icelake march

Intel Core i7-1065G7 testing with a Dell 06CDVY (1.0.9 BIOS) and Intel Iris Plus ICL GT2 16GB on Ubuntu 23.10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2403273-NE-ICELAKEMA80
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
March 26
  4 Hours, 59 Minutes
b
March 27
  4 Hours, 48 Minutes
Invert Behavior (Only Show Selected Data)
  4 Hours, 54 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


icelake marchOpenBenchmarking.orgPhoronix Test SuiteIntel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads)Dell 06CDVY (1.0.9 BIOS)Intel Ice Lake-LP DRAM16GBToshiba KBG40ZPZ512G NVMe 512GB + 2 x 0GB MassStorageClassIntel Iris Plus ICL GT2 16GB (1100MHz)Realtek ALC289Intel Ice Lake-LP PCH CNVi WiFiUbuntu 23.106.7.0-060700rc5-generic (x86_64)GNOME Shell 45.1X Server + Wayland4.6 Mesa 24.0~git2312230600.551924~oibaf~m (git-551924a 2023-12-23 mantic-oibaf-ppa)GCC 13.2.0ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionIcelake March BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xc2 - Thermald 2.5.4- Python 3.11.6- gather_data_sampling: Mitigation of Microcode + itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + spec_rstack_overflow: Not affected + 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 / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Mitigation of Microcode + tsx_async_abort: Not affected

a vs. b ComparisonPhoronix Test SuiteBaseline+8.4%+8.4%+16.8%+16.8%+25.2%+25.2%33.5%22.3%15.7%15.1%15.1%12.7%11.1%10.9%10.3%9.8%9.8%9.4%9.2%9.1%9.1%9%8.9%8.7%8.4%8.4%8.4%8.4%8.2%8.2%8.1%8.1%7.8%7.6%7.5%7.4%7.3%7.3%7.2%7.1%7%6.9%6.9%6.9%6.8%6.8%6.6%6.6%6.5%6.5%6.5%6.3%6.3%6.3%6.3%6.2%6.2%6.2%6.2%6.1%6.1%6%6%5.8%5.7%5.6%5.5%5.3%5.3%5.3%5.2%5.2%5.1%5%5%4.9%4.8%4.8%4.7%4.5%4.5%4.4%4.2%4.1%4%3.9%3.9%3.8%3.7%3.6%3.5%3.5%3.2%2.9%2.6%2.3%PNG - 80CPU - 1 - ResNet-15230.4%CPU - 1 - ResNet-5025.5%WAV To WavPackSeq FillR.S.A.F.I - CPUR.S.A.F.I - CPUCPU - 1 - ResNet-50OverwriteD.B.s - CPUCPUP.V.B.D.F - CPUP.V.B.D.F - CPUP.D.F - CPUP.D.F - CPUH.E.R.F.I - CPUH.E.R.F.I - CPUPNG - 90CPU - 16 - GoogLeNetPreset 8 - Bosphorus 1080pF.D.R.F - CPURead While WritingRand ReadF.D.R.F - CPUF.D.R.F.I - CPUF.D.R.F.I - CPUM.T.E.T.D.F - CPUM.T.E.T.D.F - CPUJPEG - 90JPEG - 80C.B.S.A - CPUCPU - 32 - AlexNetW.P.D.F.I - CPUW.P.D.F.I - CPUCPU - 64 - AlexNetCPU - 32 - GoogLeNetCPU - 16 - ResNet-50Update RandP.R.I.R.F - CPUP.R.I.R.F - CPUCPU - 1 - Efficientnet_v2_lA.G.R.R.0.F.I - CPUChess BenchmarkH.E.R.F - CPUR.N.N.T - CPUH.E.R.F - CPUA.G.R.R.0.F - CPUF.D.F - CPUF.D.F - CPUA.G.R.R.0.F - CPUW.P.D.F - CPUN.S.P.L.F - CPUCPU - 64 - GoogLeNetA.G.R.R.0.F.I - CPUW.P.D.F - CPUN.S.P.L.F - CPUCPU - 64 - ResNet-50BMW27 - CPU-OnlyCPU - 16 - AlexNetCPU - 32 - ResNet-50PNG - 100AllPabellon Barcelona - CPU-OnlyCPU - 32 - ResNet-152Rand FillCPU - 16 - Efficientnet_v2_lP.D.F - CPUFishy Cat - CPU-OnlyP.D.F - CPUCPU - 64 - ResNet-152JPEG - 100CPU - 1 - GoogLeNetV.D.F - CPUV.D.F - CPU1e12Preset 4 - Bosphorus 1080pCPU - 32 - Efficientnet_v2_lCPU - 64 - Efficientnet_v2_lF.D.F.I - CPUCPU - 16 - ResNet-152Preset 13 - Bosphorus 4KV.D.F.I - CPUV.D.F.I - CPUF.D.F.I - CPUIP Shapes 1D - CPUR.R.W.RR.S.A.F - CPUR.S.A.F - CPUJunkshop - CPU-OnlyCPU - 16 - ResNet-503%CPU - 1 - AlexNetPreset 4 - Bosphorus 4KCPU - 64 - ResNet-50Rand Fill Sync2.1%JPEG-XL libjxlPyTorchPyTorchWavPack Audio EncodingRocksDBOpenVINOOpenVINOTensorFlowRocksDBoneDNNChaos Group V-RAYOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOJPEG-XL libjxlTensorFlowSVT-AV1OpenVINORocksDBRocksDBOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOJPEG-XL libjxlJPEG-XL libjxloneDNNTensorFlowOpenVINOOpenVINOTensorFlowTensorFlowTensorFlowRocksDBOpenVINOOpenVINOPyTorchOpenVINOStockfishOpenVINOoneDNNOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOTensorFlowOpenVINOOpenVINOOpenVINOTensorFlowBlenderTensorFlowTensorFlowJPEG-XL libjxlJPEG-XL Decoding libjxlBlenderPyTorchRocksDBPyTorchOpenVINOBlenderOpenVINOPyTorchJPEG-XL libjxlTensorFlowOpenVINOOpenVINOPrimesieveSVT-AV1PyTorchPyTorchOpenVINOPyTorchSVT-AV1OpenVINOOpenVINOOpenVINOoneDNNRocksDBOpenVINOOpenVINOBlenderPyTorchTensorFlowSVT-AV1PyTorchRocksDBab

icelake marchblender: Pabellon Barcelona - CPU-Onlytensorflow: CPU - 64 - ResNet-50blender: Junkshop - CPU-Onlyblender: Fishy Cat - CPU-Onlypytorch: CPU - 32 - Efficientnet_v2_lpytorch: CPU - 16 - Efficientnet_v2_lpytorch: CPU - 64 - Efficientnet_v2_lblender: BMW27 - CPU-Onlypytorch: CPU - 32 - ResNet-152build-linux-kernel: defconfigpytorch: CPU - 64 - ResNet-152pytorch: CPU - 16 - ResNet-152tensorflow: CPU - 32 - ResNet-50stockfish: Chess Benchmarktensorflow: CPU - 64 - GoogLeNetpytorch: CPU - 1 - Efficientnet_v2_ltensorflow: CPU - 16 - ResNet-50jpegxl: JPEG - 80jpegxl: PNG - 80pytorch: CPU - 64 - ResNet-50pytorch: CPU - 32 - ResNet-50pytorch: CPU - 16 - ResNet-50svt-av1: Preset 4 - Bosphorus 4Ktensorflow: CPU - 32 - GoogLeNetjpegxl: JPEG - 100jpegxl: PNG - 100pytorch: CPU - 1 - ResNet-152jpegxl: PNG - 90jpegxl: JPEG - 90tensorflow: CPU - 64 - AlexNetbuild-mesa: Time To Compileonednn: Recurrent Neural Network Training - CPUonednn: Recurrent Neural Network Inference - CPUprimesieve: 1e12tensorflow: CPU - 16 - GoogLeNetsvt-av1: Preset 8 - Bosphorus 4Ktensorflow: CPU - 32 - AlexNetv-ray: CPUopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUpytorch: CPU - 1 - ResNet-50openvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUrocksdb: Rand Fill Syncopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUrocksdb: Rand Fillopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUrocksdb: Overwriteopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUrocksdb: Read While Writingrocksdb: Update Randrocksdb: Read Rand Write Randrocksdb: Rand Readjpegxl-decode: Alltensorflow: CPU - 16 - AlexNetjpegxl-decode: 1svt-av1: Preset 4 - Bosphorus 1080pcompress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compressionsvt-av1: Preset 12 - Bosphorus 4Ksvt-av1: Preset 13 - Bosphorus 4Ktensorflow: CPU - 1 - ResNet-50onednn: Deconvolution Batch shapes_1d - CPUsvt-av1: Preset 8 - Bosphorus 1080pencode-wavpack: WAV To WavPackonednn: IP Shapes 1D - CPUtensorflow: CPU - 1 - AlexNetdraco: Church Facadeonednn: IP Shapes 3D - CPUrocksdb: Seq Filltensorflow: CPU - 1 - GoogLeNetdraco: Liononednn: Convolution Batch Shapes Auto - CPUsvt-av1: Preset 12 - Bosphorus 1080ponednn: Deconvolution Batch shapes_3d - CPUsvt-av1: Preset 13 - Bosphorus 1080pab2207.357.5921.09848.452.472.462.48671.93.37496.163.393.457.44276254420.374.437.288.0488.2788.548.698.920.92820.092.9812.9978.457.5437.66245.59143.67412553.36399.7388.59219.697.55142.9335356365.090.631675.082.3720.99562.297.1460.938.66548.857.26171984.3447.3643.990.9234.26116.52151.6126.3440.6498.25108.3736.8830.02132.9505433123.0732.4710.38383.0577.4751.5962.6263.7723.86167.0316.82236.714871160.864463.622.21779.085002101863345040919192128123.51239.0457.5843.64328.58123524.90225.1185.3518.83228.8517.6577.0803711.2384215.8074581333522.17555913.7106184.73413.4544240.462092.757.96892.47806.432.582.592.59633.723.55497.1813.563.597.87294503221.634.737.798.66211.0538.748.688.660.95221.523.133.1696.488.2228.25648.86143.24911783.66341.984.58321.447.56946.138995987.530.671614.492.4716.72535.17.47426.39.36502.557.94168373.2654.5339.9799.8532.26123.67146.4827.2738.02105.0399.3740.2328.89138.11532197115.534.599.59414.4273.9154.0658.9867.7622.0118115.67253.975411610.814765.042.071894.375421531992635221459961527130.44341.3858.0413.80628.09627824.62426.1346.0316.982931.37314.4326.8263911.5683615.8313594071123.26549112.755184.08513.4885238.626OpenBenchmarking.org

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Pabellon Barcelona - Compute: CPU-Onlyba50010001500200025002092.752207.35

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 if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: ResNet-50ba2468107.967.50

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Junkshop - Compute: CPU-Onlyba2004006008001000892.47921.09

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Fishy Cat - Compute: CPU-Onlyba2004006008001000806.43848.45

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_lba0.58051.1611.74152.3222.90252.582.47MIN: 2.18 / MAX: 3.27MIN: 2.3 / MAX: 3.1

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_lba0.58281.16561.74842.33122.9142.592.46MIN: 2.34 / MAX: 3.21MIN: 2.18 / MAX: 3.06

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_lba0.58281.16561.74842.33122.9142.592.48MIN: 2.29 / MAX: 3.06MIN: 2.21 / MAX: 3.02

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: BMW27 - Compute: CPU-Onlyba140280420560700633.72671.90

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 32 - Model: ResNet-152ba0.79881.59762.39643.19523.9943.553.37MIN: 3.29 / MAX: 4.15MIN: 3.09 / MAX: 4.17

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: defconfigab110220330440550496.16497.18

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: ResNet-152ba0.8011.6022.4033.2044.0053.563.39MIN: 3.3 / MAX: 4.19MIN: 3.22 / MAX: 4.18

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 16 - Model: ResNet-152ba0.80781.61562.42343.23124.0393.593.45MIN: 3.18 / MAX: 4.56MIN: 3.28 / MAX: 4.26

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 if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: ResNet-50ba2468107.877.44

Stockfish

This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 1024 CPU threads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 16.1Chess Benchmarkba600K1200K1800K2400K3000K294503227625441. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver

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 if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: GoogLeNetba51015202521.6320.37

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_lba1.06432.12863.19294.25725.32154.734.43MIN: 4.29 / MAX: 6.39MIN: 3.92 / MAX: 6.05

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 if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 16 - Model: ResNet-50ba2468107.797.28

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.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 80ba2468108.6628.0481. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 80ba369121511.0538.2781. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: ResNet-50ba2468108.748.54MIN: 7.76 / MAX: 10.2MIN: 7.7 / MAX: 10.85

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 32 - Model: ResNet-50ab2468108.698.68MIN: 7.73 / MAX: 9.58MIN: 7.82 / MAX: 10.13

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 16 - Model: ResNet-50ab2468108.928.66MIN: 6.82 / MAX: 10.81MIN: 7.84 / MAX: 10.76

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.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4Kba0.21420.42840.64260.85681.0710.9520.9281. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: GoogLeNetba51015202521.5220.09

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.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 100ba0.70431.40862.11292.81723.52153.1302.9811. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 100ba0.7131.4262.1392.8523.5653.1692.9971. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: ResNet-152ab2468108.456.48MIN: 7.21 / MAX: 8.75MIN: 5.29 / MAX: 8.11

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.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 90ba2468108.2227.5431. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 90ba2468108.2567.6621. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

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 if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: AlexNetba112233445548.8645.59

Timed Mesa Compilation

This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 24.0Time To Compileba306090120150143.25143.67

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Training - Engine: CPUba3K6K9K12K15K11783.612553.3MIN: 11523.5MIN: 12419.51. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Inference - Engine: CPUba140028004200560070006341.906399.73MIN: 6215.67MIN: 6336.721. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Primesieve

Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e12ba2040608010084.5888.591. (CXX) g++ options: -O3

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 if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 16 - Model: GoogLeNetba51015202521.4419.69

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.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4Kba2468107.5697.5511. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: AlexNetba102030405046.1042.93

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 6.0Mode: CPUba800160024003200400038993535

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.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUba140028004200560070005987.536365.09MIN: 3948.27 / MAX: 6469.32MIN: 4117.28 / MAX: 6821.881. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUba0.15080.30160.45240.60320.7540.670.631. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUba4008001200160020001614.491675.08MIN: 989.41 / MAX: 1851.51MIN: 979.3 / MAX: 1858.761. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUba0.55581.11161.66742.22322.7792.472.371. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: ResNet-50ab51015202520.9916.72MIN: 18.42 / MAX: 21.52MIN: 14.31 / MAX: 22.33

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.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUba120240360480600535.10562.29MIN: 331.64 / MAX: 616.9MIN: 328.73 / MAX: 643.551. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUba2468107.477.101. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUba100200300400500426.30460.93MIN: 266.17 / MAX: 497.45MIN: 257.76 / MAX: 516.231. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUba36912159.368.661. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUba120240360480600502.55548.85MIN: 251.66 / MAX: 603.5MIN: 316.87 / MAX: 622.991. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUba2468107.947.261. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Fill Syncab400800120016002000171916831. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUba2040608010073.2684.34MIN: 42.21 / MAX: 97.49MIN: 42.98 / MAX: 112.291. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUba122436486054.5347.361. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUba102030405039.9743.90MIN: 22.42 / MAX: 60.47MIN: 22.03 / MAX: 69.031. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUba2040608010099.8590.921. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUba81624324032.2634.26MIN: 17.41 / MAX: 59.91MIN: 16.36 / MAX: 51.611. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUba306090120150123.67116.521. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUba306090120150146.48151.61MIN: 95.3 / MAX: 181.77MIN: 96.87 / MAX: 185.091. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUba61218243027.2726.341. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUba91827364538.0240.64MIN: 18.33 / MAX: 61.62MIN: 16.78 / MAX: 58.651. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUba20406080100105.0398.251. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUba2040608010099.37108.37MIN: 52.55 / MAX: 136.55MIN: 51.18 / MAX: 147.771. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUba91827364540.2336.881. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUba71421283528.8930.02MIN: 12.22 / MAX: 56.17MIN: 12.02 / MAX: 53.721. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUba306090120150138.11132.901. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Fillba110K220K330K440K550K5321975054331. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUba306090120150115.50123.07MIN: 62.34 / MAX: 153.58MIN: 62.42 / MAX: 153.741. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUba81624324034.5932.471. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUba36912159.5910.38MIN: 4.46 / MAX: 25.46MIN: 4.12 / MAX: 24.581. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUba90180270360450414.42383.051. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUba2040608010073.9177.47MIN: 42.25 / MAX: 102.91MIN: 41.16 / MAX: 110.741. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUba122436486054.0651.591. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUba142842567058.9862.62MIN: 30.6 / MAX: 85.41MIN: 28.99 / MAX: 93.011. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUba153045607567.7663.771. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUba61218243022.0123.86MIN: 8.86 / MAX: 45.48MIN: 9.57 / MAX: 41.511. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUba4080120160200181.00167.031. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUba4812162015.6716.82MIN: 7.56 / MAX: 33.57MIN: 6.35 / MAX: 33.71. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUba60120180240300253.97236.711. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Overwriteba120K240K360K480K600K5411614871161. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUba0.19350.3870.58050.7740.96750.810.86MIN: 0.31 / MAX: 7.17MIN: 0.32 / MAX: 7.111. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUba100020003000400050004765.044463.621. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUba0.4950.991.4851.982.4752.072.20MIN: 0.81 / MAX: 21.75MIN: 0.81 / MAX: 10.391. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUba4008001200160020001894.371779.081. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While Writingba120K240K360K480K600K5421535002101. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Update Randomba40K80K120K160K200K1992631863341. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read Random Write Randomba110K220K330K440K550K5221455040911. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Readba2M4M6M8M10M996152791921281. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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.orgMP/s, More Is BetterJPEG-XL Decoding libjxl 0.10.1CPU Threads: Allba306090120150130.44123.51

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 if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 16 - Model: AlexNetba91827364541.3839.04

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.orgMP/s, More Is BetterJPEG-XL Decoding libjxl 0.10.1CPU Threads: 1ba132639526558.0457.58

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.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 1080pba0.85641.71282.56923.42564.2823.8063.6431. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Parallel BZIP2 Compression

This test measures the time needed to compress a file (FreeBSD-13.0-RELEASE-amd64-memstick.img) using Parallel BZIP2 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.13FreeBSD-13.0-RELEASE-amd64-memstick.img Compressionba71421283528.1028.581. (CXX) g++ options: -O2 -pthread -lbz2 -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.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4Kab61218243024.9024.621. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4Kba61218243026.1325.121. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: ResNet-50ba2468106.035.35

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_1d - Engine: CPUba51015202516.9818.83MIN: 15.81MIN: 16.91. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

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.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 1080pba71421283531.3728.851. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

WavPack Audio Encoding

This test times how long it takes to encode a sample WAV file to WavPack format with very high quality settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.7WAV To WavPackba4812162014.4317.66

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 1D - Engine: CPUba2468106.826397.08037MIN: 6.61MIN: 6.621. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

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 if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: AlexNetba369121511.5611.23

Google Draco

Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: Church Facadeba2K4K6K8K10K836184211. (CXX) g++ options: -O3

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 3D - Engine: CPUab1.31212.62423.93635.24846.56055.807455.83135MIN: 5.67MIN: 5.681. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Sequential Fillba200K400K600K800K1000K9407118133351. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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 if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: GoogLeNetba61218243023.2622.17

Google Draco

Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: Lionba12002400360048006000549155591. (CXX) g++ options: -O3

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Convolution Batch Shapes Auto - Engine: CPUba4812162012.7613.71MIN: 12.13MIN: 11.941. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

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.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 1080pab4080120160200184.73184.091. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_3d - Engine: CPUab369121513.4513.49MIN: 13.22MIN: 13.241. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

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.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 1080pab50100150200250240.46238.631. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

108 Results Shown

Blender
TensorFlow
Blender:
  Junkshop - CPU-Only
  Fishy Cat - CPU-Only
PyTorch:
  CPU - 32 - Efficientnet_v2_l
  CPU - 16 - Efficientnet_v2_l
  CPU - 64 - Efficientnet_v2_l
Blender
PyTorch
Timed Linux Kernel Compilation
PyTorch:
  CPU - 64 - ResNet-152
  CPU - 16 - ResNet-152
TensorFlow
Stockfish
TensorFlow
PyTorch
TensorFlow
JPEG-XL libjxl:
  JPEG - 80
  PNG - 80
PyTorch:
  CPU - 64 - ResNet-50
  CPU - 32 - ResNet-50
  CPU - 16 - ResNet-50
SVT-AV1
TensorFlow
JPEG-XL libjxl:
  JPEG - 100
  PNG - 100
PyTorch
JPEG-XL libjxl:
  PNG - 90
  JPEG - 90
TensorFlow
Timed Mesa Compilation
oneDNN:
  Recurrent Neural Network Training - CPU
  Recurrent Neural Network Inference - CPU
Primesieve
TensorFlow
SVT-AV1
TensorFlow
Chaos Group V-RAY
OpenVINO:
  Face Detection FP16 - CPU:
    ms
    FPS
  Face Detection FP16-INT8 - CPU:
    ms
    FPS
PyTorch
OpenVINO:
  Person Detection FP32 - CPU:
    ms
    FPS
  Machine Translation EN To DE FP16 - CPU:
    ms
    FPS
  Person Detection FP16 - CPU:
    ms
    FPS
RocksDB
OpenVINO:
  Road Segmentation ADAS FP16-INT8 - CPU:
    ms
    FPS
  Person Vehicle Bike Detection FP16 - CPU:
    ms
    FPS
  Noise Suppression Poconet-Like FP16 - CPU:
    ms
    FPS
  Road Segmentation ADAS FP16 - CPU:
    ms
    FPS
  Person Re-Identification Retail FP16 - CPU:
    ms
    FPS
  Handwritten English Recognition FP16-INT8 - CPU:
    ms
    FPS
  Vehicle Detection FP16-INT8 - CPU:
    ms
    FPS
RocksDB
OpenVINO:
  Handwritten English Recognition FP16 - CPU:
    ms
    FPS
  Face Detection Retail FP16-INT8 - CPU:
    ms
    FPS
  Vehicle Detection FP16 - CPU:
    ms
    FPS
  Weld Porosity Detection FP16 - CPU:
    ms
    FPS
  Face Detection Retail FP16 - CPU:
    ms
    FPS
  Weld Porosity Detection FP16-INT8 - CPU:
    ms
    FPS
RocksDB
OpenVINO:
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    ms
    FPS
  Age Gender Recognition Retail 0013 FP16 - CPU:
    ms
    FPS
RocksDB:
  Read While Writing
  Update Rand
  Read Rand Write Rand
  Rand Read
JPEG-XL Decoding libjxl
TensorFlow
JPEG-XL Decoding libjxl
SVT-AV1
Parallel BZIP2 Compression
SVT-AV1:
  Preset 12 - Bosphorus 4K
  Preset 13 - Bosphorus 4K
TensorFlow
oneDNN
SVT-AV1
WavPack Audio Encoding
oneDNN
TensorFlow
Google Draco
oneDNN
RocksDB
TensorFlow
Google Draco
oneDNN
SVT-AV1
oneDNN
SVT-AV1