2888

Intel Xeon E E-2488 testing with a Supermicro Super Server X13SCL-F v0123456789 (1.1 BIOS) and llvmpipe on Ubuntu 22.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2403223-NE-28881544411&grs&sor&rro.

2888ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionabcdIntel Xeon E E-2488 @ 3.20GHz (8 Cores / 16 Threads)Supermicro Super Server X13SCL-F v0123456789 (1.1 BIOS)Intel Device 7a272 x 32GB DRAM-4400MT/s Micron MTC20C2085S1EC48BA1960GB Micron_7450_MTFDKBA960TFR + 3201GB Micron_7450_MTFDKCC3T2TFSllvmpipeVE2282 x Intel I210Ubuntu 22.046.2.0-26-generic (x86_64)GNOME Shell 42.9X Server 1.21.1.44.5 Mesa 23.0.4-0ubuntu1~22.04.1 (LLVM 15.0.7 256 bits)1.3.238GCC 11.4.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x11f - Thermald 2.4.9 Python Details- Python 3.10.12Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + 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

2888speedb: Seq Fillonednn: Deconvolution Batch shapes_1d - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUsvt-av1: Preset 8 - Bosphorus 1080psvt-av1: Preset 13 - Bosphorus 4Ksvt-av1: Preset 12 - Bosphorus 4Kquicksilver: CORAL2 P1rocksdb: Read While Writingspeedb: Read While Writingprimesieve: 1e12stockfish: Chess Benchmarkopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection Retail FP16 - CPUrocksdb: Seq Fillopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamspeedb: Rand Readdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamonednn: IP Shapes 1D - CPUsvt-av1: Preset 8 - Bosphorus 4Kquicksilver: CORAL2 P2openvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUsvt-av1: Preset 4 - Bosphorus 4Kdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamnamd: ATPase with 327,506 Atomsrocksdb: Overwriteospray: gravity_spheres_volume/dim_512/scivis/real_timespeedb: Read Rand Write Randdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamquicksilver: CTS2rocksdb: Rand Readdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamsvt-av1: Preset 4 - Bosphorus 1080popenvino: Face Detection FP16-INT8 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamopenvino: Face Detection Retail FP16-INT8 - CPUdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamopenvino: Vehicle Detection FP16-INT8 - CPUdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16 - CPUprimesieve: 1e13deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamrocksdb: Read Rand Write Randopenvino: Vehicle Detection FP16 - CPUbuild-linux-kernel: defconfigopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUospray-studio: 2 - 1080p - 16 - Path Tracer - CPUrocksdb: Rand Fillopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUospray-studio: 3 - 1080p - 16 - Path Tracer - CPUdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamrocksdb: Update Randblender: BMW27 - CPU-Onlyopenvino: Age Gender Recognition Retail 0013 FP16 - CPUospray: gravity_spheres_volume/dim_512/ao/real_timespeedb: Update Randopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamspeedb: Rand Fillopenvino: Handwritten English Recognition FP16 - CPUsvt-av1: Preset 12 - Bosphorus 1080popenvino: Handwritten English Recognition FP16 - CPUblender: Fishy Cat - CPU-Onlyospray-studio: 1 - 1080p - 32 - Path Tracer - CPUospray-studio: 3 - 1080p - 32 - Path Tracer - CPUv-ray: CPUdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamsvt-av1: Preset 13 - Bosphorus 1080pcompress-7zip: Compression Ratingspeedb: Rand Fill Syncbrl-cad: VGR Performance Metricopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamcompress-7zip: Decompression Ratingospray-studio: 2 - 1080p - 32 - Path Tracer - CPUospray: particle_volume/scivis/real_timeospray-studio: 2 - 4K - 16 - Path Tracer - CPUdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamospray-studio: 1 - 1080p - 16 - Path Tracer - CPUblender: Barbershop - CPU-Onlyonednn: Convolution Batch Shapes Auto - CPUdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Face Detection FP16 - CPUospray: particle_volume/pathtracer/real_timedeepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Streamdeepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Streamopenvino: Person Vehicle Bike Detection FP16 - CPUonednn: Recurrent Neural Network Training - CPUospray-studio: 1 - 4K - 16 - Path Tracer - CPUrocksdb: Rand Fill Syncospray-studio: 2 - 4K - 32 - Path Tracer - CPUospray-studio: 3 - 4K - 16 - Path Tracer - CPUnamd: STMV with 1,066,628 Atomsblender: Pabellon Barcelona - CPU-Onlyospray-studio: 3 - 4K - 32 - Path Tracer - CPUblender: Classroom - CPU-Onlyonednn: Deconvolution Batch shapes_3d - CPUospray: particle_volume/ao/real_timeospray-studio: 2 - 1080p - 1 - Path Tracer - CPUospray: gravity_spheres_volume/dim_512/pathtracer/real_timegromacs: MPI CPU - water_GMX50_bareospray-studio: 3 - 4K - 1 - Path Tracer - CPUbuild-linux-kernel: allmodconfigopenvino: Face Detection FP16 - CPUonednn: Recurrent Neural Network Inference - CPUdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Streamdeepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Streamospray-studio: 1 - 1080p - 1 - Path Tracer - CPUospray-studio: 3 - 1080p - 1 - Path Tracer - CPUospray-studio: 1 - 4K - 1 - Path Tracer - CPUonednn: IP Shapes 3D - CPUospray-studio: 2 - 4K - 1 - Path Tracer - CPUospray-studio: 1 - 4K - 32 - Path Tracer - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUabcd10572037.1879693.3942.81134.857116.362115.906133200002258480298686820.26817776692815.199.82001345137.4729.0925.60260086996156.14132.8958635.4531900000036.78217.38137.7829.034.3149.1491437.18930.6738314857242.6545824497824.8981111.25735.9425814.331211.7159341.044712930000567246639.7178102.802116.2370.26441.4718.1110.783.8485259.54474.881.452615.929.261107.9743502.1116.47245.051686.15782236460242.6793.0261036.921638.829.367.71412351449625180.5444.3272.34481039.2711107.8569940801123.288604.262.789747418790.93523.9315.29.0749440.763988318051.92531.292154.02165.69798249363220309110.52736.179672.404355.2365644.3269664223280318766821993.1133.55119.253.621818.644167998808305.9654615783593.927210.6449406861295.396.4243968.672614.557850.269479.5563356.627911.215410.392.67163.1015.0827779.3582384.462817.811558442062553159951846020.20897414.08367733336.894.540996.00524543.870771.405113511310.0771500.071487.6499.554410.038699.591610.03538.0241124.60762412285895697.8453397303105330.368631846.4439597.9840.8135.94103.489115.017124300002252397299204121.05616895156816.669.792076954134.4629.7426.448960307089151.14662.8099834.8571870000037.43213.64138.3628.914.2968.9375447.53750.6738214681492.6816323964994.8763109.508336.5155817.871611.9063335.621412920000573667339.7363102.612315.971372.98440.9418.1310.713.8279260.94554.891.449915.929.1867108.8472502.1516.73246.008687.0622219780238.9893.2281052.531635.429.427.6413821468080181.2844.11271.84480819.1535109.2419928889124.068497.742.809957366980.94528.0315.088.9956444.647888337552.19531.969153.23166.18799769430920474110.128736.309972.255955.3492642.6669732323117718873621852.4333.51119.3453.916118.543167818805445.9573215865993.668710.6742408491300.836.4253868.9714.495250.353279.4246357.545211.186710.412.67163.0015.0978777.0222383.872811.371562712059483149651840460.20952413.33367376335.934.537635.9898824483.873071.406113281310.8631499.891485.1899.548710.039899.53410.04058.035124.43982415286095787.839297203105940.3610455946.0305291.0743.9136.516116.115106.976134100002374402316549720.53917408986809.399.872042355137.0729.1726.223759761930152.44162.900235.3231846000036.47219.22134.929.644.3179.0093443.96910.6733414520562.7099424059774.9502109.034236.6748805.785711.9504334.36112900000574920809.7584102.38316.227377.2437.8718.2610.593.8345260.45414.921.473616.019.2712107.8541499.3116.68242.435676.40092202547239.6692.6221039.071626.27297.69415601466579180.4844.3275.68478059.1718109.0246929396123.138581.042.807827432850.93524.0615.29.0183443.529987558351.81534.965154.34164.96796299356620359109.651536.468372.820754.9206643.9459715923166418897121956.6833.72118.653.589318.655667661805175.9335515796393.732110.667407591294.936.4355368.846314.52150.149679.7457356.29111.22610.372.66162.4935.1016776.5215385.242808.21563662066353150161844230.20891414.52367235336.354.545415.989224483.864521.408113281308.2791502.741487.0599.512310.043299.580510.03688.0302124.51362413285795687.8437797223104580.3610647696.6746986.3346.3120.657109.271116.365134000002392670303655619.96217015035778.9510.262008846139.0728.7626.005158376227153.72162.8125635.9271873000037.26214.62138.128.964.49.064441.29350.6584414554232.7149124210964.8511110.855236.0728822.15711.7806339.194112680000563850819.5744104.34715.927376.51433.4818.4410.623.7815264.12194.841.45816.189.3361107.106494.2616.67242.189683.35082202307239.7891.8371047.181649.8529.197.63409691447290183.0643.68273.91474749.2635107.946939218122.498570.682.823087348140.93522.8115.238.9861445.116888077751.74530.366154.54166.34793249354320326110.532936.177972.276255.334639.3969704423239218843021874.6833.55119.2253.767518.593867622803955.9627115832094.155110.6192406411294.636.4069168.890414.511650.312979.4885356.152311.230410.42.66163.0885.0893778.3346384.292814.221562652063503156011840060.20937413.9366681336.14.533155.9990324483.866171.405113271308.9761501.441487.1999.657910.028799.677310.02638.0335124.46412414285895787.8473497273104090.36OpenBenchmarking.org

Speedb

Test: Sequential Fill

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Sequential Fillbcad200K400K600K800K1000K8631841045594105720310647691. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

oneDNN

Harness: Deconvolution Batch shapes_1d - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_1d - Engine: CPUadbc2468107.187966.674696.443956.03052MIN: 3.96MIN: 4.01MIN: 3.88MIN: 3.861. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

Model: Road Segmentation ADAS FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUdcab2040608010086.3391.0793.3997.981. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Road Segmentation ADAS FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUdcab102030405046.3043.9042.8140.80MIN: 19.55 / MAX: 53.06MIN: 31.33 / MAX: 53.09MIN: 32.46 / MAX: 50.96MIN: 16.82 / MAX: 52.811. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 1080pdabc306090120150120.66134.86135.94136.521. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4Kbdca306090120150103.49109.27116.12116.361. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4Kcbad306090120150106.98115.02115.91116.371. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Quicksilver

Input: CORAL2 P1

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P1badc3M6M9M12M15M124300001332000013400000134100001. (CXX) g++ options: -fopenmp -O3 -march=native

RocksDB

Test: Read While Writing

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While Writingbacd500K1000K1500K2000K2500K22523972258480237440223926701. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Speedb

Test: Read While Writing

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read While Writingabdc700K1400K2100K2800K3500K29868682992041303655631654971. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Primesieve

Length: 1e12

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e12bcad51015202521.0620.5420.2719.961. (CXX) g++ options: -O3

Stockfish

Chess Benchmark

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 16.1Chess Benchmarkbdca4M8M12M16M20M168951561701503517408986177766921. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver

OpenVINO

Model: Face Detection Retail FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUdcab2004006008001000778.95809.39815.19816.661. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection Retail FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUdcab369121510.269.879.809.79MIN: 5.16 / MAX: 34.39MIN: 6.06 / MAX: 39.79MIN: 6.12 / MAX: 36.26MIN: 6.41 / MAX: 38.951. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

RocksDB

Test: Sequential Fill

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Sequential Filladcb400K800K1200K1600K2000K20013452008846204235520769541. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUdacb306090120150139.07137.47137.07134.46MIN: 116.24 / MAX: 219.99MIN: 115.85 / MAX: 217.31MIN: 114.71 / MAX: 226.89MIN: 113.8 / MAX: 201.171. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUdacb71421283528.7629.0929.1729.741. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streambcda61218243026.4526.2226.0125.60

Speedb

Test: Random Read

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random Readdcab13M26M39M52M65M583762275976193060086996603070891. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streambcda306090120150151.15152.44153.72156.14

oneDNN

Harness: IP Shapes 1D - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 1D - Engine: CPUcadb0.65251.3051.95752.613.26252.900202.895862.812562.80998MIN: 2.68MIN: 2.67MIN: 2.66MIN: 2.261. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4Kbcad81624324034.8635.3235.4535.931. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Quicksilver

Input: CORAL2 P2

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P2cbda4M8M12M16M20M184600001870000018730000190000001. (CXX) g++ options: -fopenmp -O3 -march=native

OpenVINO

Model: Road Segmentation ADAS FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUbdac91827364537.4337.2636.7836.47MIN: 26.59 / MAX: 83.53MIN: 26.4 / MAX: 95MIN: 27.1 / MAX: 93.52MIN: 26.59 / MAX: 94.271. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Road Segmentation ADAS FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUbdac50100150200250213.64214.62217.38219.221. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUbdac306090120150138.36138.10137.78134.90MIN: 112.35 / MAX: 208.82MIN: 115.79 / MAX: 222.16MIN: 113.8 / MAX: 223.99MIN: 115.43 / MAX: 187.531. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUbdac71421283528.9128.9629.0329.641. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4Kbacd0.991.982.973.964.954.2964.3144.3174.4001. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streambcda36912158.93759.00939.06409.1491

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streambcda100200300400500447.54443.97441.29437.19

NAMD

Input: ATPase with 327,506 Atoms

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0b6Input: ATPase with 327,506 Atomsdcba0.15160.30320.45480.60640.7580.658440.673340.673820.67383

RocksDB

Test: Overwrite

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Overwritecdba300K600K900K1200K1500K14520561455423146814914857241. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OSPRay

Benchmark: gravity_spheres_volume/dim_512/scivis/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeabcd0.61091.22181.83272.44363.05452.654582.681632.709942.71491

Speedb

Test: Read Random Write Random

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read Random Write Randombcda500K1000K1500K2000K2500K23964992405977242109624497821. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamcabd1.11382.22763.34144.45525.5694.95024.89814.87634.8511

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamcbda20406080100109.03109.51110.86111.26

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamcbda81624324036.6736.5236.0735.94

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamcabd2004006008001000805.79814.33817.87822.16

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamcbda369121511.9511.9111.7811.72

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamcbda70140210280350334.36335.62339.19341.04

Quicksilver

Input: CTS2

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CTS2dcba3M6M9M12M15M126800001290000012920000129300001. (CXX) g++ options: -fopenmp -O3 -march=native

RocksDB

Test: Random Read

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Readdabc12M24M36M48M60M563850815672466357366733574920801. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamcbad36912159.75849.73639.71789.5744

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamcbad20406080100102.38102.61102.80104.35

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 1080pdbac4812162015.9315.9716.2016.231. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUcdba80160240320400377.20376.51372.98370.26MIN: 285.21 / MAX: 479.42MIN: 284.44 / MAX: 525.09MIN: 281.79 / MAX: 526.67MIN: 283.49 / MAX: 524.371. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Re-Identification Retail FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUdcba100200300400500433.48437.87440.94441.471. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Re-Identification Retail FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUdcba51015202518.4418.2618.1318.11MIN: 9.76 / MAX: 47.95MIN: 9.63 / MAX: 63.68MIN: 9.61 / MAX: 57.54MIN: 9.91 / MAX: 54.391. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUcdba369121510.5910.6210.7110.781. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamacbd0.86591.73182.59773.46364.32953.84853.83453.82793.7815

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamacbd60120180240300259.54260.45260.95264.12

OpenVINO

Model: Face Detection Retail FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUcbad1.1072.2143.3214.4285.5354.924.894.884.84MIN: 3.55 / MAX: 24.13MIN: 3.47 / MAX: 23.33MIN: 3.58 / MAX: 23.42MIN: 3.29 / MAX: 23.141. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamcdab0.33160.66320.99481.32641.6581.47361.45801.45261.4499

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUdcba4812162016.1816.0115.9215.92MIN: 10.16 / MAX: 60.6MIN: 10.09 / MAX: 56.58MIN: 10.24 / MAX: 55.12MIN: 10.19 / MAX: 56.151. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streambacd36912159.18679.26109.27129.3361

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streambacd20406080100108.85107.97107.85107.11

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUdcab110220330440550494.26499.31502.11502.151. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUbcda4812162016.7316.6816.6716.47MIN: 11.82 / MAX: 45.31MIN: 9.11 / MAX: 50.09MIN: 9 / MAX: 53.32MIN: 7.97 / MAX: 25.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Primesieve

Length: 1e13

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e13bacd50100150200250246.01245.05242.44242.191. (CXX) g++ options: -O3

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamcdab150300450600750676.40683.35686.16687.06

RocksDB

Test: Read Random Write Random

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read Random Write Randomdcba500K1000K1500K2000K2500K22023072202547221978022364601. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUbcda50100150200250238.98239.66239.78242.671. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Timed Linux Kernel Compilation

Build: defconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: defconfigbacd2040608010093.2393.0392.6291.84

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUacdb20040060080010001036.921039.071047.181052.531. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection Retail FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUcbad4008001200160020001626.271635.401638.801649.851. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUbadc71421283529.4229.3629.1929.00MIN: 15.68 / MAX: 85.77MIN: 15.65 / MAX: 83.22MIN: 15.64 / MAX: 77.79MIN: 15.36 / MAX: 75.661. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUacdb2468107.717.697.637.60MIN: 5.4 / MAX: 34.65MIN: 3.6 / MAX: 34.51MIN: 4.81 / MAX: 36.08MIN: 5.28 / MAX: 31.111. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OSPRay Studio

Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUcbad9K18K27K36K45K41560413824123540969

RocksDB

Test: Random Fill

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Filldacb300K600K900K1200K1500K14472901449625146657914680801. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenVINO

Model: Handwritten English Recognition FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUcabd4080120160200180.48180.54181.28183.061. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Handwritten English Recognition FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUcabd102030405044.3044.3044.1143.68MIN: 31.6 / MAX: 110.49MIN: 32.51 / MAX: 109.66MIN: 32.5 / MAX: 99.14MIN: 32.82 / MAX: 111.751. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUbadc60120180240300271.84272.34273.91275.681. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OSPRay Studio

Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUabcd10K20K30K40K50K48103480814780547474

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streambcda36912159.15359.17189.26359.2711

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streambcda20406080100109.24109.02107.95107.86

RocksDB

Test: Update Random

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Update Randombcda200K400K600K800K1000K9288899293969392189408011. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: BMW27 - Compute: CPU-Onlybacd306090120150124.06123.28123.13122.49

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUbdca2K4K6K8K10K8497.748570.688581.048604.261. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OSPRay

Benchmark: gravity_spheres_volume/dim_512/ao/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/ao/real_timeacbd0.63521.27041.90562.54083.1762.789742.807822.809952.82308

Speedb

Test: Update Random

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Update Randomdbac160K320K480K640K800K7348147366987418797432851. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUbdca0.21150.4230.63450.8461.05750.940.930.930.93MIN: 0.48 / MAX: 9.96MIN: 0.56 / MAX: 13.16MIN: 0.47 / MAX: 9.58MIN: 0.48 / MAX: 9.251. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Noise Suppression Poconet-Like FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUdacb110220330440550522.81523.93524.06528.031. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Noise Suppression Poconet-Like FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUdcab4812162015.2315.2015.2015.08MIN: 11.43 / MAX: 46.02MIN: 9.34 / MAX: 56.08MIN: 9.51 / MAX: 54.41MIN: 11.22 / MAX: 48.521. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamdbca36912158.98618.99569.01839.0749

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamdbca100200300400500445.12444.65443.53440.76

Speedb

Test: Random Fill

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random Fillcdab200K400K600K800K1000K8755838807778831808833751. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenVINO

Model: Handwritten English Recognition FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUbacd122436486052.1951.9251.8151.74MIN: 39.05 / MAX: 127.56MIN: 35.62 / MAX: 120.48MIN: 39.16 / MAX: 119.83MIN: 39.4 / MAX: 103.751. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 1080pdabc120240360480600530.37531.29531.97534.971. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenVINO

Model: Handwritten English Recognition FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUbacd306090120150153.23154.02154.34154.541. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Fishy Cat - Compute: CPU-Onlydbac4080120160200166.34166.18165.69164.96

OSPRay Studio

Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUbacd20K40K60K80K100K79976798247962979324

OSPRay Studio

Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUbacd20K40K60K80K100K94309936329356693543

Chaos Group V-RAY

Mode: CPU

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 6.0Mode: CPUadcb4K8K12K16K20K20309203262035920474

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamcbad20406080100109.65110.13110.53110.53

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamcbad81624324036.4736.3136.1836.18

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamcadb163248648072.8272.4072.2872.26

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamcadb122436486054.9255.2455.3355.35

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 1080pdbca140280420560700639.40642.67643.95644.331. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

7-Zip Compression

Test: Compression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression Ratingadcb20K40K60K80K100K966429704497159973231. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Speedb

Test: Random Fill Sync

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random Fill Syncbcda50K100K150K200K250K2311772316642323922328031. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

BRL-CAD

VGR Performance Metric

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.38.2VGR Performance Metricadbc40K80K120K160K200K1876681884301887361889711. (CXX) g++ options: -std=c++17 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lnetpbm -lregex_brl -lz_brl -lassimp -ldl -lm -ltk8.6

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUbdca5K10K15K20K25K21852.4321874.6821956.6821993.111. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUbadc81624324033.5133.5533.5533.721. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUbdac306090120150119.34119.22119.20118.60MIN: 91.54 / MAX: 206.51MIN: 90.11 / MAX: 225.31MIN: 90.34 / MAX: 220.76MIN: 92.28 / MAX: 205.271. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamcadb122436486053.5953.6253.7753.92

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamcadb51015202518.6618.6418.5918.54

7-Zip Compression

Test: Decompression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression Ratingdcba15K30K45K60K75K676226766167818679981. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

OSPRay Studio

Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUabcd20K40K60K80K100K80830805448051780395

OSPRay

Benchmark: particle_volume/scivis/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/scivis/real_timecbda1.34222.68444.02665.36886.7115.933555.957325.962715.96546

OSPRay Studio

Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUbdca30K60K90K120K150K158659158320157963157835

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamdacb2040608010094.1693.9393.7393.67

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamdacb369121510.6210.6410.6710.67

OSPRay Studio

Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUbcad9K18K27K36K45K40849407594068640641

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Barbershop - Compute: CPU-Onlybacd300600900120015001300.831295.391294.931294.63

oneDNN

Harness: Convolution Batch Shapes Auto - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Convolution Batch Shapes Auto - Engine: CPUcbad2468106.435536.425386.424396.40691MIN: 6.37MIN: 6.36MIN: 6.36MIN: 6.371. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamacdb153045607568.6768.8568.8968.97

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamacdb4812162014.5614.5214.5114.50

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streambdac112233445550.3550.3150.2750.15

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streambdac2040608010079.4279.4979.5679.75

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streambacd80160240320400357.55356.63356.29356.15

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streambacd369121511.1911.2211.2311.23

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUbdac369121510.4110.4010.3910.37MIN: 6.28 / MAX: 28.53MIN: 6.06 / MAX: 37.34MIN: 6.23 / MAX: 30.2MIN: 6.3 / MAX: 33.941. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUcdab0.60081.20161.80242.40323.0042.662.662.672.671. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OSPRay

Benchmark: particle_volume/pathtracer/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/pathtracer/real_timecbda4080120160200162.49163.00163.09163.10

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Streamadbc1.14792.29583.44374.59165.73955.08275.08935.09785.1016

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Streamadbc2004006008001000779.36778.33777.02776.52

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUbdac80160240320400383.87384.29384.46385.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

oneDNN

Harness: Recurrent Neural Network Training - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Training - Engine: CPUadbc60012001800240030002817.812814.222811.372808.20MIN: 2806.13MIN: 2802.8MIN: 2799.48MIN: 2797.011. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OSPRay Studio

Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUcbda30K60K90K120K150K156366156271156265155844

RocksDB

Test: Random Fill Sync

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Fill Syncbadc40K80K120K160K200K2059482062552063502066351. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OSPRay Studio

Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUadcb70K140K210K280K350K315995315601315016314965

OSPRay Studio

Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUacbd40K80K120K160K200K184602184423184046184006

NAMD

Input: STMV with 1,066,628 Atoms

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0b6Input: STMV with 1,066,628 Atomscadb0.04710.09420.14130.18840.23550.208910.208970.209370.20952

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Pabellon Barcelona - Compute: CPU-Onlycadb90180270360450414.52414.08413.90413.33

OSPRay Studio

Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUabcd80K160K240K320K400K367733367376367235366681

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Classroom - Compute: CPU-Onlyacdb70140210280350336.89336.35336.10335.93

oneDNN

Harness: Deconvolution Batch shapes_3d - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_3d - Engine: CPUcabd1.02272.04543.06814.09085.11354.545414.540994.537634.53315MIN: 4.53MIN: 4.52MIN: 4.52MIN: 4.521. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OSPRay

Benchmark: particle_volume/ao/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/ao/real_timecbda2468105.989205.989885.999036.00500

OSPRay Studio

Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUadcb50010001500200025002454244824482448

OSPRay

Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timecdab0.87141.74282.61423.48564.3573.864523.866173.870773.87307

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bareadbc0.31680.63360.95041.26721.5841.4051.4051.4061.4081. (CXX) g++ options: -O3 -lm

OSPRay Studio

Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUacbd2K4K6K8K10K11351113281132811327

Timed Linux Kernel Compilation

Build: allmodconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: allmodconfigbadc300600900120015001310.861310.081308.981308.28

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUcdab300600900120015001502.741501.441500.071499.89MIN: 1180.43 / MAX: 1615.47MIN: 1178.14 / MAX: 1634.11MIN: 1182.11 / MAX: 1680.75MIN: 1179.88 / MAX: 1674.651. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Inference - Engine: CPUadcb300600900120015001487.641487.191487.051485.18MIN: 1477.71MIN: 1477.26MIN: 1477.55MIN: 1474.211. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamcbad2040608010099.5199.5599.5599.66

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamcbad369121510.0410.0410.0410.03

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streambcad2040608010099.5399.5899.5999.68

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streambcad369121510.0410.0410.0410.03

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Streamacdb2468108.02418.03028.03358.0350

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Streamacdb306090120150124.61124.51124.46124.44

OSPRay Studio

Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUbdca50010001500200025002415241424132412

OSPRay Studio

Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUbdac60012001800240030002860285828582857

OSPRay Studio

Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUdbac2K4K6K8K10K9578957895699568

oneDNN

Harness: IP Shapes 3D - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 3D - Engine: CPUdacb2468107.847347.845337.843777.83920MIN: 7.82MIN: 7.81MIN: 7.8MIN: 7.81. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OSPRay Studio

Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUadcb2K4K6K8K10K9730972797229720

OSPRay Studio

Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUbacd70K140K210K280K350K310594310533310458310409

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUdcba0.0810.1620.2430.3240.4050.360.360.360.36MIN: 0.22 / MAX: 3.66MIN: 0.2 / MAX: 8.11MIN: 0.22 / MAX: 3.74MIN: 0.19 / MAX: 26.871. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Phoronix Test Suite v10.8.5