic DeepSparse CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Neural Magic DeepSparse 1.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4768.47 / Max: 5302 Min: 3500 / Avg: 4682.19 / Max: 5300 Min: 3500 / Avg: 4648.5 / Max: 5302
Neural Magic DeepSparse CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Temperature Monitor AVX-512 Off AVX-512 On AVX-512 On 512 20 40 60 80 100 Min: 39 / Avg: 74.18 / Max: 83 Min: 38 / Avg: 79.49 / Max: 92 Min: 39 / Avg: 81.82 / Max: 92
Neural Magic DeepSparse CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.35 / Avg: 183.63 / Max: 214.9 Min: 12.32 / Avg: 201.37 / Max: 246.43 Min: 12.3 / Avg: 209.51 / Max: 246.88
Neural Magic DeepSparse CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Neural Magic DeepSparse 1.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4780.8 / Max: 5312 Min: 4631 / Avg: 4780.28 / Max: 5300 Min: 3556 / Avg: 4766.8 / Max: 5302
Neural Magic DeepSparse CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 16 32 48 64 80 Min: 39 / Avg: 69.87 / Max: 78 Min: 39 / Avg: 73.25 / Max: 82 Min: 40 / Avg: 73.39 / Max: 81
Neural Magic DeepSparse CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 40 80 120 160 200 Min: 12.42 / Avg: 169 / Max: 204.27 Min: 12.55 / Avg: 190.88 / Max: 225.22 Min: 12.41 / Avg: 191.37 / Max: 225.56
Neural Magic DeepSparse CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Neural Magic DeepSparse 1.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4802.88 / Max: 5301 Min: 4700 / Avg: 4777.6 / Max: 5301 Min: 4700 / Avg: 4777.02 / Max: 5300
Neural Magic DeepSparse CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 15 30 45 60 75 Min: 38 / Avg: 66.44 / Max: 73 Min: 38 / Avg: 69.89 / Max: 79 Min: 40 / Avg: 72.9 / Max: 79
Neural Magic DeepSparse CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.39 / Avg: 153.63 / Max: 193.33 Min: 12.32 / Avg: 171.93 / Max: 211.04 Min: 12.29 / Avg: 180.67 / Max: 210.72
Neural Magic DeepSparse CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Neural Magic DeepSparse 1.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4829.28 / Max: 5301 Min: 4700 / Avg: 4800.61 / Max: 5310 Min: 4700 / Avg: 4769.5 / Max: 5309
Neural Magic DeepSparse CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 38 / Avg: 72.32 / Max: 85 Min: 39 / Avg: 78.25 / Max: 94 Min: 40 / Avg: 78.33 / Max: 92
Neural Magic DeepSparse CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On AVX-512 On 512 50 100 150 200 250 Min: 12.38 / Avg: 167.33 / Max: 219.34 Min: 12.48 / Avg: 190.62 / Max: 260.18 Min: 12.38 / Avg: 190.62 / Max: 262.43
Neural Magic DeepSparse CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Neural Magic DeepSparse 1.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On AVX-512 On 512 900 1800 2700 3600 4500 Min: 4700 / Avg: 4864.38 / Max: 5300 Min: 4550 / Avg: 4788.85 / Max: 5300 Min: 3500 / Avg: 4771.09 / Max: 5310
Neural Magic DeepSparse CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 35 / Avg: 69.17 / Max: 81 Min: 38 / Avg: 77.04 / Max: 92 Min: 39 / Avg: 79.78 / Max: 91
Neural Magic DeepSparse CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 40 80 120 160 200 Min: 12.18 / Avg: 155.44 / Max: 200.14 Min: 12.22 / Avg: 188.58 / Max: 244.57 Min: 12.52 / Avg: 194.6 / Max: 244.04
Neural Magic DeepSparse CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better Neural Magic DeepSparse 1.1 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4850.7 / Max: 5301 Min: 4669 / Avg: 4825.21 / Max: 5300 Min: 4651 / Avg: 4793.56 / Max: 5300
AI Benchmark Alpha CPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better AI Benchmark Alpha 0.1.2 CPU Temperature Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 20 40 60 80 100 Min: 27 / Avg: 70 / Max: 89 Min: 33 / Avg: 75.48 / Max: 97 Min: 29 / Avg: 75.69 / Max: 98
AI Benchmark Alpha CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better AI Benchmark Alpha 0.1.2 CPU Power Consumption Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 50 100 150 200 250 Min: 11.83 / Avg: 160.88 / Max: 250.01 Min: 12.02 / Avg: 161.75 / Max: 239 Min: 11.95 / Avg: 162.75 / Max: 242.39
AI Benchmark Alpha CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz, More Is Better AI Benchmark Alpha 0.1.2 CPU Peak Freq (Highest CPU Core Frequency) Monitor AVX-512 Off AVX-512 On 512 AVX-512 On 900 1800 2700 3600 4500 Min: 4700 / Avg: 4852.05 / Max: 5308 Min: 3475 / Avg: 4839.25 / Max: 5311 Min: 3500 / Avg: 4834.52 / Max: 5302
AI Benchmark Alpha Device AI Score OpenBenchmarking.org Score Per Watt, More Is Better AI Benchmark Alpha 0.1.2 Device AI Score AVX-512 On 512 AVX-512 On AVX-512 Off 5 10 15 20 25 21.26 21.17 16.76
Phoronix Test Suite v10.8.4