cascade lake refresh 2 x Intel Xeon Gold 5220R testing with a TYAN S7106 (V2.01.B40 BIOS) and ASPEED on Ubuntu 20.04 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 2212189-NE-CASCADELA27 a Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-Av3uEd/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: MQ-DEADLINE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x5003102Java Notes: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu220.04)Python Notes: Python 2.7.18 + Python 3.8.10Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled
b Processor: 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads), Motherboard: TYAN S7106 (V2.01.B40 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 94GB, Disk: 500GB Samsung SSD 860, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel I210 + 2 x QLogic cLOM8214 1/10GbE
OS: Ubuntu 20.04, Kernel: 5.9.0-050900rc6-generic (x86_64) 20200920, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.13, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1920x1080
cascade lake refresh OpenBenchmarking.org Phoronix Test Suite 10.8.4 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads) TYAN S7106 (V2.01.B40 BIOS) Intel Sky Lake-E DMI3 Registers 94GB 500GB Samsung SSD 860 ASPEED VE228 2 x Intel I210 + 2 x QLogic cLOM8214 1/10GbE Ubuntu 20.04 5.9.0-050900rc6-generic (x86_64) 20200920 GNOME Shell 3.36.4 X Server 1.20.13 GCC 9.4.0 ext4 1920x1080 Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Compiler File-System Screen Resolution - Transparent Huge Pages: madvise - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-Av3uEd/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - MQ-DEADLINE / errors=remount-ro,relatime,rw / Block Size: 4096 - Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x5003102 - OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu220.04) - Python 2.7.18 + Python 3.8.10 - itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled
a vs. b Comparison Phoronix Test Suite 10.8.4 Baseline +26.5% +26.5% +53% +53% +79.5% +79.5% 62.3% 44.4% 31.4% 25.3% 16.7% 16.5% 15.1% 14.6% 13.7% 12.8% 12.6% 11.4% 11.3% 10.9% 10.7% 9.6% 8.7% 8.7% 7.3% 6% 5.7% 5% 5% 4.8% 4.8% 4% 3.9% 3.9% 3.7% 3.7% 3.6% 3.6% 3.5% 3.5% 3.5% 3.3% 3.3% 3% 2.9% 2.9% 2.9% 2.7% 2.6% 2.5% 2.5% 2.2% 2.1% 2% 2% 100 - 1 - Read Write 105.8% 100 - 1 - Read Write - Average Latency 105.6% 1 - 250 - Read Write - Average Latency 74.2% 1 - 250 - Read Write 74% 1000000 - 100 - B.I.J.T.T 1000000 - 100 - R.T.T 55.5% 1 - 500 - Read Write 47.8% 1 - 500 - Read Write - Average Latency 47.5% 1000000 - 2000 - B.I.J.T.T 46% 1 - 100 - Read Write 44.5% 1 - 100 - Read Write - Average Latency 44.5% 1.R.W.A.D.F.R.C.C Rhodopsin Protein 37.2% Socket Activity 33.1% 480000 - 512 32.6% 50 - 1:1 96000 - 1024 29.6% KV, 10% Reads - 256 1000000 - 2000 - I.J.T.T 24.4% A.G.R.R.0.F.I - CPU 20.4% A.G.R.R.0.F.I - CPU 20.1% CPU Cache 16.7% CPU - 64 - ResNet-50 KV, 10% Reads - 512 100 - 50 - Read Write - Average Latency 16.2% 100 - 50 - Read Write 16.2% 3 kbps KV, 60% Reads - 512 R.N.N.I - f32 - CPU 13.8% 1000000 - 100 - I.J.T.T KV, 50% Reads - 128 13.6% 1 - 1 - Read Write 13.1% 1 - 1 - Read Write - Average Latency 13.1% MoVR - 256 Context Switching 200 - 5:1 12.2% 200 - 1:1 11.6% Rand Read 200 - 1:5 11.4% 480000 - 1024 1.R.W.A.D.T.R Speed 6 Realtime - Bosphorus 1080p 44100 - 512 10.1% KV, 60% Reads - 256 9.8% Futex 24 kbps 9.5% CPU - alexnet 9.5% CPU - vgg16 9.3% KNN CAD 9.1% Atomic 9.1% CPU-v2-v2 - mobilenet-v2 8.9% GET - 50 8.9% CPU - FastestDet 1000000 - 2000 - R.T.T CPU - efficientnet-b0 8.7% KV, 60% Reads - 128 8.6% CPU - shufflenet-v2 8.3% GET - 500 7.7% CPU-v3-v3 - mobilenet-v3 7.7% 1000000 - 2000 - Group By Test Time 1.5 kbps 6.8% CPU - googlenet 6.5% JPEG - 100 6.5% mobilenet-v1-1.0 KV, 50% Reads - 256 6% CPU - mnasnet 5.8% Speed 4 Two-Pass - Bosphorus 4K KV, 50% Reads - 512 5.6% CPU - squeezenet_ssd 50 - 1:5 Monero - 1M 192000 - 512 CPU - regnety_400m 4.6% Preset 4 - Bosphorus 4K 4.2% 96000 - 512 4.2% CPU - blazeface 4.2% 1000000 - 2000 - S.5.B.T 4.2% 1.R.W.A.D.S.R Earthgecko Skyline resnet-v2-50 CPU - yolov4-tiny 3.8% KV, 95% Reads - 128 3.7% Myriad-Groestl Q.7.C.E.7 3.7% 1000000 - 100 - Group By Test Time 1 - 1 - Read Only 3.7% Preset 13 - Bosphorus 4K KV, 50% Reads - 1024 KV, 60% Reads - 1024 CPU - resnet18 3.5% N.T.C.B.b.u.S - S.S.S Time To Compile 3.5% N.T.C.B.b.u.S - S.S.S Speed 10 Realtime - Bosphorus 1080p 3.4% KV, 10% Reads - 128 3.3% Rotate 3.3% KV, 10% Reads - 1024 S.V.M.P 3.2% MoVR - 512 3.1% 192000 - 1024 v.S 2.9% en_core_web_trf 2.9% 2 OpenMP - BM1 OpenMP - BM1 PNG - 80 2.8% Speed 6 Two-Pass - Bosphorus 1080p 100 - 100 - Read Write - Average Latency 2.6% 100 - 100 - Read Write 2.6% Default Speed 6 Realtime - Bosphorus 4K 2.6% vklBenchmark ISPC 2.5% IP Shapes 3D - bf16bf16bf16 - CPU Q.1.C.E.5 1 - 1 - Read Only - Average Latency 2.3% Swirl 2.3% Preset 4 - Bosphorus 1080p HWB Color Space 2.2% 100 - 1 - Read Only - Average Latency 2.2% V.D.F - CPU 2.2% V.D.F - CPU 2.2% B.C 2.1% PNG - 100 2.1% V.P.M 2.1% R.N.N.T - bf16bf16bf16 - CPU CPU - mobilenet Preset 12 - Bosphorus 4K 2% PostgreSQL PostgreSQL PostgreSQL PostgreSQL Apache Spark Apache Spark PostgreSQL PostgreSQL Apache Spark PostgreSQL PostgreSQL ClickHouse LAMMPS Molecular Dynamics Simulator Stress-NG Stargate Digital Audio Workstation Dragonflydb Stargate Digital Audio Workstation CockroachDB Apache Spark OpenVINO OpenVINO Stress-NG TensorFlow CockroachDB PostgreSQL PostgreSQL EnCodec CockroachDB oneDNN Apache Spark CockroachDB PostgreSQL PostgreSQL CockroachDB Stress-NG Dragonflydb Dragonflydb Facebook RocksDB Dragonflydb Stargate Digital Audio Workstation ClickHouse AOM AV1 Stargate Digital Audio Workstation CockroachDB Stress-NG EnCodec NCNN NCNN Numenta Anomaly Benchmark Stress-NG NCNN Redis NCNN Apache Spark NCNN CockroachDB NCNN Redis NCNN Apache Spark EnCodec NCNN JPEG XL libjxl Mobile Neural Network CockroachDB NCNN AOM AV1 CockroachDB NCNN Dragonflydb Xmrig Stargate Digital Audio Workstation NCNN SVT-AV1 Stargate Digital Audio Workstation NCNN Apache Spark ClickHouse Numenta Anomaly Benchmark Mobile Neural Network NCNN CockroachDB Cpuminer-Opt WebP2 Image Encode Apache Spark PostgreSQL SVT-AV1 CockroachDB CockroachDB NCNN Neural Magic DeepSparse Timed PHP Compilation Neural Magic DeepSparse AOM AV1 libavif avifenc CockroachDB GraphicsMagick CockroachDB Stress-NG CockroachDB Stargate Digital Audio Workstation OpenVKL spaCy libavif avifenc miniBUDE miniBUDE JPEG XL libjxl AOM AV1 PostgreSQL PostgreSQL WebP2 Image Encode AOM AV1 OpenVKL oneDNN WebP2 Image Encode PostgreSQL GraphicsMagick SVT-AV1 GraphicsMagick PostgreSQL OpenVINO OpenVINO Numenta Anomaly Benchmark Node.js V8 Web Tooling Benchmark JPEG XL libjxl BRL-CAD oneDNN NCNN SVT-AV1 a b
cascade lake refresh pgbench: 100 - 1 - Read Write pgbench: 100 - 1 - Read Write - Average Latency pgbench: 1 - 250 - Read Write - Average Latency pgbench: 1 - 250 - Read Write spark: 1000000 - 100 - Broadcast Inner Join Test Time spark: 1000000 - 100 - Repartition Test Time pgbench: 1 - 500 - Read Write pgbench: 1 - 500 - Read Write - Average Latency spark: 1000000 - 2000 - Broadcast Inner Join Test Time pgbench: 1 - 100 - Read Write pgbench: 1 - 100 - Read Write - Average Latency clickhouse: 100M Rows Web Analytics Dataset, First Run / Cold Cache lammps: Rhodopsin Protein stress-ng: Socket Activity stargate: 480000 - 512 dragonflydb: 50 - 1:1 stargate: 96000 - 1024 cockroach: KV, 10% Reads - 256 spark: 1000000 - 2000 - Inner Join Test Time openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU stress-ng: CPU Cache tensorflow: CPU - 64 - ResNet-50 cockroach: KV, 10% Reads - 512 pgbench: 100 - 50 - Read Write - Average Latency pgbench: 100 - 50 - Read Write encodec: 3 kbps cockroach: KV, 60% Reads - 512 onednn: Recurrent Neural Network Inference - f32 - CPU spark: 1000000 - 100 - Inner Join Test Time cockroach: KV, 50% Reads - 128 pgbench: 1 - 1 - Read Write pgbench: 1 - 1 - Read Write - Average Latency cockroach: MoVR - 256 stress-ng: Context Switching dragonflydb: 200 - 5:1 dragonflydb: 200 - 1:1 rocksdb: Rand Read dragonflydb: 200 - 1:5 stargate: 480000 - 1024 clickhouse: 100M Rows Web Analytics Dataset, Third Run aom-av1: Speed 6 Realtime - Bosphorus 1080p stargate: 44100 - 512 cockroach: KV, 60% Reads - 256 stress-ng: Futex encodec: 24 kbps ncnn: CPU - alexnet ncnn: CPU - vgg16 numenta-nab: KNN CAD stress-ng: Atomic ncnn: CPU-v2-v2 - mobilenet-v2 redis: GET - 50 ncnn: CPU - FastestDet spark: 1000000 - 2000 - Repartition Test Time ncnn: CPU - efficientnet-b0 cockroach: KV, 60% Reads - 128 ncnn: CPU - shufflenet-v2 redis: GET - 500 ncnn: CPU-v3-v3 - mobilenet-v3 spark: 1000000 - 2000 - Group By Test Time encodec: 1.5 kbps ncnn: CPU - googlenet jpegxl: JPEG - 100 mnn: mobilenet-v1-1.0 cockroach: KV, 50% Reads - 256 ncnn: CPU - mnasnet aom-av1: Speed 4 Two-Pass - Bosphorus 4K cockroach: KV, 50% Reads - 512 ncnn: CPU - squeezenet_ssd dragonflydb: 50 - 1:5 xmrig: Monero - 1M stargate: 192000 - 512 ncnn: CPU - regnety_400m svt-av1: Preset 4 - Bosphorus 4K stargate: 96000 - 512 ncnn: CPU - blazeface spark: 1000000 - 2000 - SHA-512 Benchmark Time clickhouse: 100M Rows Web Analytics Dataset, Second Run numenta-nab: Earthgecko Skyline mnn: resnet-v2-50 ncnn: CPU - yolov4-tiny cockroach: KV, 95% Reads - 128 cpuminer-opt: Myriad-Groestl webp2: Quality 75, Compression Effort 7 spark: 1000000 - 100 - Group By Test Time pgbench: 1 - 1 - Read Only svt-av1: Preset 13 - Bosphorus 4K cockroach: KV, 50% Reads - 1024 cockroach: KV, 60% Reads - 1024 ncnn: CPU - resnet18 deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream build-php: Time To Compile deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream aom-av1: Speed 10 Realtime - Bosphorus 1080p avifenc: 0 cockroach: KV, 10% Reads - 128 graphics-magick: Rotate cockroach: KV, 10% Reads - 1024 stress-ng: System V Message Passing cockroach: MoVR - 512 stargate: 192000 - 1024 openvkl: vklBenchmark Scalar spacy: en_core_web_trf avifenc: 2 minibude: OpenMP - BM1 minibude: OpenMP - BM1 jpegxl: PNG - 80 aom-av1: Speed 6 Two-Pass - Bosphorus 1080p pgbench: 100 - 100 - Read Write - Average Latency pgbench: 100 - 100 - Read Write webp2: Default aom-av1: Speed 6 Realtime - Bosphorus 4K openvkl: vklBenchmark ISPC onednn: IP Shapes 3D - bf16bf16bf16 - CPU webp2: Quality 100, Compression Effort 5 pgbench: 1 - 1 - Read Only - Average Latency graphics-magick: Swirl svt-av1: Preset 4 - Bosphorus 1080p graphics-magick: HWB Color Space pgbench: 100 - 1 - Read Only - Average Latency openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU numenta-nab: Bayesian Changepoint node-web-tooling: jpegxl: PNG - 100 brl-cad: VGR Performance Metric onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU ncnn: CPU - mobilenet svt-av1: Preset 12 - Bosphorus 4K onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU rocksdb: Read While Writing xmrig: Wownero - 1M jpegxl-decode: 1 openvino: Person Vehicle Bike Detection FP16 - CPU pgbench: 100 - 500 - Read Write openradioss: Bird Strike on Windshield pgbench: 100 - 500 - Read Write - Average Latency pgbench: 100 - 100 - Read Only openvino: Person Vehicle Bike Detection FP16 - CPU pgbench: 100 - 100 - Read Only - Average Latency y-cruncher: 500M jpegxl: PNG - 90 pgbench: 100 - 250 - Read Write - Average Latency pgbench: 100 - 250 - Read Write cockroach: MoVR - 1024 stress-ng: Glibc Qsort Data Sorting jpegxl: JPEG - 90 redis: GET - 1000 encodec: 6 kbps mnn: inception-v3 deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream mnn: mobilenetV3 cockroach: KV, 95% Reads - 1024 onednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPU stress-ng: SENDFILE mnn: MobileNetV2_224 spark: 1000000 - 2000 - Calculate Pi Benchmark spark: 1000000 - 2000 - Calculate Pi Benchmark Using Dataframe minibude: OpenMP - BM2 minibude: OpenMP - BM2 srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM stargate: 44100 - 1024 aom-av1: Speed 0 Two-Pass - Bosphorus 1080p svt-av1: Preset 8 - Bosphorus 1080p srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM jpegxl: JPEG - 80 stress-ng: CPU Stress srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM aom-av1: Speed 8 Realtime - Bosphorus 4K tensorflow: CPU - 64 - GoogLeNet blender: Classroom - CPU-Only compress-7zip: Compression Rating cockroach: KV, 95% Reads - 256 onednn: Recurrent Neural Network Inference - u8s8f32 - CPU srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM astcenc: Medium build-erlang: Time To Compile stress-ng: Memory Copying tensorflow: CPU - 64 - VGG-16 cpuminer-opt: Blake-2 S 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: Ringcoin pgbench: 1 - 50 - Read Write svt-av1: Preset 13 - Bosphorus 1080p deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream tensorflow: CPU - 64 - AlexNet deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream aircrack-ng: srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM graphics-magick: Sharpen onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU stress-ng: NUMA srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM pgbench: 1 - 50 - Read Write - Average Latency onednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPU srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM jpegxl-decode: All rocksdb: Update Rand tensorflow: CPU - 32 - AlexNet webp: Quality 100, Lossless graphics-magick: Enhanced aom-av1: Speed 8 Realtime - Bosphorus 1080p encode-flac: WAV To FLAC aom-av1: Speed 9 Realtime - Bosphorus 4K pgbench: 100 - 250 - Read Only - Average Latency mnn: SqueezeNetV1.0 deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream mnn: nasnet pgbench: 100 - 250 - Read Only stress-ng: Glibc C String Functions numenta-nab: Windowed Gaussian deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream redis: SET - 500 deepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Stream onednn: Deconvolution Batch shapes_1d - f32 - CPU openvino: Machine Translation EN To DE FP16 - CPU avifenc: 6, Lossless openvino: Machine Translation EN To DE FP16 - CPU webp: Default deepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Stream stress-ng: Matrix Math srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM aom-av1: Speed 10 Realtime - Bosphorus 4K numenta-nab: Contextual Anomaly Detector OSE pgbench: 1 - 500 - Read Only pgbench: 1 - 500 - Read Only - Average Latency svt-av1: Preset 8 - Bosphorus 4K pgbench: 100 - 1 - Read Only graphics-magick: Resizing cpuminer-opt: Quad SHA-256, Pyrite ospray-studio: 3 - 4K - 16 - Path Tracer cpuminer-opt: scrypt ospray-studio: 1 - 4K - 16 - Path Tracer ospray-studio: 1 - 4K - 32 - Path Tracer deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream ospray-studio: 2 - 1080p - 16 - Path Tracer openvino: Person Detection FP32 - CPU openfoam: drivaerFastback, Small Mesh Size - Execution Time stress-ng: MMAP openvino: Vehicle Detection FP16-INT8 - CPU blender: Pabellon Barcelona - CPU-Only openvino: Vehicle Detection FP16-INT8 - CPU build-python: Default onednn: IP Shapes 1D - u8s8f32 - CPU openradioss: Rubber O-Ring Seal Installation aom-av1: Speed 6 Two-Pass - Bosphorus 4K deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream stress-ng: MEMFD cpuminer-opt: LBC, LBRY Credits rocksdb: Read Rand Write Rand spark: 1000000 - 100 - Calculate Pi Benchmark Using Dataframe pgbench: 1 - 50 - Read Only stress-ng: Forking tensorflow: CPU - 16 - GoogLeNet ncnn: CPU - vision_transformer lammps: 20k Atoms srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM pgbench: 100 - 500 - Read Only tensorflow: CPU - 32 - VGG-16 pgbench: 1 - 250 - Read Only - Average Latency tensorflow: CPU - 32 - ResNet-50 openfoam: drivaerFastback, Small Mesh Size - Mesh Time onednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU deepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Stream build-nodejs: Time To Compile pgbench: 100 - 500 - Read Only - Average Latency avifenc: 6 pgbench: 1 - 250 - Read Only spacy: en_core_web_lg nekrs: TurboPipe Periodic build-linux-kernel: allmodconfig srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream pgbench: 1 - 100 - Read Only stress-ng: Mutex openvino: Age Gender Recognition Retail 0013 FP16 - CPU cpuminer-opt: Magi compress-7zip: Decompression Rating onednn: Deconvolution Batch shapes_3d - f32 - CPU openvino: Person Detection FP32 - CPU blender: Fishy Cat - CPU-Only openvino: Weld Porosity Detection FP16 - CPU stress-ng: Semaphores deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream onednn: IP Shapes 3D - u8s8f32 - CPU dragonflydb: 50 - 5:1 aom-av1: Speed 9 Realtime - Bosphorus 1080p openvino: Weld Porosity Detection FP16 - CPU graphics-magick: Noise-Gaussian openvino: Person Detection FP16 - CPU cpuminer-opt: Garlicoin ospray-studio: 1 - 1080p - 1 - Path Tracer onednn: IP Shapes 1D - bf16bf16bf16 - CPU deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream tensorflow: CPU - 32 - GoogLeNet openradioss: Bumper Beam onednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream tensorflow: CPU - 16 - ResNet-50 onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream ospray-studio: 2 - 4K - 1 - Path Tracer mnn: squeezenetv1.1 memtier-benchmark: Redis - 50 - 10:1 onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream astcenc: Thorough deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream spark: 1000000 - 100 - Calculate Pi Benchmark y-cruncher: 1B openfoam: drivaerFastback, Medium Mesh Size - Execution Time openvino: Weld Porosity Detection FP16-INT8 - CPU openradioss: INIVOL and Fluid Structure Interaction Drop Container ospray-studio: 3 - 1080p - 16 - Path Tracer openvino: Face Detection FP16-INT8 - CPU ospray-studio: 1 - 1080p - 16 - Path Tracer cpuminer-opt: Skeincoin stress-ng: Vector Math deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream ospray-studio: 3 - 4K - 32 - Path Tracer deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream webp: Quality 100 ospray-studio: 2 - 4K - 32 - Path Tracer ospray-studio: 2 - 1080p - 1 - Path Tracer tensorflow: CPU - 16 - VGG-16 openvino: Weld Porosity Detection FP16-INT8 - CPU onednn: IP Shapes 3D - f32 - CPU tensorflow: CPU - 16 - AlexNet stress-ng: Malloc onednn: Convolution Batch Shapes Auto - f32 - CPU cpuminer-opt: x25x srsran: OFDM_Test redis: SET - 50 build-linux-kernel: defconfig ncnn: CPU - resnet50 redis: SET - 1000 onednn: Recurrent Neural Network Training - f32 - CPU svt-av1: Preset 12 - Bosphorus 1080p onednn: IP Shapes 1D - f32 - CPU cpuminer-opt: Triple SHA-256, Onecoin ospray-studio: 2 - 1080p - 32 - Path Tracer blender: Barbershop - CPU-Only deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream unpack-linux: linux-5.19.tar.xz astcenc: Fast astcenc: Exhaustive ospray-studio: 1 - 1080p - 32 - Path Tracer ospray-studio: 3 - 4K - 1 - Path Tracer cockroach: MoVR - 128 onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU openvino: Face Detection FP16 - CPU ospray-studio: 2 - 4K - 16 - Path Tracer openvino: Face Detection FP16-INT8 - CPU blender: BMW27 - CPU-Only deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream cpuminer-opt: Deepcoin openradioss: Cell Phone Drop Test openvino: Person Detection FP16 - CPU build-python: Released Build, PGO + LTO Optimized ospray-studio: 3 - 1080p - 32 - Path Tracer ospray-studio: 1 - 4K - 1 - Path Tracer onednn: Recurrent Neural Network Training - u8s8f32 - CPU deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream stress-ng: x86_64 RdRand pgbench: 100 - 50 - Read Only avifenc: 10, Lossless stress-ng: Crypto openfoam: drivaerFastback, Medium Mesh Size - Mesh Time cockroach: KV, 95% Reads - 512 numenta-nab: Relative Entropy natron: Spaceship openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Face Detection FP16 - CPU pgbench: 100 - 50 - Read Only - Average Latency pgbench: 1 - 100 - Read Only - Average Latency pgbench: 1 - 50 - Read Only - Average Latency spark: 1000000 - 100 - SHA-512 Benchmark Time ospray-studio: 3 - 1080p - 1 - Path Tracer aom-av1: Speed 4 Two-Pass - Bosphorus 1080p aom-av1: Speed 0 Two-Pass - Bosphorus 4K webp2: Quality 100, Lossless Compression webp2: Quality 95, Compression Effort 7 webp: Quality 100, Lossless, Highest Compression webp: Quality 100, Highest Compression stress-ng: IO_uring a b 671 1.491 565.864 442 2.50 2.63 297 1682.547 4.26 623 160.474 142.18 17.951 26882.84 3.394244 707625.49 2.61702 13759.6 4.67 0.98 36342.3 89.3 19.21 29267.4 9.744 5131 40.408 58375.2 784.125 3.23 12434.3 812 1.231 202.9 6260590.45 942134.52 994293.9 107719684 1044459.26 2.90554 198.59 23.87 3.281164 30111.3 1051825.91 48.814 8.45 35.89 135.463 126894.32 11.44 2617818.25 15.69 5.61 15 15412.3 11.83 2908381.75 10.44 8.24 41.892 21.6 0.49 3.695 24394.6 10.43 5.62 49424.7 29.15 989118.75 9938.1 1.044224 48.89 2.631 1.840618 5.7 5.48 205.73 99.192 15.236 31.71 89867.4 11570 0.28 6.47 23407 106.678 61797.2 67899.4 13.35 33.8154 57.282 29.5607 48.3 115.421 6941 594 38341.3 3795441.99 111.5 1.601382 176 2007 59.901 735.749 29.43 8.15 19.6 16.541 6045 6.59 13.58 362 3.40068 7.27 0.043 816 6.245 735 0.045 421.71 21.3 34.988 9.93 0.49 257085 1409.26 23.38 120.584 786.583 5155074 16896.5 33.54 687.33 7613 205.44 65.68 882773 13.06 0.113 11.12 8.03 34.869 7170 111.1 417 7.69 2852955.5 40.508 36.76 18.6511 3.386 94378.8 2.55381 437831.75 5.143 64.825399416 4.78 776.346 31.054 293.3 3.634671 0.72 85.018 130.9 7.78 59047.56 136.3 16.04 77.03 164.77 171677 98923.9 781.001 126.1 138.0913 121.466 4644.12 10.85 2216930 114.3502 8.7441 3292.87 716 201.865 114.2741 143.41 8.7499 99753.68 324.2 220 0.477096 577.5 294 69.874 6.35819 118.9 80.94 174193 106.64 1.25 506 38.05 22.41 22.76 0.271 7.533 99.481 22.53 922066 1715303.02 7.529 180.5419 2217236.25 135.7515 11.4783 78.04 10.043 115.2 13.83 132.4405 124052.48 320.8 22.89 50.619 930850 0.537 36.589 21981 1092 401450 78464 951.15 65864 122216 99.329 14608 4.03 96.025607 564.44 1395.73 192.12 6.42 19.743 1.37489 114.39 9.12 180.9023 1021.04 182930 2545133 4.69 675675 41988.02 46.37 173.64 15.746 100.3 869450 10.22 0.255 17.9 34.008239 9.8543 18.4136 54.2553 275.436 0.575 5.298 979407 10874 124608000000 543.75 65.7 18.6156 968554 17168753.52 21846.45 701.91 158350 2.80983 2199.69 75.8 51 4585186.59 963.8114 1.25783 959933.8 46.5 704.6 392 4.04 12910 888 5.70137 197.132 61.69 125.04 9.61455 23.9046 14.77 0.693146 41.8085 3617 4.677 1501800.97 0.568809 14.8943 18.0603 67.0883 66.06 22.389 899.70168 13.17 275.47 17367 347.32 14186 253670 103156.98 113.7454 8.7764 146883 50.9512 8.92 125037 914 9.16 2717.47 3.79612 79.17 109293721.23 7.47846 1252.09 119900000 2242796 52.645 26.1 2202580.5 1380.95 227.23 1.72077 598720 29041 592.36 352.856 8.579 364.5543 1.8422 28318 4309 226.3 0.235557 6.94903 1283.2 67352 25.83 55.54 963.5663 28150 57.28 2192.85 382.188 34647 3528 1380.06 91.1877 503507.78 652544 7.053 34685.11 187.21756 96569.8 13.363 3.7 1.64 6.94 0.077 0.103 0.074 5.07 1085 10.53 0.27 0.03 0.13 0.44 3.03 326 3.065 985.483 254 1.54 4.09 201 2481.623 6.22 431 231.892 205.30 13.085 20197.23 2.559217 930057.66 2.019155 17242.8 5.81 1.18 30254.31 76.5 22.42 34085.9 11.326 4415 35.115 66868.9 892.232 2.84 10945.5 718 1.392 228.8 7049324.49 839630.53 890721.27 120010661 937646.51 3.23369 220.22 26.43 2.979784 27413.2 1152673.55 53.474 9.25 39.21 147.747 116358.2 12.46 2404467.25 14.43 5.16 16.3 14191.7 12.81 2700561.5 11.24 7.68 44.754 23.01 0.46 3.487 23024.3 11.03 5.94 46804.8 27.75 1038762.14 10411.8 1.093912 51.14 2.524 1.765949 5.94 5.71 213.89 95.428 14.662 32.91 86632.5 12000 0.27 6.24 22579 110.562 63998.7 70300.1 13.82 34.9917 59.274 28.5675 46.73 111.684 6717.4 575 39590.8 3677320.93 108.1 1.650224 171 1950 58.227 756.807 30.272 7.93 20.13 16.977 5890 6.76 13.24 353 3.31851 7.45 0.044 798 6.385 719 0.046 412.75 21.76 35.734 10.14 0.48 251911 1381.57 22.93 118.267 801.797 5254605 16579.3 32.92 674.84 7475 201.72 66.891 899014 13.3 0.111 11.319 7.89 35.484 7046 109.2 424.2 7.56 2805580.75 39.852 36.166 18.3638 3.334 92938.9 2.59337 444590.02 5.221 65.80 4.85 787.503 31.5 289.2 3.584121 0.73 86.178 129.2 7.68 58316.18 134.7 16.23 76.16 162.95 169842 99986 789.364 124.8 136.6876 122.707 4691.35 10.96 2239380 115.5038 8.6568 3325.86 709 199.966 115.3522 142.07 8.6682 98829.75 321.2 218 0.481461 572.28 291.4 70.482 6.4127 117.9 80.26 172766 105.78 1.24 502 37.75 22.58 22.59 0.273 7.588 98.7664 22.37 915519 1703193.63 7.476 181.7991 2232581.5 136.6781 11.5556 77.53 9.978 115.95 13.92 131.593 123275.06 318.8 22.75 50.914 925569 0.54 36.387 21860 1098 403630 78883 946.1 66209 122843 99.8308 14535 4.01 95.549133 561.69 1388.97 191.19 6.45 19.835 1.38109 114.9 9.08 180.1226 1016.64 183720 2534266 4.71 672851 42163.36 46.18 172.93 15.683 99.9 866030 10.18 0.256 17.97 33.881804 9.81832 18.3466 54.452 276.403 0.577 5.28 976093 10838 124198000000 545.447 65.5 18.6722 971447 17219955.71 21782.56 703.92 157899 2.81784 2205.86 75.59 50.86 4572788.09 966.403 1.25446 962500.62 46.38 706.42 391 4.03 12940 890 5.71409 196.7007 61.82 124.78 9.6345 23.9542 14.74 0.694553 41.7245 3624 4.686 1504675.76 0.567734 14.9224 18.0936 66.9674 65.95 22.426 898.33703 13.19 275.88 17342 347.82 14166 253330 103019.74 113.8925 8.7659 147053 51.0098 8.91 125174 915 9.15 2714.67 3.80003 79.09 109184164.47 7.48562 1253.15 120000000 2244608.5 52.687 26.12 2204248 1379.94 227.064 1.71954 598300 29061 591.97 352.6274 8.584 364.3485 1.8432 28332 4311 226.4 0.235658 6.94611 1283.73 67325 25.82 55.56 963.9121 28140 57.26 2193.51 382.303 34637 3529 1380.45 91.2096 503602.92 652647 7.052 34689.96 187.19525 96577.9 13.364 3.7 1.64 6.94 0.077 0.103 0.074 5.07 1085 10.53 0.27 0.03 0.13 0.44 3.03 OpenBenchmarking.org
PostgreSQL OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Write a b 140 280 420 560 700 671 326 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Write - Average Latency a b 0.6896 1.3792 2.0688 2.7584 3.448 1.491 3.065 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Write - Average Latency a b 200 400 600 800 1000 565.86 985.48 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Write a b 100 200 300 400 500 442 254 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Write a b 60 120 180 240 300 297 201 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Write - Average Latency a b 500 1000 1500 2000 2500 1682.55 2481.62 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Write a b 130 260 390 520 650 623 431 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency a b 50 100 150 200 250 160.47 231.89 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
ClickHouse 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 50 100 150 200 250 142.18 205.30 MIN: 12.92 / MAX: 2000 MIN: 22.56 / MAX: 6000 1. ClickHouse server version 22.5.4.19 (official build).
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 26882.84 20197.23 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stargate Digital Audio Workstation OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 480000 - Buffer Size: 512 a b 0.7637 1.5274 2.2911 3.0548 3.8185 3.394244 2.559217 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Dragonflydb OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 1:1 a b 200K 400K 600K 800K 1000K 707625.49 930057.66 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Stargate Digital Audio Workstation OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 96000 - Buffer Size: 1024 a b 0.5888 1.1776 1.7664 2.3552 2.944 2.617020 2.019155 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b 0.2655 0.531 0.7965 1.062 1.3275 0.98 1.18 MIN: 0.59 / MAX: 15.38 MIN: 0.59 / MAX: 10.36 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b 8K 16K 24K 32K 40K 36342.30 30254.31 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: CPU Cache a b 20 40 60 80 100 89.3 76.5 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
PostgreSQL OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency a b 3 6 9 12 15 9.744 11.326 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Write a b 1100 2200 3300 4400 5500 5131 4415 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU a b 200 400 600 800 1000 784.13 892.23 MIN: 777.45 MIN: 775.18 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
PostgreSQL OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Write a b 200 400 600 800 1000 812 718 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average Latency a b 0.3132 0.6264 0.9396 1.2528 1.566 1.231 1.392 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Context Switching a b 1.5M 3M 4.5M 6M 7.5M 6260590.45 7049324.49 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Dragonflydb OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 200 - Set To Get Ratio: 5:1 a b 200K 400K 600K 800K 1000K 942134.52 839630.53 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 200 - Set To Get Ratio: 1:1 a b 200K 400K 600K 800K 1000K 994293.90 890721.27 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Random Read a b 30M 60M 90M 120M 150M 107719684 120010661 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Dragonflydb OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 200 - Set To Get Ratio: 1:5 a b 200K 400K 600K 800K 1000K 1044459.26 937646.51 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Stargate Digital Audio Workstation OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 480000 - Buffer Size: 1024 a b 0.7276 1.4552 2.1828 2.9104 3.638 2.90554 3.23369 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
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 50 100 150 200 250 198.59 220.22 MIN: 26.85 / MAX: 1578.95 MIN: 27 / MAX: 6000 1. ClickHouse server version 22.5.4.19 (official build).
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p a b 6 12 18 24 30 23.87 26.43 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Stargate Digital Audio Workstation OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 44100 - Buffer Size: 512 a b 0.7383 1.4766 2.2149 2.9532 3.6915 3.281164 2.979784 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Futex a b 200K 400K 600K 800K 1000K 1051825.91 1152673.55 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: alexnet a b 3 6 9 12 15 8.45 9.25 MIN: 8.26 / MAX: 11.64 MIN: 8.49 / MAX: 68.95 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vgg16 a b 9 18 27 36 45 35.89 39.21 MIN: 34.05 / MAX: 85.91 MIN: 38.84 / MAX: 55.18 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Atomic a b 30K 60K 90K 120K 150K 126894.32 116358.20 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v2-v2 - Model: mobilenet-v2 a b 3 6 9 12 15 11.44 12.46 MIN: 11.11 / MAX: 20.16 MIN: 12.01 / MAX: 23.54 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Redis OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: GET - Parallel Connections: 50 a b 600K 1200K 1800K 2400K 3000K 2617818.25 2404467.25 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: FastestDet a b 4 8 12 16 20 15.69 14.43 MIN: 15.41 / MAX: 17.05 MIN: 14.16 / MAX: 15.42 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: efficientnet-b0 a b 4 8 12 16 20 15.0 16.3 MIN: 14.75 / MAX: 15.78 MIN: 16 / MAX: 20.8 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: shufflenet-v2 a b 3 6 9 12 15 11.83 12.81 MIN: 11.61 / MAX: 13.09 MIN: 12.55 / MAX: 14.41 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Redis OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: GET - Parallel Connections: 500 a b 600K 1200K 1800K 2400K 3000K 2908381.75 2700561.50 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v3-v3 - Model: mobilenet-v3 a b 3 6 9 12 15 10.44 11.24 MIN: 10.18 / MAX: 12.88 MIN: 10.99 / MAX: 12.7 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: googlenet a b 6 12 18 24 30 21.60 23.01 MIN: 21.26 / MAX: 22.11 MIN: 22.72 / MAX: 23.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
JPEG XL libjxl OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: JPEG - Quality: 100 a b 0.1103 0.2206 0.3309 0.4412 0.5515 0.49 0.46 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic
Mobile Neural Network OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenet-v1-1.0 a b 0.8314 1.6628 2.4942 3.3256 4.157 3.695 3.487 MIN: 3.57 / MAX: 4.07 MIN: 3.38 / MAX: 3.9 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: mnasnet a b 3 6 9 12 15 10.43 11.03 MIN: 10.23 / MAX: 11.32 MIN: 10.77 / MAX: 11.59 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
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 1.3365 2.673 4.0095 5.346 6.6825 5.62 5.94 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: squeezenet_ssd a b 7 14 21 28 35 29.15 27.75 MIN: 28.61 / MAX: 32.07 MIN: 26.83 / MAX: 101.49 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Dragonflydb OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 1:5 a b 200K 400K 600K 800K 1000K 989118.75 1038762.14 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Xmrig OpenBenchmarking.org H/s, More Is Better Xmrig 6.18.1 Variant: Monero - Hash Count: 1M a b 2K 4K 6K 8K 10K 9938.1 10411.8 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
Stargate Digital Audio Workstation OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 512 a b 0.2461 0.4922 0.7383 0.9844 1.2305 1.044224 1.093912 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: regnety_400m a b 12 24 36 48 60 48.89 51.14 MIN: 48.18 / MAX: 56.99 MIN: 50.45 / MAX: 52.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 4 - Input: Bosphorus 4K a b 0.592 1.184 1.776 2.368 2.96 2.631 2.524 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Stargate Digital Audio Workstation OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 96000 - Buffer Size: 512 a b 0.4141 0.8282 1.2423 1.6564 2.0705 1.840618 1.765949 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: blazeface a b 1.3365 2.673 4.0095 5.346 6.6825 5.70 5.94 MIN: 5.55 / MAX: 6.94 MIN: 5.79 / MAX: 7.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
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 50 100 150 200 250 205.73 213.89 MIN: 28.36 / MAX: 6000 MIN: 26.86 / MAX: 5454.55 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: resnet-v2-50 a b 4 8 12 16 20 15.24 14.66 MIN: 14.25 / MAX: 102.15 MIN: 14.18 / MAX: 125.14 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 8 16 24 32 40 31.71 32.91 MIN: 31.39 / MAX: 33.18 MIN: 32.4 / MAX: 34.49 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
PostgreSQL OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Only a b 5K 10K 15K 20K 25K 23407 22579 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 13 - Input: Bosphorus 4K a b 20 40 60 80 100 106.68 110.56 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet18 a b 4 8 12 16 20 13.35 13.82 MIN: 13.14 / MAX: 15.08 MIN: 13.57 / MAX: 15.57 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p a b 11 22 33 44 55 48.30 46.73 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
GraphicsMagick OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Rotate a b 130 260 390 520 650 594 575 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -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: System V Message Passing a b 800K 1600K 2400K 3200K 4000K 3795441.99 3677320.93 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stargate Digital Audio Workstation OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 1024 a b 0.3713 0.7426 1.1139 1.4852 1.8565 1.601382 1.650224 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
miniBUDE OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 a b 160 320 480 640 800 735.75 756.81 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 a b 7 14 21 28 35 29.43 30.27 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
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 8.15 7.93 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic
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 5 10 15 20 25 19.60 20.13 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
PostgreSQL OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency a b 4 8 12 16 20 16.54 16.98 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Write a b 1300 2600 3900 5200 6500 6045 5890 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K a b 3 6 9 12 15 13.58 13.24 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU a b 0.7652 1.5304 2.2956 3.0608 3.826 3.40068 3.31851 MIN: 2.9 MIN: 2.91 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
PostgreSQL OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average Latency a b 0.0099 0.0198 0.0297 0.0396 0.0495 0.043 0.044 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
GraphicsMagick OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Swirl a b 200 400 600 800 1000 816 798 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 4 - Input: Bosphorus 1080p a b 2 4 6 8 10 6.245 6.385 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
GraphicsMagick OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: HWB Color Space a b 160 320 480 640 800 735 719 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
PostgreSQL OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Only - Average Latency a b 0.0104 0.0208 0.0312 0.0416 0.052 0.045 0.046 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU a b 90 180 270 360 450 421.71 412.75 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU a b 5 10 15 20 25 21.30 21.76 MIN: 17.61 / MAX: 58.97 MIN: 17.7 / MAX: 58.16 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
JPEG XL libjxl OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: PNG - Quality: 100 a b 0.1103 0.2206 0.3309 0.4412 0.5515 0.49 0.48 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic
BRL-CAD OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.32.6 VGR Performance Metric a b 60K 120K 180K 240K 300K 257085 251911 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 -pthread -ldl -lm
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU a b 300 600 900 1200 1500 1409.26 1381.57 MIN: 1374.19 MIN: 1372.52 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mobilenet a b 6 12 18 24 30 23.38 22.93 MIN: 22.74 / MAX: 43.44 MIN: 22.51 / MAX: 24.62 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 4K a b 30 60 90 120 150 120.58 118.27 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU a b 200 400 600 800 1000 786.58 801.80 MIN: 780.44 MIN: 779.44 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Read While Writing a b 1.1M 2.2M 3.3M 4.4M 5.5M 5155074 5254605 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Xmrig OpenBenchmarking.org H/s, More Is Better Xmrig 6.18.1 Variant: Wownero - Hash Count: 1M a b 4K 8K 12K 16K 20K 16896.5 16579.3 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU a b 150 300 450 600 750 687.33 674.84 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
PostgreSQL OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Write a b 1600 3200 4800 6400 8000 7613 7475 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency a b 15 30 45 60 75 65.68 66.89 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Only a b 200K 400K 600K 800K 1000K 882773 899014 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU a b 3 6 9 12 15 13.06 13.30 MIN: 11.64 / MAX: 41.68 MIN: 12.04 / MAX: 41.55 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
PostgreSQL OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency a b 0.0254 0.0508 0.0762 0.1016 0.127 0.113 0.111 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
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 8.03 7.89 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic
PostgreSQL OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency a b 8 16 24 32 40 34.87 35.48 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Write a b 1500 3000 4500 6000 7500 7170 7046 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Glibc Qsort Data Sorting a b 90 180 270 360 450 417.0 424.2 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
JPEG XL libjxl OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: JPEG - Quality: 90 a b 2 4 6 8 10 7.69 7.56 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic
Redis OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: GET - Parallel Connections: 1000 a b 600K 1200K 1800K 2400K 3000K 2852955.50 2805580.75 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Mobile Neural Network OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: inception-v3 a b 8 16 24 32 40 36.76 36.17 MIN: 36.21 / MAX: 49.89 MIN: 35.24 / MAX: 154.36 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
Mobile Neural Network OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenetV3 a b 0.7619 1.5238 2.2857 3.0476 3.8095 3.386 3.334 MIN: 3.3 / MAX: 3.62 MIN: 3.22 / MAX: 3.71 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
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU a b 0.5835 1.167 1.7505 2.334 2.9175 2.55381 2.59337 MIN: 2.3 MIN: 2.34 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: SENDFILE a b 100K 200K 300K 400K 500K 437831.75 444590.02 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Mobile Neural Network OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: MobileNetV2_224 a b 1.1747 2.3494 3.5241 4.6988 5.8735 5.143 5.221 MIN: 4.38 / MAX: 18.18 MIN: 4.5 / MAX: 26.7 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
miniBUDE OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 a b 200 400 600 800 1000 776.35 787.50 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 a b 7 14 21 28 35 31.05 31.50 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
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 60 120 180 240 300 293.3 289.2 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -lm
Stargate Digital Audio Workstation OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 44100 - Buffer Size: 1024 a b 0.8178 1.6356 2.4534 3.2712 4.089 3.634671 3.584121 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
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 0.1643 0.3286 0.4929 0.6572 0.8215 0.72 0.73 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 8 - Input: Bosphorus 1080p a b 20 40 60 80 100 85.02 86.18 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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 30 60 90 120 150 130.9 129.2 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -lm
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 7.78 7.68 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: CPU Stress a b 13K 26K 39K 52K 65K 59047.56 58316.18 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -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 30 60 90 120 150 136.3 134.7 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -lm
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K a b 4 8 12 16 20 16.04 16.23 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU a b 200 400 600 800 1000 781.00 789.36 MIN: 770.18 MIN: 781.32 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
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 30 60 90 120 150 126.1 124.8 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -lm
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Memory Copying a b 1000 2000 3000 4000 5000 4644.12 4691.35 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Cpuminer-Opt OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Blake-2 S a b 500K 1000K 1500K 2000K 2500K 2216930 2239380 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
PostgreSQL OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Write a b 150 300 450 600 750 716 709 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 13 - Input: Bosphorus 1080p a b 40 80 120 160 200 201.87 199.97 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Aircrack-ng OpenBenchmarking.org k/s, More Is Better Aircrack-ng 1.7 a b 20K 40K 60K 80K 100K 99753.68 98829.75 1. (CXX) g++ options: -std=gnu++17 -O3 -fvisibility=hidden -fcommon -rdynamic -lnl-3 -lnl-genl-3 -lpcre -lpthread -lz -lssl -lcrypto -lhwloc -ldl -lm -lbsd -pthread
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 70 140 210 280 350 324.2 321.2 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -lm
GraphicsMagick OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Sharpen a b 50 100 150 200 250 220 218 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU a b 0.1083 0.2166 0.3249 0.4332 0.5415 0.477096 0.481461 MIN: 0.46 MIN: 0.46 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: NUMA a b 120 240 360 480 600 577.50 572.28 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
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 60 120 180 240 300 294.0 291.4 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -lm
PostgreSQL OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average Latency a b 16 32 48 64 80 69.87 70.48 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU a b 2 4 6 8 10 6.35819 6.41270 MIN: 6.32 MIN: 6.32 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -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 30 60 90 120 150 118.9 117.9 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -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 174193 172766 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
WebP Image Encode OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless a b 0.2813 0.5626 0.8439 1.1252 1.4065 1.25 1.24 1. (CC) gcc options: -fvisibility=hidden -O2 -lm -pthread
GraphicsMagick OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Enhanced a b 110 220 330 440 550 506 502 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -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 8 Realtime - Input: Bosphorus 1080p a b 9 18 27 36 45 38.05 37.75 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 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 22.76 22.59 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
PostgreSQL OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency a b 0.0614 0.1228 0.1842 0.2456 0.307 0.271 0.273 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Mobile Neural Network OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: SqueezeNetV1.0 a b 2 4 6 8 10 7.533 7.588 MIN: 7.39 / MAX: 7.71 MIN: 7.43 / MAX: 7.98 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
Mobile Neural Network OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: nasnet a b 5 10 15 20 25 22.53 22.37 MIN: 22.21 / MAX: 22.9 MIN: 22.08 / MAX: 29.94 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
PostgreSQL OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Only a b 200K 400K 600K 800K 1000K 922066 915519 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Glibc C String Functions a b 400K 800K 1200K 1600K 2000K 1715303.02 1703193.63 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Redis OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 500 a b 500K 1000K 1500K 2000K 2500K 2217236.25 2232581.50 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU a b 3 6 9 12 15 11.48 11.56 MIN: 9.71 MIN: 9.44 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU a b 20 40 60 80 100 78.04 77.53 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU a b 30 60 90 120 150 115.20 115.95 MIN: 98.32 / MAX: 349.37 MIN: 93.14 / MAX: 374.14 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Matrix Math a b 30K 60K 90K 120K 150K 124052.48 123275.06 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
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 70 140 210 280 350 320.8 318.8 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -lm
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 22.89 22.75 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
PostgreSQL OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Only a b 200K 400K 600K 800K 1000K 930850 925569 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Only - Average Latency a b 0.1215 0.243 0.3645 0.486 0.6075 0.537 0.540 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 8 - Input: Bosphorus 4K a b 8 16 24 32 40 36.59 36.39 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
PostgreSQL OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Only a b 5K 10K 15K 20K 25K 21981 21860 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
GraphicsMagick OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Resizing a b 200 400 600 800 1000 1092 1098 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Cpuminer-Opt OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Quad SHA-256, Pyrite a b 90K 180K 270K 360K 450K 401450 403630 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
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 78464 78883 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -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: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer a b 14K 28K 42K 56K 70K 65864 66209 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
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 122216 122843 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -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: 16 - Renderer: Path Tracer a b 3K 6K 9K 12K 15K 14608 14535 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU a b 0.9068 1.8136 2.7204 3.6272 4.534 4.03 4.01 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenFOAM OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Execution Time a b 20 40 60 80 100 96.03 95.55 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: MMAP a b 120 240 360 480 600 564.44 561.69 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU a b 300 600 900 1200 1500 1395.73 1388.97 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU a b 2 4 6 8 10 6.42 6.45 MIN: 6.2 / MAX: 22.94 MIN: 6.23 / MAX: 21.87 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU a b 0.3107 0.6214 0.9321 1.2428 1.5535 1.37489 1.38109 MIN: 1.28 MIN: 1.29 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
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 9.12 9.08 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: MEMFD a b 200 400 600 800 1000 1021.04 1016.64 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Cpuminer-Opt OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: LBC, LBRY Credits a b 40K 80K 120K 160K 200K 182930 183720 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Read Random Write Random a b 500K 1000K 1500K 2000K 2500K 2545133 2534266 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Apache Spark OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark Using Dataframe a b 1.0598 2.1196 3.1794 4.2392 5.299 4.69 4.71
PostgreSQL OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Only a b 140K 280K 420K 560K 700K 675675 672851 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Stress-NG OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Forking a b 9K 18K 27K 36K 45K 41988.02 42163.36 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
NCNN OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vision_transformer a b 40 80 120 160 200 173.64 172.93 MIN: 166.7 / MAX: 356.98 MIN: 167.69 / MAX: 270.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
srsRAN OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM a b 20 40 60 80 100 100.3 99.9 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -lm
PostgreSQL OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Only a b 200K 400K 600K 800K 1000K 869450 866030 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Only - Average Latency a b 0.0576 0.1152 0.1728 0.2304 0.288 0.255 0.256 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenFOAM OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Mesh Time a b 8 16 24 32 40 34.01 33.88 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU a b 3 6 9 12 15 9.85430 9.81832 MIN: 9.66 MIN: 9.66 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
PostgreSQL OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency a b 0.1298 0.2596 0.3894 0.5192 0.649 0.575 0.577 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Only a b 200K 400K 600K 800K 1000K 979407 976093 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm