okt Tests for a future article. AMD Ryzen 9 3900XT 12-Core testing with a MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS) and AMD Radeon RX 56/64 8GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2310316-NE-OKT95575789&grs .
okt Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution a b AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads) MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS) AMD Starship/Matisse 16GB 500GB Seagate FireCuda 520 SSD ZP500GM30002 AMD Radeon RX 56/64 8GB (1630/945MHz) AMD Vega 10 HDMI Audio ASUS MG28U Realtek Device 2600 + Realtek Killer E3000 2.5GbE + Intel Wi-Fi 6 AX200 Ubuntu 22.04 6.2.0-35-generic (x86_64) GNOME Shell 42.2 X Server + Wayland 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.49) 1.3.204 GCC 11.4.0 ext4 3840x2160 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-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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 Disk Details - NONE / errors=remount-ro,relatime,rw / Block Size: 4096 Processor Details - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8701021 Graphics Details - BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D0500100-102 Java Details - OpenJDK Runtime Environment (build 11.0.20.1+1-post-Ubuntu-0ubuntu122.04) Python Details - Python 3.10.12 Security Details - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_rstack_overflow: Mitigation of safe RET + 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
okt sqlite: 8 sqlite: 4 sqlite: 2 apache-iotdb: 800 - 100 - 500 - 100 apache-iotdb: 800 - 100 - 500 - 100 apache-iotdb: 800 - 100 - 800 - 100 apache-iotdb: 800 - 100 - 800 - 100 cryptopp: Unkeyed Algorithms liquid-dsp: 1 - 256 - 32 stress-ng: CPU Stress onednn: IP Shapes 3D - f32 - CPU oidn: RTLightmap.hdr.4096x4096 - CPU-Only onednn: IP Shapes 1D - u8s8f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU pgbench: 100 - 1000 - Read Only - Average Latency pgbench: 100 - 1000 - Read Only cpuminer-opt: Garlicoin apache-iotdb: 800 - 1 - 200 - 400 apache-iotdb: 800 - 100 - 800 - 400 apache-iotdb: 800 - 100 - 800 - 400 build2: Time To Compile qmcpack: H4_ae stress-ng: MEMFD srsran: Downlink Processor Benchmark stress-ng: IO_uring cpuminer-opt: Ringcoin liquid-dsp: 1 - 256 - 57 qmcpack: LiH_ae_MSD apache-iotdb: 800 - 1 - 200 - 400 apache-iotdb: 800 - 1 - 800 - 400 stress-ng: Glibc C String Functions ncnn: CPU - blazeface cpuminer-opt: Skeincoin oidn: RT.hdr_alb_nrm.3840x2160 - CPU-Only apache-iotdb: 800 - 1 - 500 - 100 apache-iotdb: 800 - 100 - 500 - 400 apache-iotdb: 800 - 1 - 800 - 400 stress-ng: Matrix 3D Math apache-iotdb: 800 - 1 - 500 - 100 whisper-cpp: ggml-medium.en - 2016 State of the Union hadoop: Create - 20 - 100000 liquid-dsp: 2 - 256 - 32 openvino: Person Detection FP32 - CPU ncnn: CPU - regnety_400m openvino: Person Detection FP32 - CPU z3: 2.smt2 build-llvm: Unix Makefiles liquid-dsp: 24 - 256 - 57 apache-iotdb: 800 - 100 - 200 - 100 stress-ng: Matrix Math avifenc: 6 onednn: Deconvolution Batch shapes_1d - f32 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU liquid-dsp: 2 - 256 - 57 ospray: particle_volume/pathtracer/real_time svt-av1: Preset 4 - Bosphorus 4K svt-av1: Preset 12 - Bosphorus 4K nginx: 100 liquid-dsp: 8 - 256 - 57 avifenc: 2 openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU svt-av1: Preset 13 - Bosphorus 4K ospray-studio: 3 - 4K - 16 - Path Tracer - CPU ncnn: CPU - googlenet nginx: 1000 stress-ng: Forking embree: Pathtracer - Crown openvino: Person Detection FP16 - CPU openvino: Person Detection FP16 - CPU stress-ng: Pipe liquid-dsp: 16 - 256 - 32 onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU liquid-dsp: 8 - 256 - 512 cloverleaf: clover_bm avifenc: 10, Lossless ncnn: CPU - alexnet deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream cassandra: Writes deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream encode-opus: WAV To Opus Encode stress-ng: Function Call cpuminer-opt: Deepcoin svt-av1: Preset 8 - Bosphorus 1080p onednn: IP Shapes 1D - f32 - CPU onednn: Recurrent Neural Network Training - u8s8f32 - CPU blender: BMW27 - CPU-Only stress-ng: CPU Cache ospray: gravity_spheres_volume/dim_512/ao/real_time ncnn: CPU - resnet50 svt-av1: Preset 13 - Bosphorus 1080p liquid-dsp: 4 - 256 - 32 liquid-dsp: 8 - 256 - 32 ncnn: CPU - vgg16 cpuminer-opt: Myriad-Groestl whisper-cpp: ggml-small.en - 2016 State of the Union openvino: Handwritten English Recognition FP16 - CPU qmcpack: simple-H2O liquid-dsp: 16 - 256 - 512 build-gem5: Time To Compile openvino: Handwritten English Recognition FP16 - CPU openvkl: vklBenchmarkCPU Scalar tensorflow: CPU - 16 - ResNet-50 onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU sqlite: 1 apache-iotdb: 800 - 100 - 200 - 100 avifenc: 6, Lossless stress-ng: Context Switching onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU stress-ng: MMAP onednn: Recurrent Neural Network Training - f32 - CPU stress-ng: Atomic qmcpack: Li2_STO_ae qmcpack: O_ae_pyscf_UHF ncnn: CPU - resnet18 apache-iotdb: 800 - 1 - 200 - 100 openvino: Face Detection FP16 - CPU apache-iotdb: 800 - 100 - 500 - 400 deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream ospray-studio: 1 - 1080p - 16 - Path Tracer - CPU deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream stress-ng: Wide Vector Math openvino: Vehicle Detection FP16 - CPU memcached: 1:10 apache-iotdb: 800 - 1 - 200 - 100 openvino: Vehicle Detection FP16 - CPU 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 liquid-dsp: 4 - 256 - 57 apache-iotdb: 800 - 1 - 800 - 100 stress-ng: Semaphores onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU ospray-studio: 1 - 1080p - 32 - Path Tracer - CPU 3dmark: 1920 x 1080 blender: Pabellon Barcelona - CPU-Only deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream ncnn: CPU-v3-v3 - mobilenet-v3 ospray: gravity_spheres_volume/dim_512/scivis/real_time embree: Pathtracer - Asian Dragon Obj deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream z3: 1.smt2 deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream onednn: Deconvolution Batch shapes_3d - f32 - CPU deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream memcached: 1:100 deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream nginx: 500 ncnn: CPU - vision_transformer stress-ng: Zlib openvino: Road Segmentation ADAS FP16 - CPU whisper-cpp: ggml-base.en - 2016 State of the Union openvino: Road Segmentation ADAS FP16 - CPU ncnn: CPU - efficientnet-b0 deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream svt-av1: Preset 12 - Bosphorus 1080p embree: Pathtracer ISPC - Crown openvino: Face Detection Retail FP16 - CPU palabos: 100 embree: Pathtracer ISPC - Asian Dragon openvino: Face Detection Retail FP16 - CPU openradioss: Rubber O-Ring Seal Installation ospray-studio: 3 - 1080p - 16 - Path Tracer - CPU stress-ng: Socket Activity ncnn: CPU - shufflenet-v2 stress-ng: AVL Tree stress-ng: Hash vvenc: Bosphorus 1080p - Fast dav1d: Chimera 1080p stress-ng: Poll blender: Classroom - CPU-Only ospray-studio: 2 - 1080p - 1 - Path Tracer - CPU ncnn: CPU - FastestDet stress-ng: Pthread blender: Fishy Cat - CPU-Only cpuminer-opt: Triple SHA-256, Onecoin 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 vvenc: Bosphorus 4K - Faster embree: Pathtracer - Asian Dragon brl-cad: VGR Performance Metric openradioss: Cell Phone Drop Test liquid-dsp: 1 - 256 - 512 deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream apache-iotdb: 800 - 1 - 500 - 400 deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream nginx: 200 nekrs: Kershaw deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream ospray-studio: 1 - 4K - 32 - Path Tracer - CPU stress-ng: NUMA libxsmm: 128 openvino: Weld Porosity Detection FP16 - CPU deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream ospray-studio: 1 - 4K - 16 - Path Tracer - CPU deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream openvino: Weld Porosity Detection FP16 - CPU cpuminer-opt: Quad SHA-256, Pyrite quantlib: Single-Threaded ospray-studio: 3 - 1080p - 1 - Path Tracer - CPU build-llvm: Ninja openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream svt-av1: Preset 4 - Bosphorus 1080p deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream openvino: Age Gender Recognition Retail 0013 FP16 - CPU ospray-studio: 2 - 4K - 32 - Path Tracer - CPU apache-iotdb: 800 - 1 - 800 - 100 cp2k: H20-64 onednn: Recurrent Neural Network Inference - u8s8f32 - CPU ncnn: CPU-v2-v2 - mobilenet-v2 stress-ng: Vector Shuffle stress-ng: Floating Point stress-ng: Malloc deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream stress-ng: Glibc Qsort Data Sorting ospray-studio: 1 - 1080p - 1 - Path Tracer - CPU easywave: e2Asean Grid + BengkuluSept2007 Source - 240 deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream cpuminer-opt: Magi hpcg: 104 104 104 - 60 stress-ng: SENDFILE openvino: Road Segmentation ADAS FP16-INT8 - CPU deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream ncnn: CPU - yolov4-tiny stress-ng: Futex openvino: Road Segmentation ADAS FP16-INT8 - CPU srsran: PUSCH Processor Benchmark, Throughput Total ospray-studio: 2 - 4K - 1 - Path Tracer - CPU deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream libxsmm: 32 deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream ospray-studio: 3 - 4K - 32 - Path Tracer - CPU openvino: Face Detection Retail FP16-INT8 - CPU stress-ng: Mixed Scheduler stress-ng: AVX-512 VNNI onednn: Recurrent Neural Network Inference - f32 - CPU deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream ncnn: CPU - squeezenet_ssd srsran: PUSCH Processor Benchmark, Throughput Thread stress-ng: Vector Floating Point vvenc: Bosphorus 4K - Fast stress-ng: Mutex avifenc: 0 onednn: Convolution Batch Shapes Auto - f32 - CPU openvino: Vehicle Detection FP16-INT8 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU quantlib: Multi-Threaded cpuminer-opt: LBC, LBRY Credits liquid-dsp: 24 - 256 - 512 deepsparse: ResNet-50, Baseline - Asynchronous Multi-Stream deepsparse: ResNet-50, Baseline - Asynchronous Multi-Stream stress-ng: Crypto deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream openradioss: INIVOL and Fluid Structure Interaction Drop Container openradioss: Bird Strike on Windshield openvino: Face Detection Retail FP16-INT8 - CPU ospray: gravity_spheres_volume/dim_512/pathtracer/real_time openradioss: Bumper Beam stress-ng: Memory Copying ospray-studio: 1 - 4K - 1 - Path Tracer - CPU openvino: Vehicle Detection FP16-INT8 - CPU liquid-dsp: 16 - 256 - 57 stress-ng: Fused Multiply-Add dav1d: Summer Nature 1080p deepsparse: ResNet-50, Baseline - Synchronous Single-Stream deepsparse: ResNet-50, Baseline - Synchronous Single-Stream openradioss: Chrysler Neon 1M ospray-studio: 2 - 1080p - 16 - Path Tracer - CPU dav1d: Chimera 1080p 10-bit pgbench: 100 - 1000 - Read Write stress-ng: Vector Math pgbench: 100 - 1000 - Read Write - Average Latency apache-iotdb: 800 - 1 - 500 - 400 tensorflow: CPU - 32 - ResNet-50 deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream stress-ng: System V Message Passing cloverleaf: clover_bm64_short deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream libxsmm: 64 qmcpack: FeCO6_b3lyp_gms deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream ospray: particle_volume/ao/real_time vvenc: Bosphorus 1080p - Faster ncnn: CPU - mobilenet deepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Stream openvino: Weld Porosity Detection FP16-INT8 - CPU liquid-dsp: 2 - 256 - 512 deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream openvino: Weld Porosity Detection FP16-INT8 - CPU deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream build-godot: Time To Compile liquid-dsp: 4 - 256 - 512 easywave: e2Asean Grid + BengkuluSept2007 Source - 1200 build-gcc: Time To Compile stress-ng: Cloning cpuminer-opt: Blake-2 S openvino: Face Detection FP16-INT8 - CPU ospray-studio: 3 - 1080p - 32 - Path Tracer - CPU deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream embree: Pathtracer ISPC - Asian Dragon Obj liquid-dsp: 24 - 256 - 32 openvino: Handwritten English Recognition FP16-INT8 - CPU deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream openvino: Handwritten English Recognition FP16-INT8 - CPU deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream cpuminer-opt: scrypt blender: Barbershop - CPU-Only ospray-studio: 3 - 4K - 1 - Path Tracer - CPU gpaw: Carbon Nanotube ospray: particle_volume/scivis/real_time ospray-studio: 2 - 4K - 16 - Path Tracer - CPU cp2k: Fayalite-FIST dav1d: Summer Nature 4K stress-ng: x86_64 RdRand nekrs: TurboPipe Periodic ospray-studio: 2 - 1080p - 32 - Path Tracer - CPU svt-av1: Preset 8 - Bosphorus 4K openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection FP16 - CPU ncnn: CPU - mnasnet build-nodejs: Time To Compile openvkl: vklBenchmarkCPU ISPC oidn: RT.ldr_alb_nrm.3840x2160 - CPU-Only cp2k: H2O-DFT-LS a b 46.349 31.238 26.109 214.04 22648486 335.42 23311141 415.494466 47740000 31748.06 10.6365 0.23 1.87701 0.893574 2.029 492881 1281.81 82.72 1540.09 19627767 123.554 24.37 167.93 824.7 151644.87 1882.92 53633000 111.68 883206 151.1 13058517.39 1.76 18940 0.46 1598972 783.24 1946289 887.15 29.57 1447.53988 18804 88956000 24.7 10.3 242.84 75.478 591.045 732320000 27513199 76846.98 6.329 7.4047 34.38 174.33 102790000 111.963 3.15 92.08 79156.02 391000000 63.918 18.23 328.8 92.635 210828 14.18 63534.92 25858.27 15.3439 24.67 242.85 5085408.46 640290000 23.944 78180000 134.11 6.291 9.14 19.314 110053 51.7574 29.929 9373.74 4267.42 80.613 4.76396 3923.99 106.56 1265046.6 1.94041 18.14 397.449 174840000 344230000 52.11 6257.66 475.27406 92.88 26.114 145080000 460.886 129.11 125 10.21 3937.24 15.155 68.27 10.593 2670705.05 3.44831 169.42 3936.51 546.82 229.86 185.19 9.75 21.46 1907.31 23078340 43.7603 49808 137.0885 587699.43 39.83 1646210.97 870895 150.52 50.4539 19.8169 200240000 1353913 14365053.84 2.47724 92700 251.67 345.49 490.268 12.2373 3.64 1.82533 14.6908 55.5772 29.481 32.1494 31.0984 5.39869 31.7265 1590140.06 189.0831 72766.53 70.77 1529.17 153.43 160.65923 39.08 6.21 107.8695 352.036 14.034 674.92 40.839 15.5772 8.87 134.16 57406 7209.11 4.62 116.18 2849944.32 14.143 402.46 1274815.51 289.11 2773 5.11 112428.11 134.28 40300 7.644 130.7431 9.018 16.2704 189733 98.05 10723000 17.4329 108.87 57.339 76304.8 1771410000 94.1953 63.6788 354104 134.28 231 19.82 63.8366 15.6588 46.3632 178923 21.5583 302.35 28470 3064.1 3222 573.501 14175.7 603.4131 602.3735 8.875 48.1839 9800.16 359981 57.1 102.991 2410.82 4.24 8782.71 4282.52 6492227.26 126.6146 370.88 2712 12.292 122.6699 8.1515 370.56 5.10918 127691.03 37.79 124.4685 24.32 2719437.33 158.63 2003.6 11044 466.2224 2.1424 55 56.4458 415946 5.62 8305.74 527354.87 2418.33 47.3217 11.93 245.5 35283.23 4.422 3757618.65 128.999 22.3492 354.56 2409.49 42432.3 8168.31 198510000 47.9742 125.0097 30063.86 11.6861 85.5166 600.03 272.77 1065.97 3.07954 131.78 3721.25 10796 16.91 630380000 13209967.5 793.04 85.9707 11.6246 1612.17 50479 457.63 9823 87181.78 101.804 1680328 10.05 9.9597 8498512.2 391.22 473.3056 12.676 8.1486 122.7143 106.2711 112.8 169.28 9.9426 3.83843 28.39 13.21 9.3034 107.4805 28.23 21283000 737.2404 8.1177 424.82 21.4011 46.7111 281.547 39977000 382.078 1095.023 876.55 73570 1389.42 108963 237.5691 13.4423 890410000 89.28 69.4918 25.2289 134.26 86.3167 11.2075 89.2132 128.03 1113.55 12790 310.499 3.79088 182398 171.292 196.13 6422.15 2989030000 94954 43.194 0.84 1.22 4.3 3.14 3.81 230 0.44 153.746 66.299 43.165 193.72 25003579 356.7 21936964 439.590685 45239000 30131.49 11.1973 0.22 1.79957 0.931971 1.947 513618 1333.62 79.59 1597.52 18927006 119.192 23.6 173.1 800.9 147373.62 1936.29 52191000 108.69 907114 154.86 12751183.72 1.72 18510 0.45 1634118 800.04 1907446 871.12 29.06 1472.8675 19128 90487000 24.3 10.14 246.67 76.66 600.278 721140000 27931670 77971.11 6.238 7.51062 34.87 171.89 104190000 110.473 3.109 93.275 78192.19 395730000 63.175 18.44 325.14 91.617 213159 14.03 62870.64 26129.74 15.1862 24.42 245.33 5137270.21 633870000 24.1847 78962000 135.45 6.229 9.23 19.126 111134 52.2652 29.64 9463.1 4307.38 79.873 4.7208 3959.79 107.52 1276371.48 1.95769 17.98 394.016 176360000 341300000 52.55 6205.35 471.32178 92.11 26.329 143910000 457.199 130.15 126 10.29 3967.68 15.272 67.75 10.513 2690991.53 3.47437 168.18 3965.21 550.8 231.53 186.52 9.82 21.31 1894.17 22919674 44.0421 49490 136.2151 584000.31 40.08 1656534.13 876234 149.62 50.7568 19.6988 201440000 1345876 14280745.55 2.46296 93216 253.07 343.58 487.5642 12.3051 3.62 1.83527 14.7704 55.8768 29.326 32.3176 30.9366 5.37146 31.5674 1598152.08 190.0338 72403.86 70.42 1536.76 152.68 159.8743 39.27 6.18 107.3495 350.351 14.1009 678.1 40.6509 15.649 8.83 134.76 57662 7240.74 4.6 116.68 2861814.33 14.085 400.81 1269594.39 290.28 2762 5.09 112860.19 133.77 40150 7.6158 131.2231 9.051 16.3297 190422 97.7 10761000 17.372 108.49 57.5387 76041.37 1777340000 93.8829 63.8902 352945 134.69 230.3 19.76 64.0296 15.6117 46.4968 179435 21.497 303.21 28390 3055.5 3213 575.033 14139.29 601.8748 600.8695 8.897 48.065 9776.02 359095 57.24 102.745 2405.08 4.23 8803.33 4272.51 6507116.41 126.9044 370.05 2718 12.265 122.4024 8.1693 371.36 5.09819 127965.64 37.87 124.7254 24.27 2724951.63 158.31 1999.6 11022 467.1283 2.1383 54.9 56.3444 415202 5.61 8320.26 528272.84 2414.21 47.2413 11.91 245.1 35339.57 4.415 3763560.06 128.798 22.3837 354.06 2412.87 42491.7 8157.18 198780000 47.9091 125.1795 30023.08 11.7019 85.4024 599.25 272.42 1067.32 3.07569 131.94 3725.74 10809 16.93 631120000 13224332.05 793.9 85.8786 11.637 1610.5 50427 458.1 9833 87270.26 101.701 1678639 10.06 9.9696 8490199.38 391.60 472.8641 12.6878 8.1412 122.8253 106.3662 112.7 169.43 9.9514 3.8418 28.412 13.2 9.3103 107.4009 28.21 21268000 737.749 8.1122 425.1 21.415 46.6825 281.706 39956000 382.269 1094.513 876.19 73540 1388.86 108921 237.6562 13.4374 890730000 89.31 69.4695 25.2209 134.3 86.3419 11.2046 89.2356 128.06 1113.73 12792 310.453 3.79143 182424 171.272 196.12 6421.87 2989160000 94957 43.193 0.84 1.22 4.3 3.14 3.81 468.621 230 0.44 OpenBenchmarking.org
SQLite Threads / Copies: 8 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.41.2 Threads / Copies: 8 a b 30 60 90 120 150 46.35 153.75 1. (CC) gcc options: -O2 -lreadline -ltermcap -lz -lm
SQLite Threads / Copies: 4 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.41.2 Threads / Copies: 4 a b 15 30 45 60 75 31.24 66.30 1. (CC) gcc options: -O2 -lreadline -ltermcap -lz -lm
SQLite Threads / Copies: 2 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.41.2 Threads / Copies: 2 a b 10 20 30 40 50 26.11 43.17 1. (CC) gcc options: -O2 -lreadline -ltermcap -lz -lm
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100 a b 50 100 150 200 250 214.04 193.72 MAX: 24485.71 MAX: 24261.28
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100 a b 5M 10M 15M 20M 25M 22648486 25003579
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 a b 80 160 240 320 400 335.42 356.70 MAX: 24363.54 MAX: 25191.24
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 a b 5M 10M 15M 20M 25M 23311141 21936964
Crypto++ Test: Unkeyed Algorithms OpenBenchmarking.org MiB/second, More Is Better Crypto++ 8.8 Test: Unkeyed Algorithms a b 100 200 300 400 500 415.49 439.59 1. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe
Liquid-DSP Threads: 1 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 32 a b 10M 20M 30M 40M 50M 47740000 45239000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: CPU Stress a b 7K 14K 21K 28K 35K 31748.06 30131.49 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU a b 3 6 9 12 15 10.64 11.20 MIN: 10.51 MIN: 11.1 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Intel Open Image Denoise Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.1 Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only a b 0.0518 0.1036 0.1554 0.2072 0.259 0.23 0.22
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU a b 0.4223 0.8446 1.2669 1.6892 2.1115 1.87701 1.79957 MIN: 1.77 MIN: 1.75 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU a b 0.2097 0.4194 0.6291 0.8388 1.0485 0.893574 0.931971 MIN: 0.85 MIN: 0.89 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency a b 0.4565 0.913 1.3695 1.826 2.2825 2.029 1.947 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only a b 110K 220K 330K 440K 550K 492881 513618 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Cpuminer-Opt Algorithm: Garlicoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Garlicoin a b 300 600 900 1200 1500 1281.81 1333.62 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Apache IoTDB Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 200 - Client Number: 400 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 200 - Client Number: 400 a b 20 40 60 80 100 82.72 79.59 MAX: 27561.24 MAX: 27087.19
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 a b 300 600 900 1200 1500 1540.09 1597.52 MAX: 32073.99 MAX: 33007.11
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 a b 4M 8M 12M 16M 20M 19627767 18927006
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.15 Time To Compile a b 30 60 90 120 150 123.55 119.19
QMCPACK Input: H4_ae OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: H4_ae a b 6 12 18 24 30 24.37 23.60 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: MEMFD a b 40 80 120 160 200 167.93 173.10 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
srsRAN Project Test: Downlink Processor Benchmark OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.5 Test: Downlink Processor Benchmark a b 200 400 600 800 1000 824.7 800.9 1. (CXX) g++ options: -march=native -mfma -O3 -fno-trapping-math -fno-math-errno -lgtest
Stress-NG Test: IO_uring OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: IO_uring a b 30K 60K 90K 120K 150K 151644.87 147373.62 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
Cpuminer-Opt Algorithm: Ringcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Ringcoin a b 400 800 1200 1600 2000 1882.92 1936.29 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Liquid-DSP Threads: 1 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 57 a b 11M 22M 33M 44M 55M 53633000 52191000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
QMCPACK Input: LiH_ae_MSD OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: LiH_ae_MSD a b 30 60 90 120 150 111.68 108.69 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
Apache IoTDB Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 200 - Client Number: 400 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 200 - Client Number: 400 a b 200K 400K 600K 800K 1000K 883206 907114
Apache IoTDB Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 800 - Client Number: 400 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 800 - Client Number: 400 a b 30 60 90 120 150 151.10 154.86 MAX: 27639.32 MAX: 28090.85
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Glibc C String Functions a b 3M 6M 9M 12M 15M 13058517.39 12751183.72 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: blazeface a b 0.396 0.792 1.188 1.584 1.98 1.76 1.72 MIN: 1.73 / MAX: 2.01 MIN: 1.69 / MAX: 1.82 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Cpuminer-Opt Algorithm: Skeincoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Skeincoin a b 4K 8K 12K 16K 20K 18940 18510 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Intel Open Image Denoise Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.1 Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only a b 0.1035 0.207 0.3105 0.414 0.5175 0.46 0.45
Apache IoTDB Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 500 - Client Number: 100 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 500 - Client Number: 100 a b 300K 600K 900K 1200K 1500K 1598972 1634118
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400 a b 200 400 600 800 1000 783.24 800.04 MAX: 35456.18 MAX: 34221.05
Apache IoTDB Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 800 - Client Number: 400 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 800 - Client Number: 400 a b 400K 800K 1200K 1600K 2000K 1946289 1907446
Stress-NG Test: Matrix 3D Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Matrix 3D Math a b 200 400 600 800 1000 887.15 871.12 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
Apache IoTDB Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 500 - Client Number: 100 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 500 - Client Number: 100 a b 7 14 21 28 35 29.57 29.06 MAX: 24234.87 MAX: 24192.43
Whisper.cpp Model: ggml-medium.en - Input: 2016 State of the Union OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.4 Model: ggml-medium.en - Input: 2016 State of the Union a b 300 600 900 1200 1500 1447.54 1472.87 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread
Apache Hadoop Operation: Create - Threads: 20 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Create - Threads: 20 - Files: 100000 a b 4K 8K 12K 16K 20K 18804 19128
Liquid-DSP Threads: 2 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 32 a b 20M 40M 60M 80M 100M 88956000 90487000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Person Detection FP32 - Device: CPU a b 6 12 18 24 30 24.7 24.3 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: regnety_400m a b 3 6 9 12 15 10.30 10.14 MIN: 10.22 / MAX: 10.77 MIN: 10.05 / MAX: 11.23 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Person Detection FP32 - Device: CPU a b 50 100 150 200 250 242.84 246.67 MIN: 191.04 / MAX: 270.77 MIN: 191.91 / MAX: 277.67 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Z3 Theorem Prover SMT File: 2.smt2 OpenBenchmarking.org Seconds, Fewer Is Better Z3 Theorem Prover 4.12.1 SMT File: 2.smt2 a b 20 40 60 80 100 75.48 76.66 1. (CXX) g++ options: -lpthread -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -O3 -fPIC
Timed LLVM Compilation Build System: Unix Makefiles OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 16.0 Build System: Unix Makefiles a b 130 260 390 520 650 591.05 600.28
Liquid-DSP Threads: 24 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 24 - Buffer Length: 256 - Filter Length: 57 a b 160M 320M 480M 640M 800M 732320000 721140000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 200 - Client Number: 100 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 200 - Client Number: 100 a b 6M 12M 18M 24M 30M 27513199 27931670
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Matrix Math a b 20K 40K 60K 80K 100K 76846.98 77971.11 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
libavif avifenc Encoder Speed: 6 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6 a b 2 4 6 8 10 6.329 6.238 1. (CXX) g++ options: -O3 -fPIC -lm
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU a b 2 4 6 8 10 7.40470 7.51062 MIN: 4.55 MIN: 4.54 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU a b 8 16 24 32 40 34.38 34.87 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 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU a b 40 80 120 160 200 174.33 171.89 MIN: 158.35 / MAX: 200.36 MIN: 141.31 / MAX: 194.06 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Liquid-DSP Threads: 2 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 57 a b 20M 40M 60M 80M 100M 102790000 104190000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OSPRay Benchmark: particle_volume/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: particle_volume/pathtracer/real_time a b 30 60 90 120 150 111.96 110.47
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K a b 0.7088 1.4176 2.1264 2.8352 3.544 3.150 3.109 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 4K a b 20 40 60 80 100 92.08 93.28 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
nginx Connections: 100 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 100 a b 20K 40K 60K 80K 100K 79156.02 78192.19 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
Liquid-DSP Threads: 8 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 57 a b 80M 160M 240M 320M 400M 391000000 395730000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 2 a b 14 28 42 56 70 63.92 63.18 1. (CXX) g++ options: -O3 -fPIC -lm
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU a b 5 10 15 20 25 18.23 18.44 MIN: 16.05 / MAX: 25.61 MIN: 11.58 / MAX: 32.36 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 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU a b 70 140 210 280 350 328.80 325.14 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 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 4K a b 20 40 60 80 100 92.64 91.62 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OSPRay Studio Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU a b 50K 100K 150K 200K 250K 210828 213159
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: googlenet a b 4 8 12 16 20 14.18 14.03 MIN: 13.17 / MAX: 15.43 MIN: 13.2 / MAX: 15.03 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
nginx Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 1000 a b 14K 28K 42K 56K 70K 63534.92 62870.64 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Forking a b 6K 12K 18K 24K 30K 25858.27 26129.74 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer - Model: Crown a b 4 8 12 16 20 15.34 15.19 MIN: 15.22 / MAX: 15.63 MIN: 15.07 / MAX: 15.45
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Person Detection FP16 - Device: CPU a b 6 12 18 24 30 24.67 24.42 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 2023.2.dev Model: Person Detection FP16 - Device: CPU a b 50 100 150 200 250 242.85 245.33 MIN: 157.98 / MAX: 275.6 MIN: 164.54 / MAX: 277.99 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Stress-NG Test: Pipe OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Pipe a b 1.1M 2.2M 3.3M 4.4M 5.5M 5085408.46 5137270.21 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
Liquid-DSP Threads: 16 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 32 a b 140M 280M 420M 560M 700M 640290000 633870000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU a b 6 12 18 24 30 23.94 24.18 MIN: 23.62 MIN: 23.75 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Liquid-DSP Threads: 8 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 512 a b 20M 40M 60M 80M 100M 78180000 78962000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
CloverLeaf Input: clover_bm OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf 1.3 Input: clover_bm a b 30 60 90 120 150 134.11 135.45 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
libavif avifenc Encoder Speed: 10, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 10, Lossless a b 2 4 6 8 10 6.291 6.229 1. (CXX) g++ options: -O3 -fPIC -lm
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: alexnet a b 3 6 9 12 15 9.14 9.23 MIN: 8.83 / MAX: 11.56 MIN: 8.84 / MAX: 9.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream a b 5 10 15 20 25 19.31 19.13
Apache Cassandra Test: Writes OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.1.3 Test: Writes a b 20K 40K 60K 80K 100K 110053 111134
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream a b 12 24 36 48 60 51.76 52.27
Opus Codec Encoding WAV To Opus Encode OpenBenchmarking.org Seconds, Fewer Is Better Opus Codec Encoding 1.4 WAV To Opus Encode a b 7 14 21 28 35 29.93 29.64 1. (CXX) g++ options: -O3 -fvisibility=hidden -logg -lm
Stress-NG Test: Function Call OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Function Call a b 2K 4K 6K 8K 10K 9373.74 9463.10 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
Cpuminer-Opt Algorithm: Deepcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Deepcoin a b 900 1800 2700 3600 4500 4267.42 4307.38 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 1080p a b 20 40 60 80 100 80.61 79.87 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU a b 1.0719 2.1438 3.2157 4.2876 5.3595 4.76396 4.72080 MIN: 4.51 MIN: 4.46 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU a b 800 1600 2400 3200 4000 3923.99 3959.79 MIN: 3912.85 MIN: 3952.22 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.6 Blend File: BMW27 - Compute: CPU-Only a b 20 40 60 80 100 106.56 107.52
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: CPU Cache a b 300K 600K 900K 1200K 1500K 1265046.60 1276371.48 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OSPRay Benchmark: gravity_spheres_volume/dim_512/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/ao/real_time a b 0.4405 0.881 1.3215 1.762 2.2025 1.94041 1.95769
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet50 a b 4 8 12 16 20 18.14 17.98 MIN: 17.92 / MAX: 19.11 MIN: 17.79 / MAX: 19.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 1080p a b 90 180 270 360 450 397.45 394.02 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Liquid-DSP Threads: 4 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 32 a b 40M 80M 120M 160M 200M 174840000 176360000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 8 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 32 a b 70M 140M 210M 280M 350M 344230000 341300000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vgg16 a b 12 24 36 48 60 52.11 52.55 MIN: 51.29 / MAX: 60.85 MIN: 51.15 / MAX: 145.81 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Cpuminer-Opt Algorithm: Myriad-Groestl OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Myriad-Groestl a b 1300 2600 3900 5200 6500 6257.66 6205.35 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Whisper.cpp Model: ggml-small.en - Input: 2016 State of the Union OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.4 Model: ggml-small.en - Input: 2016 State of the Union a b 100 200 300 400 500 475.27 471.32 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread
OpenVINO Model: Handwritten English Recognition FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16 - Device: CPU a b 20 40 60 80 100 92.88 92.11 MIN: 70.91 / MAX: 128.35 MIN: 76.5 / MAX: 126.89 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
QMCPACK Input: simple-H2O OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: simple-H2O a b 6 12 18 24 30 26.11 26.33 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
Liquid-DSP Threads: 16 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 512 a b 30M 60M 90M 120M 150M 145080000 143910000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Timed Gem5 Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Gem5 Compilation 23.0.1 Time To Compile a b 100 200 300 400 500 460.89 457.20
OpenVINO Model: Handwritten English Recognition FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16 - Device: CPU a b 30 60 90 120 150 129.11 130.15 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVKL Benchmark: vklBenchmarkCPU Scalar OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 2.0.0 Benchmark: vklBenchmarkCPU Scalar a b 30 60 90 120 150 125 126 MIN: 9 / MAX: 2380 MIN: 9 / MAX: 2379
TensorFlow Device: CPU - Batch Size: 16 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: ResNet-50 a b 3 6 9 12 15 10.21 10.29
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU a b 900 1800 2700 3600 4500 3937.24 3967.68 MIN: 3929.35 MIN: 3957.76 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
SQLite Threads / Copies: 1 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.41.2 Threads / Copies: 1 a b 4 8 12 16 20 15.16 15.27 1. (CC) gcc options: -O2 -lreadline -ltermcap -lz -lm
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 200 - Client Number: 100 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 200 - Client Number: 100 a b 15 30 45 60 75 68.27 67.75 MAX: 24204.26 MAX: 24201.36
libavif avifenc Encoder Speed: 6, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6, Lossless a b 3 6 9 12 15 10.59 10.51 1. (CXX) g++ options: -O3 -fPIC -lm
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Context Switching a b 600K 1200K 1800K 2400K 3000K 2670705.05 2690991.53 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU a b 0.7817 1.5634 2.3451 3.1268 3.9085 3.44831 3.47437 MIN: 3.31 MIN: 3.34 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: MMAP a b 40 80 120 160 200 169.42 168.18 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU a b 900 1800 2700 3600 4500 3936.51 3965.21 MIN: 3929.07 MIN: 3958.22 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Atomic a b 120 240 360 480 600 546.82 550.80 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
QMCPACK Input: Li2_STO_ae OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: Li2_STO_ae a b 50 100 150 200 250 229.86 231.53 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
QMCPACK Input: O_ae_pyscf_UHF OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: O_ae_pyscf_UHF a b 40 80 120 160 200 185.19 186.52 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet18 a b 3 6 9 12 15 9.75 9.82 MIN: 9.52 / MAX: 10.76 MIN: 9.51 / MAX: 10.84 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Apache IoTDB Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 200 - Client Number: 100 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 200 - Client Number: 100 a b 5 10 15 20 25 21.46 21.31 MAX: 24134.27 MAX: 24136.07
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection FP16 - Device: CPU a b 400 800 1200 1600 2000 1907.31 1894.17 MIN: 1845.25 / MAX: 1981.52 MIN: 1783.3 / MAX: 1991.75 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Apache IoTDB Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400 a b 5M 10M 15M 20M 25M 23078340 22919674
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 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream a b 10 20 30 40 50 43.76 44.04
OSPRay Studio Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU a b 11K 22K 33K 44K 55K 49808 49490
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 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream a b 30 60 90 120 150 137.09 136.22
Stress-NG Test: Wide Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Wide Vector Math a b 130K 260K 390K 520K 650K 587699.43 584000.31 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16 - Device: CPU a b 9 18 27 36 45 39.83 40.08 MIN: 21.84 / MAX: 48.24 MIN: 30.77 / MAX: 49.12 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Memcached Set To Get Ratio: 1:10 OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:10 a b 400K 800K 1200K 1600K 2000K 1646210.97 1656534.13 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Apache IoTDB Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 200 - Client Number: 100 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 200 - Client Number: 100 a b 200K 400K 600K 800K 1000K 870895 876234
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16 - Device: CPU a b 30 60 90 120 150 150.52 149.62 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
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 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream a b 11 22 33 44 55 50.45 50.76
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 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream a b 5 10 15 20 25 19.82 19.70
Liquid-DSP Threads: 4 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 57 a b 40M 80M 120M 160M 200M 200240000 201440000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Apache IoTDB Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 800 - Client Number: 100 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 800 - Client Number: 100 a b 300K 600K 900K 1200K 1500K 1353913 1345876
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Semaphores a b 3M 6M 9M 12M 15M 14365053.84 14280745.55 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU a b 0.5574 1.1148 1.6722 2.2296 2.787 2.47724 2.46296 MIN: 2.41 MIN: 2.4 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OSPRay Studio Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU a b 20K 40K 60K 80K 100K 92700 93216
3DMark Wild Life Extreme Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better 3DMark Wild Life Extreme 1.1.2.1 Resolution: 1920 x 1080 a b 60 120 180 240 300 251.67 253.07
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.6 Blend File: Pabellon Barcelona - Compute: CPU-Only a b 80 160 240 320 400 345.49 343.58
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream a b 110 220 330 440 550 490.27 487.56
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream a b 3 6 9 12 15 12.24 12.31
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 a b 0.819 1.638 2.457 3.276 4.095 3.64 3.62 MIN: 3.58 / MAX: 4.05 MIN: 3.57 / MAX: 4.05 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OSPRay Benchmark: gravity_spheres_volume/dim_512/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time a b 0.4129 0.8258 1.2387 1.6516 2.0645 1.82533 1.83527
Embree Binary: Pathtracer - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer - Model: Asian Dragon Obj a b 4 8 12 16 20 14.69 14.77 MIN: 14.61 / MAX: 14.96 MIN: 14.69 / MAX: 15.05
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream a b 13 26 39 52 65 55.58 55.88
Z3 Theorem Prover SMT File: 1.smt2 OpenBenchmarking.org Seconds, Fewer Is Better Z3 Theorem Prover 4.12.1 SMT File: 1.smt2 a b 7 14 21 28 35 29.48 29.33 1. (CXX) g++ options: -lpthread -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -O3 -fPIC
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 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream a b 8 16 24 32 40 32.15 32.32
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 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream a b 7 14 21 28 35 31.10 30.94
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU a b 1.2147 2.4294 3.6441 4.8588 6.0735 5.39869 5.37146 MIN: 5.27 MIN: 5.28 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
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 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream a b 7 14 21 28 35 31.73 31.57
Memcached Set To Get Ratio: 1:100 OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:100 a b 300K 600K 900K 1200K 1500K 1590140.06 1598152.08 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
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 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream a b 40 80 120 160 200 189.08 190.03
nginx Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 500 a b 16K 32K 48K 64K 80K 72766.53 72403.86 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
NCNN Target: CPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vision_transformer a b 16 32 48 64 80 70.77 70.42 MIN: 70.53 / MAX: 71.58 MIN: 70.1 / MAX: 77.29 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Stress-NG Test: Zlib OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Zlib a b 300 600 900 1200 1500 1529.17 1536.76 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OpenVINO Model: Road Segmentation ADAS FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16 - Device: CPU a b 30 60 90 120 150 153.43 152.68 MIN: 59.59 / MAX: 199.32 MIN: 87.43 / MAX: 179.71 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Whisper.cpp Model: ggml-base.en - Input: 2016 State of the Union OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.4 Model: ggml-base.en - Input: 2016 State of the Union a b 40 80 120 160 200 160.66 159.87 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread
OpenVINO Model: Road Segmentation ADAS FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16 - Device: CPU a b 9 18 27 36 45 39.08 39.27 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: efficientnet-b0 a b 2 4 6 8 10 6.21 6.18 MIN: 6.16 / MAX: 6.97 MIN: 6.13 / MAX: 6.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream a b 20 40 60 80 100 107.87 107.35
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 1080p a b 80 160 240 320 400 352.04 350.35 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Crown a b 4 8 12 16 20 14.03 14.10 MIN: 13.92 / MAX: 14.37 MIN: 13.99 / MAX: 14.35
OpenVINO Model: Face Detection Retail FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16 - Device: CPU a b 150 300 450 600 750 674.92 678.10 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Palabos Grid Size: 100 OpenBenchmarking.org Mega Site Updates Per Second, More Is Better Palabos 2.3 Grid Size: 100 a b 9 18 27 36 45 40.84 40.65 1. (CXX) g++ options: -std=c++17 -pedantic -O3 -rdynamic -lcrypto -lcurl -lsz -lz -ldl -lm
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon a b 4 8 12 16 20 15.58 15.65 MIN: 15.5 / MAX: 15.87 MIN: 15.56 / MAX: 15.92
OpenVINO Model: Face Detection Retail FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16 - Device: CPU a b 2 4 6 8 10 8.87 8.83 MIN: 4.07 / MAX: 24.04 MIN: 4.02 / MAX: 23.9 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenRadioss Model: Rubber O-Ring Seal Installation OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Rubber O-Ring Seal Installation a b 30 60 90 120 150 134.16 134.76
OSPRay Studio Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU a b 12K 24K 36K 48K 60K 57406 57662
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Socket Activity a b 1600 3200 4800 6400 8000 7209.11 7240.74 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: shufflenet-v2 a b 1.0395 2.079 3.1185 4.158 5.1975 4.62 4.60 MIN: 4.57 / MAX: 5.08 MIN: 4.55 / MAX: 8.06 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Stress-NG Test: AVL Tree OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: AVL Tree a b 30 60 90 120 150 116.18 116.68 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
Stress-NG Test: Hash OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Hash a b 600K 1200K 1800K 2400K 3000K 2849944.32 2861814.33 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
VVenC Video Input: Bosphorus 1080p - Video Preset: Fast OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 1080p - Video Preset: Fast a b 4 8 12 16 20 14.14 14.09 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better dav1d 1.2.1 Video Input: Chimera 1080p a b 90 180 270 360 450 402.46 400.81 1. (CC) gcc options: -pthread -lm
Stress-NG Test: Poll OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Poll a b 300K 600K 900K 1200K 1500K 1274815.51 1269594.39 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.6 Blend File: Classroom - Compute: CPU-Only a b 60 120 180 240 300 289.11 290.28
OSPRay Studio Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU a b 600 1200 1800 2400 3000 2773 2762
NCNN Target: CPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: FastestDet a b 1.1498 2.2996 3.4494 4.5992 5.749 5.11 5.09 MIN: 5.08 / MAX: 5.23 MIN: 5.04 / MAX: 5.14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Stress-NG Test: Pthread OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Pthread a b 20K 40K 60K 80K 100K 112428.11 112860.19 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.6 Blend File: Fishy Cat - Compute: CPU-Only a b 30 60 90 120 150 134.28 133.77
Cpuminer-Opt Algorithm: Triple SHA-256, Onecoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Triple SHA-256, Onecoin a b 9K 18K 27K 36K 45K 40300 40150 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
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 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream a b 2 4 6 8 10 7.6440 7.6158
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 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream a b 30 60 90 120 150 130.74 131.22
VVenC Video Input: Bosphorus 4K - Video Preset: Faster OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Faster a b 3 6 9 12 15 9.018 9.051 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
Embree Binary: Pathtracer - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer - Model: Asian Dragon a b 4 8 12 16 20 16.27 16.33 MIN: 16.19 / MAX: 16.52 MIN: 16.24 / MAX: 16.6
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.36 VGR Performance Metric a b 40K 80K 120K 160K 200K 189733 190422 1. (CXX) g++ options: -std=c++14 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lregex_brl -lz_brl -lnetpbm -ldl -lm -ltk8.6
OpenRadioss Model: Cell Phone Drop Test OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Cell Phone Drop Test a b 20 40 60 80 100 98.05 97.70
Liquid-DSP Threads: 1 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 512 a b 2M 4M 6M 8M 10M 10723000 10761000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
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 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream a b 4 8 12 16 20 17.43 17.37
Apache IoTDB Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 500 - Client Number: 400 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 500 - Client Number: 400 a b 20 40 60 80 100 108.87 108.49 MAX: 27415.25 MAX: 27965.48
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 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream a b 13 26 39 52 65 57.34 57.54
nginx Connections: 200 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 200 a b 16K 32K 48K 64K 80K 76304.80 76041.37 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
nekRS Input: Kershaw OpenBenchmarking.org flops/rank, More Is Better nekRS 23.0 Input: Kershaw a b 400M 800M 1200M 1600M 2000M 1771410000 1777340000 1. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream a b 20 40 60 80 100 94.20 93.88
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream a b 14 28 42 56 70 63.68 63.89
OSPRay Studio Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU a b 80K 160K 240K 320K 400K 354104 352945
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: NUMA a b 30 60 90 120 150 134.28 134.69 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
libxsmm M N K: 128 OpenBenchmarking.org GFLOPS/s, More Is Better libxsmm 2-1.17-3645 M N K: 128 a b 50 100 150 200 250 231.0 230.3 1. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -pedantic -O2 -fopenmp -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -march=core-avx2
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16 - Device: CPU a b 5 10 15 20 25 19.82 19.76 MIN: 18.83 / MAX: 29.95 MIN: 18.68 / MAX: 39.87 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream a b 14 28 42 56 70 63.84 64.03
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream a b 4 8 12 16 20 15.66 15.61
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream a b 11 22 33 44 55 46.36 46.50
OSPRay Studio Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU a b 40K 80K 120K 160K 200K 178923 179435
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream a b 5 10 15 20 25 21.56 21.50
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16 - Device: CPU a b 70 140 210 280 350 302.35 303.21 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Cpuminer-Opt Algorithm: Quad SHA-256, Pyrite OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Quad SHA-256, Pyrite a b 6K 12K 18K 24K 30K 28470 28390 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
QuantLib Configuration: Single-Threaded OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Single-Threaded a b 700 1400 2100 2800 3500 3064.1 3055.5 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
OSPRay Studio Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU a b 700 1400 2100 2800 3500 3222 3213
Timed LLVM Compilation Build System: Ninja OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 16.0 Build System: Ninja a b 120 240 360 480 600 573.50 575.03
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b 3K 6K 9K 12K 15K 14175.70 14139.29 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: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream a b 130 260 390 520 650 603.41 601.87
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 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream a b 130 260 390 520 650 602.37 600.87
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 1080p a b 2 4 6 8 10 8.875 8.897 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 ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a b 11 22 33 44 55 48.18 48.07
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b 2K 4K 6K 8K 10K 9800.16 9776.02 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OSPRay Studio Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU a b 80K 160K 240K 320K 400K 359981 359095
Apache IoTDB Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 800 - Client Number: 100 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 800 - Client Number: 100 a b 13 26 39 52 65 57.10 57.24 MAX: 24233.95 MAX: 24166.47
CP2K Molecular Dynamics Input: H20-64 OpenBenchmarking.org Seconds, Fewer Is Better CP2K Molecular Dynamics 2023.1 Input: H20-64 a b 20 40 60 80 100 102.99 102.75 1. (F9X) gfortran options: -fopenmp -mtune=native -O3 -funroll-loops -fbacktrace -ffree-form -fimplicit-none -std=f2008 -lcp2kstart -lcp2kmc -lcp2kswarm -lcp2kmotion -lcp2kthermostat -lcp2kemd -lcp2ktmc -lcp2kmain -lcp2kdbt -lcp2ktas -lcp2kdbm -lcp2kgrid -lcp2kgridcpu -lcp2kgridref -lcp2kgridcommon -ldbcsrarnoldi -ldbcsrx -lcp2kshg_int -lcp2keri_mme -lcp2kminimax -lcp2khfxbase -lcp2ksubsys -lcp2kxc -lcp2kao -lcp2kpw_env -lcp2kinput -lcp2kpw -lcp2kgpu -lcp2kfft -lcp2kfpga -lcp2kfm -lcp2kcommon -lcp2koffload -lcp2kmpiwrap -lcp2kbase -ldbcsr -lsirius -lspla -lspfft -lsymspg -lvdwxc -lhdf5 -lhdf5_hl -lz -lgsl -lelpa_openmp -lcosma -lcosta -lscalapack -lxsmmf -lxsmm -ldl -lpthread -lxcf03 -lxc -lint2 -lfftw3_mpi -lfftw3 -lfftw3_omp -lmpi_cxx -lmpi -lopenblas -lvori -lstdc++ -lmpi_usempif08 -lmpi_mpifh -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU a b 500 1000 1500 2000 2500 2410.82 2405.08 MIN: 2404.84 MIN: 2398.42 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 a b 0.954 1.908 2.862 3.816 4.77 4.24 4.23 MIN: 4.18 / MAX: 4.68 MIN: 4.15 / MAX: 6.3 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Stress-NG Test: Vector Shuffle OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Shuffle a b 2K 4K 6K 8K 10K 8782.71 8803.33 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
Stress-NG Test: Floating Point OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Floating Point a b 900 1800 2700 3600 4500 4282.52 4272.51 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Malloc a b 1.4M 2.8M 4.2M 5.6M 7M 6492227.26 6507116.41 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
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 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b 30 60 90 120 150 126.61 126.90
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Glibc Qsort Data Sorting a b 80 160 240 320 400 370.88 370.05 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OSPRay Studio Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU a b 600 1200 1800 2400 3000 2712 2718
easyWave Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240 OpenBenchmarking.org Seconds, Fewer Is Better easyWave r34 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240 a b 3 6 9 12 15 12.29 12.27 1. (CXX) g++ options: -O3 -fopenmp
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 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream a b 30 60 90 120 150 122.67 122.40
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 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream a b 2 4 6 8 10 8.1515 8.1693
Cpuminer-Opt Algorithm: Magi OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Magi a b 80 160 240 320 400 370.56 371.36 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
High Performance Conjugate Gradient X Y Z: 104 104 104 - RT: 60 OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 X Y Z: 104 104 104 - RT: 60 a b 1.1496 2.2992 3.4488 4.5984 5.748 5.10918 5.09819 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: SENDFILE a b 30K 60K 90K 120K 150K 127691.03 127965.64 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU a b 9 18 27 36 45 37.79 37.87 MIN: 32.26 / MAX: 49.53 MIN: 28.43 / MAX: 64.79 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a b 30 60 90 120 150 124.47 124.73
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: yolov4-tiny a b 6 12 18 24 30 24.32 24.27 MIN: 24.14 / MAX: 25.12 MIN: 24.09 / MAX: 25.04 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Stress-NG Test: Futex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Futex a b 600K 1200K 1800K 2400K 3000K 2719437.33 2724951.63 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU a b 40 80 120 160 200 158.63 158.31 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
srsRAN Project Test: PUSCH Processor Benchmark, Throughput Total OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.5 Test: PUSCH Processor Benchmark, Throughput Total a b 400 800 1200 1600 2000 2003.6 1999.6 1. (CXX) g++ options: -march=native -mfma -O3 -fno-trapping-math -fno-math-errno -lgtest
OSPRay Studio Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU a b 2K 4K 6K 8K 10K 11044 11022
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream a b 100 200 300 400 500 466.22 467.13
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream a b 0.482 0.964 1.446 1.928 2.41 2.1424 2.1383
libxsmm M N K: 32 OpenBenchmarking.org GFLOPS/s, More Is Better libxsmm 2-1.17-3645 M N K: 32 a b 12 24 36 48 60 55.0 54.9 1. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -pedantic -O2 -fopenmp -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -march=core-avx2
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b 13 26 39 52 65 56.45 56.34
OSPRay Studio Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU a b 90K 180K 270K 360K 450K 415946 415202
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU a b 1.2645 2.529 3.7935 5.058 6.3225 5.62 5.61 MIN: 4.32 / MAX: 13.99 MIN: 4.02 / MAX: 14.15 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Stress-NG Test: Mixed Scheduler OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Mixed Scheduler a b 2K 4K 6K 8K 10K 8305.74 8320.26 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
Stress-NG Test: AVX-512 VNNI OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: AVX-512 VNNI a b 110K 220K 330K 440K 550K 527354.87 528272.84 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU a b 500 1000 1500 2000 2500 2418.33 2414.21 MIN: 2409.86 MIN: 2407.75 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
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 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b 11 22 33 44 55 47.32 47.24
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: squeezenet_ssd a b 3 6 9 12 15 11.93 11.91 MIN: 11.68 / MAX: 12.5 MIN: 11.64 / MAX: 12.21 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
srsRAN Project Test: PUSCH Processor Benchmark, Throughput Thread OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.5 Test: PUSCH Processor Benchmark, Throughput Thread a b 50 100 150 200 250 245.5 245.1 1. (CXX) g++ options: -march=native -mfma -O3 -fno-trapping-math -fno-math-errno -lgtest
Stress-NG Test: Vector Floating Point OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Floating Point a b 8K 16K 24K 32K 40K 35283.23 35339.57 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
VVenC Video Input: Bosphorus 4K - Video Preset: Fast OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Fast a b 0.995 1.99 2.985 3.98 4.975 4.422 4.415 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
Stress-NG Test: Mutex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Mutex a b 800K 1600K 2400K 3200K 4000K 3757618.65 3763560.06 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 0 a b 30 60 90 120 150 129.00 128.80 1. (CXX) g++ options: -O3 -fPIC -lm
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU a b 5 10 15 20 25 22.35 22.38 MIN: 21.78 MIN: 21.99 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU a b 80 160 240 320 400 354.56 354.06 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU a b 500 1000 1500 2000 2500 2409.49 2412.87 MIN: 2402.26 MIN: 2406.34 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
QuantLib Configuration: Multi-Threaded OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Multi-Threaded a b 9K 18K 27K 36K 45K 42432.3 42491.7 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
Cpuminer-Opt Algorithm: LBC, LBRY Credits OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: LBC, LBRY Credits a b 2K 4K 6K 8K 10K 8168.31 8157.18 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Liquid-DSP Threads: 24 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 24 - Buffer Length: 256 - Filter Length: 512 a b 40M 80M 120M 160M 200M 198510000 198780000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream a b 11 22 33 44 55 47.97 47.91
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream a b 30 60 90 120 150 125.01 125.18
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Crypto a b 6K 12K 18K 24K 30K 30063.86 30023.08 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream a b 3 6 9 12 15 11.69 11.70
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream a b 20 40 60 80 100 85.52 85.40
OpenRadioss Model: INIVOL and Fluid Structure Interaction Drop Container OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: INIVOL and Fluid Structure Interaction Drop Container a b 130 260 390 520 650 600.03 599.25
OpenRadioss Model: Bird Strike on Windshield OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Bird Strike on Windshield a b 60 120 180 240 300 272.77 272.42
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU a b 200 400 600 800 1000 1065.97 1067.32 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OSPRay Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time a b 0.6929 1.3858 2.0787 2.7716 3.4645 3.07954 3.07569
OpenRadioss Model: Bumper Beam OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Bumper Beam a b 30 60 90 120 150 131.78 131.94
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Memory Copying a b 800 1600 2400 3200 4000 3721.25 3725.74 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OSPRay Studio Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU a b 2K 4K 6K 8K 10K 10796 10809
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU a b 4 8 12 16 20 16.91 16.93 MIN: 9.89 / MAX: 26.56 MIN: 9.9 / MAX: 26.26 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Liquid-DSP Threads: 16 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 57 a b 140M 280M 420M 560M 700M 630380000 631120000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Stress-NG Test: Fused Multiply-Add OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Fused Multiply-Add a b 3M 6M 9M 12M 15M 13209967.50 13224332.05 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 1.2.1 Video Input: Summer Nature 1080p a b 200 400 600 800 1000 793.04 793.90 1. (CC) gcc options: -pthread -lm
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream a b 20 40 60 80 100 85.97 85.88
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream a b 3 6 9 12 15 11.62 11.64
OpenRadioss Model: Chrysler Neon 1M OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Chrysler Neon 1M a b 300 600 900 1200 1500 1612.17 1610.50
OSPRay Studio Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU a b 11K 22K 33K 44K 55K 50479 50427
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 1.2.1 Video Input: Chimera 1080p 10-bit a b 100 200 300 400 500 457.63 458.10 1. (CC) gcc options: -pthread -lm
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write a b 2K 4K 6K 8K 10K 9823 9833 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Math a b 20K 40K 60K 80K 100K 87181.78 87270.26 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency a b 20 40 60 80 100 101.80 101.70 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Apache IoTDB Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 500 - Client Number: 400 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 1 - Sensor Count: 500 - Client Number: 400 a b 400K 800K 1200K 1600K 2000K 1680328 1678639
TensorFlow Device: CPU - Batch Size: 32 - Model: ResNet-50 OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: ResNet-50 a b 3 6 9 12 15 10.05 10.06
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 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream a b 3 6 9 12 15 9.9597 9.9696
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: System V Message Passing a b 2M 4M 6M 8M 10M 8498512.20 8490199.38 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
CloverLeaf Input: clover_bm64_short OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf 1.3 Input: clover_bm64_short a b 80 160 240 320 400 391.22 391.60 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream a b 100 200 300 400 500 473.31 472.86
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream a b 3 6 9 12 15 12.68 12.69
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 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream a b 2 4 6 8 10 8.1486 8.1412
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 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream a b 30 60 90 120 150 122.71 122.83
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b 20 40 60 80 100 106.27 106.37
libxsmm M N K: 64 OpenBenchmarking.org GFLOPS/s, More Is Better libxsmm 2-1.17-3645 M N K: 64 a b 30 60 90 120 150 112.8 112.7 1. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -pedantic -O2 -fopenmp -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -march=core-avx2
QMCPACK Input: FeCO6_b3lyp_gms OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: FeCO6_b3lyp_gms a b 40 80 120 160 200 169.28 169.43 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
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 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream a b 3 6 9 12 15 9.9426 9.9514
OSPRay Benchmark: particle_volume/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: particle_volume/ao/real_time a b 0.8644 1.7288 2.5932 3.4576 4.322 3.83843 3.84180
VVenC Video Input: Bosphorus 1080p - Video Preset: Faster OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 1080p - Video Preset: Faster a b 7 14 21 28 35 28.39 28.41 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mobilenet a b 3 6 9 12 15 13.21 13.20 MIN: 13.09 / MAX: 14.18 MIN: 13.12 / MAX: 13.37 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream a b 3 6 9 12 15 9.3034 9.3103
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream a b 20 40 60 80 100 107.48 107.40
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU a b 7 14 21 28 35 28.23 28.21 MIN: 22.9 / MAX: 46.18 MIN: 20.68 / MAX: 35.43 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Liquid-DSP Threads: 2 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 512 a b 5M 10M 15M 20M 25M 21283000 21268000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b 160 320 480 640 800 737.24 737.75
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b 2 4 6 8 10 8.1177 8.1122
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU a b 90 180 270 360 450 424.82 425.10 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream a b 5 10 15 20 25 21.40 21.42
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream a b 11 22 33 44 55 46.71 46.68
Timed Godot Game Engine Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 4.0 Time To Compile a b 60 120 180 240 300 281.55 281.71
Liquid-DSP Threads: 4 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 512 a b 9M 18M 27M 36M 45M 39977000 39956000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
easyWave Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200 OpenBenchmarking.org Seconds, Fewer Is Better easyWave r34 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200 a b 80 160 240 320 400 382.08 382.27 1. (CXX) g++ options: -O3 -fopenmp
Timed GCC Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GCC Compilation 13.2 Time To Compile a b 200 400 600 800 1000 1095.02 1094.51
Stress-NG Test: Cloning OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Cloning a b 200 400 600 800 1000 876.55 876.19 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
Cpuminer-Opt Algorithm: Blake-2 S OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: Blake-2 S a b 16K 32K 48K 64K 80K 73570 73540 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU a b 300 600 900 1200 1500 1389.42 1388.86 MIN: 1339.19 / MAX: 1419.26 MIN: 1363.36 / MAX: 1429.32 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OSPRay Studio Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU a b 20K 40K 60K 80K 100K 108963 108921
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 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b 50 100 150 200 250 237.57 237.66
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Obj a b 3 6 9 12 15 13.44 13.44 MIN: 13.37 / MAX: 13.61 MIN: 13.37 / MAX: 13.62
Liquid-DSP Threads: 24 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 24 - Buffer Length: 256 - Filter Length: 32 a b 200M 400M 600M 800M 1000M 890410000 890730000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU a b 20 40 60 80 100 89.28 89.31 MIN: 78.99 / MAX: 107.97 MIN: 78.81 / MAX: 108.46 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream a b 15 30 45 60 75 69.49 69.47
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 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b 6 12 18 24 30 25.23 25.22
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU a b 30 60 90 120 150 134.26 134.30 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream a b 20 40 60 80 100 86.32 86.34
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream a b 3 6 9 12 15 11.21 11.20
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream a b 20 40 60 80 100 89.21 89.24
Cpuminer-Opt Algorithm: scrypt OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 23.5 Algorithm: scrypt a b 30 60 90 120 150 128.03 128.06 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.6 Blend File: Barbershop - Compute: CPU-Only a b 200 400 600 800 1000 1113.55 1113.73
OSPRay Studio Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU a b 3K 6K 9K 12K 15K 12790 12792
GPAW Input: Carbon Nanotube OpenBenchmarking.org Seconds, Fewer Is Better GPAW 23.6 Input: Carbon Nanotube a b 70 140 210 280 350 310.50 310.45 1. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi
OSPRay Benchmark: particle_volume/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: particle_volume/scivis/real_time a b 0.8531 1.7062 2.5593 3.4124 4.2655 3.79088 3.79143
OSPRay Studio Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU a b 40K 80K 120K 160K 200K 182398 182424
CP2K Molecular Dynamics Input: Fayalite-FIST OpenBenchmarking.org Seconds, Fewer Is Better CP2K Molecular Dynamics 2023.1 Input: Fayalite-FIST a b 40 80 120 160 200 171.29 171.27 1. (F9X) gfortran options: -fopenmp -mtune=native -O3 -funroll-loops -fbacktrace -ffree-form -fimplicit-none -std=f2008 -lcp2kstart -lcp2kmc -lcp2kswarm -lcp2kmotion -lcp2kthermostat -lcp2kemd -lcp2ktmc -lcp2kmain -lcp2kdbt -lcp2ktas -lcp2kdbm -lcp2kgrid -lcp2kgridcpu -lcp2kgridref -lcp2kgridcommon -ldbcsrarnoldi -ldbcsrx -lcp2kshg_int -lcp2keri_mme -lcp2kminimax -lcp2khfxbase -lcp2ksubsys -lcp2kxc -lcp2kao -lcp2kpw_env -lcp2kinput -lcp2kpw -lcp2kgpu -lcp2kfft -lcp2kfpga -lcp2kfm -lcp2kcommon -lcp2koffload -lcp2kmpiwrap -lcp2kbase -ldbcsr -lsirius -lspla -lspfft -lsymspg -lvdwxc -lhdf5 -lhdf5_hl -lz -lgsl -lelpa_openmp -lcosma -lcosta -lscalapack -lxsmmf -lxsmm -ldl -lpthread -lxcf03 -lxc -lint2 -lfftw3_mpi -lfftw3 -lfftw3_omp -lmpi_cxx -lmpi -lopenblas -lvori -lstdc++ -lmpi_usempif08 -lmpi_mpifh -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 1.2.1 Video Input: Summer Nature 4K a b 40 80 120 160 200 196.13 196.12 1. (CC) gcc options: -pthread -lm
Stress-NG Test: x86_64 RdRand OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: x86_64 RdRand a b 1400 2800 4200 5600 7000 6422.15 6421.87 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
nekRS Input: TurboPipe Periodic OpenBenchmarking.org flops/rank, More Is Better nekRS 23.0 Input: TurboPipe Periodic a b 600M 1200M 1800M 2400M 3000M 2989030000 2989160000 1. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi
OSPRay Studio Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.13 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU a b 20K 40K 60K 80K 100K 94954 94957
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K a b 10 20 30 40 50 43.19 43.19 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b 0.189 0.378 0.567 0.756 0.945 0.84 0.84 MIN: 0.52 / MAX: 3.12 MIN: 0.52 / MAX: 8.49 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 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b 0.2745 0.549 0.8235 1.098 1.3725 1.22 1.22 MIN: 0.7 / MAX: 10.62 MIN: 0.67 / MAX: 3.57 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 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU a b 0.9675 1.935 2.9025 3.87 4.8375 4.3 4.3 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 FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection FP16 - Device: CPU a b 0.7065 1.413 2.1195 2.826 3.5325 3.14 3.14 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mnasnet a b 0.8573 1.7146 2.5719 3.4292 4.2865 3.81 3.81 MIN: 3.75 / MAX: 4.2 MIN: 3.75 / MAX: 4.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 19.8.1 Time To Compile b 100 200 300 400 500 468.62
OpenVKL Benchmark: vklBenchmarkCPU ISPC OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 2.0.0 Benchmark: vklBenchmarkCPU ISPC a b 50 100 150 200 250 230 230 MIN: 18 / MAX: 2978 MIN: 19 / MAX: 2962
Intel Open Image Denoise Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.1 Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only a b 0.099 0.198 0.297 0.396 0.495 0.44 0.44
Phoronix Test Suite v10.8.5