Intel Xeon Gold 6226R testing with a Supermicro X11SPL-F v1.02 (3.1 BIOS) and ASPEED on Ubuntu 20.10 via the Phoronix Test Suite.
Linux 5.10.130 Processor: Intel Xeon Gold 6226R @ 3.90GHz (16 Cores / 32 Threads), Motherboard: Supermicro X11SPL-F v1.02 (3.1 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 192GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel I210
OS: Ubuntu 20.10, Kernel: 5.10.130-0510130-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-poYruo/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-poYruo/gcc-10-10.3.0/debian/tmp-gcn/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-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 -vProcessor Notes: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x5003102Python Notes: Python 3.8.10Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Vulnerable: Clear buffers attempted no microcode; SMT vulnerable + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Vulnerable: eIBRS with unprivileged eBPF + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled
Linux 5.15.83 OS: Ubuntu 20.10, Kernel: 5.15.83-051583-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-poYruo/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-poYruo/gcc-10-10.3.0/debian/tmp-gcn/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-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 -vProcessor Notes: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x5003102Python Notes: Python 3.8.10Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Vulnerable: Clear buffers attempted no microcode; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + 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 PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled
Linux 6.1 OS: Ubuntu 20.10, Kernel: 6.1.0-phx (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-poYruo/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-poYruo/gcc-10-10.3.0/debian/tmp-gcn/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-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 -vProcessor Notes: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x5003102Python Notes: Python 3.8.10Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Vulnerable: Clear buffers attempted no microcode; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled
Xeon Gold Cascade Lake Refresh LTS Linux Benchmarks OpenBenchmarking.org Phoronix Test Suite Intel Xeon Gold 6226R @ 3.90GHz (16 Cores / 32 Threads) Supermicro X11SPL-F v1.02 (3.1 BIOS) Intel Sky Lake-E DMI3 Registers 192GB 280GB INTEL SSDPED1D280GA ASPEED VE228 2 x Intel I210 Ubuntu 20.10 5.10.130-0510130-generic (x86_64) 5.15.83-051583-generic (x86_64) 6.1.0-phx (x86_64) GNOME Shell 3.38.1 X Server 1.20.9 GCC 10.3.0 ext4 1920x1080 Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernels Desktop Display Server Compiler File-System Screen Resolution Xeon Gold Cascade Lake Refresh LTS Linux Benchmarks Performance System Logs - Transparent Huge Pages: madvise - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-poYruo/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-poYruo/gcc-10-10.3.0/debian/tmp-gcn/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-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 - Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x5003102 - Python 3.8.10 - Linux 5.10.130: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Vulnerable: Clear buffers attempted no microcode; SMT vulnerable + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Vulnerable: eIBRS with unprivileged eBPF + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled - Linux 5.15.83: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Vulnerable: Clear buffers attempted no microcode; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + 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 PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled - Linux 6.1: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Vulnerable: Clear buffers attempted no microcode; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled
Linux 5.10.130 Linux 5.15.83 Linux 6.1 Result Overview Phoronix Test Suite 100% 107% 115% 122% 130% ctx_clock Dragonflydb JPEG XL Decoding libjxl EnCodec PostgreSQL GraphicsMagick C-Blosc Stress-NG AOM AV1 JPEG XL libjxl Facebook RocksDB Timed Linux Kernel Compilation Stargate Digital Audio Workstation spaCy ClickHouse Timed Erlang/OTP Compilation Timed Godot Game Engine Compilation libavif avifenc Mobile Neural Network Timed Node.js Compilation FLAC Audio Encoding Timed PHP Compilation miniBUDE Timed CPython Compilation 7-Zip Compression NCNN BRL-CAD Neural Magic DeepSparse srsRAN SVT-AV1 nekRS OpenVINO Y-Cruncher Xmrig Cpuminer-Opt WebP Image Encode OpenRadioss LAMMPS Molecular Dynamics Simulator TensorFlow Numenta Anomaly Benchmark Blender oneDNN ASTC Encoder Primesieve Aircrack-ng Natron OSPRay Studio OpenFOAM
Xeon Gold Cascade Lake Refresh LTS Linux Benchmarks minibude: OpenMP - BM1 minibude: OpenMP - BM2 stress-ng: MMAP stress-ng: NUMA stress-ng: Futex stress-ng: MEMFD stress-ng: Mutex stress-ng: Atomic stress-ng: Crypto stress-ng: Malloc stress-ng: Forking stress-ng: IO_uring stress-ng: SENDFILE stress-ng: CPU Cache stress-ng: CPU Stress stress-ng: Semaphores stress-ng: Matrix Math stress-ng: Vector Math stress-ng: x86_64 RdRand stress-ng: Memory Copying stress-ng: Socket Activity stress-ng: Context Switching stress-ng: Glibc C String Functions stress-ng: Glibc Qsort Data Sorting stress-ng: System V Message Passing srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM nekrs: TurboPipe Periodic openvino: Face Detection FP16 - CPU openvino: Person Detection FP16 - CPU openvino: Person Detection FP32 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU natron: Spaceship aom-av1: Speed 6 Two-Pass - Bosphorus 4K aom-av1: Speed 8 Realtime - Bosphorus 4K aom-av1: Speed 9 Realtime - Bosphorus 4K aom-av1: Speed 10 Realtime - Bosphorus 4K svt-av1: Preset 4 - Bosphorus 4K svt-av1: Preset 8 - Bosphorus 4K svt-av1: Preset 12 - Bosphorus 4K svt-av1: Preset 13 - Bosphorus 4K svt-av1: Preset 4 - Bosphorus 1080p svt-av1: Preset 8 - Bosphorus 1080p svt-av1: Preset 12 - Bosphorus 1080p svt-av1: Preset 13 - Bosphorus 1080p minibude: OpenMP - BM1 minibude: OpenMP - BM2 xmrig: Monero - 1M xmrig: Wownero - 1M tensorflow: CPU - 16 - AlexNet tensorflow: CPU - 32 - AlexNet tensorflow: CPU - 64 - AlexNet tensorflow: CPU - 256 - AlexNet tensorflow: CPU - 16 - GoogLeNet tensorflow: CPU - 16 - ResNet-50 tensorflow: CPU - 32 - GoogLeNet tensorflow: CPU - 32 - ResNet-50 tensorflow: CPU - 64 - GoogLeNet tensorflow: CPU - 64 - ResNet-50 tensorflow: CPU - 256 - GoogLeNet tensorflow: CPU - 256 - ResNet-50 deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream deepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream graphics-magick: Swirl graphics-magick: Rotate graphics-magick: Sharpen graphics-magick: Enhanced graphics-magick: Resizing graphics-magick: Noise-Gaussian graphics-magick: HWB Color Space aircrack-ng: cpuminer-opt: Magi cpuminer-opt: x25x cpuminer-opt: scrypt cpuminer-opt: Deepcoin cpuminer-opt: Ringcoin cpuminer-opt: Blake-2 S cpuminer-opt: Garlicoin cpuminer-opt: Skeincoin cpuminer-opt: Myriad-Groestl cpuminer-opt: LBC, LBRY Credits cpuminer-opt: Quad SHA-256, Pyrite cpuminer-opt: Triple SHA-256, Onecoin blosc: blosclz shuffle blosc: blosclz bitshuffle compress-7zip: Compression Rating compress-7zip: Decompression Rating jpegxl: PNG - 80 jpegxl: PNG - 90 jpegxl: JPEG - 80 jpegxl: JPEG - 90 jpegxl: PNG - 100 jpegxl: JPEG - 100 jpegxl-decode: 1 jpegxl-decode: All webp: Default webp: Quality 100 webp: Quality 100, Lossless webp: Quality 100, Highest Compression webp: Quality 100, Lossless, Highest Compression astcenc: Fast astcenc: Medium astcenc: Thorough astcenc: Exhaustive lammps: 20k Atoms lammps: Rhodopsin Protein rocksdb: Rand Fill rocksdb: Rand Read rocksdb: Update Rand rocksdb: Seq Fill rocksdb: Rand Fill Sync rocksdb: Read While Writing rocksdb: Read Rand Write Rand dragonflydb: 50 - 1:1 dragonflydb: 50 - 1:5 dragonflydb: 50 - 5:1 dragonflydb: 200 - 1:1 dragonflydb: 200 - 1:5 dragonflydb: 200 - 5:1 clickhouse: 100M Rows Web Analytics Dataset, First Run / Cold Cache clickhouse: 100M Rows Web Analytics Dataset, Second Run clickhouse: 100M Rows Web Analytics Dataset, Third Run stargate: 44100 - 512 stargate: 96000 - 512 stargate: 192000 - 512 stargate: 44100 - 1024 stargate: 480000 - 512 stargate: 96000 - 1024 stargate: 192000 - 1024 stargate: 480000 - 1024 srsran: OFDM_Test spacy: en_core_web_lg spacy: en_core_web_trf pgbench: 100 - 100 - Read Only pgbench: 100 - 250 - Read Only pgbench: 100 - 500 - Read Only pgbench: 100 - 100 - Read Write pgbench: 100 - 250 - Read Write pgbench: 100 - 500 - Read Write srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM brl-cad: VGR Performance Metric ctx-clock: Context Switch Time onednn: IP Shapes 1D - f32 - CPU onednn: IP Shapes 3D - f32 - CPU onednn: IP Shapes 1D - u8s8f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: Deconvolution Batch shapes_1d - f32 - CPU onednn: Deconvolution Batch shapes_3d - f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU onednn: Recurrent Neural Network Training - f32 - CPU onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Recurrent Neural Network Training - u8s8f32 - CPU onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU ospray-studio: 1 - 4K - 1 - Path Tracer ospray-studio: 2 - 4K - 1 - Path Tracer ospray-studio: 3 - 4K - 1 - Path Tracer ospray-studio: 1 - 4K - 16 - Path Tracer ospray-studio: 1 - 4K - 32 - Path Tracer ospray-studio: 2 - 4K - 16 - Path Tracer ospray-studio: 2 - 4K - 32 - Path Tracer ospray-studio: 3 - 4K - 16 - Path Tracer ospray-studio: 3 - 4K - 32 - Path Tracer ospray-studio: 1 - 1080p - 1 - Path Tracer ospray-studio: 2 - 1080p - 1 - Path Tracer ospray-studio: 3 - 1080p - 1 - Path Tracer ospray-studio: 1 - 1080p - 16 - Path Tracer ospray-studio: 1 - 1080p - 32 - Path Tracer ospray-studio: 2 - 1080p - 16 - Path Tracer ospray-studio: 2 - 1080p - 32 - Path Tracer ospray-studio: 3 - 1080p - 16 - Path Tracer ospray-studio: 3 - 1080p - 32 - Path Tracer pgbench: 100 - 100 - Read Only - Average Latency pgbench: 100 - 250 - Read Only - Average Latency pgbench: 100 - 500 - Read Only - Average Latency pgbench: 100 - 100 - Read Write - Average Latency pgbench: 100 - 250 - Read Write - Average Latency pgbench: 100 - 500 - Read Write - Average Latency mnn: nasnet mnn: mobilenetV3 mnn: squeezenetv1.1 mnn: resnet-v2-50 mnn: SqueezeNetV1.0 mnn: MobileNetV2_224 mnn: mobilenet-v1-1.0 mnn: inception-v3 ncnn: CPU - mobilenet ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU - shufflenet-v2 ncnn: CPU - mnasnet ncnn: CPU - efficientnet-b0 ncnn: CPU - blazeface ncnn: CPU - googlenet ncnn: CPU - vgg16 ncnn: CPU - resnet18 ncnn: CPU - alexnet ncnn: CPU - resnet50 ncnn: CPU - yolov4-tiny ncnn: CPU - squeezenet_ssd ncnn: CPU - regnety_400m ncnn: CPU - vision_transformer ncnn: CPU - FastestDet openvino: Face Detection FP16 - CPU openvino: Person Detection FP16 - CPU openvino: Person Detection FP32 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream deepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream openfoam: drivaerFastback, Small Mesh Size - Mesh Time openfoam: drivaerFastback, Small Mesh Size - Execution Time openfoam: drivaerFastback, Medium Mesh Size - Mesh Time openfoam: drivaerFastback, Medium Mesh Size - Execution Time openradioss: Bumper Beam openradioss: Cell Phone Drop Test openradioss: Bird Strike on Windshield openradioss: Rubber O-Ring Seal Installation openradioss: INIVOL and Fluid Structure Interaction Drop Container avifenc: 0 avifenc: 2 avifenc: 6 avifenc: 6, Lossless avifenc: 10, Lossless build-godot: Time To Compile build-linux-kernel: defconfig build-linux-kernel: allmodconfig build-nodejs: Time To Compile build-php: Time To Compile build-python: Default build-python: Released Build, PGO + LTO Optimized primesieve: 1e12 primesieve: 1e13 y-cruncher: 1B y-cruncher: 500M build-erlang: Time To Compile encode-flac: WAV To FLAC blender: BMW27 - CPU-Only blender: Classroom - CPU-Only blender: Fishy Cat - CPU-Only blender: Barbershop - CPU-Only blender: Pabellon Barcelona - CPU-Only encodec: 3 kbps encodec: 6 kbps encodec: 24 kbps encodec: 1.5 kbps numenta-nab: KNN CAD numenta-nab: Relative Entropy numenta-nab: Windowed Gaussian numenta-nab: Earthgecko Skyline numenta-nab: Bayesian Changepoint numenta-nab: Contextual Anomaly Detector OSE Linux 5.10.130 Linux 5.15.83 Linux 6.1 21.211 21.389 390.20 358.05 1498828.70 1008.62 8606774.99 223731.70 18742.67 22392194.28 56719.51 36489.15 241610.68 116.33 34273.52 3214994.83 55915.36 55351.58 252390.56 4201.02 10160.91 5500706.76 911917.94 194.36 6490812.35 279.8 279.8 303.4 307.0 98.6 70649766667 5.88 3.31 3.25 272.09 19.11 969.33 625.50 64.82 1991.75 485.36 15259.86 31167.81 3.6 11.70 37.88 48.05 48.34 2.475 34.519 126.497 120.794 7.046 95.493 415.136 423.649 530.266 534.738 6794.5 9492.2 166.55 211.25 243.30 278.63 114.41 37.68 121.72 40.23 125.79 41.90 130.21 43.50 10.5210 9.5996 55.4233 43.7612 86.6567 75.2616 219.3569 132.6485 108.5475 73.6039 55.5433 38.4438 10.5403 9.6153 502 757 199 315 1333 335 976 50605.559 374.94 640.06 491.90 14497 2833.09 1149103 6572.81 135103 17363 96820 218830 315913 15238.1 10158.9 106357 86432 7.70 7.58 7.45 7.30 0.54 0.53 38.17 208.79 14.37 9.00 1.27 3.07 0.48 193.1315 72.1595 9.3225 0.9371 10.427 10.659 983199 65094239 625695 1204255 216464 3100899 2132608 978963.31 1047699.23 989148.97 971725.25 1021149.38 918617.37 205.76 212.60 212.42 3.909552 2.537891 1.536255 4.385893 3.726933 2.999611 1.889268 4.199568 122000000 11314 2446 465422 413949 370238 53656 47676 38503 117.3 123.3 126.9 131.0 65.9 167771 154 2.29636 3.10144 0.496613 1.25271 4.29153 4.70699 3.30606 4.15869 0.540654 0.851455 1613.12 909.632 1621.84 911.816 0.956399 0.313238 7055 7242 8633 121467 234216 124428 239935 146583 284699 1778 1826 2178 28409 65271 29172 66823 34786 78016 0.215 0.604 1.350 1.864 5.244 12.986 14.910 2.091 2.592 10.148 4.892 3.855 2.678 22.733 14.54 5.56 4.95 5.66 4.91 7.06 2.38 11.57 26.95 8.09 5.46 14.20 23.60 17.13 18.83 160.27 7.02 1357.37 2400.02 2436.30 29.37 417.71 8.24 25.53 123.34 8.02 16.47 1.04 0.50 758.0277 104.1622 144.2410 22.8396 92.2142 13.2689 36.4390 7.5265 73.6759 13.5771 144.0062 26.0011 752.8319 103.9960 38.53511 188.28208 241.48551 1598.6991 152.41 96.21 256.43 159.75 443.72 145.012 70.517 6.689 11.376 6.637 97.246 70.169 907.748 453.613 65.325 19.449 383.514 14.443 174.722 24.449 11.345 91.560 21.110 106.13 318.28 144.25 1145.90 373.74 29.141 29.495 34.162 28.208 185.330 15.803 9.070 114.813 41.392 55.734 21.170 21.317 381.23 335.58 2364278.75 879.67 9013626.15 225144.33 18733.10 20930090.96 60087.36 32758.89 285766.99 128.31 34238.77 3314461.38 55890.23 55415.01 252393.88 4129.34 17786.17 2284154.16 916397.13 194.88 8257907.06 282.7 282.0 310.0 307.9 98.6 70923633333 5.88 3.30 3.25 272.80 19.15 957.08 623.36 64.28 1993.58 485.19 15258.56 31007.38 3.6 11.77 37.86 47.66 48.33 2.483 34.818 127.534 122.978 6.985 95.043 418.022 425.263 529.240 532.924 6829.8 9531.3 166.90 211.47 242.73 279.05 115.15 38.09 122.18 40.41 126.29 42.05 130.40 43.41 10.4539 9.6141 55.5849 42.9013 86.9402 75.0401 219.0088 134.1326 108.3377 72.0552 54.4332 37.7602 10.4339 9.6111 499 731 199 314 1321 331 957 50607.738 373.55 641.61 489.83 14500 2812.34 1150583 6594.18 134833 17610 96663 218493 313917 15998.6 10555.7 108058 86735 7.71 7.54 7.40 7.25 0.54 0.53 37.90 209.18 14.40 9.02 1.28 3.09 0.48 193.0244 72.1219 9.3267 0.9375 10.414 10.639 982848 65233649 616626 1193837 234969 3043279 2129359 1123953.55 1186278.25 1068662.91 1060251.05 1117321.90 993337.90 204.26 209.58 215.02 3.972591 2.579045 1.567049 4.431098 3.790321 3.063511 1.989680 4.270897 122633333 11236 2416 515273 475175 426428 56230 45922 33824 118.3 123.9 128.0 131.6 66.0 166852 179 2.29385 3.08561 0.497248 1.25174 4.31178 4.70834 3.29633 4.20343 0.540452 0.846543 1611.14 912.066 1614.87 908.188 0.961682 0.316005 7046 7246 8628 121486 234142 124556 240311 146570 284853 1778 1826 2176 28417 65242 29206 66817 34801 77997 0.194 0.526 1.173 1.779 5.444 14.783 14.880 2.071 2.537 9.850 4.897 3.752 2.639 22.438 14.71 5.53 4.95 5.59 4.85 6.99 2.29 11.46 27.69 8.05 5.48 14.21 23.89 16.85 18.67 161.23 6.91 1356.35 2401.74 2441.67 29.29 416.95 8.34 25.62 124.34 8.01 16.46 1.03 0.5 759.3525 104.0054 143.8065 23.3139 91.9860 13.3089 36.4973 7.4408 73.8216 13.8679 146.9505 26.4774 760.8374 104.0376 38.235781 186.39843 242.25487 1611.5943 151.82 96.31 256.19 159.15 445.17 144.709 71.065 6.749 11.425 6.666 97.568 70.488 911.083 453.307 65.143 19.493 383.962 14.429 174.658 24.562 11.366 91.754 21.098 106.38 317.07 144.34 1144.82 373.54 28.660 29.530 33.917 28.349 182.657 15.813 9.018 115.529 41.433 55.659 21.422 21.552 310.22 256.61 2433807.14 667.82 7375258.06 225639.32 18727.61 15989079.77 53632.67 32918.80 284966.04 115.59 34059.43 3315660.88 55875.18 55344.32 252372.29 4181.80 16990.75 2054658.64 916843.52 194.30 14896082.79 280.2 280.3 307.4 305.5 98.3 70481500000 5.89 3.28 3.23 267.62 19.17 957.41 620.61 63.96 1992.23 491.24 15144.32 30632.46 3.6 11.65 36.10 45.41 45.97 2.460 34.723 126.763 121.596 7.024 95.151 409.127 419.750 535.565 538.790 6767.3 9527.7 166.31 211.06 242.34 279.22 116.16 38.01 123.19 40.32 126.49 42.06 130.47 43.37 10.4097 9.5393 55.4366 43.3202 86.8832 75.2635 218.6936 132.5077 108.7443 71.8852 54.2726 37.2115 10.3832 9.6532 491 668 197 311 1299 322 872 50609.276 373.45 638.64 491.85 14420 2800.62 1137550 6571.66 134320 17477 96010 217237 315723 15256.1 10161.3 106968 86680 7.36 7.20 7.08 6.94 0.53 0.52 36.37 181.54 14.38 8.95 1.27 3.08 0.48 192.9917 72.0972 9.3103 0.9368 10.399 10.608 935285 65337175 594485 1134991 218454 2985392 2133528 1130454.03 1180450.09 1074996.43 1046604.15 1099078.40 979549.43 198.51 204.43 212.92 3.817268 2.497164 1.520040 4.311382 3.718812 3.012585 1.928814 4.208880 120733333 11231 2341 523788 487468 467167 54365 45223 36109 117.1 123.3 127.2 130.3 65.9 168334 200 2.29708 3.09433 0.496776 1.24871 4.28618 4.98067 3.31244 4.18096 0.541430 0.831866 1614.07 909.147 1618.86 913.943 0.963400 0.313975 7048 7245 8633 123000 234371 126341 240430 146692 284235 1779 1824 2173 28479 65894 29165 67837 34779 79804 0.191 0.513 1.070 1.839 5.528 13.847 15.122 2.083 2.606 9.932 4.969 3.831 2.640 22.789 14.45 5.57 4.95 5.63 4.89 7.04 2.36 11.48 26.52 7.85 5.46 13.83 23.35 16.76 18.70 160.39 6.96 1357.10 2415.31 2451.10 29.86 416.16 8.33 25.73 124.97 8.02 16.27 1.04 0.51 764.7425 104.8348 144.2114 23.0718 92.0462 13.2691 36.5392 7.5359 73.5456 13.9013 147.3804 26.8656 763.3064 103.5823 38.361993 186.93467 242.92307 1607.4012 153.23 96.30 255.89 160.27 446.66 145.036 71.201 6.798 11.580 6.909 99.420 72.558 934.265 459.753 65.964 19.777 385.5 14.424 174.977 24.455 11.294 93.739 21.376 106.46 318.71 144.29 1145.18 374.17 30.426 32.017 36.321 30.493 180.519 15.525 9.073 115.831 41.936 55.815 OpenBenchmarking.org
miniBUDE MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Linux 5.15.83 Linux 5.10.130 Linux 6.1 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 21.17 21.21 21.42 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 Linux 5.15.83 Linux 5.10.130 Linux 6.1 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 21.32 21.39 21.55 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: MMAP Linux 6.1 Linux 5.15.83 Linux 5.10.130 80 160 240 320 400 SE +/- 2.76, N = 3 SE +/- 0.56, N = 3 SE +/- 0.74, N = 3 310.22 381.23 390.20 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: NUMA Linux 6.1 Linux 5.15.83 Linux 5.10.130 80 160 240 320 400 SE +/- 1.78, N = 3 SE +/- 0.90, N = 3 SE +/- 2.82, N = 3 256.61 335.58 358.05 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Futex Linux 5.10.130 Linux 5.15.83 Linux 6.1 500K 1000K 1500K 2000K 2500K SE +/- 33488.35, N = 15 SE +/- 32600.02, N = 3 SE +/- 9882.04, N = 3 1498828.70 2364278.75 2433807.14 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: MEMFD Linux 6.1 Linux 5.15.83 Linux 5.10.130 200 400 600 800 1000 SE +/- 0.28, N = 3 SE +/- 0.39, N = 3 SE +/- 0.88, N = 3 667.82 879.67 1008.62 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Mutex Linux 6.1 Linux 5.10.130 Linux 5.15.83 2M 4M 6M 8M 10M SE +/- 24065.62, N = 3 SE +/- 10182.54, N = 3 SE +/- 112044.15, N = 15 7375258.06 8606774.99 9013626.15 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Atomic Linux 5.10.130 Linux 5.15.83 Linux 6.1 50K 100K 150K 200K 250K SE +/- 1447.49, N = 3 SE +/- 1620.65, N = 3 SE +/- 3644.44, N = 3 223731.70 225144.33 225639.32 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Crypto Linux 6.1 Linux 5.15.83 Linux 5.10.130 4K 8K 12K 16K 20K SE +/- 66.53, N = 3 SE +/- 83.58, N = 3 SE +/- 47.41, N = 3 18727.61 18733.10 18742.67 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Malloc Linux 6.1 Linux 5.15.83 Linux 5.10.130 5M 10M 15M 20M 25M SE +/- 91731.80, N = 3 SE +/- 130302.14, N = 3 SE +/- 90978.10, N = 3 15989079.77 20930090.96 22392194.28 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Forking Linux 6.1 Linux 5.10.130 Linux 5.15.83 13K 26K 39K 52K 65K SE +/- 386.64, N = 3 SE +/- 175.99, N = 3 SE +/- 184.20, N = 3 53632.67 56719.51 60087.36 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: IO_uring Linux 5.15.83 Linux 6.1 Linux 5.10.130 8K 16K 24K 32K 40K SE +/- 501.84, N = 3 SE +/- 240.39, N = 3 SE +/- 401.23, N = 3 32758.89 32918.80 36489.15 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: SENDFILE Linux 5.10.130 Linux 6.1 Linux 5.15.83 60K 120K 180K 240K 300K SE +/- 2449.06, N = 3 SE +/- 1947.11, N = 3 SE +/- 2143.98, N = 3 241610.68 284966.04 285766.99 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: CPU Cache Linux 6.1 Linux 5.10.130 Linux 5.15.83 30 60 90 120 150 SE +/- 2.00, N = 15 SE +/- 2.89, N = 15 SE +/- 6.07, N = 12 115.59 116.33 128.31 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: CPU Stress Linux 6.1 Linux 5.15.83 Linux 5.10.130 7K 14K 21K 28K 35K SE +/- 27.28, N = 3 SE +/- 3.47, N = 3 SE +/- 248.24, N = 14 34059.43 34238.77 34273.52 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Semaphores Linux 5.10.130 Linux 5.15.83 Linux 6.1 700K 1400K 2100K 2800K 3500K SE +/- 159.78, N = 3 SE +/- 1860.75, N = 3 SE +/- 1806.60, N = 3 3214994.83 3314461.38 3315660.88 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Matrix Math Linux 6.1 Linux 5.15.83 Linux 5.10.130 12K 24K 36K 48K 60K SE +/- 647.24, N = 3 SE +/- 503.37, N = 3 SE +/- 476.25, N = 3 55875.18 55890.23 55915.36 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Vector Math Linux 6.1 Linux 5.10.130 Linux 5.15.83 12K 24K 36K 48K 60K SE +/- 321.30, N = 3 SE +/- 337.57, N = 3 SE +/- 330.15, N = 3 55344.32 55351.58 55415.01 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: x86_64 RdRand Linux 6.1 Linux 5.10.130 Linux 5.15.83 50K 100K 150K 200K 250K SE +/- 12.63, N = 3 SE +/- 0.71, N = 3 SE +/- 1.57, N = 3 252372.29 252390.56 252393.88 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Memory Copying Linux 5.15.83 Linux 6.1 Linux 5.10.130 900 1800 2700 3600 4500 SE +/- 42.48, N = 3 SE +/- 29.72, N = 3 SE +/- 31.35, N = 3 4129.34 4181.80 4201.02 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Socket Activity Linux 5.10.130 Linux 6.1 Linux 5.15.83 4K 8K 12K 16K 20K SE +/- 302.66, N = 15 SE +/- 112.51, N = 3 SE +/- 80.02, N = 3 10160.91 16990.75 17786.17 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Context Switching Linux 6.1 Linux 5.15.83 Linux 5.10.130 1.2M 2.4M 3.6M 4.8M 6M SE +/- 3492.53, N = 3 SE +/- 7040.94, N = 3 SE +/- 72191.04, N = 3 2054658.64 2284154.16 5500706.76 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Glibc C String Functions Linux 5.10.130 Linux 5.15.83 Linux 6.1 200K 400K 600K 800K 1000K SE +/- 6508.49, N = 3 SE +/- 3709.52, N = 3 SE +/- 8664.27, N = 3 911917.94 916397.13 916843.52 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Glibc Qsort Data Sorting Linux 6.1 Linux 5.10.130 Linux 5.15.83 40 80 120 160 200 SE +/- 1.25, N = 3 SE +/- 1.58, N = 3 SE +/- 1.18, N = 3 194.30 194.36 194.88 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
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: System V Message Passing Linux 5.10.130 Linux 5.15.83 Linux 6.1 3M 6M 9M 12M 15M SE +/- 23387.52, N = 3 SE +/- 4399.60, N = 3 SE +/- 26770.64, N = 3 6490812.35 8257907.06 14896082.79 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 srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM Linux 5.10.130 Linux 6.1 Linux 5.15.83 60 120 180 240 300 SE +/- 0.15, N = 3 SE +/- 0.27, N = 3 SE +/- 0.17, N = 3 279.8 280.2 282.7 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
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Linux 5.10.130 Linux 6.1 Linux 5.15.83 60 120 180 240 300 SE +/- 0.30, N = 3 SE +/- 0.15, N = 3 SE +/- 0.09, N = 3 279.8 280.3 282.0 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Linux 5.10.130 Linux 6.1 Linux 5.15.83 70 140 210 280 350 SE +/- 1.79, N = 3 SE +/- 0.35, N = 3 SE +/- 0.22, N = 3 303.4 307.4 310.0 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Linux 6.1 Linux 5.10.130 Linux 5.15.83 70 140 210 280 350 SE +/- 0.09, N = 3 SE +/- 0.25, N = 3 SE +/- 0.15, N = 3 305.5 307.0 307.9 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
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Linux 6.1 Linux 5.10.130 Linux 5.15.83 20 40 60 80 100 SE +/- 0.15, N = 3 SE +/- 0.35, N = 3 SE +/- 0.10, N = 3 98.3 98.6 98.6 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -lm
nekRS nekRS is an open-source Navier Stokes solver based on the spectral element method. NekRS supports both CPU and GPU/accelerator support though this test profile is currently configured for CPU execution. NekRS is part of Nek5000 of the Mathematics and Computer Science MCS at Argonne National Laboratory. This nekRS benchmark is primarily relevant to large core count HPC servers and otherwise may be very time consuming. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FLOP/s, More Is Better nekRS 22.0 Input: TurboPipe Periodic Linux 6.1 Linux 5.10.130 Linux 5.15.83 15000M 30000M 45000M 60000M 75000M SE +/- 48731133.10, N = 3 SE +/- 144216808.24, N = 3 SE +/- 219477639.96, N = 3 70481500000 70649766667 70923633333 1. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -pthread -lmpi_cxx -lmpi
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU Linux 5.10.130 Linux 5.15.83 Linux 6.1 1.3253 2.6506 3.9759 5.3012 6.6265 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 5.88 5.88 5.89 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: Person Detection FP16 - Device: CPU Linux 6.1 Linux 5.15.83 Linux 5.10.130 0.7448 1.4896 2.2344 2.9792 3.724 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 3.28 3.30 3.31 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: Person Detection FP32 - Device: CPU Linux 6.1 Linux 5.10.130 Linux 5.15.83 0.7313 1.4626 2.1939 2.9252 3.6565 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 3.23 3.25 3.25 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: Vehicle Detection FP16 - Device: CPU Linux 6.1 Linux 5.10.130 Linux 5.15.83 60 120 180 240 300 SE +/- 1.20, N = 3 SE +/- 1.08, N = 3 SE +/- 0.06, N = 3 267.62 272.09 272.80 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: Face Detection FP16-INT8 - Device: CPU Linux 5.10.130 Linux 5.15.83 Linux 6.1 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 19.11 19.15 19.17 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: Vehicle Detection FP16-INT8 - Device: CPU Linux 5.15.83 Linux 6.1 Linux 5.10.130 200 400 600 800 1000 SE +/- 1.74, N = 3 SE +/- 0.69, N = 3 SE +/- 5.71, N = 3 957.08 957.41 969.33 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: Weld Porosity Detection FP16 - Device: CPU Linux 6.1 Linux 5.15.83 Linux 5.10.130 140 280 420 560 700 SE +/- 1.31, N = 3 SE +/- 0.90, N = 3 SE +/- 0.68, N = 3 620.61 623.36 625.50 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: Machine Translation EN To DE FP16 - Device: CPU Linux 6.1 Linux 5.15.83 Linux 5.10.130 14 28 42 56 70 SE +/- 0.40, N = 3 SE +/- 0.24, N = 3 SE +/- 0.70, N = 3 63.96 64.28 64.82 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: Weld Porosity Detection FP16-INT8 - Device: CPU Linux 5.10.130 Linux 6.1 Linux 5.15.83 400 800 1200 1600 2000 SE +/- 1.36, N = 3 SE +/- 1.06, N = 3 SE +/- 0.98, N = 3 1991.75 1992.23 1993.58 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: Person Vehicle Bike Detection FP16 - Device: CPU Linux 5.15.83 Linux 5.10.130 Linux 6.1 110 220 330 440 550 SE +/- 4.62, N = 3 SE +/- 4.00, N = 13 SE +/- 4.29, N = 11 485.19 485.36 491.24 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 - Device: CPU Linux 6.1 Linux 5.15.83 Linux 5.10.130 3K 6K 9K 12K 15K SE +/- 96.54, N = 3 SE +/- 108.60, N = 3 SE +/- 110.56, N = 3 15144.32 15258.56 15259.86 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 Linux 6.1 Linux 5.15.83 Linux 5.10.130 7K 14K 21K 28K 35K SE +/- 16.23, N = 3 SE +/- 38.88, N = 3 SE +/- 85.59, N = 3 30632.46 31007.38 31167.81 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
AOM AV1 This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K Linux 6.1 Linux 5.10.130 Linux 5.15.83 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 11.65 11.70 11.77 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K Linux 6.1 Linux 5.15.83 Linux 5.10.130 9 18 27 36 45 SE +/- 0.08, N = 3 SE +/- 0.19, N = 3 SE +/- 0.08, N = 3 36.10 37.86 37.88 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Linux 6.1 Linux 5.15.83 Linux 5.10.130 11 22 33 44 55 SE +/- 0.11, N = 3 SE +/- 0.14, N = 3 SE +/- 0.06, N = 3 45.41 47.66 48.05 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K Linux 6.1 Linux 5.15.83 Linux 5.10.130 11 22 33 44 55 SE +/- 0.14, N = 3 SE +/- 0.20, N = 3 SE +/- 0.10, N = 3 45.97 48.33 48.34 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 4 - Input: Bosphorus 4K Linux 6.1 Linux 5.10.130 Linux 5.15.83 0.5587 1.1174 1.6761 2.2348 2.7935 SE +/- 0.005, N = 3 SE +/- 0.003, N = 3 SE +/- 0.005, N = 3 2.460 2.475 2.483 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 8 - Input: Bosphorus 4K Linux 5.10.130 Linux 6.1 Linux 5.15.83 8 16 24 32 40 SE +/- 0.07, N = 3 SE +/- 0.20, N = 3 SE +/- 0.15, N = 3 34.52 34.72 34.82 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 4K Linux 5.10.130 Linux 6.1 Linux 5.15.83 30 60 90 120 150 SE +/- 0.46, N = 3 SE +/- 0.29, N = 3 SE +/- 0.62, N = 3 126.50 126.76 127.53 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 13 - Input: Bosphorus 4K Linux 5.10.130 Linux 6.1 Linux 5.15.83 30 60 90 120 150 SE +/- 0.69, N = 3 SE +/- 0.62, N = 3 SE +/- 0.32, N = 3 120.79 121.60 122.98 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Linux 5.15.83 Linux 6.1 Linux 5.10.130 2 4 6 8 10 SE +/- 0.016, N = 3 SE +/- 0.044, N = 3 SE +/- 0.057, N = 3 6.985 7.024 7.046 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Linux 5.15.83 Linux 6.1 Linux 5.10.130 20 40 60 80 100 SE +/- 0.30, N = 3 SE +/- 0.46, N = 3 SE +/- 0.40, N = 3 95.04 95.15 95.49 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Linux 6.1 Linux 5.10.130 Linux 5.15.83 90 180 270 360 450 SE +/- 2.62, N = 3 SE +/- 0.88, N = 3 SE +/- 0.85, N = 3 409.13 415.14 418.02 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Linux 6.1 Linux 5.10.130 Linux 5.15.83 90 180 270 360 450 SE +/- 1.64, N = 3 SE +/- 0.82, N = 3 SE +/- 1.29, N = 3 419.75 423.65 425.26 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
miniBUDE MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Linux 5.15.83 Linux 5.10.130 Linux 6.1 120 240 360 480 600 SE +/- 0.39, N = 3 SE +/- 0.13, N = 3 SE +/- 0.30, N = 3 529.24 530.27 535.57 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 Linux 5.15.83 Linux 5.10.130 Linux 6.1 120 240 360 480 600 SE +/- 0.02, N = 3 SE +/- 0.18, N = 3 SE +/- 0.18, N = 3 532.92 534.74 538.79 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
Xmrig Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org H/s, More Is Better Xmrig 6.18.1 Variant: Monero - Hash Count: 1M Linux 6.1 Linux 5.10.130 Linux 5.15.83 1500 3000 4500 6000 7500 SE +/- 54.19, N = 3 SE +/- 3.14, N = 3 SE +/- 23.74, N = 3 6767.3 6794.5 6829.8 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.org H/s, More Is Better Xmrig 6.18.1 Variant: Wownero - Hash Count: 1M Linux 5.10.130 Linux 6.1 Linux 5.15.83 2K 4K 6K 8K 10K SE +/- 67.20, N = 3 SE +/- 49.24, N = 3 SE +/- 34.41, N = 3 9492.2 9527.7 9531.3 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries too. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: AlexNet Linux 6.1 Linux 5.10.130 Linux 5.15.83 40 80 120 160 200 SE +/- 0.22, N = 3 SE +/- 0.44, N = 3 SE +/- 0.13, N = 3 166.31 166.55 166.90
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: AlexNet Linux 6.1 Linux 5.10.130 Linux 5.15.83 50 100 150 200 250 SE +/- 0.28, N = 3 SE +/- 0.47, N = 3 SE +/- 0.13, N = 3 211.06 211.25 211.47
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: AlexNet Linux 6.1 Linux 5.15.83 Linux 5.10.130 50 100 150 200 250 SE +/- 0.27, N = 3 SE +/- 0.39, N = 3 SE +/- 0.06, N = 3 242.34 242.73 243.30
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: AlexNet Linux 5.10.130 Linux 5.15.83 Linux 6.1 60 120 180 240 300 SE +/- 0.53, N = 3 SE +/- 0.66, N = 3 SE +/- 0.40, N = 3 278.63 279.05 279.22
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: GoogLeNet Linux 5.10.130 Linux 5.15.83 Linux 6.1 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.10, N = 3 SE +/- 0.17, N = 3 114.41 115.15 116.16
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: ResNet-50 Linux 5.10.130 Linux 6.1 Linux 5.15.83 9 18 27 36 45 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 37.68 38.01 38.09
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: GoogLeNet Linux 5.10.130 Linux 5.15.83 Linux 6.1 30 60 90 120 150 SE +/- 0.14, N = 3 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 121.72 122.18 123.19
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: ResNet-50 Linux 5.10.130 Linux 6.1 Linux 5.15.83 9 18 27 36 45 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 40.23 40.32 40.41
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: GoogLeNet Linux 5.10.130 Linux 5.15.83 Linux 6.1 30 60 90 120 150 SE +/- 0.05, N = 3 SE +/- 0.14, N = 3 SE +/- 0.18, N = 3 125.79 126.29 126.49
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: ResNet-50 Linux 5.10.130 Linux 5.15.83 Linux 6.1 10 20 30 40 50 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 41.90 42.05 42.06
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: GoogLeNet Linux 5.10.130 Linux 5.15.83 Linux 6.1 30 60 90 120 150 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 130.21 130.40 130.47
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: ResNet-50 Linux 6.1 Linux 5.15.83 Linux 5.10.130 10 20 30 40 50 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 43.37 43.41 43.50
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream Linux 6.1 Linux 5.15.83 Linux 5.10.130 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 10.41 10.45 10.52
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream Linux 6.1 Linux 5.10.130 Linux 5.15.83 3 6 9 12 15 SE +/- 0.0848, N = 3 SE +/- 0.0301, N = 3 SE +/- 0.0357, N = 3 9.5393 9.5996 9.6141
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream Linux 5.10.130 Linux 6.1 Linux 5.15.83 12 24 36 48 60 SE +/- 0.15, N = 3 SE +/- 0.16, N = 3 SE +/- 0.12, N = 3 55.42 55.44 55.58
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream Linux 5.15.83 Linux 6.1 Linux 5.10.130 10 20 30 40 50 SE +/- 0.47, N = 7 SE +/- 0.21, N = 3 SE +/- 0.26, N = 3 42.90 43.32 43.76
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream Linux 5.10.130 Linux 6.1 Linux 5.15.83 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 86.66 86.88 86.94
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream Linux 5.15.83 Linux 5.10.130 Linux 6.1 20 40 60 80 100 SE +/- 0.14, N = 3 SE +/- 0.01, N = 3 SE +/- 0.10, N = 3 75.04 75.26 75.26
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream Linux 6.1 Linux 5.15.83 Linux 5.10.130 50 100 150 200 250 SE +/- 0.45, N = 3 SE +/- 0.45, N = 3 SE +/- 0.10, N = 3 218.69 219.01 219.36
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream Linux 6.1 Linux 5.10.130 Linux 5.15.83 30 60 90 120 150 SE +/- 2.16, N = 3 SE +/- 1.67, N = 3 SE +/- 0.54, N = 3 132.51 132.65 134.13
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream Linux 5.15.83 Linux 5.10.130 Linux 6.1 20 40 60 80 100 SE +/- 0.53, N = 3 SE +/- 0.05, N = 3 SE +/- 0.47, N = 3 108.34 108.55 108.74
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream Linux 6.1 Linux 5.15.83 Linux 5.10.130 16 32 48 64 80 SE +/- 0.51, N = 3 SE +/- 0.33, N = 3 SE +/- 0.65, N = 3 71.89 72.06 73.60
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream Linux 6.1 Linux 5.15.83 Linux 5.10.130 12 24 36 48 60 SE +/- 0.16, N = 3 SE +/- 0.27, N = 3 SE +/- 0.12, N = 3 54.27 54.43 55.54
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream Linux 6.1 Linux 5.15.83 Linux 5.10.130 9 18 27 36 45 SE +/- 0.31, N = 3 SE +/- 0.41, N = 3 SE +/- 0.15, N = 3 37.21 37.76 38.44
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream Linux 6.1 Linux 5.15.83 Linux 5.10.130 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 10.38 10.43 10.54
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream Linux 5.15.83 Linux 5.10.130 Linux 6.1 3 6 9 12 15 SE +/- 0.0282, N = 3 SE +/- 0.0549, N = 3 SE +/- 0.0209, N = 3 9.6111 9.6153 9.6532
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Swirl Linux 6.1 Linux 5.15.83 Linux 5.10.130 110 220 330 440 550 SE +/- 1.53, N = 3 SE +/- 1.53, N = 3 SE +/- 2.40, N = 3 491 499 502 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Rotate Linux 6.1 Linux 5.15.83 Linux 5.10.130 160 320 480 640 800 SE +/- 5.43, N = 15 SE +/- 1.76, N = 3 SE +/- 9.97, N = 5 668 731 757 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Sharpen Linux 6.1 Linux 5.10.130 Linux 5.15.83 40 80 120 160 200 SE +/- 1.33, N = 3 SE +/- 1.33, N = 3 SE +/- 1.20, N = 3 197 199 199 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Enhanced Linux 6.1 Linux 5.15.83 Linux 5.10.130 70 140 210 280 350 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 311 314 315 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Resizing Linux 6.1 Linux 5.15.83 Linux 5.10.130 300 600 900 1200 1500 SE +/- 2.91, N = 3 SE +/- 2.73, N = 3 SE +/- 7.42, N = 3 1299 1321 1333 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Noise-Gaussian Linux 6.1 Linux 5.15.83 Linux 5.10.130 70 140 210 280 350 SE +/- 1.76, N = 3 322 331 335 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: HWB Color Space Linux 6.1 Linux 5.15.83 Linux 5.10.130 200 400 600 800 1000 SE +/- 1.67, N = 3 SE +/- 1.53, N = 3 872 957 976 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Aircrack-ng Aircrack-ng is a tool for assessing WiFi/WLAN network security. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org k/s, More Is Better Aircrack-ng 1.7 Linux 5.10.130 Linux 5.15.83 Linux 6.1 11K 22K 33K 44K 55K SE +/- 129.98, N = 3 SE +/- 118.77, N = 3 SE +/- 144.43, N = 3 50605.56 50607.74 50609.28 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
Cpuminer-Opt Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Magi Linux 6.1 Linux 5.15.83 Linux 5.10.130 80 160 240 320 400 SE +/- 4.81, N = 3 SE +/- 4.11, N = 3 SE +/- 4.81, N = 3 373.45 373.55 374.94 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: x25x Linux 6.1 Linux 5.10.130 Linux 5.15.83 140 280 420 560 700 SE +/- 0.34, N = 3 SE +/- 0.20, N = 3 SE +/- 1.51, N = 3 638.64 640.06 641.61 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: scrypt Linux 5.15.83 Linux 6.1 Linux 5.10.130 110 220 330 440 550 SE +/- 5.31, N = 3 SE +/- 2.46, N = 3 SE +/- 3.92, N = 3 489.83 491.85 491.90 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Deepcoin Linux 6.1 Linux 5.10.130 Linux 5.15.83 3K 6K 9K 12K 15K SE +/- 46.67, N = 3 SE +/- 50.00, N = 3 14420 14497 14500 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Ringcoin Linux 6.1 Linux 5.15.83 Linux 5.10.130 600 1200 1800 2400 3000 SE +/- 1.62, N = 3 SE +/- 0.80, N = 3 SE +/- 27.91, N = 3 2800.62 2812.34 2833.09 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Blake-2 S Linux 6.1 Linux 5.10.130 Linux 5.15.83 200K 400K 600K 800K 1000K SE +/- 3289.87, N = 3 SE +/- 6874.21, N = 3 SE +/- 10686.26, N = 3 1137550 1149103 1150583 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Garlicoin Linux 6.1 Linux 5.10.130 Linux 5.15.83 1400 2800 4200 5600 7000 SE +/- 2.16, N = 3 SE +/- 2.21, N = 3 SE +/- 11.67, N = 3 6571.66 6572.81 6594.18 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Skeincoin Linux 6.1 Linux 5.15.83 Linux 5.10.130 30K 60K 90K 120K 150K SE +/- 283.78, N = 3 SE +/- 3.33, N = 3 SE +/- 169.54, N = 3 134320 134833 135103 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Myriad-Groestl Linux 5.10.130 Linux 6.1 Linux 5.15.83 4K 8K 12K 16K 20K SE +/- 286.72, N = 3 SE +/- 135.32, N = 3 SE +/- 185.02, N = 3 17363 17477 17610 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: LBC, LBRY Credits Linux 6.1 Linux 5.15.83 Linux 5.10.130 20K 40K 60K 80K 100K SE +/- 615.39, N = 3 SE +/- 167.46, N = 3 SE +/- 656.84, N = 3 96010 96663 96820 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Quad SHA-256, Pyrite Linux 6.1 Linux 5.15.83 Linux 5.10.130 50K 100K 150K 200K 250K SE +/- 258.61, N = 3 SE +/- 6.67, N = 3 SE +/- 820.33, N = 3 217237 218493 218830 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Triple SHA-256, Onecoin Linux 5.15.83 Linux 6.1 Linux 5.10.130 70K 140K 210K 280K 350K SE +/- 661.12, N = 3 SE +/- 2222.66, N = 3 SE +/- 2642.36, N = 3 313917 315723 315913 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.3 Test: blosclz bitshuffle Linux 5.10.130 Linux 6.1 Linux 5.15.83 2K 4K 6K 8K 10K SE +/- 20.30, N = 3 SE +/- 25.18, N = 3 SE +/- 12.20, N = 3 10158.9 10161.3 10555.7 1. (CC) gcc options: -std=gnu99 -O3 -lrt -pthread -lm
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating Linux 5.10.130 Linux 6.1 Linux 5.15.83 20K 40K 60K 80K 100K SE +/- 259.98, N = 3 SE +/- 264.89, N = 3 SE +/- 150.80, N = 3 86432 86680 86735 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
JPEG XL libjxl The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: PNG - Quality: 80 Linux 6.1 Linux 5.10.130 Linux 5.15.83 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 7.36 7.70 7.71 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: PNG - Quality: 90 Linux 6.1 Linux 5.15.83 Linux 5.10.130 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 7.20 7.54 7.58 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: JPEG - Quality: 80 Linux 6.1 Linux 5.15.83 Linux 5.10.130 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 7.08 7.40 7.45 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: JPEG - Quality: 90 Linux 6.1 Linux 5.15.83 Linux 5.10.130 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 6.94 7.25 7.30 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: PNG - Quality: 100 Linux 6.1 Linux 5.10.130 Linux 5.15.83 0.1215 0.243 0.3645 0.486 0.6075 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.53 0.54 0.54 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: JPEG - Quality: 100 Linux 6.1 Linux 5.10.130 Linux 5.15.83 0.1193 0.2386 0.3579 0.4772 0.5965 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.52 0.53 0.53 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic
JPEG XL Decoding libjxl The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is suited for JPEG XL decode performance testing to PNG output file, the pts/jpexl test is for encode performance. The JPEG XL encoding/decoding is done using the libjxl codebase. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better JPEG XL Decoding libjxl 0.7 CPU Threads: 1 Linux 6.1 Linux 5.15.83 Linux 5.10.130 9 18 27 36 45 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 36.37 37.90 38.17
OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100 Linux 6.1 Linux 5.10.130 Linux 5.15.83 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 8.95 9.00 9.02 1. (CC) gcc options: -fvisibility=hidden -O2 -lm -pthread
OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless Linux 5.10.130 Linux 6.1 Linux 5.15.83 0.288 0.576 0.864 1.152 1.44 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.27 1.27 1.28 1. (CC) gcc options: -fvisibility=hidden -O2 -lm -pthread
OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Highest Compression Linux 5.10.130 Linux 6.1 Linux 5.15.83 0.6953 1.3906 2.0859 2.7812 3.4765 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.07 3.08 3.09 1. (CC) gcc options: -fvisibility=hidden -O2 -lm -pthread
OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless, Highest Compression Linux 5.10.130 Linux 5.15.83 Linux 6.1 0.108 0.216 0.324 0.432 0.54 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.48 0.48 0.48 1. (CC) gcc options: -fvisibility=hidden -O2 -lm -pthread
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Fast Linux 6.1 Linux 5.15.83 Linux 5.10.130 40 80 120 160 200 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 192.99 193.02 193.13 1. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Medium Linux 6.1 Linux 5.15.83 Linux 5.10.130 16 32 48 64 80 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 72.10 72.12 72.16 1. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Thorough Linux 6.1 Linux 5.10.130 Linux 5.15.83 3 6 9 12 15 SE +/- 0.0088, N = 3 SE +/- 0.0023, N = 3 SE +/- 0.0055, N = 3 9.3103 9.3225 9.3267 1. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Exhaustive Linux 6.1 Linux 5.10.130 Linux 5.15.83 0.2109 0.4218 0.6327 0.8436 1.0545 SE +/- 0.0006, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 0.9368 0.9371 0.9375 1. (CXX) g++ options: -O3 -flto -pthread
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Random Fill Linux 6.1 Linux 5.15.83 Linux 5.10.130 200K 400K 600K 800K 1000K SE +/- 2558.50, N = 3 SE +/- 11892.65, N = 3 SE +/- 10947.16, N = 3 935285 982848 983199 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Random Read Linux 5.10.130 Linux 5.15.83 Linux 6.1 14M 28M 42M 56M 70M SE +/- 547664.44, N = 3 SE +/- 139131.71, N = 3 SE +/- 360247.64, N = 3 65094239 65233649 65337175 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Update Random Linux 6.1 Linux 5.15.83 Linux 5.10.130 130K 260K 390K 520K 650K SE +/- 2022.46, N = 3 SE +/- 1069.98, N = 3 SE +/- 3662.51, N = 3 594485 616626 625695 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Sequential Fill Linux 6.1 Linux 5.15.83 Linux 5.10.130 300K 600K 900K 1200K 1500K SE +/- 11595.14, N = 3 SE +/- 3547.16, N = 3 SE +/- 10501.31, N = 3 1134991 1193837 1204255 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Random Fill Sync Linux 5.10.130 Linux 6.1 Linux 5.15.83 50K 100K 150K 200K 250K SE +/- 254.19, N = 3 SE +/- 160.74, N = 3 SE +/- 684.45, N = 3 216464 218454 234969 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Read While Writing Linux 6.1 Linux 5.15.83 Linux 5.10.130 700K 1400K 2100K 2800K 3500K SE +/- 14227.22, N = 3 SE +/- 29968.88, N = 3 SE +/- 49813.03, N = 3 2985392 3043279 3100899 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Read Random Write Random Linux 5.15.83 Linux 5.10.130 Linux 6.1 500K 1000K 1500K 2000K 2500K SE +/- 8919.50, N = 3 SE +/- 16550.67, N = 3 SE +/- 10651.17, N = 3 2129359 2132608 2133528 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Dragonflydb Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 1:1 Linux 5.10.130 Linux 5.15.83 Linux 6.1 200K 400K 600K 800K 1000K SE +/- 19609.96, N = 13 SE +/- 643.98, N = 3 SE +/- 1471.72, N = 3 978963.31 1123953.55 1130454.03 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 1:5 Linux 5.10.130 Linux 6.1 Linux 5.15.83 300K 600K 900K 1200K 1500K SE +/- 872.80, N = 3 SE +/- 1580.99, N = 3 SE +/- 1515.54, N = 3 1047699.23 1180450.09 1186278.25 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 5:1 Linux 5.10.130 Linux 5.15.83 Linux 6.1 200K 400K 600K 800K 1000K SE +/- 8046.26, N = 3 SE +/- 3987.52, N = 3 SE +/- 741.75, N = 3 989148.97 1068662.91 1074996.43 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 Linux 5.10.130 Linux 6.1 Linux 5.15.83 200K 400K 600K 800K 1000K SE +/- 1890.11, N = 3 SE +/- 6338.63, N = 3 SE +/- 1111.75, N = 3 971725.25 1046604.15 1060251.05 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: 1:5 Linux 5.10.130 Linux 6.1 Linux 5.15.83 200K 400K 600K 800K 1000K SE +/- 515.57, N = 3 SE +/- 797.47, N = 3 SE +/- 3993.93, N = 3 1021149.38 1099078.40 1117321.90 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: 5:1 Linux 5.10.130 Linux 6.1 Linux 5.15.83 200K 400K 600K 800K 1000K SE +/- 4444.49, N = 3 SE +/- 1905.52, N = 3 SE +/- 845.72, N = 3 918617.37 979549.43 993337.90 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
ClickHouse ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all queries performed. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, First Run / Cold Cache Linux 6.1 Linux 5.15.83 Linux 5.10.130 50 100 150 200 250 SE +/- 0.88, N = 3 SE +/- 1.58, N = 14 SE +/- 1.55, N = 15 198.51 204.26 205.76 MIN: 22.14 / MAX: 20000 MIN: 22.52 / MAX: 20000 MIN: 22.01 / MAX: 20000 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, Second Run Linux 6.1 Linux 5.15.83 Linux 5.10.130 50 100 150 200 250 SE +/- 4.28, N = 3 SE +/- 1.25, N = 14 SE +/- 0.88, N = 15 204.43 209.58 212.60 MIN: 22.33 / MAX: 20000 MIN: 22.65 / MAX: 20000 MIN: 22.96 / MAX: 20000 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, Third Run Linux 5.10.130 Linux 6.1 Linux 5.15.83 50 100 150 200 250 SE +/- 1.01, N = 15 SE +/- 1.08, N = 3 SE +/- 0.78, N = 14 212.42 212.92 215.02 MIN: 22.81 / MAX: 20000 MIN: 22.26 / MAX: 20000 MIN: 22.68 / MAX: 20000 1. ClickHouse server version 22.5.4.19 (official build).
Stargate Digital Audio Workstation Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 44100 - Buffer Size: 512 Linux 6.1 Linux 5.10.130 Linux 5.15.83 0.8938 1.7876 2.6814 3.5752 4.469 SE +/- 0.063340, N = 3 SE +/- 0.028488, N = 3 SE +/- 0.017996, N = 3 3.817268 3.909552 3.972591 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 96000 - Buffer Size: 512 Linux 6.1 Linux 5.10.130 Linux 5.15.83 0.5803 1.1606 1.7409 2.3212 2.9015 SE +/- 0.031971, N = 3 SE +/- 0.035214, N = 3 SE +/- 0.013088, N = 3 2.497164 2.537891 2.579045 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 512 Linux 6.1 Linux 5.10.130 Linux 5.15.83 0.3526 0.7052 1.0578 1.4104 1.763 SE +/- 0.006196, N = 3 SE +/- 0.008212, N = 3 SE +/- 0.017482, N = 3 1.520040 1.536255 1.567049 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 44100 - Buffer Size: 1024 Linux 6.1 Linux 5.10.130 Linux 5.15.83 0.997 1.994 2.991 3.988 4.985 SE +/- 0.047576, N = 3 SE +/- 0.002245, N = 3 SE +/- 0.011431, N = 3 4.311382 4.385893 4.431098 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 480000 - Buffer Size: 512 Linux 6.1 Linux 5.10.130 Linux 5.15.83 0.8528 1.7056 2.5584 3.4112 4.264 SE +/- 0.044488, N = 3 SE +/- 0.019070, N = 3 SE +/- 0.052597, N = 3 3.718812 3.726933 3.790321 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 96000 - Buffer Size: 1024 Linux 5.10.130 Linux 6.1 Linux 5.15.83 0.6893 1.3786 2.0679 2.7572 3.4465 SE +/- 0.016716, N = 3 SE +/- 0.021684, N = 3 SE +/- 0.004654, N = 3 2.999611 3.012585 3.063511 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 1024 Linux 5.10.130 Linux 6.1 Linux 5.15.83 0.4477 0.8954 1.3431 1.7908 2.2385 SE +/- 0.016352, N = 3 SE +/- 0.012895, N = 3 SE +/- 0.011134, N = 3 1.889268 1.928814 1.989680 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 480000 - Buffer Size: 1024 Linux 5.10.130 Linux 6.1 Linux 5.15.83 0.961 1.922 2.883 3.844 4.805 SE +/- 0.030220, N = 3 SE +/- 0.017869, N = 3 SE +/- 0.015411, N = 3 4.199568 4.208880 4.270897 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Samples / Second, More Is Better srsRAN 22.04.1 Test: OFDM_Test Linux 6.1 Linux 5.10.130 Linux 5.15.83 30M 60M 90M 120M 150M SE +/- 417665.47, N = 3 SE +/- 251661.15, N = 3 SE +/- 352766.84, N = 3 120733333 122000000 122633333 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
spaCy The spaCy library is an open-source solution for advanced neural language processing (NLP). The spaCy library leverages Python and is a leading neural language processing solution. This test profile times the spaCy CPU performance with various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org tokens/sec, More Is Better spaCy 3.4.1 Model: en_core_web_lg Linux 6.1 Linux 5.15.83 Linux 5.10.130 2K 4K 6K 8K 10K SE +/- 18.76, N = 3 SE +/- 10.74, N = 3 SE +/- 15.62, N = 3 11231 11236 11314
OpenBenchmarking.org tokens/sec, More Is Better spaCy 3.4.1 Model: en_core_web_trf Linux 6.1 Linux 5.15.83 Linux 5.10.130 500 1000 1500 2000 2500 SE +/- 7.51, N = 3 SE +/- 6.33, N = 3 SE +/- 9.87, N = 3 2341 2416 2446
PostgreSQL This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Only Linux 5.10.130 Linux 5.15.83 Linux 6.1 110K 220K 330K 440K 550K SE +/- 1779.96, N = 3 SE +/- 92.73, N = 3 SE +/- 1990.45, N = 3 465422 515273 523788 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 Only Linux 5.10.130 Linux 5.15.83 Linux 6.1 100K 200K 300K 400K 500K SE +/- 2810.03, N = 3 SE +/- 286.86, N = 3 SE +/- 5532.44, N = 3 413949 475175 487468 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: 500 - Mode: Read Only Linux 5.10.130 Linux 5.15.83 Linux 6.1 100K 200K 300K 400K 500K SE +/- 956.06, N = 3 SE +/- 666.01, N = 3 SE +/- 757.53, N = 3 370238 426428 467167 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 Linux 5.10.130 Linux 6.1 Linux 5.15.83 12K 24K 36K 48K 60K SE +/- 146.53, N = 3 SE +/- 90.59, N = 3 SE +/- 125.21, N = 3 53656 54365 56230 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 Linux 6.1 Linux 5.15.83 Linux 5.10.130 10K 20K 30K 40K 50K SE +/- 71.67, N = 3 SE +/- 31.67, N = 3 SE +/- 132.15, N = 3 45223 45922 47676 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: 500 - Mode: Read Write Linux 5.15.83 Linux 6.1 Linux 5.10.130 8K 16K 24K 32K 40K SE +/- 99.01, N = 3 SE +/- 91.02, N = 3 SE +/- 59.40, N = 3 33824 36109 38503 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM Linux 6.1 Linux 5.10.130 Linux 5.15.83 30 60 90 120 150 SE +/- 0.03, N = 3 SE +/- 0.27, N = 3 SE +/- 0.07, N = 3 117.1 117.3 118.3 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -lm
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Linux 5.10.130 Linux 6.1 Linux 5.15.83 30 60 90 120 150 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 SE +/- 0.06, N = 3 123.3 123.3 123.9 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
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Linux 5.10.130 Linux 6.1 Linux 5.15.83 30 60 90 120 150 SE +/- 0.13, N = 3 SE +/- 0.15, N = 3 SE +/- 0.18, N = 3 126.9 127.2 128.0 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -lm
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Linux 6.1 Linux 5.10.130 Linux 5.15.83 30 60 90 120 150 SE +/- 0.15, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 130.3 131.0 131.6 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -lm
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Linux 5.10.130 Linux 6.1 Linux 5.15.83 15 30 45 60 75 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.15, N = 3 65.9 65.9 66.0 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -lpthread -ldl -lm
BRL-CAD BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.32.6 VGR Performance Metric Linux 5.15.83 Linux 5.10.130 Linux 6.1 40K 80K 120K 160K 200K 166852 167771 168334 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: IP Shapes 1D - Data Type: f32 - Engine: CPU Linux 6.1 Linux 5.10.130 Linux 5.15.83 0.5168 1.0336 1.5504 2.0672 2.584 SE +/- 0.00145, N = 3 SE +/- 0.00305, N = 3 SE +/- 0.00109, N = 3 2.29708 2.29636 2.29385 MIN: 2.22 MIN: 2.22 MIN: 2.19 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU Linux 5.10.130 Linux 6.1 Linux 5.15.83 0.6978 1.3956 2.0934 2.7912 3.489 SE +/- 0.00480, N = 3 SE +/- 0.00478, N = 3 SE +/- 0.01196, N = 3 3.10144 3.09433 3.08561 MIN: 3.06 MIN: 3.06 MIN: 3.05 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU Linux 5.15.83 Linux 6.1 Linux 5.10.130 0.1119 0.2238 0.3357 0.4476 0.5595 SE +/- 0.000206, N = 3 SE +/- 0.000335, N = 3 SE +/- 0.000232, N = 3 0.497248 0.496776 0.496613 MIN: 0.48 MIN: 0.48 MIN: 0.48 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU Linux 5.10.130 Linux 5.15.83 Linux 6.1 0.2819 0.5638 0.8457 1.1276 1.4095 SE +/- 0.00257, N = 3 SE +/- 0.00241, N = 3 SE +/- 0.00376, N = 3 1.25271 1.25174 1.24871 MIN: 1.22 MIN: 1.22 MIN: 1.21 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU Linux 5.15.83 Linux 5.10.130 Linux 6.1 0.9702 1.9404 2.9106 3.8808 4.851 SE +/- 0.01348, N = 3 SE +/- 0.00912, N = 3 SE +/- 0.00632, N = 3 4.31178 4.29153 4.28618 MIN: 4.24 MIN: 4.25 MIN: 4.24 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU Linux 6.1 Linux 5.15.83 Linux 5.10.130 1.1207 2.2414 3.3621 4.4828 5.6035 SE +/- 0.02580, N = 3 SE +/- 0.01367, N = 3 SE +/- 0.01724, N = 3 4.98067 4.70834 4.70699 MIN: 4.62 MIN: 4.4 MIN: 4.43 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU Linux 6.1 Linux 5.10.130 Linux 5.15.83 0.7453 1.4906 2.2359 2.9812 3.7265 SE +/- 0.00768, N = 3 SE +/- 0.00465, N = 3 SE +/- 0.00438, N = 3 3.31244 3.30606 3.29633 MIN: 3.26 MIN: 3.27 MIN: 3.27 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU Linux 5.15.83 Linux 6.1 Linux 5.10.130 0.9458 1.8916 2.8374 3.7832 4.729 SE +/- 0.00929, N = 3 SE +/- 0.00677, N = 3 SE +/- 0.01257, N = 3 4.20343 4.18096 4.15869 MIN: 4.13 MIN: 4.13 MIN: 4.09 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU Linux 6.1 Linux 5.10.130 Linux 5.15.83 0.1218 0.2436 0.3654 0.4872 0.609 SE +/- 0.000200, N = 3 SE +/- 0.000704, N = 3 SE +/- 0.000263, N = 3 0.541430 0.540654 0.540452 MIN: 0.53 MIN: 0.53 MIN: 0.53 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU Linux 5.10.130 Linux 5.15.83 Linux 6.1 0.1916 0.3832 0.5748 0.7664 0.958 SE +/- 0.006451, N = 3 SE +/- 0.010105, N = 3 SE +/- 0.003867, N = 3 0.851455 0.846543 0.831866 MIN: 0.83 MIN: 0.82 MIN: 0.81 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU Linux 6.1 Linux 5.10.130 Linux 5.15.83 300 600 900 1200 1500 SE +/- 0.44, N = 3 SE +/- 0.83, N = 3 SE +/- 0.39, N = 3 1614.07 1613.12 1611.14 MIN: 1609.86 MIN: 1608.28 MIN: 1608.25 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU Linux 5.15.83 Linux 5.10.130 Linux 6.1 200 400 600 800 1000 SE +/- 1.01, N = 3 SE +/- 2.14, N = 3 SE +/- 1.41, N = 3 912.07 909.63 909.15 MIN: 908.55 MIN: 903.56 MIN: 904.93 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU Linux 5.10.130 Linux 6.1 Linux 5.15.83 300 600 900 1200 1500 SE +/- 2.14, N = 3 SE +/- 1.70, N = 3 SE +/- 3.87, N = 3 1621.84 1618.86 1614.87 MIN: 1617.11 MIN: 1614.3 MIN: 1607.67 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU Linux 6.1 Linux 5.10.130 Linux 5.15.83 200 400 600 800 1000 SE +/- 2.67, N = 3 SE +/- 1.27, N = 3 SE +/- 0.73, N = 3 913.94 911.82 908.19 MIN: 907.08 MIN: 907.5 MIN: 904.52 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU Linux 6.1 Linux 5.15.83 Linux 5.10.130 0.2168 0.4336 0.6504 0.8672 1.084 SE +/- 0.002932, N = 3 SE +/- 0.003629, N = 3 SE +/- 0.001517, N = 3 0.963400 0.961682 0.956399 MIN: 0.93 MIN: 0.93 MIN: 0.93 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU Linux 5.15.83 Linux 6.1 Linux 5.10.130 0.0711 0.1422 0.2133 0.2844 0.3555 SE +/- 0.001833, N = 3 SE +/- 0.000082, N = 3 SE +/- 0.000694, N = 3 0.316005 0.313975 0.313238 MIN: 0.3 MIN: 0.3 MIN: 0.3 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -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: 1 - Renderer: Path Tracer Linux 5.10.130 Linux 6.1 Linux 5.15.83 1500 3000 4500 6000 7500 SE +/- 10.90, N = 3 SE +/- 1.45, N = 3 7055 7048 7046 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer Linux 5.15.83 Linux 6.1 Linux 5.10.130 1600 3200 4800 6400 8000 SE +/- 3.79, N = 3 SE +/- 2.52, N = 3 SE +/- 2.33, N = 3 7246 7245 7242 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer Linux 6.1 Linux 5.10.130 Linux 5.15.83 2K 4K 6K 8K 10K SE +/- 9.45, N = 3 SE +/- 5.51, N = 3 8633 8633 8628 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: 16 - Renderer: Path Tracer Linux 6.1 Linux 5.15.83 Linux 5.10.130 30K 60K 90K 120K 150K SE +/- 1530.19, N = 5 SE +/- 135.52, N = 3 SE +/- 26.43, N = 3 123000 121486 121467 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 Linux 6.1 Linux 5.10.130 Linux 5.15.83 50K 100K 150K 200K 250K SE +/- 262.34, N = 3 SE +/- 254.40, N = 3 SE +/- 19.15, N = 3 234371 234216 234142 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer Linux 6.1 Linux 5.15.83 Linux 5.10.130 30K 60K 90K 120K 150K SE +/- 1877.65, N = 3 SE +/- 104.41, N = 3 SE +/- 68.75, N = 3 126341 124556 124428 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer Linux 6.1 Linux 5.15.83 Linux 5.10.130 50K 100K 150K 200K 250K SE +/- 131.54, N = 3 SE +/- 62.00, N = 3 SE +/- 103.12, N = 3 240430 240311 239935 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer Linux 6.1 Linux 5.10.130 Linux 5.15.83 30K 60K 90K 120K 150K SE +/- 27.67, N = 3 SE +/- 58.33, N = 3 SE +/- 69.67, N = 3 146692 146583 146570 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer Linux 5.15.83 Linux 5.10.130 Linux 6.1 60K 120K 180K 240K 300K SE +/- 192.14, N = 3 SE +/- 239.39, N = 3 SE +/- 92.98, N = 3 284853 284699 284235 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer Linux 6.1 Linux 5.15.83 Linux 5.10.130 400 800 1200 1600 2000 SE +/- 0.58, N = 3 SE +/- 1.33, N = 3 SE +/- 0.67, N = 3 1779 1778 1778 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer Linux 5.15.83 Linux 5.10.130 Linux 6.1 400 800 1200 1600 2000 SE +/- 0.67, N = 3 SE +/- 1.15, N = 3 SE +/- 1.00, N = 3 1826 1826 1824 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer Linux 5.10.130 Linux 5.15.83 Linux 6.1 500 1000 1500 2000 2500 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 2178 2176 2173 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer Linux 6.1 Linux 5.15.83 Linux 5.10.130 6K 12K 18K 24K 30K SE +/- 9.70, N = 3 SE +/- 21.40, N = 3 SE +/- 8.11, N = 3 28479 28417 28409 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer Linux 6.1 Linux 5.10.130 Linux 5.15.83 14K 28K 42K 56K 70K SE +/- 527.74, N = 3 SE +/- 37.27, N = 3 SE +/- 20.81, N = 3 65894 65271 65242 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer Linux 5.15.83 Linux 5.10.130 Linux 6.1 6K 12K 18K 24K 30K SE +/- 5.24, N = 3 SE +/- 28.26, N = 3 29206 29172 29165 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer Linux 6.1 Linux 5.10.130 Linux 5.15.83 15K 30K 45K 60K 75K SE +/- 539.86, N = 14 SE +/- 35.09, N = 3 SE +/- 44.92, N = 3 67837 66823 66817 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer Linux 5.15.83 Linux 5.10.130 Linux 6.1 7K 14K 21K 28K 35K SE +/- 4.51, N = 3 SE +/- 21.06, N = 3 SE +/- 5.29, N = 3 34801 34786 34779 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer Linux 6.1 Linux 5.10.130 Linux 5.15.83 20K 40K 60K 80K 100K SE +/- 964.72, N = 6 SE +/- 96.91, N = 3 SE +/- 75.54, N = 3 79804 78016 77997 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
PostgreSQL This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency Linux 5.10.130 Linux 5.15.83 Linux 6.1 0.0484 0.0968 0.1452 0.1936 0.242 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 0.215 0.194 0.191 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: 250 - Mode: Read Only - Average Latency Linux 5.10.130 Linux 5.15.83 Linux 6.1 0.1359 0.2718 0.4077 0.5436 0.6795 SE +/- 0.004, N = 3 SE +/- 0.000, N = 3 SE +/- 0.006, N = 3 0.604 0.526 0.513 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: 500 - Mode: Read Only - Average Latency Linux 5.10.130 Linux 5.15.83 Linux 6.1 0.3038 0.6076 0.9114 1.2152 1.519 SE +/- 0.003, N = 3 SE +/- 0.002, N = 3 SE +/- 0.002, N = 3 1.350 1.173 1.070 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: 100 - Mode: Read Write - Average Latency Linux 5.10.130 Linux 6.1 Linux 5.15.83 0.4194 0.8388 1.2582 1.6776 2.097 SE +/- 0.005, N = 3 SE +/- 0.003, N = 3 SE +/- 0.004, N = 3 1.864 1.839 1.779 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: 250 - Mode: Read Write - Average Latency Linux 6.1 Linux 5.15.83 Linux 5.10.130 1.2438 2.4876 3.7314 4.9752 6.219 SE +/- 0.009, N = 3 SE +/- 0.004, N = 3 SE +/- 0.015, N = 3 5.528 5.444 5.244 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: 500 - Mode: Read Write - Average Latency Linux 5.15.83 Linux 6.1 Linux 5.10.130 4 8 12 16 20 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 14.78 13.85 12.99 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Mobile Neural Network MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. This MNN test profile is building the OpenMP / CPU threaded version for processor benchmarking and not any GPU-accelerated test. MNN does allow making use of AVX-512 extensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: nasnet Linux 6.1 Linux 5.10.130 Linux 5.15.83 4 8 12 16 20 SE +/- 0.15, N = 9 SE +/- 0.12, N = 3 SE +/- 0.10, N = 3 15.12 14.91 14.88 MIN: 14.55 / MAX: 29.56 MIN: 14.46 / MAX: 28.47 MIN: 14.51 / MAX: 33.86 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
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenetV3 Linux 5.10.130 Linux 6.1 Linux 5.15.83 0.4705 0.941 1.4115 1.882 2.3525 SE +/- 0.010, N = 3 SE +/- 0.009, N = 9 SE +/- 0.009, N = 3 2.091 2.083 2.071 MIN: 1.99 / MAX: 3.26 MIN: 1.98 / MAX: 6.07 MIN: 1.99 / MAX: 4.73 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
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: squeezenetv1.1 Linux 6.1 Linux 5.10.130 Linux 5.15.83 0.5864 1.1728 1.7592 2.3456 2.932 SE +/- 0.012, N = 9 SE +/- 0.020, N = 3 SE +/- 0.015, N = 3 2.606 2.592 2.537 MIN: 2.49 / MAX: 16.46 MIN: 2.48 / MAX: 5.22 MIN: 2.47 / MAX: 4.14 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
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: resnet-v2-50 Linux 5.10.130 Linux 6.1 Linux 5.15.83 3 6 9 12 15 SE +/- 0.099, N = 3 SE +/- 0.037, N = 9 SE +/- 0.025, N = 3 10.148 9.932 9.850 MIN: 9.88 / MAX: 23.7 MIN: 9.74 / MAX: 23.92 MIN: 9.74 / MAX: 31.53 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
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: SqueezeNetV1.0 Linux 6.1 Linux 5.15.83 Linux 5.10.130 1.118 2.236 3.354 4.472 5.59 SE +/- 0.019, N = 9 SE +/- 0.009, N = 3 SE +/- 0.043, N = 3 4.969 4.897 4.892 MIN: 4.87 / MAX: 7.19 MIN: 4.84 / MAX: 18.25 MIN: 4.79 / MAX: 17.74 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
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: MobileNetV2_224 Linux 5.10.130 Linux 6.1 Linux 5.15.83 0.8674 1.7348 2.6022 3.4696 4.337 SE +/- 0.007, N = 3 SE +/- 0.020, N = 9 SE +/- 0.020, N = 3 3.855 3.831 3.752 MIN: 3.65 / MAX: 16.53 MIN: 3.59 / MAX: 5.87 MIN: 3.56 / MAX: 17.6 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
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenet-v1-1.0 Linux 5.10.130 Linux 6.1 Linux 5.15.83 0.6026 1.2052 1.8078 2.4104 3.013 SE +/- 0.044, N = 3 SE +/- 0.028, N = 9 SE +/- 0.047, N = 3 2.678 2.640 2.639 MIN: 2.4 / MAX: 5.22 MIN: 2.36 / MAX: 16.9 MIN: 2.38 / MAX: 3.73 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
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: inception-v3 Linux 6.1 Linux 5.10.130 Linux 5.15.83 5 10 15 20 25 SE +/- 0.32, N = 9 SE +/- 0.36, N = 3 SE +/- 0.38, N = 3 22.79 22.73 22.44 MIN: 21.59 / MAX: 102.89 MIN: 22.05 / MAX: 36.04 MIN: 21.58 / MAX: 36.88 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 NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mobilenet Linux 5.15.83 Linux 5.10.130 Linux 6.1 4 8 12 16 20 SE +/- 0.18, N = 6 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 14.71 14.54 14.45 MIN: 14.26 / MAX: 15.75 MIN: 14.37 / MAX: 17.06 MIN: 14.31 / MAX: 15.47 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v2-v2 - Model: mobilenet-v2 Linux 6.1 Linux 5.10.130 Linux 5.15.83 1.2533 2.5066 3.7599 5.0132 6.2665 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 6 5.57 5.56 5.53 MIN: 5.49 / MAX: 6.18 MIN: 5.44 / MAX: 6.03 MIN: 5.41 / MAX: 10.99 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v3-v3 - Model: mobilenet-v3 Linux 6.1 Linux 5.15.83 Linux 5.10.130 1.1138 2.2276 3.3414 4.4552 5.569 SE +/- 0.01, N = 3 SE +/- 0.04, N = 6 SE +/- 0.01, N = 3 4.95 4.95 4.95 MIN: 4.86 / MAX: 5.26 MIN: 4.8 / MAX: 63.45 MIN: 4.85 / MAX: 5.91 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: shufflenet-v2 Linux 5.10.130 Linux 6.1 Linux 5.15.83 1.2735 2.547 3.8205 5.094 6.3675 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 6 5.66 5.63 5.59 MIN: 5.54 / MAX: 17.07 MIN: 5.53 / MAX: 6.55 MIN: 5.48 / MAX: 6.6 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mnasnet Linux 5.10.130 Linux 6.1 Linux 5.15.83 1.1048 2.2096 3.3144 4.4192 5.524 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 6 4.91 4.89 4.85 MIN: 4.74 / MAX: 16.51 MIN: 4.81 / MAX: 5.21 MIN: 4.72 / MAX: 7.62 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: efficientnet-b0 Linux 5.10.130 Linux 6.1 Linux 5.15.83 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 6 7.06 7.04 6.99 MIN: 6.92 / MAX: 7.42 MIN: 6.92 / MAX: 7.34 MIN: 6.89 / MAX: 8.15 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: blazeface Linux 5.10.130 Linux 6.1 Linux 5.15.83 0.5355 1.071 1.6065 2.142 2.6775 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 6 2.38 2.36 2.29 MIN: 2.2 / MAX: 2.75 MIN: 2.3 / MAX: 2.62 MIN: 2.23 / MAX: 3.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: googlenet Linux 5.10.130 Linux 6.1 Linux 5.15.83 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 6 11.57 11.48 11.46 MIN: 11.39 / MAX: 11.86 MIN: 11.33 / MAX: 12.45 MIN: 11.27 / MAX: 12.43 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vgg16 Linux 5.15.83 Linux 5.10.130 Linux 6.1 7 14 21 28 35 SE +/- 1.00, N = 6 SE +/- 0.13, N = 3 SE +/- 0.10, N = 3 27.69 26.95 26.52 MIN: 26.21 / MAX: 33.47 MIN: 26.65 / MAX: 27.51 MIN: 26.22 / MAX: 27.61 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet18 Linux 5.10.130 Linux 5.15.83 Linux 6.1 2 4 6 8 10 SE +/- 0.04, N = 3 SE +/- 0.22, N = 6 SE +/- 0.01, N = 3 8.09 8.05 7.85 MIN: 7.89 / MAX: 9.29 MIN: 7.68 / MAX: 9.97 MIN: 7.74 / MAX: 10.2 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: alexnet Linux 5.15.83 Linux 6.1 Linux 5.10.130 1.233 2.466 3.699 4.932 6.165 SE +/- 0.08, N = 6 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 5.48 5.46 5.46 MIN: 5.3 / MAX: 6.07 MIN: 5.35 / MAX: 9.83 MIN: 5.35 / MAX: 5.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet50 Linux 5.15.83 Linux 5.10.130 Linux 6.1 4 8 12 16 20 SE +/- 0.34, N = 6 SE +/- 0.05, N = 3 SE +/- 0.13, N = 3 14.21 14.20 13.83 MIN: 13.45 / MAX: 157.72 MIN: 13.99 / MAX: 15.03 MIN: 13.51 / MAX: 26.19 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: yolov4-tiny Linux 5.15.83 Linux 5.10.130 Linux 6.1 6 12 18 24 30 SE +/- 0.39, N = 6 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 23.89 23.60 23.35 MIN: 22.91 / MAX: 31.78 MIN: 23.16 / MAX: 27.3 MIN: 23.01 / MAX: 26.25 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: squeezenet_ssd Linux 5.10.130 Linux 5.15.83 Linux 6.1 4 8 12 16 20 SE +/- 0.12, N = 3 SE +/- 0.12, N = 6 SE +/- 0.14, N = 3 17.13 16.85 16.76 MIN: 16.75 / MAX: 17.86 MIN: 16.41 / MAX: 19.23 MIN: 16.41 / MAX: 17.26 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: regnety_400m Linux 5.10.130 Linux 6.1 Linux 5.15.83 5 10 15 20 25 SE +/- 0.15, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 6 18.83 18.70 18.67 MIN: 18.43 / MAX: 58.94 MIN: 18.43 / MAX: 19.5 MIN: 18.39 / MAX: 21.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vision_transformer Linux 5.15.83 Linux 6.1 Linux 5.10.130 40 80 120 160 200 SE +/- 0.40, N = 6 SE +/- 0.61, N = 3 SE +/- 0.96, N = 3 161.23 160.39 160.27 MIN: 158.43 / MAX: 179.56 MIN: 158.59 / MAX: 172.13 MIN: 158.5 / MAX: 166.42 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: FastestDet Linux 5.10.130 Linux 6.1 Linux 5.15.83 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 6 7.02 6.96 6.91 MIN: 6.87 / MAX: 7.89 MIN: 6.86 / MAX: 7.19 MIN: 6.78 / MAX: 7.67 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU Linux 5.10.130 Linux 6.1 Linux 5.15.83 300 600 900 1200 1500 SE +/- 7.68, N = 3 SE +/- 5.43, N = 3 SE +/- 8.21, N = 3 1357.37 1357.10 1356.35 MIN: 1303.04 / MAX: 1429.1 MIN: 1311.47 / MAX: 1435.45 MIN: 1238.64 / MAX: 1424.43 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: Person Detection FP16 - Device: CPU Linux 6.1 Linux 5.15.83 Linux 5.10.130 500 1000 1500 2000 2500 SE +/- 4.48, N = 3 SE +/- 6.63, N = 3 SE +/- 6.79, N = 3 2415.31 2401.74 2400.02 MIN: 2186.01 / MAX: 2533.33 MIN: 2074.14 / MAX: 2532.54 MIN: 1971.05 / MAX: 2519.43 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: Person Detection FP32 - Device: CPU Linux 6.1 Linux 5.15.83 Linux 5.10.130 500 1000 1500 2000 2500 SE +/- 5.75, N = 3 SE +/- 9.26, N = 3 SE +/- 6.93, N = 3 2451.10 2441.67 2436.30 MIN: 2080.43 / MAX: 2583.81 MIN: 2123.66 / MAX: 2621.99 MIN: 2086.23 / MAX: 2572.2 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 Linux 6.1 Linux 5.10.130 Linux 5.15.83 7 14 21 28 35 SE +/- 0.14, N = 3 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 29.86 29.37 29.29 MIN: 11.2 / MAX: 55.83 MIN: 11.56 / MAX: 50.23 MIN: 13.39 / MAX: 49.34 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: Face Detection FP16-INT8 - Device: CPU Linux 5.10.130 Linux 5.15.83 Linux 6.1 90 180 270 360 450 SE +/- 0.17, N = 3 SE +/- 0.53, N = 3 SE +/- 0.59, N = 3 417.71 416.95 416.16 MIN: 260.74 / MAX: 433.77 MIN: 240.72 / MAX: 434.4 MIN: 211.14 / MAX: 443.45 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-INT8 - Device: CPU Linux 5.15.83 Linux 6.1 Linux 5.10.130 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 8.34 8.33 8.24 MIN: 4.49 / MAX: 23.48 MIN: 4.48 / MAX: 25.96 MIN: 4.42 / MAX: 23.84 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: Weld Porosity Detection FP16 - Device: CPU Linux 6.1 Linux 5.15.83 Linux 5.10.130 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 25.73 25.62 25.53 MIN: 14.41 / MAX: 47.88 MIN: 14.62 / MAX: 46.69 MIN: 13.67 / MAX: 47.14 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: Machine Translation EN To DE FP16 - Device: CPU Linux 6.1 Linux 5.15.83 Linux 5.10.130 30 60 90 120 150 SE +/- 0.78, N = 3 SE +/- 0.46, N = 3 SE +/- 1.34, N = 3 124.97 124.34 123.34 MIN: 64.13 / MAX: 142.04 MIN: 64.41 / MAX: 139.86 MIN: 64 / MAX: 136.84 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: Weld Porosity Detection FP16-INT8 - Device: CPU Linux 6.1 Linux 5.10.130 Linux 5.15.83 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 8.02 8.02 8.01 MIN: 6 / MAX: 25.19 MIN: 4.07 / MAX: 22.04 MIN: 5.89 / MAX: 26.32 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: Person Vehicle Bike Detection FP16 - Device: CPU Linux 5.10.130 Linux 5.15.83 Linux 6.1 4 8 12 16 20 SE +/- 0.14, N = 13 SE +/- 0.16, N = 3 SE +/- 0.15, N = 11 16.47 16.46 16.27 MIN: 7.86 / MAX: 36.14 MIN: 9.28 / MAX: 33.36 MIN: 7.67 / MAX: 36.05 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: Age Gender Recognition Retail 0013 FP16 - Device: CPU Linux 6.1 Linux 5.10.130 Linux 5.15.83 0.234 0.468 0.702 0.936 1.17 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 1.04 1.04 1.03 MIN: 0.61 / MAX: 17.76 MIN: 0.61 / MAX: 17.55 MIN: 0.61 / MAX: 17.94 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: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Linux 6.1 Linux 5.15.83 Linux 5.10.130 0.1148 0.2296 0.3444 0.4592 0.574 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.51 0.50 0.50 MIN: 0.32 / MAX: 15.06 MIN: 0.31 / MAX: 28.92 MIN: 0.31 / MAX: 16.57 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream Linux 6.1 Linux 5.15.83 Linux 5.10.130 160 320 480 640 800 SE +/- 4.45, N = 3 SE +/- 2.20, N = 3 SE +/- 1.03, N = 3 764.74 759.35 758.03
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream Linux 6.1 Linux 5.10.130 Linux 5.15.83 20 40 60 80 100 SE +/- 0.93, N = 3 SE +/- 0.33, N = 3 SE +/- 0.39, N = 3 104.83 104.16 104.01