zen 1 epyc 2 x AMD EPYC 7601 32-Core testing with a Dell 02MJ3T (1.2.5 BIOS) and Matrox G200eW3 on Ubuntu 22.04 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2211191-NE-ZEN1EPYC673 a Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: CPU Microcode: 0x8001250Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected
b Processor: 2 x AMD EPYC 7601 32-Core (64 Cores / 128 Threads), Motherboard: Dell 02MJ3T (1.2.5 BIOS), Chipset: AMD 17h, Memory: 512GB, Disk: 280GB INTEL SSDPED1D280GA + 12 x 500GB Samsung SSD 860 + 120GB INTEL SSDSCKJB120G7R, Graphics: Matrox G200eW3, Monitor: VE228, Network: 2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA + 2 x Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 22.04, Kernel: 5.15.0-40-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 1600x1200
zen 1 epyc OpenBenchmarking.org Phoronix Test Suite 10.8.4 2 x AMD EPYC 7601 32-Core (64 Cores / 128 Threads) Dell 02MJ3T (1.2.5 BIOS) AMD 17h 512GB 280GB INTEL SSDPED1D280GA + 12 x 500GB Samsung SSD 860 + 120GB INTEL SSDSCKJB120G7R Matrox G200eW3 VE228 2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA + 2 x Broadcom NetXtreme BCM5720 PCIe Ubuntu 22.04 5.15.0-40-generic (x86_64) GNOME Shell 42.2 X Server 1.21.1.3 1.2.204 GCC 11.3.0 ext4 1600x1200 Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Vulkan Compiler File-System Screen Resolution Zen 1 Epyc Benchmarks System Logs - Transparent Huge Pages: madvise - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - NONE / errors=remount-ro,relatime,rw / Block Size: 4096 - CPU Microcode: 0x8001250 - Python 3.10.6 - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected
a vs. b Comparison Phoronix Test Suite 10.8.4 Baseline +15.3% +15.3% +30.6% +30.6% +45.9% +45.9% +61.2% +61.2% 61.2% 54.7% 48.8% 46.3% 37.8% 36.7% 30.4% 28.5% 23.1% 22.5% 22.1% 13.4% 12.6% 12% 11.1% 10.6% 10.2% 10% 8% 8% 7.9% 7.1% 7% 6.9% 6.8% 6.4% 6.3% 5.1% 4.9% 4.7% 4.6% 4.4% 4% 3.9% 3.9% 3.5% 3% 2.9% 2.6% 2.6% 2.5% 2.5% 2.5% 2.4% 2.3% CPU - resnet50 CPU-v2-v2 - mobilenet-v2 CPU - FastestDet CPU - shufflenet-v2 CPU - regnety_400m CPU - blazeface CPU Cache CPU-v3-v3 - mobilenet-v3 29.5% CPU - resnet18 Resizing 23.7% CPU - mnasnet M.M.B.S.T - f32 - CPU CPU - alexnet Monero - 1M 17.2% CPU - mobilenet 17% HWB Color Space 15.7% Speed 9 Realtime - Bosphorus 1080p 13.6% Preset 10 - Bosphorus 4K CPU - vgg16 Preset 12 - Bosphorus 1080p D.B.s - u8s8f32 - CPU 11.9% Noise-Gaussian 11.8% IP Shapes 1D - u8s8f32 - CPU 1.5 kbps 11% Default CPU - googlenet Atomic R.N.N.T - f32 - CPU 8.7% Speed 8 Realtime - Bosphorus 1080p 8.6% Speed 10 Realtime - Bosphorus 1080p 8.1% Speed 8 Realtime - Bosphorus 4K 8% N.Q.A.B.b.u.S.1.P - S.S.S N.Q.A.B.b.u.S.1.P - S.S.S resnet-v2-50 Read While Writing D.B.s - f32 - CPU CPU - vision_transformer Memory Copying CPU - squeezenet_ssd nasnet 1.R.W.A.D.T.R 6% 1.R.W.A.D.F.R.C.C C.B.S.A - f32 - CPU squeezenetv1.1 Context Switching SqueezeNetV1.0 20k Atoms 4.3% Garlicoin 1.R.W.A.D.S.R mobilenet-v1-1.0 CPU - yolov4-tiny 3.9% Preset 12 - Bosphorus 4K 24 kbps 3.5% CPU - efficientnet-b0 3.3% Speed 6 Realtime - Bosphorus 4K 3.3% MMAP 3.2% R.N.N.T - u8s8f32 - CPU 3.2% M.M.B.S.T - u8s8f32 - CPU Spaceship S.V.M.P 2.8% Speed 6 Two-Pass - Bosphorus 4K 2.8% 3 kbps 2.7% Q.7.C.E.7 2.7% G.C.S.F R.N.N.I - f32 - CPU M.T.E.T.D.F - CPU d.S.M.S - Execution Time 2.5% M.T.E.T.D.F - CPU Speed 6 Two-Pass - Bosphorus 1080p 2.5% Socket Activity Q.1.L.H.C mobilenetV3 en_core_web_trf 2.3% 2.3% CPU - 32 - GoogLeNet 2.3% libx265 - Live 2.1% libx265 - Live 2.1% Speed 4 Two-Pass - Bosphorus 1080p 2% NCNN NCNN NCNN NCNN NCNN NCNN Stress-NG NCNN NCNN GraphicsMagick NCNN oneDNN NCNN Xmrig NCNN GraphicsMagick AOM AV1 SVT-AV1 NCNN SVT-AV1 oneDNN GraphicsMagick oneDNN EnCodec WebP2 Image Encode NCNN Stress-NG oneDNN AOM AV1 AOM AV1 AOM AV1 Neural Magic DeepSparse Neural Magic DeepSparse Mobile Neural Network Facebook RocksDB oneDNN NCNN Stress-NG NCNN Mobile Neural Network ClickHouse ClickHouse oneDNN Mobile Neural Network Stress-NG Mobile Neural Network LAMMPS Molecular Dynamics Simulator Cpuminer-Opt ClickHouse Mobile Neural Network NCNN SVT-AV1 EnCodec NCNN AOM AV1 Stress-NG oneDNN oneDNN Natron Stress-NG AOM AV1 EnCodec WebP2 Image Encode Stress-NG oneDNN OpenVINO OpenFOAM OpenVINO AOM AV1 Stress-NG WebP Image Encode Mobile Neural Network spaCy Aircrack-ng TensorFlow FFmpeg FFmpeg AOM AV1 a b
zen 1 epyc ncnn: CPU - resnet50 ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU - FastestDet ncnn: CPU - shufflenet-v2 ncnn: CPU - regnety_400m ncnn: CPU - blazeface stress-ng: CPU Cache ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU - resnet18 graphics-magick: Resizing ncnn: CPU - mnasnet onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU ncnn: CPU - alexnet xmrig: Monero - 1M ncnn: CPU - mobilenet graphics-magick: HWB Color Space aom-av1: Speed 9 Realtime - Bosphorus 1080p svt-av1: Preset 10 - Bosphorus 4K ncnn: CPU - vgg16 svt-av1: Preset 12 - Bosphorus 1080p onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU graphics-magick: Noise-Gaussian onednn: IP Shapes 1D - u8s8f32 - CPU encodec: 1.5 kbps webp2: Default ncnn: CPU - googlenet stress-ng: Atomic onednn: Recurrent Neural Network Training - f32 - CPU aom-av1: Speed 8 Realtime - Bosphorus 1080p aom-av1: Speed 10 Realtime - Bosphorus 1080p aom-av1: Speed 8 Realtime - Bosphorus 4K 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 mnn: resnet-v2-50 rocksdb: Read While Writing onednn: Deconvolution Batch shapes_3d - f32 - CPU ncnn: CPU - vision_transformer stress-ng: Memory Copying ncnn: CPU - squeezenet_ssd mnn: nasnet clickhouse: 100M Rows Web Analytics Dataset, Third Run clickhouse: 100M Rows Web Analytics Dataset, First Run / Cold Cache onednn: Convolution Batch Shapes Auto - f32 - CPU mnn: squeezenetv1.1 stress-ng: Context Switching mnn: SqueezeNetV1.0 lammps: 20k Atoms cpuminer-opt: Garlicoin clickhouse: 100M Rows Web Analytics Dataset, Second Run mnn: mobilenet-v1-1.0 ncnn: CPU - yolov4-tiny svt-av1: Preset 12 - Bosphorus 4K encodec: 24 kbps ncnn: CPU - efficientnet-b0 aom-av1: Speed 6 Realtime - Bosphorus 4K stress-ng: MMAP onednn: Recurrent Neural Network Training - u8s8f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU natron: Spaceship stress-ng: System V Message Passing aom-av1: Speed 6 Two-Pass - Bosphorus 4K encodec: 3 kbps webp2: Quality 75, Compression Effort 7 stress-ng: Glibc C String Functions onednn: Recurrent Neural Network Inference - f32 - CPU openvino: Machine Translation EN To DE FP16 - CPU openfoam: drivaerFastback, Small Mesh Size - Execution Time openvino: Machine Translation EN To DE FP16 - CPU aom-av1: Speed 6 Two-Pass - Bosphorus 1080p stress-ng: Socket Activity webp: Quality 100, Lossless, Highest Compression mnn: mobilenetV3 spacy: en_core_web_trf aircrack-ng: tensorflow: CPU - 32 - GoogLeNet ffmpeg: libx265 - Live ffmpeg: libx265 - Live aom-av1: Speed 4 Two-Pass - Bosphorus 1080p aom-av1: Speed 9 Realtime - Bosphorus 4K y-cruncher: 500M onednn: IP Shapes 1D - f32 - CPU aom-av1: Speed 0 Two-Pass - Bosphorus 1080p brl-cad: VGR Performance Metric nginx: 200 node-web-tooling: openvino: Person Detection FP32 - CPU astcenc: Fast minibude: OpenMP - BM2 minibude: OpenMP - BM2 onednn: IP Shapes 3D - u8s8f32 - CPU minibude: OpenMP - BM1 minibude: OpenMP - BM1 stress-ng: Mutex deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream tensorflow: CPU - 16 - GoogLeNet openradioss: INIVOL and Fluid Structure Interaction Drop Container svt-av1: Preset 10 - Bosphorus 1080p stress-ng: Forking graphics-magick: Rotate cpuminer-opt: Myriad-Groestl graphics-magick: Sharpen deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream ai-benchmark: Device Inference Score openvino: Person Detection FP32 - CPU rocksdb: Rand Read smhasher: t1ha0_aes_avx2 x86_64 onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU aom-av1: Speed 6 Realtime - Bosphorus 1080p nginx: 1000 mnn: MobileNetV2_224 webp2: Quality 100, Compression Effort 5 webp: Quality 100, Lossless tensorflow: CPU - 32 - ResNet-50 avifenc: 6, Lossless nginx: 500 openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU svt-av1: Preset 8 - Bosphorus 4K ai-benchmark: Device AI Score deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream unpack-linux: linux-5.19.tar.xz deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream svt-av1: Preset 4 - Bosphorus 1080p deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream stress-ng: Glibc Qsort Data Sorting ospray-studio: 2 - 1080p - 32 - Path Tracer tensorflow: CPU - 256 - GoogLeNet ffmpeg: libx264 - Platform ffmpeg: libx264 - Platform openradioss: Bird Strike on Windshield openvino: Person Detection FP16 - CPU ospray-studio: 3 - 4K - 16 - Path Tracer deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream onednn: Recurrent Neural Network Inference - u8s8f32 - CPU stress-ng: Futex openvino: Face Detection FP16 - CPU tensorflow: CPU - 512 - ResNet-50 stress-ng: Malloc cpuminer-opt: scrypt onednn: IP Shapes 3D - f32 - CPU jpegxl: JPEG - 80 build-nodejs: Time To Compile deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream tensorflow: CPU - 512 - GoogLeNet deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU srsran: OFDM_Test deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream rocksdb: Update Rand blender: Classroom - CPU-Only svt-av1: Preset 8 - Bosphorus 1080p tensorflow: CPU - 64 - ResNet-50 openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU jpegxl-decode: 1 tensorflow: CPU - 256 - ResNet-50 aom-av1: Speed 10 Realtime - Bosphorus 4K srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM xmrig: Wownero - 1M aom-av1: Speed 4 Two-Pass - Bosphorus 4K ospray-studio: 2 - 4K - 16 - Path Tracer svt-av1: Preset 4 - Bosphorus 4K cpuminer-opt: Magi ai-benchmark: Device Training Score avifenc: 10, Lossless openvino: Face Detection FP16 - CPU tensorflow: CPU - 16 - AlexNet openvino: Age Gender Recognition Retail 0013 FP16 - CPU jpegxl: JPEG - 90 openvino: Age Gender Recognition Retail 0013 FP16 - CPU blosc: blosclz shuffle rocksdb: Read Rand Write Rand ospray-studio: 3 - 1080p - 32 - Path Tracer ffmpeg: libx265 - Upload primesieve: 1e12 ffmpeg: libx265 - Upload deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream encodec: 6 kbps srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream tensorflow: CPU - 32 - AlexNet encode-flac: WAV To FLAC stress-ng: MEMFD ffmpeg: libx265 - Video On Demand ffmpeg: libx265 - Video On Demand cpuminer-opt: x25x graphics-magick: Enhanced deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream build-wasmer: Time To Compile stress-ng: CPU Stress onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU ospray-studio: 3 - 1080p - 1 - Path Tracer ospray-studio: 3 - 1080p - 16 - Path Tracer tensorflow: CPU - 256 - AlexNet primesieve: 1e13 build-python: Default blender: Fishy Cat - CPU-Only jpegxl-decode: All ospray-studio: 2 - 1080p - 1 - Path Tracer deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream tensorflow: CPU - 64 - AlexNet srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM deepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Stream blender: BMW27 - CPU-Only deepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Stream graphics-magick: Swirl jpegxl: PNG - 90 openvino: Vehicle Detection FP16 - CPU ospray-studio: 2 - 4K - 1 - Path Tracer openvino: Vehicle Detection FP16 - CPU stress-ng: IO_uring astcenc: Medium ospray-studio: 1 - 1080p - 16 - Path Tracer avifenc: 2 srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM openfoam: drivaerFastback, Small Mesh Size - Mesh Time webp: Quality 100 ospray-studio: 2 - 1080p - 16 - Path Tracer openvino: Person Detection FP16 - CPU ffmpeg: libx264 - Upload deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream mnn: inception-v3 deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream ffmpeg: libx264 - Live srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM ffmpeg: libx264 - Live ffmpeg: libx264 - Upload smhasher: Spooky32 cpuminer-opt: Ringcoin deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream openvino: Vehicle Detection FP16-INT8 - CPU ospray-studio: 1 - 4K - 32 - Path Tracer openvino: Vehicle Detection FP16-INT8 - CPU srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM blender: Barbershop - CPU-Only stress-ng: Semaphores ospray-studio: 1 - 1080p - 1 - Path Tracer tensorflow: CPU - 512 - AlexNet openradioss: Bumper Beam ffmpeg: libx264 - Video On Demand deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream blosc: blosclz bitshuffle ospray-studio: 1 - 4K - 16 - Path Tracer build-python: Released Build, PGO + LTO Optimized openradioss: Cell Phone Drop Test ffmpeg: libx264 - Video On Demand webp: Default jpegxl: PNG - 80 lammps: Rhodopsin Protein deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM ospray-studio: 1 - 4K - 1 - Path Tracer ffmpeg: libx265 - Platform ospray-studio: 2 - 4K - 32 - Path Tracer openradioss: Rubber O-Ring Seal Installation astcenc: Thorough deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream tensorflow: CPU - 16 - ResNet-50 ffmpeg: libx265 - Platform build-erlang: Time To Compile smhasher: FarmHash128 srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM stress-ng: NUMA srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM onednn: Deconvolution Batch shapes_1d - f32 - CPU openfoam: drivaerFastback, Medium Mesh Size - Execution Time build-php: Time To Compile onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU smhasher: wyhash y-cruncher: 1B smhasher: MeowHash x86_64 AES-NI cpuminer-opt: Deepcoin openvino: Weld Porosity Detection FP16-INT8 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU openvino: Face Detection FP16-INT8 - CPU ospray-studio: 1 - 1080p - 32 - Path Tracer ospray-studio: 3 - 4K - 1 - Path Tracer ospray-studio: 3 - 4K - 32 - Path Tracer nekrs: TurboPipe Periodic stress-ng: SENDFILE stress-ng: Matrix Math blender: Pabellon Barcelona - CPU-Only openvino: Weld Porosity Detection FP16-INT8 - CPU stress-ng: Vector Math smhasher: FarmHash32 x86_64 AVX spacy: en_core_web_lg cpuminer-opt: Blake-2 S openfoam: drivaerFastback, Medium Mesh Size - Mesh Time tensorflow: CPU - 64 - GoogLeNet smhasher: t1ha2_atonce openvino: Weld Porosity Detection FP16 - CPU astcenc: Exhaustive stress-ng: Crypto smhasher: SHA3-256 openvino: Weld Porosity Detection FP16 - CPU cpuminer-opt: Triple SHA-256, Onecoin cpuminer-opt: Skeincoin avifenc: 0 smhasher: fasthash32 deepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Stream cpuminer-opt: Quad SHA-256, Pyrite deepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Stream openvino: Face Detection FP16-INT8 - CPU cpuminer-opt: LBC, LBRY Credits avifenc: 6 aom-av1: Speed 0 Two-Pass - Bosphorus 4K srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM webp2: Quality 100, Lossless Compression webp2: Quality 95, Compression Effort 7 webp: Quality 100, Highest Compression jpegxl: JPEG - 100 jpegxl: PNG - 100 smhasher: MeowHash x86_64 AES-NI smhasher: t1ha0_aes_avx2 x86_64 smhasher: FarmHash32 x86_64 AVX smhasher: t1ha2_atonce smhasher: FarmHash128 smhasher: fasthash32 smhasher: Spooky32 smhasher: SHA3-256 smhasher: wyhash a b 178.31 74.59 76.99 64 286.78 42.63 199.02 45.3 81.24 167 51.66 9.48918 65.6 12797.7 70.65 1107 48.34 46.683 139.33 209.488 4.14024 692 4.23625 67.588 5.77 111.2 156802.93 7823 41.79 45.43 18.51 56.2277 17.7786 50.815 5807440 6.0371 319.23 2328.14 100.38 42.874 272.09 241.18 21.0326 10.633 14423511.17 15.675 24.029 13970 260.83 7.677 75.13 67.124 78.457 55.09 16.41 2418.27 7893.57 29.7727 3.5 7616183.78 8.95 66.471 0.38 5250106.25 5300.36 59.76 61.454018 533.65 24.96 25316.76 0.41 5.475 701 76103.367 29.09 58.22 86.74 11.06 21.01 11.184 5.12686 0.6 413004 100112.06 7.13 8245.26 382.0137 30.127 753.17 4.52585 27.872 696.801 17481256.34 123.0974 8.1225 24.77 210.39 161.41 19768.12 443 154070 561 26.3211 37.9743 1245 3.85 198794977 77196.31 5157.6 33.12 96265.52 9.862 7.42 1.06 9.6 9.994 99535.87 513.24 62.29 27.818 2009 1387.0925 10.559 8.3625 3.531 119.5632 673.06 35696 30.11 249.00936878 30.42 185.26 8087.11 91958 19.4996 51.2365 5167.4 802471.3 5452.5 11.24 146984386.17 496.52 20.1433 6.1 217.334 249.2856 30.61 128.0038 3.26 65700000 362.7795 199394 87.25 76.278 10.11 19469.8 26.86 10.92 21.95 92 19243.7 5.59 80769 1.314 1711.45 764 7.613 5.85 42.69 3.94 5.91 16068.58 8493.2 1551427 41292 10.45 4.638 241.646159513 96.0986 74.538 274.2 13.5743 48.66 28.868 1751.42 21.21 357.150956529 1458.5 743 73.5683 73.78 106647.2 8045.7 1282 20597 69.6 56.028 22.619 51.46 151.09 1096 87.6373 59.55 86.2 25.014 35.5 39.942 1243 6.27 90.64 4416 352.62 45731.6 151.8067 17188 78.895 38 34.098937 7.73 17838 3.9 8.03 166.1119 56.231 1387.2953 129.99 257.5 38.85 314.58 17912.16 18480 331.234 52.03 145358 614.56 252.8 409.74 7247266.69 1062 69.82 108.51 250.83 192.2873 5328.2 78125 399.66 41.65 30.20 12.25 6.37 24.104 22.6007 279.8 4233 21.24 150980 118 19.4177 22.6456 8.13 356.59243127 124.066 19050.24 93.7 140.8 98.9 19.1966 541.95263 62.123 2.51501 30087.23 21.577 41424.16 27510 751.84 28.7725 4182.46 34160 5127 173492 184723000000 678380.72 215006.68 126.81 85.05 266411.19 32899.32 6798 1098730 167.0036 30.13 18815.25 626.61 2.2087 67640.35 171.09 51.03 718010 222070 136.608 8316.13 121.842 374460 261.4175 7.61 56960 5.268 0.21 69.7 0.04 0.20 2.43 0.4 0.4 47.356 27.314 34.619 27.774 51.419 29.558 40.875 2294.234 20.507 110.59 48.21 51.75 43.74 208.14 31.18 259.54 58.67 63.2 135 41.96 7.74858 53.71 10914.9 82.64 957 42.57 52.96 123.73 234.707 4.63109 619 3.81237 75.036 6.38 100.95 172559.2 8504.29 38.47 42.01 17.14 52.0728 19.1958 47.115 6220606 5.6399 298.72 2485.61 94.37 40.336 256.64 253.55 20.0581 10.152 15090386.73 15.008 23.033 14530 271.13 7.386 78.03 69.476 81.167 56.92 15.89 2342.6 8148.11 28.8968 3.6 7408445.43 8.71 68.291 0.37 5386266.71 5167.81 61.27 62.974805 520.79 24.36 25937.03 0.42 5.35 685 74378.891 28.44 57.01 88.58 10.84 21.39 10.987 5.03993 0.59 406201 101709.29 7.02 8119.63 376.393 29.692 742.296 4.58464 27.515 687.884 17702491.79 121.5902 8.2228 24.47 207.85 159.55 19540.99 448 152420 555 26.046 38.3752 1232 3.89 196826975 76443.61 5207.64 33.44 95346.38 9.957 7.35 1.05 9.69 10.085 98639.62 508.7 62.84 28.06 1992 1398.9258 10.649 8.2919 3.561 120.5776 667.4 35397 29.87 250.99 30.18 186.71 8150.2 92675 19.3504 51.6311 5128.18 796565.52 5492 11.32 148029623.74 499.97 20.2831 6.06 215.92 250.8978 30.42 127.2104 3.24 66100000 364.9851 198198 87.77 76.731 10.17 19580.12 27.01 10.86 21.83 91.5 19140.2 5.56 80340 1.321 1702.45 760 7.653 5.82 42.91 3.92 5.94 16149.43 8534.5 1558868 41490 10.50 4.66 240.519283432 96.5473 74.885 273 13.5155 48.45 28.744 1743.95 21.12 358.61 1452.6 740 73.866 73.485 107074.79 8013.88 1277 20517 69.33 56.246 22.707 51.66 151.66 1100 87.3202 59.76 85.9 24.9281 35.62 40.071 1247 6.29 90.91 4403 351.6 45863.96 152.2417 17139 79.112 38.1 34.188105 7.71 17792 3.89 8.01 165.7009 56.096 1390.6109 130.30 256.9 38.76 315.290203876 17951.6 18440 330.5267 52.14 145660 613.31 252.3 408.93 7261328.18 1060 69.69 108.31 250.37 192.6373 5318.7 78264 400.368 41.58 30.25 12.23 6.38 24.069 22.568 279.4 4239 21.27 151192 117.84 19.4423 22.674 8.12 356.16 124.216 19028.89 93.6 140.65 99 19.1791 542.44501 62.178 2.51294 30062.54 21.561 41393.48 27490 751.3 28.7918 4185.2 34140 5130 173590 184827000000 678714.22 215110.79 126.75 85.09 266535.54 32884.37 6795 1098280 167.06876 30.12 18809.49 626.42 2.2093 67622.54 171.13 51.04 718140 222040 136.591 8317.14 121.8565 374430 261.4233 7.61 56960 5.268 0.21 69.7 0.04 0.20 2.43 0.4 0.4 47.348 27.314 34.546 27.774 51.419 29.586 40.792 2294.164 20.508 OpenBenchmarking.org
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet50 a b 40 80 120 160 200 178.31 110.59 MIN: 95.64 / MAX: 698.94 MIN: 83.5 / MAX: 688.52 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v2-v2 - Model: mobilenet-v2 a b 20 40 60 80 100 74.59 48.21 MIN: 33.31 / MAX: 533.66 MIN: 33.67 / MAX: 520.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: FastestDet a b 20 40 60 80 100 76.99 51.75 MIN: 50.2 / MAX: 651.74 MIN: 47.57 / MAX: 300.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: shufflenet-v2 a b 14 28 42 56 70 64.00 43.74 MIN: 39.84 / MAX: 607.1 MIN: 41.64 / MAX: 214.3 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: regnety_400m a b 60 120 180 240 300 286.78 208.14 MIN: 186.63 / MAX: 3348.9 MIN: 182.64 / MAX: 1526.45 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: blazeface a b 10 20 30 40 50 42.63 31.18 MIN: 20.26 / MAX: 315.89 MIN: 20.06 / MAX: 313.69 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: CPU Cache a b 60 120 180 240 300 199.02 259.54 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v3-v3 - Model: mobilenet-v3 a b 13 26 39 52 65 45.30 58.67 MIN: 34.34 / MAX: 507.69 MIN: 35.55 / MAX: 509.29 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet18 a b 20 40 60 80 100 81.24 63.20 MIN: 48.42 / MAX: 297.84 MIN: 44.6 / MAX: 292.13 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
GraphicsMagick OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Resizing a b 40 80 120 160 200 167 135 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mnasnet a b 12 24 36 48 60 51.66 41.96 MIN: 32.72 / MAX: 481.89 MIN: 33.28 / MAX: 465.54 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU a b 3 6 9 12 15 9.48918 7.74858 MIN: 8.93 MIN: 7.21 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: alexnet a b 15 30 45 60 75 65.60 53.71 MIN: 37.25 / MAX: 140.97 MIN: 30.79 / MAX: 138.09 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Xmrig OpenBenchmarking.org H/s, More Is Better Xmrig 6.18.1 Variant: Monero - Hash Count: 1M a b 3K 6K 9K 12K 15K 12797.7 10914.9 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mobilenet a b 20 40 60 80 100 70.65 82.64 MIN: 60.46 / MAX: 546.37 MIN: 59.78 / MAX: 558.19 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
GraphicsMagick OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: HWB Color Space a b 200 400 600 800 1000 1107 957 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p a b 11 22 33 44 55 48.34 42.57 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 10 - Input: Bosphorus 4K a b 12 24 36 48 60 46.68 52.96 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vgg16 a b 30 60 90 120 150 139.33 123.73 MIN: 87.74 / MAX: 205.11 MIN: 86.64 / MAX: 206.07 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 12 - Input: Bosphorus 1080p a b 50 100 150 200 250 209.49 234.71 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU a b 1.042 2.084 3.126 4.168 5.21 4.14024 4.63109 MIN: 3.72 MIN: 4.26 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
GraphicsMagick OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Noise-Gaussian a b 150 300 450 600 750 692 619 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU a b 0.9532 1.9064 2.8596 3.8128 4.766 4.23625 3.81237 MIN: 3.68 MIN: 3.29 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: googlenet a b 20 40 60 80 100 111.20 100.95 MIN: 70.72 / MAX: 809.14 MIN: 69.07 / MAX: 774.08 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Atomic a b 40K 80K 120K 160K 200K 156802.93 172559.20 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU a b 2K 4K 6K 8K 10K 7823.00 8504.29 MIN: 7444.07 MIN: 8211.26 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p a b 10 20 30 40 50 41.79 38.47 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p a b 10 20 30 40 50 45.43 42.01 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K a b 5 10 15 20 25 18.51 17.14 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Mobile Neural Network OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: resnet-v2-50 a b 11 22 33 44 55 50.82 47.12 MIN: 47.3 / MAX: 154.36 MIN: 42.84 / MAX: 126.19 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Read While Writing a b 1.3M 2.6M 3.9M 5.2M 6.5M 5807440 6220606 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU a b 2 4 6 8 10 6.0371 5.6399 MIN: 5.87 MIN: 5.49 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vision_transformer a b 70 140 210 280 350 319.23 298.72 MIN: 270.65 / MAX: 367.03 MIN: 248.9 / MAX: 3220.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Memory Copying a b 500 1000 1500 2000 2500 2328.14 2485.61 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: squeezenet_ssd a b 20 40 60 80 100 100.38 94.37 MIN: 74.34 / MAX: 677.58 MIN: 69.13 / MAX: 706.07 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Mobile Neural Network OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: nasnet a b 10 20 30 40 50 42.87 40.34 MIN: 37.41 / MAX: 68.89 MIN: 33.86 / MAX: 71.11 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
ClickHouse OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, Third Run a b 60 120 180 240 300 272.09 256.64 MIN: 38.46 / MAX: 6000 MIN: 41.35 / MAX: 4285.71 1. ClickHouse server version 22.5.4.19 (official build).
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, First Run / Cold Cache a b 60 120 180 240 300 241.18 253.55 MIN: 26.36 / MAX: 3529.41 MIN: 24.97 / MAX: 12000 1. ClickHouse server version 22.5.4.19 (official build).
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU a b 5 10 15 20 25 21.03 20.06 MIN: 18.77 MIN: 18.98 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Mobile Neural Network OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: squeezenetv1.1 a b 3 6 9 12 15 10.63 10.15 MIN: 9.92 / MAX: 17.37 MIN: 9.78 / MAX: 10.82 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Context Switching a b 3M 6M 9M 12M 15M 14423511.17 15090386.73 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
Mobile Neural Network OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: SqueezeNetV1.0 a b 4 8 12 16 20 15.68 15.01 MIN: 15.23 / MAX: 18.11 MIN: 14.21 / MAX: 16.99 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
ClickHouse OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, Second Run a b 60 120 180 240 300 260.83 271.13 MIN: 35.4 / MAX: 12000 MIN: 42.58 / MAX: 12000 1. ClickHouse server version 22.5.4.19 (official build).
Mobile Neural Network OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenet-v1-1.0 a b 2 4 6 8 10 7.677 7.386 MIN: 7.4 / MAX: 8.68 MIN: 6.86 / MAX: 15.47 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: yolov4-tiny a b 20 40 60 80 100 75.13 78.03 MIN: 66.22 / MAX: 281.19 MIN: 65.59 / MAX: 285.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 12 - Input: Bosphorus 4K a b 15 30 45 60 75 67.12 69.48 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: efficientnet-b0 a b 13 26 39 52 65 55.09 56.92 MIN: 47.62 / MAX: 609.55 MIN: 48.95 / MAX: 685.42 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K a b 4 8 12 16 20 16.41 15.89 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: MMAP a b 500 1000 1500 2000 2500 2418.27 2342.60 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU a b 2K 4K 6K 8K 10K 7893.57 8148.11 MIN: 7395.65 MIN: 7996.39 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU a b 7 14 21 28 35 29.77 28.90 MIN: 28.66 MIN: 27.84 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: System V Message Passing a b 1.6M 3.2M 4.8M 6.4M 8M 7616183.78 7408445.43 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K a b 3 6 9 12 15 8.95 8.71 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Glibc C String Functions a b 1.2M 2.4M 3.6M 4.8M 6M 5250106.25 5386266.71 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU a b 1100 2200 3300 4400 5500 5300.36 5167.81 MIN: 5196.31 MIN: 5104.36 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU a b 14 28 42 56 70 59.76 61.27 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenFOAM OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Execution Time a b 14 28 42 56 70 61.45 62.97 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU a b 120 240 360 480 600 533.65 520.79 MIN: 247.13 / MAX: 2304.56 MIN: 296.95 / MAX: 2494.76 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p a b 6 12 18 24 30 24.96 24.36 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Socket Activity a b 6K 12K 18K 24K 30K 25316.76 25937.03 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
WebP Image Encode OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless, Highest Compression a b 0.0945 0.189 0.2835 0.378 0.4725 0.41 0.42 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
Mobile Neural Network OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenetV3 a b 1.2319 2.4638 3.6957 4.9276 6.1595 5.475 5.350 MIN: 5.32 / MAX: 6.04 MIN: 5.21 / MAX: 9.76 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Aircrack-ng OpenBenchmarking.org k/s, More Is Better Aircrack-ng 1.7 a b 16K 32K 48K 64K 80K 76103.37 74378.89 1. (CXX) g++ options: -std=gnu++17 -O3 -fvisibility=hidden -fcommon -rdynamic -lnl-3 -lnl-genl-3 -lsqlite3 -lpthread -lz -lssl -lcrypto -lhwloc -ldl -lm -pthread
FFmpeg OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Live a b 13 26 39 52 65 58.22 57.01 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Live a b 20 40 60 80 100 86.74 88.58 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p a b 3 6 9 12 15 11.06 10.84 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K a b 5 10 15 20 25 21.01 21.39 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU a b 1.1535 2.307 3.4605 4.614 5.7675 5.12686 5.03993 MIN: 4.73 MIN: 4.31 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p a b 0.135 0.27 0.405 0.54 0.675 0.60 0.59 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
BRL-CAD OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.32.6 VGR Performance Metric a b 90K 180K 270K 360K 450K 413004 406201 1. (CXX) g++ options: -std=c++11 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -ldl -lm
nginx OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 200 a b 20K 40K 60K 80K 100K 100112.06 101709.29 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU a b 2K 4K 6K 8K 10K 8245.26 8119.63 MIN: 7461.03 / MAX: 9786.72 MIN: 7294.93 / MAX: 9612.39 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
miniBUDE OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 a b 7 14 21 28 35 30.13 29.69 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 a b 160 320 480 640 800 753.17 742.30 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU a b 1.0315 2.063 3.0945 4.126 5.1575 4.52585 4.58464 MIN: 4.25 MIN: 4.26 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
miniBUDE OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 a b 7 14 21 28 35 27.87 27.52 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 a b 150 300 450 600 750 696.80 687.88 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Mutex a b 4M 8M 12M 16M 20M 17481256.34 17702491.79 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 10 - Input: Bosphorus 1080p a b 40 80 120 160 200 161.41 159.55 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Forking a b 4K 8K 12K 16K 20K 19768.12 19540.99 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
GraphicsMagick OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Rotate a b 100 200 300 400 500 443 448 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Sharpen a b 120 240 360 480 600 561 555 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU a b 0.8753 1.7506 2.6259 3.5012 4.3765 3.85 3.89 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Random Read a b 40M 80M 120M 160M 200M 198794977 196826975 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU a b 1100 2200 3300 4400 5500 5157.60 5207.64 MIN: 5062.05 MIN: 5136.46 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p a b 8 16 24 32 40 33.12 33.44 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
nginx OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 1000 a b 20K 40K 60K 80K 100K 96265.52 95346.38 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
Mobile Neural Network OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: MobileNetV2_224 a b 3 6 9 12 15 9.862 9.957 MIN: 8.86 / MAX: 19.89 MIN: 9.44 / MAX: 24.23 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
nginx OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 500 a b 20K 40K 60K 80K 100K 99535.87 98639.62 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU a b 110 220 330 440 550 513.24 508.70 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU a b 14 28 42 56 70 62.29 62.84 MIN: 33.1 / MAX: 180.25 MIN: 29.52 / MAX: 192.77 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 8 - Input: Bosphorus 4K a b 7 14 21 28 35 27.82 28.06 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 4 - Input: Bosphorus 1080p a b 0.8012 1.6024 2.4036 3.2048 4.006 3.531 3.561 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Glibc Qsort Data Sorting a b 150 300 450 600 750 673.06 667.40 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer a b 8K 16K 24K 32K 40K 35696 35397 1. (CXX) g++ options: -O3 -lm -ldl
FFmpeg OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Platform a b 50 100 150 200 250 249.01 250.99 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Platform a b 7 14 21 28 35 30.42 30.18 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU a b 2K 4K 6K 8K 10K 8087.11 8150.20 MIN: 7045.22 / MAX: 9970.66 MIN: 7213.66 / MAX: 9844.05 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer a b 20K 40K 60K 80K 100K 91958 92675 1. (CXX) g++ options: -O3 -lm -ldl
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU a b 1100 2200 3300 4400 5500 5167.40 5128.18 MIN: 4891.41 MIN: 4632.83 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Futex a b 200K 400K 600K 800K 1000K 802471.30 796565.52 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU a b 1200 2400 3600 4800 6000 5452.5 5492.0 MIN: 4562.64 / MAX: 10241.51 MIN: 4746.67 / MAX: 7784.35 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Malloc a b 30M 60M 90M 120M 150M 146984386.17 148029623.74 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU a b 5 10 15 20 25 20.14 20.28 MIN: 19.59 MIN: 19.81 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
JPEG XL libjxl OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: JPEG - Quality: 80 a b 2 4 6 8 10 6.10 6.06 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b 0.7335 1.467 2.2005 2.934 3.6675 3.26 3.24 MIN: 1.85 / MAX: 36.31 MIN: 1.96 / MAX: 34.56 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
srsRAN OpenBenchmarking.org Samples / Second, More Is Better srsRAN 22.04.1 Test: OFDM_Test a b 14M 28M 42M 56M 70M 65700000 66100000 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Update Random a b 40K 80K 120K 160K 200K 199394 198198 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 8 - Input: Bosphorus 1080p a b 20 40 60 80 100 76.28 76.73 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b 4K 8K 12K 16K 20K 19469.80 19580.12 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K a b 5 10 15 20 25 21.95 21.83 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
srsRAN OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM a b 20 40 60 80 100 92.0 91.5 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
Xmrig OpenBenchmarking.org H/s, More Is Better Xmrig 6.18.1 Variant: Wownero - Hash Count: 1M a b 4K 8K 12K 16K 20K 19243.7 19140.2 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K a b 1.2578 2.5156 3.7734 5.0312 6.289 5.59 5.56 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer a b 20K 40K 60K 80K 100K 80769 80340 1. (CXX) g++ options: -O3 -lm -ldl
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 4 - Input: Bosphorus 4K a b 0.2972 0.5944 0.8916 1.1888 1.486 1.314 1.321 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU a b 1.3163 2.6326 3.9489 5.2652 6.5815 5.85 5.82 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b 0.8865 1.773 2.6595 3.546 4.4325 3.94 3.92 MIN: 1.94 / MAX: 58.65 MIN: 2.08 / MAX: 45.65 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
JPEG XL libjxl OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: JPEG - Quality: 90 a b 1.3365 2.673 4.0095 5.346 6.6825 5.91 5.94 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b 3K 6K 9K 12K 15K 16068.58 16149.43 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Read Random Write Random a b 300K 600K 900K 1200K 1500K 1551427 1558868 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer a b 9K 18K 27K 36K 45K 41292 41490 1. (CXX) g++ options: -O3 -lm -ldl
FFmpeg OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Upload a b 3 6 9 12 15 10.45 10.50 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Upload a b 50 100 150 200 250 241.65 240.52 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
srsRAN OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM a b 60 120 180 240 300 274.2 273.0 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: MEMFD a b 400 800 1200 1600 2000 1751.42 1743.95 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
FFmpeg OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Video On Demand a b 5 10 15 20 25 21.21 21.12 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Video On Demand a b 80 160 240 320 400 357.15 358.61 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
GraphicsMagick OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Enhanced a b 160 320 480 640 800 743 740 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: CPU Stress a b 20K 40K 60K 80K 100K 106647.20 107074.79 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU a b 2K 4K 6K 8K 10K 8045.70 8013.88 MIN: 7776.35 MIN: 6974.32 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer a b 300 600 900 1200 1500 1282 1277 1. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer a b 4K 8K 12K 16K 20K 20597 20517 1. (CXX) g++ options: -O3 -lm -ldl
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer a b 200 400 600 800 1000 1096 1100 1. (CXX) g++ options: -O3 -lm -ldl
srsRAN OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM a b 20 40 60 80 100 86.2 85.9 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
GraphicsMagick OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Swirl a b 300 600 900 1200 1500 1243 1247 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
JPEG XL libjxl OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: PNG - Quality: 90 a b 2 4 6 8 10 6.27 6.29 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU a b 20 40 60 80 100 90.64 90.91 MIN: 47.23 / MAX: 198.88 MIN: 53.11 / MAX: 177.44 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer a b 900 1800 2700 3600 4500 4416 4403 1. (CXX) g++ options: -O3 -lm -ldl
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU a b 80 160 240 320 400 352.62 351.60 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: IO_uring a b 10K 20K 30K 40K 50K 45731.60 45863.96 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer a b 4K 8K 12K 16K 20K 17188 17139 1. (CXX) g++ options: -O3 -lm -ldl
srsRAN OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM a b 9 18 27 36 45 38.0 38.1 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenFOAM OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Mesh Time a b 8 16 24 32 40 34.10 34.19 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer a b 4K 8K 12K 16K 20K 17838 17792 1. (CXX) g++ options: -O3 -lm -ldl
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU a b 0.8775 1.755 2.6325 3.51 4.3875 3.90 3.89 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
FFmpeg OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Upload a b 2 4 6 8 10 8.03 8.01 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Mobile Neural Network OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: inception-v3 a b 13 26 39 52 65 56.23 56.10 MIN: 52.68 / MAX: 141.21 MIN: 52.83 / MAX: 181.73 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
FFmpeg OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Live a b 30 60 90 120 150 129.99 130.30 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
srsRAN OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM a b 60 120 180 240 300 257.5 256.9 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
FFmpeg OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Live a b 9 18 27 36 45 38.85 38.76 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Upload a b 70 140 210 280 350 314.58 315.29 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU a b 12 24 36 48 60 52.03 52.14 MIN: 40.33 / MAX: 91.5 MIN: 32.77 / MAX: 93.03 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer a b 30K 60K 90K 120K 150K 145358 145660 1. (CXX) g++ options: -O3 -lm -ldl
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU a b 130 260 390 520 650 614.56 613.31 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
srsRAN OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM a b 60 120 180 240 300 252.8 252.3 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Semaphores a b 1.6M 3.2M 4.8M 6.4M 8M 7247266.69 7261328.18 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer a b 200 400 600 800 1000 1062 1060 1. (CXX) g++ options: -O3 -lm -ldl
FFmpeg OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Video On Demand a b 50 100 150 200 250 250.83 250.37 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
C-Blosc OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.3 Test: blosclz bitshuffle a b 1100 2200 3300 4400 5500 5328.2 5318.7 1. (CC) gcc options: -std=gnu99 -O3 -lrt -lm
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer a b 20K 40K 60K 80K 100K 78125 78264 1. (CXX) g++ options: -O3 -lm -ldl
FFmpeg OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx264 - Scenario: Video On Demand a b 7 14 21 28 35 30.20 30.25 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
JPEG XL libjxl OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: PNG - Quality: 80 a b 2 4 6 8 10 6.37 6.38 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
srsRAN OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM a b 60 120 180 240 300 279.8 279.4 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer a b 900 1800 2700 3600 4500 4233 4239 1. (CXX) g++ options: -O3 -lm -ldl
FFmpeg OpenBenchmarking.org FPS, More Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Platform a b 5 10 15 20 25 21.24 21.27 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer a b 30K 60K 90K 120K 150K 150980 151192 1. (CXX) g++ options: -O3 -lm -ldl
FFmpeg OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 5.1.2 Encoder: libx265 - Scenario: Platform a b 80 160 240 320 400 356.59 356.16 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
srsRAN OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM a b 20 40 60 80 100 93.7 93.6 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: NUMA a b 30 60 90 120 150 140.80 140.65 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
srsRAN OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM a b 20 40 60 80 100 98.9 99.0 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU a b 5 10 15 20 25 19.20 19.18 MIN: 17.49 MIN: 17.59 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenFOAM OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Execution Time a b 120 240 360 480 600 541.95 542.45 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU a b 0.5659 1.1318 1.6977 2.2636 2.8295 2.51501 2.51294 MIN: 2.45 MIN: 2.44 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread