ffhgf AMD Ryzen 5 5500U testing with a NB01 TUXEDO Aura 15 Gen2 NL5xNU (1.07.11RTR1 BIOS) and AMD Lucienne 512MB on Tuxedo 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2403164-NE-FFHGF146295&rdt&grs .
ffhgf Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution a b c AMD Ryzen 5 5500U @ 4.06GHz (6 Cores / 12 Threads) NB01 TUXEDO Aura 15 Gen2 NL5xNU (1.07.11RTR1 BIOS) AMD Renoir/Cezanne 2 x 8GB DDR4-3200MT/s Samsung M471A1K43DB1-CWE Samsung SSD 970 EVO Plus 500GB AMD Lucienne 512MB (1800/400MHz) AMD Renoir Radeon HD Audio Realtek RTL8111/8168/8411 + Intel Wi-Fi 6 AX200 Tuxedo 22.04 6.0.0-1010-oem (x86_64) KDE Plasma 5.26.5 X Server 1.21.1.3 4.6 Mesa 22.3.7 (LLVM 14.0.0 DRM 3.48) 1.3.230 GCC 11.3.0 ext4 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: amd-pstate ondemand (Boost: Enabled) - CPU Microcode: 0x8608103 Python Details - Python 3.10.6 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
ffhgf openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU onednn: Deconvolution Batch shapes_1d - CPU svt-av1: Preset 12 - Bosphorus 4K srsran: PDSCH Processor Benchmark, Throughput Thread jpegxl-decode: All primesieve: 1e12 deepsparse: ResNet-50, Baseline - Asynchronous Multi-Stream deepsparse: ResNet-50, Baseline - Asynchronous Multi-Stream svt-av1: Preset 13 - Bosphorus 1080p encode-wavpack: WAV To WavPack draco: Church Facade openvino: Person Detection FP16 - CPU openvino: Person Detection FP16 - CPU primesieve: 1e13 onednn: Deconvolution Batch shapes_3d - CPU svt-av1: Preset 12 - Bosphorus 1080p deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream onednn: IP Shapes 1D - CPU deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream jpegxl-decode: 1 draco: Lion openvino: Person Detection FP32 - CPU openvino: Person Detection FP32 - CPU openvino: Face Detection Retail FP16-INT8 - CPU svt-av1: Preset 8 - Bosphorus 1080p deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream openvino: Face Detection Retail FP16-INT8 - CPU svt-av1: Preset 13 - Bosphorus 4K openvino: Vehicle Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU svt-av1: Preset 8 - Bosphorus 4K deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream svt-av1: Preset 4 - Bosphorus 1080p openvino: Handwritten English Recognition FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU onednn: Recurrent Neural Network Training - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU svt-av1: Preset 4 - Bosphorus 4K deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream onednn: Recurrent Neural Network Inference - CPU onednn: IP Shapes 3D - CPU openvino: Face Detection FP16 - CPU openvino: Face Detection Retail FP16 - CPU srsran: PDSCH Processor Benchmark, Throughput Total deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream openvino: Face Detection Retail FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU compress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compression openvino: Machine Translation EN To DE FP16 - CPU jpegxl: PNG - 90 jpegxl: PNG - 80 openvino: Age Gender Recognition Retail 0013 FP16 - CPU deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream jpegxl: JPEG - 80 deepsparse: ResNet-50, Baseline - Synchronous Single-Stream deepsparse: ResNet-50, Baseline - Synchronous Single-Stream openvino: Road Segmentation ADAS FP16 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU v-ray: CPU openvino: Road Segmentation ADAS FP16 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Face Detection FP16 - CPU onednn: Convolution Batch Shapes Auto - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Person Re-Identification Retail FP16 - CPU openvino: Person Re-Identification Retail FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream jpegxl: PNG - 100 deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream jpegxl: JPEG - 90 openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU jpegxl: JPEG - 100 openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU deepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Stream a b c 2321.44 1.71 11.7594 43.434 314.8 191.398 37.342 50.0338 59.8992 245.376 7.692 9515 14.83 269.72 473.567 11.7203 202.302 4.3724 7.22621 681.9059 4.5244 220.4253 54.82 6409 271.53 14.71 459.92 51.475 50.6529 59.1547 8.69 45.109 141.94 28.16 16.292 120.27 85.9092 11.6311 24.9236 7.495 98.43 60.91 6067.92 1.18 38.82 102.94 2.06 312.3789 9.5805 3135.38 14.3913 1.45 378.86 2124.4 4.3554 229.5887 10.53 5051.32 232.78 20.87 191.4 14.579856 17.17 16.214 17.594 1.88 51.4072 58.3096 17.449 21.4706 46.5486 167.55 31.85 7052 23.86 56.83 70.33 2740.33 22.4888 188.24 4.7151 3160.64 212.6 18.79 131.99 30.28 4.3416 230.3157 210.0086 4.7614 101.4254 634.5354 46.6998 21.4013 29.534 4.5018 6.88 665.1773 73.352 26.698 37.4422 40.87 23.0973 43.2842 39.0337 25.6066 16.51 18.01 221.74 6.808 91.44 65.59 2456.33 1.62 12.086 45.377 302.6 197.721 36.222 51.5443 58.1743 250.82 7.578 9536 14.56 274.43 464.649 11.9338 206.832 4.4546 7.3269 670.4488 4.5824 217.6355 55.055 6315 274 14.57 458.71 52.064 51.3019 58.4502 8.71 45.65 140.29 28.49 16.46 118.9649 86.7099 11.5237 25.18 7.555 97.56 61.46 6016.25 1.17 38.5 103.79 2.073 314.947 9.5031 3110.94 14.3419 1.44 376.67 2110.1 4.358 229.4528 10.59 5066.06 231.3 20.92 191 14.50946 17.27 16.19 17.512 1.89 51.1871 58.5538 17.445 21.3682 46.7715 166.76 31.89 7019 23.97 56.84 70.31 2748.14 22.5758 188.05 4.7167 3147.58 212.76 18.78 131.82 30.32 4.3352 230.6559 209.9382 4.763 101.5569 633.8932 46.6428 21.4271 29.4939 4.49 6.88 665.4893 73.1801 26.6361 37.5286 40.953 23.1057 43.2686 39.0245 25.6128 16.492 18.02 221.65 6.812 91.39 65.61 2437.33 1.62 11.5182 45.438 307 197.639 36.284 50.6221 59.2132 252.602 7.794 9766 14.9 268.2 462.998 11.6718 204.567 4.4236 7.1952 672.1069 4.5062 221.3073 55.732 6400 275.49 14.51 453.71 52.162 51.3099 58.4006 8.8 45.471 140.41 28.46 16.48 119.8962 86.8258 11.5086 25.0064 7.569 97.51 61.48 6024.94 1.18 38.74 103.13 2.077 314.5417 9.5153 3118.61 14.289 1.45 376.3 2116.7 4.3291 230.9809 10.6 5032.95 231.39 21 190.23 14.490876 17.26 16.28 17.606 1.88 51.139 58.6004 17.532 21.3915 46.7201 166.96 32 7052 23.94 57.09 70.01 2752.56 22.5887 187.42 4.7347 3154.67 211.95 18.85 132.29 30.22 4.349 229.9275 209.3586 4.7761 101.7126 632.7488 46.7734 21.3677 29.4531 4.49 6.897 666.7407 73.2979 26.6514 37.5073 40.8905 23.0607 43.353 39.0886 25.571 16.489 18 221.88 6.815 91.41 65.6 OpenBenchmarking.org
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU a b c 500 1000 1500 2000 2500 2321.44 2456.33 2437.33 MIN: 2113.11 / MAX: 3253.9 MIN: 1779.95 / MAX: 3009.84 MIN: 2025.66 / MAX: 3552.28 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU a b c 0.3848 0.7696 1.1544 1.5392 1.924 1.71 1.62 1.62 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Deconvolution Batch shapes_1d - Engine: CPU a b c 3 6 9 12 15 11.76 12.09 11.52 MIN: 8.57 MIN: 8.58 MIN: 8.53 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K a b c 10 20 30 40 50 43.43 45.38 45.44 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
srsRAN Project Test: PDSCH Processor Benchmark, Throughput Thread OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240219 Test: PDSCH Processor Benchmark, Throughput Thread a b c 70 140 210 280 350 314.8 302.6 307.0 1. (CXX) g++ options: -march=native -mavx2 -mavx -msse4.1 -mfma -O3 -fno-trapping-math -fno-math-errno -ldl
JPEG-XL Decoding libjxl CPU Threads: All OpenBenchmarking.org MP/s, More Is Better JPEG-XL Decoding libjxl 0.10.1 CPU Threads: All a b c 40 80 120 160 200 191.40 197.72 197.64
Primesieve Length: 1e12 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.1 Length: 1e12 a b c 9 18 27 36 45 37.34 36.22 36.28 1. (CXX) g++ options: -O3
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream a b c 12 24 36 48 60 50.03 51.54 50.62
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream a b c 13 26 39 52 65 59.90 58.17 59.21
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 1080p a b c 60 120 180 240 300 245.38 250.82 252.60 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
WavPack Audio Encoding WAV To WavPack OpenBenchmarking.org Seconds, Fewer Is Better WavPack Audio Encoding 5.7 WAV To WavPack a b c 2 4 6 8 10 7.692 7.578 7.794
Google Draco Model: Church Facade OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.6 Model: Church Facade a b c 2K 4K 6K 8K 10K 9515 9536 9766 1. (CXX) g++ options: -O3
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU a b c 4 8 12 16 20 14.83 14.56 14.90 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU a b c 60 120 180 240 300 269.72 274.43 268.20 MIN: 234.64 / MAX: 306.72 MIN: 148.02 / MAX: 308.41 MIN: 136.25 / MAX: 310.48 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Primesieve Length: 1e13 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.1 Length: 1e13 a b c 100 200 300 400 500 473.57 464.65 463.00 1. (CXX) g++ options: -O3
oneDNN Harness: Deconvolution Batch shapes_3d - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Deconvolution Batch shapes_3d - Engine: CPU a b c 3 6 9 12 15 11.72 11.93 11.67 MIN: 11.2 MIN: 11.26 MIN: 11.19 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 1080p a b c 50 100 150 200 250 202.30 206.83 204.57 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream a b c 1.0023 2.0046 3.0069 4.0092 5.0115 4.3724 4.4546 4.4236
oneDNN Harness: IP Shapes 1D - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: IP Shapes 1D - Engine: CPU a b c 2 4 6 8 10 7.22621 7.32690 7.19520 MIN: 6.22 MIN: 6.31 MIN: 6.19 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
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 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream a b c 150 300 450 600 750 681.91 670.45 672.11
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 1.031 2.062 3.093 4.124 5.155 4.5244 4.5824 4.5062
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 50 100 150 200 250 220.43 217.64 221.31
JPEG-XL Decoding libjxl CPU Threads: 1 OpenBenchmarking.org MP/s, More Is Better JPEG-XL Decoding libjxl 0.10.1 CPU Threads: 1 a b c 13 26 39 52 65 54.82 55.06 55.73
Google Draco Model: Lion OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.6 Model: Lion a b c 1400 2800 4200 5600 7000 6409 6315 6400 1. (CXX) g++ options: -O3
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Detection FP32 - Device: CPU a b c 60 120 180 240 300 271.53 274.00 275.49 MIN: 210.59 / MAX: 309.26 MIN: 210.36 / MAX: 310.41 MIN: 229.07 / MAX: 422.38 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Detection FP32 - Device: CPU a b c 4 8 12 16 20 14.71 14.57 14.51 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU a b c 100 200 300 400 500 459.92 458.71 453.71 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 1080p a b c 12 24 36 48 60 51.48 52.06 52.16 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a b c 12 24 36 48 60 50.65 51.30 51.31
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a b c 13 26 39 52 65 59.15 58.45 58.40
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU a b c 2 4 6 8 10 8.69 8.71 8.80 MIN: 6.54 / MAX: 18.65 MIN: 5.16 / MAX: 17.4 MIN: 5.6 / MAX: 19.39 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 4K a b c 10 20 30 40 50 45.11 45.65 45.47 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU a b c 30 60 90 120 150 141.94 140.29 140.41 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU a b c 7 14 21 28 35 28.16 28.49 28.46 MIN: 22.61 / MAX: 42.4 MIN: 16.22 / MAX: 42.86 MIN: 22.46 / MAX: 44.26 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K a b c 4 8 12 16 20 16.29 16.46 16.48 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 30 60 90 120 150 120.27 118.96 119.90
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 20 40 60 80 100 85.91 86.71 86.83
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 3 6 9 12 15 11.63 11.52 11.51
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 6 12 18 24 30 24.92 25.18 25.01
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 1080p a b c 2 4 6 8 10 7.495 7.555 7.569 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenVINO Model: Handwritten English Recognition FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16 - Device: CPU a b c 20 40 60 80 100 98.43 97.56 97.51 MIN: 63.19 / MAX: 224.34 MIN: 63.86 / MAX: 122.52 MIN: 64.36 / MAX: 125.21 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Handwritten English Recognition FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16 - Device: CPU a b c 14 28 42 56 70 60.91 61.46 61.48 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
oneDNN Harness: Recurrent Neural Network Training - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Recurrent Neural Network Training - Engine: CPU a b c 1300 2600 3900 5200 6500 6067.92 6016.25 6024.94 MIN: 6009.45 MIN: 5939.52 MIN: 5948.41 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b c 0.2655 0.531 0.7965 1.062 1.3275 1.18 1.17 1.18 MIN: 0.58 / MAX: 10.19 MIN: 0.58 / MAX: 9.01 MIN: 0.59 / MAX: 15.55 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU a b c 9 18 27 36 45 38.82 38.50 38.74 MIN: 25.47 / MAX: 87.45 MIN: 29.34 / MAX: 61 MIN: 18.87 / MAX: 78.37 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU a b c 20 40 60 80 100 102.94 103.79 103.13 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 4K a b c 0.4673 0.9346 1.4019 1.8692 2.3365 2.060 2.073 2.077 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 70 140 210 280 350 312.38 314.95 314.54
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 3 6 9 12 15 9.5805 9.5031 9.5153
oneDNN Harness: Recurrent Neural Network Inference - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Recurrent Neural Network Inference - Engine: CPU a b c 700 1400 2100 2800 3500 3135.38 3110.94 3118.61 MIN: 3072.86 MIN: 3038.51 MIN: 3052.5 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: IP Shapes 3D - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: IP Shapes 3D - Engine: CPU a b c 4 8 12 16 20 14.39 14.34 14.29 MIN: 13.56 MIN: 13.53 MIN: 13.53 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection FP16 - Device: CPU a b c 0.3263 0.6526 0.9789 1.3052 1.6315 1.45 1.44 1.45 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Face Detection Retail FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16 - Device: CPU a b c 80 160 240 320 400 378.86 376.67 376.30 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
srsRAN Project Test: PDSCH Processor Benchmark, Throughput Total OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240219 Test: PDSCH Processor Benchmark, Throughput Total a b c 500 1000 1500 2000 2500 2124.4 2110.1 2116.7 1. (CXX) g++ options: -march=native -mavx2 -mavx -msse4.1 -mfma -O3 -fno-trapping-math -fno-math-errno -ldl
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 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream a b c 0.9806 1.9612 2.9418 3.9224 4.903 4.3554 4.3580 4.3291
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 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream a b c 50 100 150 200 250 229.59 229.45 230.98
OpenVINO Model: Face Detection Retail FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16 - Device: CPU a b c 3 6 9 12 15 10.53 10.59 10.60 MIN: 5.73 / MAX: 24.87 MIN: 7.59 / MAX: 21.42 MIN: 7.14 / MAX: 22.37 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b c 1100 2200 3300 4400 5500 5051.32 5066.06 5032.95 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU a b c 50 100 150 200 250 232.78 231.30 231.39 MIN: 158.33 / MAX: 295.68 MIN: 164.36 / MAX: 262.63 MIN: 171.44 / MAX: 265.55 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU a b c 5 10 15 20 25 20.87 20.92 21.00 MIN: 13.72 / MAX: 44.43 MIN: 14.64 / MAX: 37.38 MIN: 15.65 / MAX: 37.11 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU a b c 40 80 120 160 200 191.40 191.00 190.23 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Parallel BZIP2 Compression FreeBSD-13.0-RELEASE-amd64-memstick.img Compression OpenBenchmarking.org Seconds, Fewer Is Better Parallel BZIP2 Compression 1.1.13 FreeBSD-13.0-RELEASE-amd64-memstick.img Compression a b c 4 8 12 16 20 14.58 14.51 14.49 1. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU a b c 4 8 12 16 20 17.17 17.27 17.26 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
JPEG-XL libjxl Input: PNG - Quality: 90 OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 90 a b c 4 8 12 16 20 16.21 16.19 16.28 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
JPEG-XL libjxl Input: PNG - Quality: 80 OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 80 a b c 4 8 12 16 20 17.59 17.51 17.61 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b c 0.4253 0.8506 1.2759 1.7012 2.1265 1.88 1.89 1.88 MIN: 1.01 / MAX: 12.21 MIN: 1.01 / MAX: 84.2 MIN: 0.95 / MAX: 10.89 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 12 24 36 48 60 51.41 51.19 51.14
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 13 26 39 52 65 58.31 58.55 58.60
JPEG-XL libjxl Input: JPEG - Quality: 80 OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 80 a b c 4 8 12 16 20 17.45 17.45 17.53 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream a b c 5 10 15 20 25 21.47 21.37 21.39
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream a b c 11 22 33 44 55 46.55 46.77 46.72
OpenVINO Model: Road Segmentation ADAS FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16 - Device: CPU a b c 40 80 120 160 200 167.55 166.76 166.96 MIN: 116.23 / MAX: 213.59 MIN: 73.08 / MAX: 216.16 MIN: 67.28 / MAX: 215 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU a b c 7 14 21 28 35 31.85 31.89 32.00 MIN: 25.39 / MAX: 45.6 MIN: 18.32 / MAX: 45.73 MIN: 23.29 / MAX: 47.13 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Chaos Group V-RAY Mode: CPU OpenBenchmarking.org vsamples, More Is Better Chaos Group V-RAY 6.0 Mode: CPU a b c 1500 3000 4500 6000 7500 7052 7019 7052
OpenVINO Model: Road Segmentation ADAS FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16 - Device: CPU a b c 6 12 18 24 30 23.86 23.97 23.94 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU a b c 13 26 39 52 65 56.83 56.84 57.09 MIN: 42.49 / MAX: 78.95 MIN: 34.6 / MAX: 77.32 MIN: 33.74 / MAX: 79.45 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU a b c 16 32 48 64 80 70.33 70.31 70.01 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection FP16 - Device: CPU a b c 600 1200 1800 2400 3000 2740.33 2748.14 2752.56 MIN: 2203.03 / MAX: 2836.59 MIN: 2160.17 / MAX: 2860.69 MIN: 2291.93 / MAX: 2877.15 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Convolution Batch Shapes Auto - Engine: CPU a b c 5 10 15 20 25 22.49 22.58 22.59 MIN: 21.68 MIN: 21.78 MIN: 21.74 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU a b c 40 80 120 160 200 188.24 188.05 187.42 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream a b c 1.0653 2.1306 3.1959 4.2612 5.3265 4.7151 4.7167 4.7347
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b c 700 1400 2100 2800 3500 3160.64 3147.58 3154.67 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Re-Identification Retail FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU a b c 50 100 150 200 250 212.60 212.76 211.95 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Re-Identification Retail FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU a b c 5 10 15 20 25 18.79 18.78 18.85 MIN: 15.44 / MAX: 33.87 MIN: 12.18 / MAX: 33.46 MIN: 11.63 / MAX: 37.02 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU a b c 30 60 90 120 150 131.99 131.82 132.29 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU a b c 7 14 21 28 35 30.28 30.32 30.22 MIN: 25.1 / MAX: 48.08 MIN: 17.72 / MAX: 46.79 MIN: 23.15 / MAX: 46.15 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
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 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream a b c 0.9785 1.957 2.9355 3.914 4.8925 4.3416 4.3352 4.3490
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 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream a b c 50 100 150 200 250 230.32 230.66 229.93
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream a b c 50 100 150 200 250 210.01 209.94 209.36
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream a b c 1.0746 2.1492 3.2238 4.2984 5.373 4.7614 4.7630 4.7761
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 20 40 60 80 100 101.43 101.56 101.71
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream a b c 140 280 420 560 700 634.54 633.89 632.75
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream a b c 11 22 33 44 55 46.70 46.64 46.77
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream a b c 5 10 15 20 25 21.40 21.43 21.37
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 7 14 21 28 35 29.53 29.49 29.45
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 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream a b c 1.0129 2.0258 3.0387 4.0516 5.0645 4.5018 4.4900 4.4900
JPEG-XL libjxl Input: PNG - Quality: 100 OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 100 a b c 2 4 6 8 10 6.880 6.880 6.897 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
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 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream a b c 140 280 420 560 700 665.18 665.49 666.74
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream a b c 16 32 48 64 80 73.35 73.18 73.30
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream a b c 6 12 18 24 30 26.70 26.64 26.65
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream a b c 9 18 27 36 45 37.44 37.53 37.51
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream a b c 9 18 27 36 45 40.87 40.95 40.89
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 6 12 18 24 30 23.10 23.11 23.06
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 10 20 30 40 50 43.28 43.27 43.35
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 9 18 27 36 45 39.03 39.02 39.09
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 6 12 18 24 30 25.61 25.61 25.57
JPEG-XL libjxl Input: JPEG - Quality: 90 OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 90 a b c 4 8 12 16 20 16.51 16.49 16.49 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
OpenVINO Model: Noise Suppression Poconet-Like FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU a b c 4 8 12 16 20 18.01 18.02 18.00 MIN: 14.99 / MAX: 32.02 MIN: 13.78 / MAX: 33.52 MIN: 13.26 / MAX: 32.43 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Noise Suppression Poconet-Like FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU a b c 50 100 150 200 250 221.74 221.65 221.88 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
JPEG-XL libjxl Input: JPEG - Quality: 100 OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 100 a b c 2 4 6 8 10 6.808 6.812 6.815 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU a b c 20 40 60 80 100 91.44 91.39 91.41 MIN: 77.37 / MAX: 116.23 MIN: 75.74 / MAX: 114.4 MIN: 59.9 / MAX: 113.94 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU a b c 15 30 45 60 75 65.59 65.61 65.60 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Phoronix Test Suite v10.8.5