xeon eo march

2 x Intel Xeon Platinum 8380 testing with a Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) and ASPEED on Ubuntu 22.10 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 2304015-NE-XEONEOMAR92
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

Limit displaying results to tests within:

AV1 3 Tests
Timed Code Compilation 5 Tests
C/C++ Compiler Tests 12 Tests
CPU Massive 14 Tests
Creator Workloads 11 Tests
Cryptography 2 Tests
Database Test Suite 3 Tests
Encoding 6 Tests
Game Development 3 Tests
HPC - High Performance Computing 6 Tests
Common Kernel Benchmarks 4 Tests
Machine Learning 4 Tests
Multi-Core 18 Tests
NVIDIA GPU Compute 2 Tests
Intel oneAPI 2 Tests
OpenMPI Tests 2 Tests
Programmer / Developer System Benchmarks 6 Tests
Python Tests 6 Tests
Server 6 Tests
Server CPU Tests 10 Tests
Video Encoding 6 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
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
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
March 31 2023
  8 Hours, 52 Minutes
b
March 31 2023
  7 Hours, 24 Minutes
c
April 01 2023
  6 Hours, 16 Minutes
Invert Hiding All Results Option
  7 Hours, 31 Minutes

Only show results where is faster than
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):


xeon eo marchOpenBenchmarking.orgPhoronix Test Suite2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads)Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS)Intel Ice Lake IEH512GB7682GB INTEL SSDPF2KX076TZASPEEDVE2282 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFPUbuntu 22.106.2.0-rc5-phx-dodt (x86_64)GNOME Shell 43.0X Server 1.21.1.31.3.224GCC 12.2.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionXeon Eo March BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/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-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: 0xd000375 - Python 3.10.7- dodt: Mitigation of DOITM + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

abcResult OverviewPhoronix Test Suite100%149%197%246%John The RipperStress-NGMemcachedGoogle DracoZstd CompressionDarmstadt Automotive Parallel Heterogeneous SuiteBuild2Timed Node.js CompilationSPECFEM3DTimed Godot Game Engine CompilationRocksDBVP9 libvpx Encodingdav1dVVenCnginxONNX RuntimeGROMACSEmbreeOpenSSLAOM AV1SVT-AV1Timed LLVM CompilationTensorFlowTimed FFmpeg CompilationFFmpegMariaDBBlender

xeon eo marchrocksdb: Seq Fillmysqlslap: 512mysqlslap: 1024mysqlslap: 2048mysqlslap: 4096tensorflow: CPU - 512 - ResNet-50onednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUopencv: Graph APIonednn: Recurrent Neural Network Training - f32 - CPUopencv: Stitchingffmpeg: libx265 - Video On Demandffmpeg: libx265 - Video On Demandffmpeg: libx265 - Platformffmpeg: libx265 - Platformtensorflow: CPU - 256 - ResNet-50ffmpeg: libx265 - Uploadffmpeg: libx265 - Uploadffmpeg: libx264 - Uploadffmpeg: libx264 - Uploadopencv: Image Processingopencv: Features 2Dbuild-llvm: Unix Makefilesblender: Barbershop - CPU-Onlyffmpeg: libx264 - Video On Demandffmpeg: libx264 - Video On Demandffmpeg: libx264 - Platformffmpeg: libx264 - Platformtensorflow: CPU - 512 - GoogLeNetvpxenc: Speed 0 - Bosphorus 4Kbuild-nodejs: Time To Compiletensorflow: CPU - 64 - ResNet-50vvenc: Bosphorus 4K - Fastffmpeg: libx265 - Liveffmpeg: libx265 - Livebuild-llvm: Ninjaopenssl: ChaCha20-Poly1305openssl: AES-256-GCMopenssl: AES-128-GCMopenssl: ChaCha20openssl: SHA256openssl: SHA512onednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUaom-av1: Speed 4 Two-Pass - Bosphorus 4Kbuild-godot: Time To Compiletensorflow: CPU - 256 - GoogLeNetopencv: Videovvenc: Bosphorus 4K - Fastertensorflow: CPU - 32 - ResNet-50onednn: IP Shapes 1D - f32 - CPUvpxenc: Speed 5 - Bosphorus 4Konednn: IP Shapes 1D - u8s8f32 - CPUtensorflow: CPU - 512 - AlexNetopencv: Object Detectionopencv: DNN - Deep Neural Networkvpxenc: Speed 0 - Bosphorus 1080paom-av1: Speed 6 Two-Pass - Bosphorus 4Konednn: IP Shapes 1D - bf16bf16bf16 - CPUbuild2: Time To Compileonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: GPT-2 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Parallelonnx: yolov4 - CPU - Parallelonnx: yolov4 - CPU - Parallelonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardonnx: yolov4 - CPU - Standardonnx: yolov4 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardnginx: 500nginx: 200onnx: CaffeNet 12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Parallelapache: 500onnx: CaffeNet 12-int8 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Standardapache: 200onnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Standardonnx: super-resolution-10 - CPU - Standardopencv: Coreaom-av1: Speed 4 Two-Pass - Bosphorus 1080ptensorflow: CPU - 16 - ResNet-50daphne: OpenMP - Points2Imagecompress-zstd: 19, Long Mode - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speedvvenc: Bosphorus 1080p - Fastblender: Pabellon Barcelona - CPU-Onlysvt-av1: Preset 4 - Bosphorus 4Konednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 3D - bf16bf16bf16 - CPUtensorflow: CPU - 256 - AlexNetffmpeg: libx264 - Liveffmpeg: libx264 - Livedav1d: Chimera 1080p 10-bitmemcached: 1:100dav1d: Chimera 1080pmemcached: 1:10memcached: 1:5compress-zstd: 8, Long Mode - Decompression Speedcompress-zstd: 8, Long Mode - Compression Speedcompress-zstd: 3, Long Mode - Decompression Speedcompress-zstd: 3, Long Mode - Compression Speedcompress-zstd: 3 - Decompression Speedcompress-zstd: 3 - Compression Speedcompress-zstd: 8 - Decompression Speedcompress-zstd: 8 - Compression Speedblender: Classroom - CPU-Onlycompress-zstd: 12 - Decompression Speedcompress-zstd: 12 - Compression Speedcompress-zstd: 19 - Decompression Speedcompress-zstd: 19 - Compression Speedrocksdb: Rand Fill Syncaom-av1: Speed 0 Two-Pass - Bosphorus 4Krocksdb: Rand Fillonednn: IP Shapes 3D - u8s8f32 - CPUjohn-the-ripper: MD5rocksdb: Update Randrocksdb: Read Rand Write Randjohn-the-ripper: HMAC-SHA512rocksdb: Read While Writingrocksdb: Rand Readopenssl: RSA4096openssl: RSA4096tensorflow: CPU - 64 - GoogLeNetdav1d: Summer Nature 4Kvpxenc: Speed 5 - Bosphorus 1080paom-av1: Speed 6 Two-Pass - Bosphorus 1080pvvenc: Bosphorus 1080p - Fasteronednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUaom-av1: Speed 8 Realtime - Bosphorus 4Kaom-av1: Speed 6 Realtime - Bosphorus 4Ktensorflow: CPU - 32 - GoogLeNetaom-av1: Speed 10 Realtime - Bosphorus 4Kaom-av1: Speed 9 Realtime - Bosphorus 4Kdav1d: Summer Nature 1080pspecfem3d: Water-layered Halfspacetensorflow: CPU - 64 - AlexNetspecfem3d: Layered Halfspacestress-ng: Atomicblender: Fishy Cat - CPU-Onlystress-ng: Futexstress-ng: Pthreadstress-ng: Zlibstress-ng: Socket Activitystress-ng: Memory Copyingjohn-the-ripper: WPA PSKstress-ng: IO_uringjohn-the-ripper: bcryptjohn-the-ripper: Blowfishstress-ng: CPU Cachestress-ng: Mallocstress-ng: System V Message Passingstress-ng: MEMFDstress-ng: NUMAstress-ng: Pollstress-ng: Glibc C String Functionsstress-ng: Semaphoresstress-ng: Vector Mathstress-ng: Matrix Mathstress-ng: CPU Stressstress-ng: Hashstress-ng: SENDFILEstress-ng: Function Callstress-ng: Mutexstress-ng: Forkingstress-ng: Cryptostress-ng: MMAPstress-ng: x86_64 RdRandstress-ng: Glibc Qsort Data Sortingstress-ng: Context Switchingtensorflow: CPU - 16 - GoogLeNetgromacs: MPI CPU - water_GMX50_bareaom-av1: Speed 0 Two-Pass - Bosphorus 1080pdaphne: OpenMP - Euclidean Clusterdaphne: OpenMP - NDT Mappingblender: BMW27 - CPU-Onlysvt-av1: Preset 8 - Bosphorus 4Ktensorflow: CPU - 32 - AlexNetonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUaom-av1: Speed 6 Realtime - Bosphorus 1080pspecfem3d: Homogeneous Halfspaceaom-av1: Speed 8 Realtime - Bosphorus 1080paom-av1: Speed 10 Realtime - Bosphorus 1080pembree: Pathtracer - Asian Dragon Objaom-av1: Speed 9 Realtime - Bosphorus 1080pembree: Pathtracer ISPC - Asian Dragon Objspecfem3d: Tomographic Modelonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUbuild-ffmpeg: Time To Compilespecfem3d: Mount St. Helenstensorflow: CPU - 16 - AlexNetonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUembree: Pathtracer - Crownsvt-av1: Preset 12 - Bosphorus 4Ksvt-av1: Preset 13 - Bosphorus 4Kembree: Pathtracer - Asian Dragondraco: Church Facadeembree: Pathtracer ISPC - Crowndraco: Lionembree: Pathtracer ISPC - Asian Dragonnginx: 100abc10606111011011111571.38705.678466.729671086708.53050810516.90448.2069175516.88448.63363874160.218.62292.8016574329.91254.898947776356989270872286.217244.236.21209.22028551635.63212.621669857257.442.88203.67538.93.26133.78149.480929923180.771293957452870709965487310799202790060425091630970576117668502261758354035.4599711.380453.911455.5955.01148.771214.31211735.02930.871.465715.22.56877518.731194941153855.718.1618.0114693.00410.810792.4315.45281183.295320.9623.115698.118310.191475.441213.254962.010916.125730.598832.679427.624736.196187.99211.3641106.6629.3749944.863122.288937.673926.5412222945.56245504.321.59956624.46337442.61.42719699.96334680.575.25466190.2634.54812219.83216.182861.78915.09499196.246884258.8223.339474.39917.27.887.99876.922.3752.039962.30887408.72133.0537.96130.691970590.49134.662137824.961774418.861161.62951190.22581128.42013.11128.862463.071095.6161.4907.714.6734400.3310415930.271432103840009777292042615199300080599872730390941189343.736965132.4366.1711.4215.9713.3533.904270.37323715.3916.15100.5715.8216.0496.831.466335812236.0829.635032517139.832.22957096.287858.716374.2294302.8910941.3748332826355.621147771144991441584.05190168476.5210295375.81766.9437.269551392.9860467587.411840389.35306730.85335705.12152655.2912949136.281143575.46429335.8336280764.7665824.56105894.933124.36658591.721550.533511158.3573.819.2680.73842.32817.5224.237.744178.523.6705628.7818.0276431729.3930.0476.165931.789.180115.2987941680.20123517.80813.743206283138.071.419551.171922.101200.87533871.2659116.88597.16184.3522676587.99675502103.13610614711011011211571.21656.795471.804597049737.56348926516.87448.9916.90448.2660.098.66291.5695067059.97253.32293481356993286.237243.7135.16215.4435.64212.54258.172.9202.82638.633.22134.57146.069290258181.169294463651570712463205990802646430240425550559910548109753202264117527039.8033752.425437.395447.3634.93148.85213.491331004.99830.81.65885.0410.0555513.221039861078275.668.45.3758794.96910.889791.76375.34648186.943341.1932.9308698.605410.141176.751813.028561.293716.314530.598432.679629.68933.678784.050611.8969105.5329.4753945.560221.947831.200232.0474226231.19244509.871.64503607.23537076.951.41212707.30638092.885.33429187.4234.62093216.36416.997658.82715.075197.018831218.7922.999912.90928.77.258.01477.292.3361.808952.21121407.51130.0938.82130.121946110.38133.011736416.842133650.031163.4278.41172.3313.71132.321851140.460362.711075.5180.692414.3747710.341043560.668506102950009786195934015298100075311972681950001186897.436899.1132.2665.2111.5315.5813.13.934360.3795415.3615.53101.7916.4316.5696.0730.372995715228.1629.523601764163.2632.291018129.2487532.45549.2179477.3410922.2448232326364.631148251073881691720.8191206280.210283641.13583.83432.49566416.7559352709.9112234144.91306299.59341137.35152455.9313204487.511162795.27413303.5336505304.666467.95108459.263115.23658461.441546.693508321.2972.819.1990.73796.63771.2624.3638.178174.814.1646727.9318.18230517629.8130.2176.663931.189.286414.7141325020.2183317.86513.461312471145.791.405631.161012.163460.92547871.8254119.69197.1984.2763670288.5715479104.479310622711011111111471.7416.79451.2616.84449.8660.718.71289.929.81257.31288.948244.8935.33214.3836.21209.19258.132.88207.6138.713.19134.24147.51180.05929400115118071040716718080624182368042519543753057348072400222288996904.95146.51213.695.012315.02514.45.737.9992.47510.707693.32055.4061184.883340.9942.9325799.405510.059474.464813.428662.651915.960731.312231.934726.984437.053885.508811.6941106.3539.4022225697.84246434.821.59992624.351.41518705.7958.8623.238791.23920.96.958.11977.152.327410.27130.8838.58130.271527158.77134.12222180.61820534.681129.3285.61189.7267.41126.32209.8831.7638.263.141072.1169.990714.4745730.341040862766000977229548521929200081927932731972001188772.436977.5131.9865.711.3116.0712.97715.5116.33101.1816.3316.6395.8630.958272243227.6429.647600618349.8932.071056011.6490272.056511.9850201.5710908.225582926405.0164015515171657780.82190376822.5873426960.15583.2433.529500903.3558278938.7812232435.5306225.09341249.75157803.1913066446.381165355.2431183.8336276764.0465696.65107612.443092.95658542.681547.23511599.9472.79.2590.73848.69892.1324.4237.328175.3128.6118.28706106529.5630.9876.408330.0188.887914.95881809817.83713.567236154145.4571.888120.06497.57484.5925676787.855521104.2777OpenBenchmarking.org

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 8.0Test: Sequential Fillabc20K40K60K80K100K1060611061471062271. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

MariaDB

This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.0.1Clients: 512abc204060801001101101101. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.0.1Clients: 1024abc204060801001101101111. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.0.1Clients: 2048abc3060901201501111121111. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.0.1Clients: 4096abc3060901201501151151141. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

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 2.12Device: CPU - Batch Size: 512 - Model: ResNet-50abc163248648071.3871.2171.74

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 3.1Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUab150300450600750SE +/- 9.93, N = 15705.68656.80MIN: 626MIN: 632.151. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUab100200300400500SE +/- 6.11, N = 15466.73471.80MIN: 406.85MIN: 461.641. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Graph APIab140K280K420K560K700K6710865970491. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

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 3.1Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUab160320480640800SE +/- 13.20, N = 13708.53737.56MIN: 616.19MIN: 712.911. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Stitchingab110K220K330K440K550K5081054892651. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Video On Demandabc4812162016.9016.8716.791. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Video On Demandabc100200300400500448.21448.99451.261. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Platformabc4812162016.8816.9016.841. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Platformabc100200300400500448.63448.26449.861. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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 2.12Device: CPU - Batch Size: 256 - Model: ResNet-50abc142842567060.2160.0960.71

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Uploadabc2468108.628.668.711. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Uploadabc60120180240300292.80291.57289.921. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Uploadabc36912159.919.979.811. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Uploadabc60120180240300254.90253.32257.311. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Image Processingab80K160K240K320K400K3569892934811. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Features 2Dab80K160K240K320K400K2708723569931. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

Timed LLVM Compilation

This test times how long it takes to compile/build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix Makefilesabc60120180240300286.22286.24288.95

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 3.5Blend File: Barbershop - Compute: CPU-Onlyabc50100150200250244.20243.71244.89

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Video On Demandabc81624324036.2135.1635.331. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Video On Demandabc50100150200250209.22215.44214.381. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Platformabc81624324035.6335.6436.211. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Platformabc50100150200250212.62212.54209.191. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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 2.12Device: CPU - Batch Size: 512 - Model: GoogLeNetabc60120180240300257.44258.17258.13

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.13Speed: Speed 0 - Input: Bosphorus 4Kabc0.65251.3051.95752.613.26252.882.902.881. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 19.8.1Time To Compileabc50100150200250203.68202.83207.61

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 2.12Device: CPU - Batch Size: 64 - Model: ResNet-50abc91827364538.9038.6338.71

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 4K - Video Preset: Fastabc0.73371.46742.20112.93483.66853.2613.2213.1911. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Liveabc81624324033.7834.5734.241. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Liveabc306090120150149.48146.07147.511. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Timed LLVM Compilation

This test times how long it takes to compile/build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Ninjaabc4080120160200180.77181.17180.06

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20-Poly1305abc60000M120000M180000M240000M300000M2939574528702944636515702940011511801. (CC) gcc options: -pthread -m64 -O3 -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-256-GCMabc150000M300000M450000M600000M750000M7099654873107124632059907104071671801. (CC) gcc options: -pthread -m64 -O3 -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-128-GCMabc200000M400000M600000M800000M1000000M7992027900608026464302408062418236801. (CC) gcc options: -pthread -m64 -O3 -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20abc90000M180000M270000M360000M450000M4250916309704255505599104251954375301. (CC) gcc options: -pthread -m64 -O3 -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA256abc12000M24000M36000M48000M60000M5761176685054810975320573480724001. (CC) gcc options: -pthread -m64 -O3 -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA512abc5000M10000M15000M20000M25000M2261758354022641175270222288996901. (CC) gcc options: -pthread -m64 -O3 -ldl

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 3.1Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUab918273645SE +/- 1.54, N = 1535.4639.80MIN: 13.46MIN: 26.161. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUab160320480640800SE +/- 2.91, N = 3711.38752.43MIN: 680.93MIN: 723.131. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUab100200300400500SE +/- 2.89, N = 3453.91437.40MIN: 437.57MIN: 425.411. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUab100200300400500SE +/- 6.28, N = 3455.60447.36MIN: 430.98MIN: 435.411. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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.orgFrames Per Second, More Is BetterAOM AV1 3.6Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4Kabc1.12732.25463.38194.50925.63655.014.934.951. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Timed Godot Game Engine Compilation

This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To Compileabc306090120150148.77148.85146.51

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 2.12Device: CPU - Batch Size: 256 - Model: GoogLeNetabc50100150200250214.30213.49213.69

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Videoab30K60K90K120K150K1211731331001. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 4K - Video Preset: Fasterabc1.13152.2633.39454.5265.65755.0294.9985.0121. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

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 2.12Device: CPU - Batch Size: 32 - Model: ResNet-50abc71421283530.8730.8031.00

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 3.1Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUab0.37320.74641.11961.49281.866SE +/- 0.05971, N = 151.465711.65880MIN: 1.06MIN: 1.31. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.13Speed: Speed 5 - Input: Bosphorus 4Kabc1.172.343.514.685.855.205.045.021. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

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 3.1Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUab3691215SE +/- 0.35622, N = 152.5687710.05550MIN: 1.1MIN: 3.31. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -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 2.12Device: CPU - Batch Size: 512 - Model: AlexNetabc110220330440550518.73513.22514.40

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Object Detectionab30K60K90K120K150K1194941039861. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: DNN - Deep Neural Networkab20K40K60K80K100K1153851078271. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.13Speed: Speed 0 - Input: Bosphorus 1080pabc1.28932.57863.86795.15726.44655.715.665.731. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

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.orgFrames Per Second, More Is BetterAOM AV1 3.6Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4Kabc2468108.168.407.991. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

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 3.1Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUab48121620SE +/- 10.58609, N = 1218.011465.37587MIN: 3.07MIN: 3.861. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Build2

This test profile measures the time to bootstrap/install the build2 C++ build toolchain from source. Build2 is a cross-platform build toolchain for C/C++ code and features Cargo-like features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.15Time To Compileabc2040608010093.0094.9792.48

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: Parallelabc369121510.8110.8910.711. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: Parallelabc2040608010092.4391.7693.321. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: Standardabc1.22692.45383.68074.90766.13455.452815.346485.406101. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: Standardabc4080120160200183.30186.94184.881. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: Parallelabc70140210280350320.96341.19340.991. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: Parallelabc0.7011.4022.1032.8043.5053.115602.930862.932571. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: yolov4 - Device: CPU - Executor: Parallelabc2040608010098.1298.6199.411. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: yolov4 - Device: CPU - Executor: Parallelabc369121510.1910.1410.061. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: bertsquad-12 - Device: CPU - Executor: Parallelabc2040608010075.4476.7574.461. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: bertsquad-12 - Device: CPU - Executor: Parallelabc369121513.2513.0313.431. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: bertsquad-12 - Device: CPU - Executor: Standardabc142842567062.0161.2962.651. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: bertsquad-12 - Device: CPU - Executor: Standardabc4812162016.1316.3115.961. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallelabc71421283530.6030.6031.311. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallelabc81624324032.6832.6831.931. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: ArcFace ResNet-100 - Device: CPU - Executor: Standardabc71421283527.6229.6926.981. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: ArcFace ResNet-100 - Device: CPU - Executor: Standardabc91827364536.2033.6837.051. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: yolov4 - Device: CPU - Executor: Standardabc2040608010087.9984.0585.511. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: yolov4 - Device: CPU - Executor: Standardabc369121511.3611.9011.691. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: Standardabc20406080100106.66105.53106.351. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: Standardabc36912159.374999.475399.402201. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallelab102030405044.8645.561. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallelab51015202522.2921.951. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standardab91827364537.6731.201. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standardab71421283526.5432.051. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500abc50K100K150K200K250K222945.56226231.19225697.841. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 200abc50K100K150K200K250K245504.32244509.87246434.821. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallelabc0.37010.74021.11031.48041.85051.599561.645031.599921. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallelabc130260390520650624.46607.24624.351. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 500ab8K16K24K32K40K37442.6037076.951. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: CaffeNet 12-int8 - Device: CPU - Executor: Standardabc0.32110.64220.96331.28441.60551.427191.412121.415181. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: CaffeNet 12-int8 - Device: CPU - Executor: Standardabc150300450600750699.96707.31705.801. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 200ab8K16K24K32K40K34680.5738092.881. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallelab1.20022.40043.60064.80086.0015.254665.334291. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallelab4080120160200190.26187.421. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standardab1.03972.07943.11914.15885.19854.548124.620931. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standardab50100150200250219.83216.361. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: super-resolution-10 - Device: CPU - Executor: Parallelab4812162016.1817.001. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: super-resolution-10 - Device: CPU - Executor: Parallelab142842567061.7958.831. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: super-resolution-10 - Device: CPU - Executor: Standardab1.14642.29283.43924.58565.7325.094995.075001. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: super-resolution-10 - Device: CPU - Executor: Standardab4080120160200196.25197.021. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Coreab20K40K60K80K100K88425831211. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

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.orgFrames Per Second, More Is BetterAOM AV1 3.6Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080pabc2468108.828.798.861. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -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 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50abc61218243023.3322.9923.23

Darmstadt Automotive Parallel Heterogeneous Suite

DAPHNE is the Darmstadt Automotive Parallel HeterogeNEous Benchmark Suite with OpenCL / CUDA / OpenMP test cases for these automotive benchmarks for evaluating programming models in context to vehicle autonomous driving capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous Suite 2021.11.02Backend: OpenMP - Kernel: Points2Imageabc2K4K6K8K10K9474.399912.908791.231. (CXX) g++ options: -O3 -std=c++11 -fopenmp

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression Speedabc2004006008001000917.2928.7920.91. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression Speedabc2468107.887.256.951. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 1080p - Video Preset: Fastabc2468107.9988.0148.1191. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

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 3.5Blend File: Pabellon Barcelona - Compute: CPU-Onlyabc2040608010076.9277.2977.15

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 4 - Input: Bosphorus 4Kabc0.53441.06881.60322.13762.6722.3752.3362.3271. (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 3.1Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUab0.4590.9181.3771.8362.295SE +/- 0.20405, N = 152.039961.80895MIN: 1.44MIN: 1.631. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUab0.51951.0391.55852.0782.5975SE +/- 0.04986, N = 152.308872.21121MIN: 1.77MIN: 1.771. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -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 2.12Device: CPU - Batch Size: 256 - Model: AlexNetabc90180270360450408.72407.51410.27

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Liveabc306090120150133.05130.09130.881. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Liveabc91827364537.9638.8238.581. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.1Video Input: Chimera 1080p 10-bitabc306090120150130.69130.12130.271. (CC) gcc options: -pthread

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100abc400K800K1200K1600K2000K1970590.491946110.381527158.771. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.1Video Input: Chimera 1080pabc306090120150134.66133.01134.101. (CC) gcc options: -pthread

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10abc500K1000K1500K2000K2500K2137824.961736416.842222180.601. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:5abc500K1000K1500K2000K2500K1774418.862133650.031820534.681. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Decompression Speedabc300600900120015001161.61163.41129.31. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Compression Speedabc60120180240300295.0278.4285.61. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 3, Long Mode - Decompression Speedabc300600900120015001190.21172.31189.71. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 3, Long Mode - Compression Speedabc70140210280350258.0313.7267.41. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 3 - Decompression Speedabc20040060080010001128.41132.31126.31. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 3 - Compression Speedabc50010001500200025002013.12185.02209.81. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Decompression Speedabc20040060080010001128.81140.4831.71. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Compression Speedabc140280420560700624.0603.0638.21. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

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 3.5Blend File: Classroom - Compute: CPU-Onlyabc142842567063.0762.7163.14

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Decompression Speedabc20040060080010001095.61075.51072.11. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Compression Speedabc4080120160200161.4180.6169.91. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression Speedabc2004006008001000907.7924.0907.01. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression Speedabc4812162014.614.314.41. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

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 8.0Test: Random Fill Syncabc16K32K48K64K80K7344074771745731. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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.orgFrames Per Second, More Is BetterAOM AV1 3.6Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4Kabc0.07650.1530.22950.3060.38250.330.340.341. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

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 8.0Test: Random Fillabc20K40K60K80K100K1041591043561040861. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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 3.1Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUab714212835SE +/- 8.531398, N = 1230.2714320.668506MIN: 0.451. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: MD5abc2M4M6M8M10M103840001029500027660001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

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 8.0Test: Update Randomabc20K40K60K80K100K9777297861977221. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Read Random Write Randomabc200K400K600K800K1000K9204269593409548521. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: HMAC-SHA512abc30M60M90M120M150M151993000152981000192920001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

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 8.0Test: Read While Writingabc2M4M6M8M10M8059987753119781927931. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Random Readabc60M120M180M240M300M2730390942681950002731972001. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096abc300K600K900K1200K1500K1189343.71186897.41188772.41. (CC) gcc options: -pthread -m64 -O3 -ldl

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096abc8K16K24K32K40K36965.036899.136977.51. (CC) gcc options: -pthread -m64 -O3 -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 2.12Device: CPU - Batch Size: 64 - Model: GoogLeNetabc306090120150132.43132.26131.98

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.1Video Input: Summer Nature 4Kabc153045607566.1765.2165.701. (CC) gcc options: -pthread

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.13Speed: Speed 5 - Input: Bosphorus 1080pabc369121511.4211.5311.311. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

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.orgFrames Per Second, More Is BetterAOM AV1 3.6Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080pabc4812162015.9715.5816.071. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 1080p - Video Preset: Fasterabc369121513.3513.1012.981. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

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 3.1Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUab0.88521.77042.65563.54084.426SE +/- 0.00278, N = 33.904273.93436MIN: 3.68MIN: 3.681. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUab0.08540.17080.25620.34160.427SE +/- 0.003364, N = 30.3732370.379540MIN: 0.33MIN: 0.331. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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.orgFrames Per Second, More Is BetterAOM AV1 3.6Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4Kabc4812162015.3915.3615.511. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.6Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4Kabc4812162016.1515.5316.331. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -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 2.12Device: CPU - Batch Size: 32 - Model: GoogLeNetabc20406080100100.57101.79101.18

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.orgFrames Per Second, More Is BetterAOM AV1 3.6Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4Kabc4812162015.8216.4316.331. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.6Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4Kabc4812162016.0416.5616.631. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.1Video Input: Summer Nature 1080pabc2040608010096.8096.0795.861. (CC) gcc options: -pthread

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Water-layered Halfspaceabc71421283531.4730.3730.961. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

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 2.12Device: CPU - Batch Size: 64 - Model: AlexNetabc50100150200250236.08228.16227.64

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Layered Halfspaceabc71421283529.6429.5229.651. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Atomicabc80160240320400139.80163.26349.891. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

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 3.5Blend File: Fishy Cat - Compute: CPU-Onlyabc71421283532.2232.2932.07

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Futexabc200K400K600K800K1000K957096.201018129.241056011.641. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Pthreadabc20K40K60K80K100K87858.7187532.4090272.051. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Zlibabc140028004200560070006374.225549.216511.981. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Socket Activityabc20K40K60K80K100K94302.8979477.3450201.571. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Memory Copyingabc2K4K6K8K10K10941.3710922.2410908.201. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKabc100K200K300K400K500K4833284823232558291. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: IO_uringabc6K12K18K24K30K26355.6226364.6326405.011. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptabc20K40K60K80K100K114777114825640151. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: Blowfishabc20K40K60K80K100K114499107388515171. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: CPU Cacheabc400K800K1200K1600K2000K1441584.051691720.801657780.821. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Mallocabc40M80M120M160M200M190168476.52191206280.20190376822.581. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: System V Message Passingabc16M32M48M64M80M10295375.8110283641.1373426960.151. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: MEMFDabc170340510680850766.90583.83583.201. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: NUMAabc90180270360450437.26432.40433.521. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Pollabc2M4M6M8M10M9551392.989566416.759500903.351. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Glibc C String Functionsabc13M26M39M52M65M60467587.4059352709.9158278938.781. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Semaphoresabc3M6M9M12M15M11840389.3512234144.9112232435.501. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Vector Mathabc70K140K210K280K350K306730.85306299.59306225.091. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Matrix Mathabc70K140K210K280K350K335705.12341137.35341249.751. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: CPU Stressabc30K60K90K120K150K152655.29152455.93157803.191. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Hashabc3M6M9M12M15M12949136.2813204487.5113066446.381. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: SENDFILEabc200K400K600K800K1000K1143575.461162795.271165355.201. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Function Callabc90K180K270K360K450K429335.83413303.53431183.831. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Mutexabc8M16M24M32M40M36280764.7636505304.6036276764.041. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Forkingabc14K28K42K56K70K65824.5666467.9565696.651. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Cryptoabc20K40K60K80K100K105894.93108459.26107612.441. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: MMAPabc70014002100280035003124.363115.233092.951. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: x86_64 RdRandabc140K280K420K560K700K658591.72658461.44658542.681. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Glibc Qsort Data Sortingabc300600900120015001550.531546.691547.201. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Context Switchingabc800K1600K2400K3200K4000K3511158.353508321.293511599.941. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

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 2.12Device: CPU - Batch Size: 16 - Model: GoogLeNetabc163248648073.8172.8172.70

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2023Implementation: MPI CPU - Input: water_GMX50_bareabc36912159.2689.1999.2591. (CXX) g++ options: -O3

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.orgFrames Per Second, More Is BetterAOM AV1 3.6Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080pabc0.16430.32860.49290.65720.82150.730.730.731. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Darmstadt Automotive Parallel Heterogeneous Suite

DAPHNE is the Darmstadt Automotive Parallel HeterogeNEous Benchmark Suite with OpenCL / CUDA / OpenMP test cases for these automotive benchmarks for evaluating programming models in context to vehicle autonomous driving capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous Suite 2021.11.02Backend: OpenMP - Kernel: Euclidean Clusterabc2004006008001000842.32796.63848.691. (CXX) g++ options: -O3 -std=c++11 -fopenmp

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous Suite 2021.11.02Backend: OpenMP - Kernel: NDT Mappingabc2004006008001000817.52771.26892.131. (CXX) g++ options: -O3 -std=c++11 -fopenmp

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 3.5Blend File: BMW27 - Compute: CPU-Onlyabc61218243024.2024.3624.42

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 8 - Input: Bosphorus 4Kabc91827364537.7438.1837.331. (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 2.12Device: CPU - Batch Size: 32 - Model: AlexNetabc4080120160200178.52174.81175.31

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 3.1Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUab0.93711.87422.81133.74844.6855SE +/- 0.04476, N = 143.670564.16467MIN: 3.52MIN: 3.581. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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.orgFrames Per Second, More Is BetterAOM AV1 3.6Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080pabc71421283528.7827.9328.611. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Homogeneous Halfspaceabc4812162018.0318.1818.291. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

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.orgFrames Per Second, More Is BetterAOM AV1 3.6Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080pabc71421283529.3929.8129.561. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.6Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080pabc71421283530.0430.2130.981. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer - Model: Asian Dragon Objabc2040608010076.1776.6676.41MIN: 73.69 / MAX: 79.67MIN: 74.78 / MAX: 80.24MIN: 74.48 / MAX: 78.97

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.orgFrames Per Second, More Is BetterAOM AV1 3.6Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080pabc71421283531.7031.1030.011. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer ISPC - Model: Asian Dragon Objabc2040608010089.1889.2988.89MIN: 87.45 / MAX: 91.82MIN: 87.48 / MAX: 93.27MIN: 87.09 / MAX: 93.32

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Tomographic Modelabc4812162015.3014.7114.961. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

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 3.1Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUab0.04910.09820.14730.19640.2455SE +/- 0.001478, N = 110.2012350.218330MIN: 0.18MIN: 0.191. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Timed FFmpeg Compilation

This test times how long it takes to build the FFmpeg multimedia library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 6.0Time To Compileabc4812162017.8117.8717.84

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Mount St. Helensabc4812162013.7413.4613.571. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

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 2.12Device: CPU - Batch Size: 16 - Model: AlexNetabc306090120150138.07145.79145.45

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 3.1Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUab0.31940.63880.95821.27761.597SE +/- 0.00845, N = 31.419551.40563MIN: 1.24MIN: 1.161. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUab0.26370.52740.79111.05481.3185SE +/- 0.00262, N = 31.171921.16101MIN: 0.97MIN: 0.981. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUab0.48680.97361.46041.94722.434SE +/- 0.02056, N = 32.101202.16346MIN: 2.03MIN: 2.031. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUab0.20820.41640.62460.83281.041SE +/- 0.008834, N = 60.8753380.925478MIN: 0.82MIN: 0.821. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer - Model: Crownabc163248648071.2771.8371.89MIN: 67.7 / MAX: 79.85MIN: 68.18 / MAX: 79.7MIN: 67.5 / MAX: 80.61

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 12 - Input: Bosphorus 4Kabc306090120150116.89119.69120.061. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 13 - Input: Bosphorus 4Kabc2040608010097.1697.1997.571. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer - Model: Asian Dragonabc2040608010084.3584.2884.59MIN: 81.19 / MAX: 88.18MIN: 81.06 / MAX: 88.82MIN: 82.73 / MAX: 90.07

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 Facadeabc150030004500600075006765670267671. (CXX) g++ options: -O3

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer ISPC - Model: Crownabc2040608010088.0088.5787.85MIN: 84.5 / MAX: 93.11MIN: 84.55 / MAX: 93.3MIN: 84.35 / MAX: 92.29

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: Lionabc120024003600480060005502547955211. (CXX) g++ options: -O3

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer ISPC - Model: Asian Dragonabc20406080100103.14104.48104.28MIN: 101.66 / MAX: 108.37MIN: 103 / MAX: 108.93MIN: 102.35 / MAX: 108.15

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

Connections: 1000

a: The test quit with a non-zero exit status.

b: The test quit with a non-zero exit status.

c: The test quit with a non-zero exit status.

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

Concurrent Requests: 1000

a: The test quit with a non-zero exit status.

b: The test quit with a non-zero exit status.

Concurrent Requests: 100

a: The test quit with a non-zero exit status.

b: The test quit with a non-zero exit status.

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

Connections: 100

a: The test quit with a non-zero exit status.

b: The test quit with a non-zero exit status.

c: The test quit with a non-zero exit status.

227 Results Shown

RocksDB
MariaDB:
  512
  1024
  2048
  4096
TensorFlow
oneDNN:
  Recurrent Neural Network Training - u8s8f32 - CPU
  Recurrent Neural Network Inference - f32 - CPU
OpenCV
oneDNN
OpenCV
FFmpeg:
  libx265 - Video On Demand:
    FPS
    Seconds
  libx265 - Platform:
    FPS
    Seconds
TensorFlow
FFmpeg:
  libx265 - Upload:
    FPS
    Seconds
  libx264 - Upload:
    FPS
    Seconds
OpenCV:
  Image Processing
  Features 2D
Timed LLVM Compilation
Blender
FFmpeg:
  libx264 - Video On Demand:
    FPS
    Seconds
  libx264 - Platform:
    FPS
    Seconds
TensorFlow
VP9 libvpx Encoding
Timed Node.js Compilation
TensorFlow
VVenC
FFmpeg:
  libx265 - Live:
    FPS
    Seconds
Timed LLVM Compilation
OpenSSL:
  ChaCha20-Poly1305
  AES-256-GCM
  AES-128-GCM
  ChaCha20
  SHA256
  SHA512
oneDNN:
  Deconvolution Batch shapes_1d - f32 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
AOM AV1
Timed Godot Game Engine Compilation
TensorFlow
OpenCV
VVenC
TensorFlow
oneDNN
VP9 libvpx Encoding
oneDNN
TensorFlow
OpenCV:
  Object Detection
  DNN - Deep Neural Network
VP9 libvpx Encoding
AOM AV1
oneDNN
Build2
ONNX Runtime:
  GPT-2 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  GPT-2 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  fcn-resnet101-11 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  yolov4 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  bertsquad-12 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  bertsquad-12 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  ArcFace ResNet-100 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  ArcFace ResNet-100 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  yolov4 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  fcn-resnet101-11 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  Faster R-CNN R-50-FPN-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  Faster R-CNN R-50-FPN-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
nginx:
  500
  200
ONNX Runtime:
  CaffeNet 12-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
Apache HTTP Server
ONNX Runtime:
  CaffeNet 12-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
Apache HTTP Server
ONNX Runtime:
  ResNet50 v1-12-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  ResNet50 v1-12-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  super-resolution-10 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  super-resolution-10 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
OpenCV
AOM AV1
TensorFlow
Darmstadt Automotive Parallel Heterogeneous Suite
Zstd Compression:
  19, Long Mode - Decompression Speed
  19, Long Mode - Compression Speed
VVenC
Blender
SVT-AV1
oneDNN:
  IP Shapes 3D - f32 - CPU
  IP Shapes 3D - bf16bf16bf16 - CPU
TensorFlow
FFmpeg:
  libx264 - Live:
    FPS
    Seconds
dav1d
Memcached
dav1d
Memcached:
  1:10
  1:5
Zstd Compression:
  8, Long Mode - Decompression Speed
  8, Long Mode - Compression Speed
  3, Long Mode - Decompression Speed
  3, Long Mode - Compression Speed
  3 - Decompression Speed
  3 - Compression Speed
  8 - Decompression Speed
  8 - Compression Speed
Blender
Zstd Compression:
  12 - Decompression Speed
  12 - Compression Speed
  19 - Decompression Speed
  19 - Compression Speed
RocksDB
AOM AV1
RocksDB
oneDNN
John The Ripper
RocksDB:
  Update Rand
  Read Rand Write Rand
John The Ripper
RocksDB:
  Read While Writing
  Rand Read
OpenSSL:
  RSA4096:
    verify/s
    sign/s
TensorFlow
dav1d
VP9 libvpx Encoding
AOM AV1
VVenC
oneDNN:
  Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
AOM AV1:
  Speed 8 Realtime - Bosphorus 4K
  Speed 6 Realtime - Bosphorus 4K
TensorFlow
AOM AV1:
  Speed 10 Realtime - Bosphorus 4K
  Speed 9 Realtime - Bosphorus 4K
dav1d
SPECFEM3D
TensorFlow
SPECFEM3D
Stress-NG
Blender
Stress-NG:
  Futex
  Pthread
  Zlib
  Socket Activity
  Memory Copying
John The Ripper
Stress-NG
John The Ripper:
  bcrypt
  Blowfish
Stress-NG:
  CPU Cache
  Malloc
  System V Message Passing
  MEMFD
  NUMA
  Poll
  Glibc C String Functions
  Semaphores
  Vector Math
  Matrix Math
  CPU Stress
  Hash
  SENDFILE
  Function Call
  Mutex
  Forking
  Crypto
  MMAP
  x86_64 RdRand
  Glibc Qsort Data Sorting
  Context Switching
TensorFlow
GROMACS
AOM AV1
Darmstadt Automotive Parallel Heterogeneous Suite:
  OpenMP - Euclidean Cluster
  OpenMP - NDT Mapping
Blender
SVT-AV1
TensorFlow
oneDNN
AOM AV1
SPECFEM3D
AOM AV1:
  Speed 8 Realtime - Bosphorus 1080p
  Speed 10 Realtime - Bosphorus 1080p
Embree
AOM AV1
Embree
SPECFEM3D
oneDNN
Timed FFmpeg Compilation
SPECFEM3D
TensorFlow
oneDNN:
  Convolution Batch Shapes Auto - f32 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
  Convolution Batch Shapes Auto - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_3d - f32 - CPU
Embree
SVT-AV1:
  Preset 12 - Bosphorus 4K
  Preset 13 - Bosphorus 4K
Embree
Google Draco
Embree
Google Draco
Embree