ddf

Tests for a future article. AMD EPYC 8534PN 64-Core testing with a AMD Cinnabar (RCB1009C BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2401089-NE-DDF54911740&rdt&grs.

ddfProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionabAMD EPYC 8534PN 64-Core @ 2.00GHz (64 Cores / 128 Threads)AMD Cinnabar (RCB1009C BIOS)AMD Device 14a4192GB3201GB Micron_7450_MTFDKCB3T2TFSASPEED2 x Broadcom NetXtreme BCM5720 PCIeUbuntu 23.106.5.0-5-generic (x86_64)GNOME ShellX Server 1.21.1.7GCC 13.2.0ext4640x480OpenBenchmarking.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,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-FTCNCZ/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-FTCNCZ/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212 Python Details- Python 3.11.5Security Details- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

ddflczero: BLASwebp2: Quality 75, Compression Effort 7build-gem5: Time To Compilesvt-av1: Preset 13 - Bosphorus 4Kwebp2: Quality 95, Compression Effort 7quantlib: Multi-Threadedlczero: Eigenpytorch: CPU - 16 - ResNet-152speedb: Update Randxmrig: CryptoNight-Heavy - 1Msvt-av1: Preset 4 - Bosphorus 1080pdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamspeedb: Rand Fill Syncsvt-av1: Preset 8 - Bosphorus 1080ppytorch: CPU - 64 - ResNet-152cloverleaf: clover_bmsvt-av1: Preset 12 - Bosphorus 4Ksvt-av1: Preset 4 - Bosphorus 4Kpytorch: CPU - 32 - ResNet-152svt-av1: Preset 12 - Bosphorus 1080ppytorch: CPU - 64 - ResNet-50embree: Pathtracer - Crownspeedb: Read While Writingopenradioss: Bird Strike on Windshieldembree: Pathtracer ISPC - Crownopenradioss: Rubber O-Ring Seal Installationffmpeg: libx265 - Livepytorch: CPU - 1 - Efficientnet_v2_lrav1e: 6deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamsvt-av1: Preset 8 - Bosphorus 4Kpytorch: CPU - 32 - ResNet-50svt-av1: Preset 13 - Bosphorus 1080popenradioss: INIVOL and Fluid Structure Interaction Drop Containerspeedb: Seq Fillembree: Pathtracer - Asian Dragon Objwebp2: Defaultblender: Classroom - CPU-Onlypytorch: CPU - 16 - ResNet-50blender: Fishy Cat - CPU-Onlydeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streambuild-ffmpeg: Time To Compileeasywave: e2Asean Grid + BengkuluSept2007 Source - 240deepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Streamtensorflow: CPU - 16 - ResNet-50pytorch: CPU - 1 - ResNet-50deepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamopenradioss: Chrysler Neon 1Mxmrig: Wownero - 1Mtensorflow: CPU - 16 - AlexNetdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamquicksilver: CTS2webp2: Quality 100, Compression Effort 5y-cruncher: 1Bdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streameasywave: e2Asean Grid + BengkuluSept2007 Source - 1200ffmpeg: libx265 - Uploadspeedb: Rand Fillembree: Pathtracer ISPC - Asian Dragondeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamrav1e: 5pytorch: CPU - 16 - Efficientnet_v2_lpytorch: CPU - 32 - Efficientnet_v2_lquicksilver: CORAL2 P1deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamrav1e: 10deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamopenradioss: Cell Phone Drop Testdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamxmrig: KawPow - 1Mpytorch: CPU - 1 - ResNet-152y-cruncher: 10Bdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamcloverleaf: clover_bm64_shortembree: Pathtracer - Asian Dragontensorflow: CPU - 16 - VGG-16deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamffmpeg: libx265 - Platformxmrig: GhostRider - 1Mblender: BMW27 - CPU-Onlyy-cruncher: 5Bdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamquicksilver: CORAL2 P2blender: Barbershop - CPU-Onlydeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamspeedb: Rand Readdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamxmrig: Monero - 1Mdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamy-cruncher: 500Mdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamxmrig: CryptoNight-Femto UPX2 - 1Mdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamembree: Pathtracer ISPC - Asian Dragon Objdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamopenradioss: Bumper Beamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamffmpeg: libx265 - Video On Demanddeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamtensorflow: CPU - 1 - AlexNeteasywave: e2Asean Grid + BengkuluSept2007 Source - 2400deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamblender: Pabellon Barcelona - CPU-Onlyquantlib: Single-Threadedspeedb: Read Rand Write Randtensorflow: CPU - 16 - GoogLeNettensorflow: CPU - 1 - ResNet-50tensorflow: CPU - 1 - GoogLeNettensorflow: CPU - 1 - VGG-16pytorch: CPU - 64 - Efficientnet_v2_lrav1e: 1webp2: Quality 100, Lossless Compressionab3150.54211.562187.0770.27176928.127214.7035061220666.717.075195.65.1074239469131.914.8913.67190.9496.62814.37511.85336.8767.931315411684143.8569.203176.78114.749.534.8515.3704185.986467.9836.66597.058164.6737185769.08677.4467.0636.1235.5436.811818.1451.94732.969930.321351.0645.19185.30075.3901297.0840330.7299.15698.35741624000011.6310.24545.7574130.92067.630539.64323.2036902383.87713813.63798.37093.5846.006.0621350000145.623212.326.855431.94496.337364.0666673.334320682.116.54112.543222.2492143.531546.96351458.04957.2177.258135.2137.08865.6643486.604321.924347.154436.226.7153.068852.176216170000239.8327.573236.258815.784930386604836.348727.504863.287320714.7800.59165.11145.02120698.465.69171.245671.49396.7843147.247288.1124.3612854.122141.0087323.066247.0398.8186220.070630.46111.038485.998986.142634.42539184155.775.97179.876.030.850.063540.51223.062194.5870.26170381.328214.1836119220071.917.467191.48245.217244535129.18114.6113.93194.496.7514.13503.61836.2967.113815231425142.3868.582776.1115.739.614.8915.4136184.507868.52336.38601.573163.4636917868.59487.4967.5136.3535.3337.022518.0421.95833.144530.161750.845.42186.23515.3631295.7240146.1297.84695.34811631000011.6810.20245.9477131.45767.599439.48423.2936768483.58313800.67728.3993.5965.986.0821280000145.148512.366.877531.84497.621663.9058674.986120732.716.58112.813221.7174143.844246.86261454.989957.0977.10335.1437.1665.7823485.732321.962347.074442.926.7553.146853.308516190000240.1227.540436.301615.7730414312736.31627.529563.343120732.3799.95815.106144.91232068365.74051.246571.44286.7891147.148588.1624.3739853.69440.9888322.918947.0598.8586220.154530.45111.072485.878586.162633.82539687155.785.97179.876.030.850.06OpenBenchmarking.org

LeelaChessZero

Backend: BLAS

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.30Backend: BLASab801602403204003153541. (CXX) g++ options: -flto -pthread

WebP2 Image Encode

Encode Settings: Quality 75, Compression Effort 7

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 75, Compression Effort 7ab0.12150.2430.36450.4860.60750.540.511. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

Timed Gem5 Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 23.0.1Time To Compileab50100150200250211.56223.06

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 4Kab4080120160200187.08194.591. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

WebP2 Image Encode

Encode Settings: Quality 95, Compression Effort 7

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 95, Compression Effort 7ab0.06080.12160.18240.24320.3040.270.261. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

QuantLib

Configuration: Multi-Threaded

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-Threadedab40K80K120K160K200K176928.1170381.31. (CXX) g++ options: -O3 -march=native -fPIE -pie

LeelaChessZero

Backend: Eigen

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.30Backend: Eigenab601201802403002722821. (CXX) g++ options: -flto -pthread

PyTorch

Device: CPU - Batch Size: 16 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-152ab4812162014.7014.18MIN: 14.51 / MAX: 14.85MIN: 14.06 / MAX: 14.27

Speedb

Test: Update Random

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Update Randomab80K160K240K320K400K3506123611921. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Xmrig

Variant: CryptoNight-Heavy - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Heavy - Hash Count: 1Mab4K8K12K16K20K20666.720071.91. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 1080pab4812162017.0817.471. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamab4080120160200195.60191.48

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 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamab1.17382.34763.52144.69525.8695.10745.2170

Speedb

Test: Random Fill Sync

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random Fill Syncab50K100K150K200K250K2394692445351. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 1080pab306090120150131.90129.181. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

PyTorch

Device: CPU - Batch Size: 64 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-152ab4812162014.8914.61MIN: 13.43 / MAX: 14.98MIN: 13.45 / MAX: 14.71

CloverLeaf

Input: clover_bm

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bmab4812162013.6713.931. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 4Kab4080120160200190.95194.491. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 4Kab2468106.6286.7501. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

PyTorch

Device: CPU - Batch Size: 32 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-152ab4812162014.3714.13MIN: 13.3 / MAX: 14.46MIN: 12.97 / MAX: 14.21

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 1080pab110220330440550511.85503.621. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

PyTorch

Device: CPU - Batch Size: 64 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-50ab81624324036.8736.29MIN: 35.7 / MAX: 37.3MIN: 35.06 / MAX: 36.7

Embree

Binary: Pathtracer - Model: Crown

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer - Model: Crownab153045607567.9367.11MIN: 66.43 / MAX: 69.87MIN: 65.7 / MAX: 68.8

Speedb

Test: Read While Writing

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read While Writingab3M6M9M12M15M15411684152314251. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenRadioss

Model: Bird Strike on Windshield

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bird Strike on Windshieldab306090120150143.85142.38

Embree

Binary: Pathtracer ISPC - Model: Crown

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Crownab153045607569.2068.58MIN: 67.75 / MAX: 70.94MIN: 67.24 / MAX: 70.49

OpenRadioss

Model: Rubber O-Ring Seal Installation

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Rubber O-Ring Seal Installationab2040608010076.7876.10

FFmpeg

Encoder: libx265 - Scenario: Live

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Liveab306090120150114.74115.731. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

PyTorch

Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_lab36912159.539.61MIN: 9.35 / MAX: 9.64MIN: 9.52 / MAX: 9.7

rav1e

Speed: 6

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.7Speed: 6ab1.10052.2013.30154.4025.50254.8514.891

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamab1.21812.43623.65434.87246.09055.37045.4136

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamab4080120160200185.99184.51

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 4Kab153045607567.9868.521. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

PyTorch

Device: CPU - Batch Size: 32 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-50ab81624324036.6636.38MIN: 29.64 / MAX: 37.04MIN: 30.16 / MAX: 36.75

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 1080pab130260390520650597.06601.571. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenRadioss

Model: INIVOL and Fluid Structure Interaction Drop Container

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: INIVOL and Fluid Structure Interaction Drop Containerab4080120160200164.67163.46

Speedb

Test: Sequential Fill

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Sequential Fillab80K160K240K320K400K3718573691781. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Embree

Binary: Pathtracer - Model: Asian Dragon Obj

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer - Model: Asian Dragon Objab153045607569.0968.59MIN: 68.49 / MAX: 70.1MIN: 67.96 / MAX: 69.51

WebP2 Image Encode

Encode Settings: Default

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Defaultab2468107.447.491. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Classroom - Compute: CPU-Onlyab153045607567.0667.51

PyTorch

Device: CPU - Batch Size: 16 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-50ab81624324036.1236.35MIN: 35.2 / MAX: 36.51MIN: 35.07 / MAX: 36.8

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Fishy Cat - Compute: CPU-Onlyab81624324035.5435.33

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamab91827364536.8137.02

Timed FFmpeg Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 6.1Time To Compileab4812162018.1518.04

easyWave

Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240ab0.44060.88121.32181.76242.2031.9471.9581. (CXX) g++ options: -O3 -fopenmp

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamab81624324032.9733.14

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamab71421283530.3230.16

TensorFlow

Device: CPU - Batch Size: 16 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50ab122436486051.0650.80

PyTorch

Device: CPU - Batch Size: 1 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50ab102030405045.1945.42MIN: 43.72 / MAX: 45.91MIN: 44.29 / MAX: 45.97

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamab4080120160200185.30186.24

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamab1.21282.42563.63844.85126.0645.39015.3631

OpenRadioss

Model: Chrysler Neon 1M

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Chrysler Neon 1Mab60120180240300297.08295.72

Xmrig

Variant: Wownero - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Wownero - Hash Count: 1Mab9K18K27K36K45K40330.740146.11. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

TensorFlow

Device: CPU - Batch Size: 16 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: AlexNetab70140210280350299.15297.84

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamab150300450600750698.36695.35

Quicksilver

Input: CTS2

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CTS2ab3M6M9M12M15M16240000163100001. (CXX) g++ options: -fopenmp -O3 -march=native

WebP2 Image Encode

Encode Settings: Quality 100, Compression Effort 5

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 100, Compression Effort 5ab369121511.6311.681. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

Y-Cruncher

Pi Digits To Calculate: 1B

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 1Bab369121510.2510.20

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamab102030405045.7645.95

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamab306090120150130.92131.46

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamab2468107.63057.5994

easyWave

Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200ab91827364539.6439.481. (CXX) g++ options: -O3 -fopenmp

FFmpeg

Encoder: libx265 - Scenario: Upload

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Uploadab61218243023.2023.291. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Speedb

Test: Random Fill

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random Fillab80K160K240K320K400K3690233676841. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragonab2040608010083.8883.58MIN: 83.23 / MAX: 85.03MIN: 82.9 / MAX: 84.61

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamab80016002400320040003813.643800.68

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamab2468108.37098.3990

rav1e

Speed: 5

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.7Speed: 5ab0.80911.61822.42733.23644.04553.5843.596

PyTorch

Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_lab2468106.005.98MIN: 5.47 / MAX: 6.12MIN: 5.52 / MAX: 6.11

PyTorch

Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_lab2468106.066.08MIN: 5.71 / MAX: 6.17MIN: 5.69 / MAX: 6.19

Quicksilver

Input: CORAL2 P1

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P1ab5M10M15M20M25M21350000212800001. (CXX) g++ options: -fopenmp -O3 -march=native

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamab306090120150145.62145.15

rav1e

Speed: 10

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.7Speed: 10ab369121512.3212.36

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamab2468106.85546.8775

OpenRadioss

Model: Cell Phone Drop Test

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Cell Phone Drop Testab71421283531.9431.84

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamab110220330440550496.34497.62

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamab142842567064.0763.91

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamab150300450600750673.33674.99

Xmrig

Variant: KawPow - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: KawPow - Hash Count: 1Mab4K8K12K16K20K20682.120732.71. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

PyTorch

Device: CPU - Batch Size: 1 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-152ab4812162016.5416.58MIN: 16.37 / MAX: 16.68MIN: 16.43 / MAX: 16.69

Y-Cruncher

Pi Digits To Calculate: 10B

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 10Bab306090120150112.54112.81

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamab50100150200250222.25221.72

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamab306090120150143.53143.84

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamab112233445546.9646.86

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 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamab300600900120015001458.051454.99

CloverLeaf

Input: clover_bm64_short

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bm64_shortab132639526557.2157.091. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

Embree

Binary: Pathtracer - Model: Asian Dragon

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer - Model: Asian Dragonab2040608010077.2677.10MIN: 76.76 / MAX: 78.27MIN: 76.54 / MAX: 78.04

TensorFlow

Device: CPU - Batch Size: 16 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: VGG-16ab81624324035.2135.14

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamab91827364537.0937.16

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamab153045607565.6665.78

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamab110220330440550486.60485.73

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 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamab51015202521.9221.96

FFmpeg

Encoder: libx265 - Scenario: Platform

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Platformab112233445547.1547.071. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Xmrig

Variant: GhostRider - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1Mab100020003000400050004436.24442.91. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: BMW27 - Compute: CPU-Onlyab61218243026.7126.75

Y-Cruncher

Pi Digits To Calculate: 5B

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 5Bab122436486053.0753.15

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamab2004006008001000852.18853.31

Quicksilver

Input: CORAL2 P2

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P2ab3M6M9M12M15M16170000161900001. (CXX) g++ options: -fopenmp -O3 -march=native

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Barbershop - Compute: CPU-Onlyab50100150200250239.83240.12

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamab61218243027.5727.54

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamab81624324036.2636.30

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamab4812162015.7815.77

Speedb

Test: Random Read

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random Readab70M140M210M280M350M3038660483041431271. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamab81624324036.3536.32

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamab61218243027.5027.53

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamab142842567063.2963.34

Xmrig

Variant: Monero - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Monero - Hash Count: 1Mab4K8K12K16K20K20714.720732.31. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamab2004006008001000800.59799.96

Y-Cruncher

Pi Digits To Calculate: 500M

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 500Mab1.14982.29963.44944.59925.7495.1105.106

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamab306090120150145.02144.91

Xmrig

Variant: CryptoNight-Femto UPX2 - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Femto UPX2 - Hash Count: 1Mab4K8K12K16K20K20698.420683.01. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamab153045607565.6965.74

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamab0.28050.5610.84151.1221.40251.24561.2465

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon Obj

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragon Objab163248648071.4971.44MIN: 70.94 / MAX: 72.42MIN: 70.79 / MAX: 72.51

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamab2468106.78436.7891

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamab306090120150147.25147.15

OpenRadioss

Model: Bumper Beam

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bumper Beamab2040608010088.1188.16

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamab61218243024.3624.37

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamab2004006008001000854.12853.69

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamab91827364541.0140.99

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamab70140210280350323.07322.92

FFmpeg

Encoder: libx265 - Scenario: Video On Demand

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Video On Demandab112233445547.0347.051. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamab2040608010098.8298.86

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamab50100150200250220.07220.15

TensorFlow

Device: CPU - Batch Size: 1 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 1 - Model: AlexNetab71421283530.4630.45

easyWave

Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400ab20406080100111.04111.071. (CXX) g++ options: -O3 -fopenmp

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamab110220330440550486.00485.88

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Pabellon Barcelona - Compute: CPU-Onlyab2040608010086.1486.16

QuantLib

Configuration: Single-Threaded

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Single-Threadedab60012001800240030002634.42633.81. (CXX) g++ options: -O3 -march=native -fPIE -pie

Speedb

Test: Read Random Write Random

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read Random Write Randomab500K1000K1500K2000K2500K253918425396871. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

TensorFlow

Device: CPU - Batch Size: 16 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: GoogLeNetab306090120150155.77155.78

TensorFlow

Device: CPU - Batch Size: 1 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 1 - Model: ResNet-50ab1.34332.68664.02995.37326.71655.975.97

TensorFlow

Device: CPU - Batch Size: 1 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 1 - Model: GoogLeNetab481216201717

TensorFlow

Device: CPU - Batch Size: 1 - Model: VGG-16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 1 - Model: VGG-16ab36912159.879.87

PyTorch

Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_lab2468106.036.03MIN: 5.52 / MAX: 6.16MIN: 5.51 / MAX: 6.13

rav1e

Speed: 1

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.7Speed: 1ab0.19130.38260.57390.76520.95650.850.85

WebP2 Image Encode

Encode Settings: Quality 100, Lossless Compression

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 100, Lossless Compressionab0.01350.0270.04050.0540.06750.060.061. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl


Phoronix Test Suite v10.8.5