9600X

Benchmarks for a future article. AMD Ryzen 5 9600X 6-Core testing with a ASUS ROG STRIX X670E-E GAMING WIFI (2308 BIOS) and AMD Radeon RX 7900 GRE 16GB on Ubuntu 24.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2409118-PTS-9600X70297
Jump To Table - Results

View

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

Statistics

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

Graph Settings

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

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
September 11
  4 Hours, 40 Minutes
b
September 11
  4 Hours, 40 Minutes
Invert Behavior (Only Show Selected Data)
  4 Hours, 40 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


9600XOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 5 9600X 6-Core @ 5.48GHz (6 Cores / 12 Threads)ASUS ROG STRIX X670E-E GAMING WIFI (2308 BIOS)AMD Device 14d82 x 16GB DDR5-6000MT/s G Skill F5-6000J3038F16G2000GB Corsair MP700 PROAMD Radeon RX 7900 GRE 16GBAMD Navi 31 HDMI/DPDELL U2723QEIntel I225-V + Intel Wi-Fi 6EUbuntu 24.046.10.0-phx (x86_64)GNOME Shell 46.0X Server + Wayland4.6 Mesa 24.2~git2406040600.8112d4~oibaf~n (git-8112d44 2024-06-04 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57)GCC 13.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen Resolution9600X BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/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-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xb40401c- Python 3.12.3- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

a vs. b ComparisonPhoronix Test SuiteBaseline+5.5%+5.5%+11%+11%+16.5%+16.5%5.6%4%2.9%2.8%2.6%2.2%2.2%4%2.9%Chess Benchmark21.8%Resizing20.4%1.smt28.6%Eigen6.9%BLAS6.2%Rotate6%mobilenetV3DistinctUserID5%ZFNet-512 - CPU - Parallel2.smt23%ArcFace ResNet-100 - CPU - Parallelinception-v3squeezenetv1.1GPT-2 - CPU - ParallelHWB Color Space2%T5 Encoder - CPU - Parallel2%GPT-2 - CPU - ParallelZFNet-512 - CPU - ParallelT5 Encoder - CPU - Parallel2%ArcFace ResNet-100 - CPU - ParallelStockfishGraphicsMagickZ3 Theorem ProverLeelaChessZeroLeelaChessZeroGraphicsMagickMobile Neural NetworksimdjsonONNX RuntimeZ3 Theorem ProverONNX RuntimeMobile Neural NetworkMobile Neural NetworkONNX RuntimeGraphicsMagickONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX Runtimeab

9600Xsvt-av1: Preset 3 - Bosphorus 4Ksvt-av1: Preset 5 - Bosphorus 4Ksvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 13 - Bosphorus 4Ksvt-av1: Preset 3 - Bosphorus 1080psvt-av1: Preset 5 - Bosphorus 1080psvt-av1: Preset 8 - Bosphorus 1080psvt-av1: Preset 13 - Bosphorus 1080psvt-av1: Preset 3 - Beauty 4K 10-bitsvt-av1: Preset 5 - Beauty 4K 10-bitsvt-av1: Preset 8 - Beauty 4K 10-bitsvt-av1: Preset 13 - Beauty 4K 10-bitx265: Bosphorus 4Kx265: Bosphorus 1080psimdjson: Kostyasimdjson: TopTweetsimdjson: LargeRandsimdjson: PartialTweetssimdjson: DistinctUserIDmt-dgemm: Sustained Floating-Point Rateoidn: RT.hdr_alb_nrm.3840x2160 - CPU-Onlyoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyoidn: RTLightmap.hdr.4096x4096 - CPU-Onlyonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: yolov4 - CPU - Parallelonnx: yolov4 - CPU - Standardonnx: ZFNet-512 - CPU - Parallelonnx: ZFNet-512 - CPU - Standardonnx: T5 Encoder - CPU - Parallelonnx: T5 Encoder - CPU - Standardonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Standardonnx: ResNet101_DUC_HDC-12 - CPU - Parallelonnx: ResNet101_DUC_HDC-12 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardospray: particle_volume/ao/real_timeospray: particle_volume/scivis/real_timeospray: particle_volume/pathtracer/real_timeospray: gravity_spheres_volume/dim_512/ao/real_timeospray: gravity_spheres_volume/dim_512/scivis/real_timeospray: gravity_spheres_volume/dim_512/pathtracer/real_timegraphics-magick: Swirlgraphics-magick: Rotategraphics-magick: Sharpengraphics-magick: Enhancedgraphics-magick: Resizinggraphics-magick: Noise-Gaussiangraphics-magick: HWB Color Spacebyte: Pipebyte: Dhrystone 2byte: System Callcompress-lz4: 1 - Compression Speedcompress-lz4: 1 - Decompression Speedcompress-lz4: 2 - Compression Speedcompress-lz4: 2 - Decompression Speedcompress-lz4: 3 - Compression Speedcompress-lz4: 3 - Decompression Speedcompress-lz4: 9 - Compression Speedcompress-lz4: 9 - Decompression Speedcompress-lz4: 12 - Compression Speedcompress-lz4: 12 - Decompression Speedetcpak: Multi-Threaded - ETC2byte: Whetstone Doublelczero: BLASlczero: Eigenstockfish: Chess Benchmarkstockfish: Chess Benchmarkgromacs: MPI CPU - water_GMX50_baregromacs: water_GMX50_bareonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: yolov4 - CPU - Parallelonnx: yolov4 - CPU - Standardonnx: ZFNet-512 - CPU - Parallelonnx: ZFNet-512 - CPU - Standardonnx: T5 Encoder - CPU - Parallelonnx: T5 Encoder - CPU - Standardonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Standardonnx: ResNet101_DUC_HDC-12 - CPU - Parallelonnx: ResNet101_DUC_HDC-12 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardmnn: nasnetmnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3z3: 1.smt2z3: 2.smt2build2: Time To Compiley-cruncher: 1By-cruncher: 500Mpovray: Trace Timeblender: BMW27 - CPU-Onlyblender: Junkshop - CPU-Onlyblender: Classroom - CPU-Onlyblender: Fishy Cat - CPU-Onlyblender: Barbershop - CPU-Onlyblender: Pabellon Barcelona - CPU-Onlywhisperfile: Tinywhisperfile: Smallwhisperfile: Mediumxnnpack: FP32MobileNetV2xnnpack: FP32MobileNetV3Largexnnpack: FP32MobileNetV3Smallxnnpack: FP16MobileNetV2xnnpack: FP16MobileNetV3Largexnnpack: FP16MobileNetV3Smallxnnpack: QU8MobileNetV2xnnpack: QU8MobileNetV3Largexnnpack: QU8MobileNetV3Smallab5.59721.89650.953167.00319.80271.958171.004706.480.8693.7655.1138.89818.3967.5813.12.0612.4213.37144.4837770.690.690.3351.751140.5378.495715.139754.971113.3866.1263163.53712.71826.9653173.531869.3251.614852.8089823.403852.079131.248536.30167.8881205.4870.8663411.3056839.05859.50444.741954.75488184.8453.835413.749144.3763912621219502836825744538458.478117575143927689.41033.446687.6474.965923.8168.656167.860.496446.920.746644.3291.957149214.739529626172950205546681.7411.0619.327.11087117.70466.049218.1898.8182115.12136.1130178.626537.08215.761641.14962619.25355.99842.726719.19867.618271.863914.72934.865621154.28765.88325.600716.80244.3570.5870.956.9041.4911.0791.21811.16616.40336.985163.7823.4210.08838.055113.2159.46317.03159.341128.79357.1432.88129156.75258424.172568461040301125211984785896042905.61121.72450.654166.58719.77571.817170.251706.9190.873.7775.0818.88718.697.257.5213.22.0512.3912.73144.970940.690.690.3352.8859140.8988.4161715.318357.1637114.77464.8427161.52312.559227.1211172.466865.2241.635282.8219524.081252.038132.978533.48867.4844206.7340.8640631.3093138.806558.98694.729124.75153183.8443.845063.740534.3644712520019502356725244695866.6780130318.143955081.61029.676700.2476.475922.1168.616174.260.476478.620.76643.3294.19814906037227721488082203866021.7431.05618.90577.09276118.81665.27917.49228.7108915.42086.1888579.620636.86855.797321.15518611.513354.36241.524619.2157.519171.8736214.81734.836251157.24763.75625.766616.94984.3520.5560.9266.8371.511.0821.21410.86217.81138.081164.20823.6529.94638.072112.43160.26316.58160.431129.22356.6832.87604156.82827423.64619849102530212511193482594605290OpenBenchmarking.org

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 3 - Input: Bosphorus 4Kab1.26252.5253.78755.056.31255.5975.6111. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 5 - Input: Bosphorus 4Kab51015202521.9021.721. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 8 - Input: Bosphorus 4Kab112233445550.9550.651. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 13 - Input: Bosphorus 4Kab4080120160200167.00166.591. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 3 - Input: Bosphorus 1080pab51015202519.8019.781. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 5 - Input: Bosphorus 1080pab163248648071.9671.821. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 8 - Input: Bosphorus 1080pab4080120160200171.00170.251. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 13 - Input: Bosphorus 1080pab150300450600750706.48706.921. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 3 - Input: Beauty 4K 10-bitab0.19580.39160.58740.78320.9790.8690.8701. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 5 - Input: Beauty 4K 10-bitab0.84981.69962.54943.39924.2493.7653.7771. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 8 - Input: Beauty 4K 10-bitab1.15042.30083.45124.60165.7525.1135.0811. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 13 - Input: Beauty 4K 10-bitab2468108.8988.8871. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

x265

OpenBenchmarking.orgFrames Per Second, More Is Betterx265Video Input: Bosphorus 4Kab51015202518.318.61. x265 [info]: HEVC encoder version 3.5+1-f0c1022b6

OpenBenchmarking.orgFrames Per Second, More Is Betterx265Video Input: Bosphorus 1080pab2040608010096.0097.251. x265 [info]: HEVC encoder version 3.5+1-f0c1022b6

simdjson

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: Kostyaab2468107.587.521. (CXX) g++ options: -O3 -lrt

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: TopTweetab369121513.113.21. (CXX) g++ options: -O3 -lrt

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: LargeRandomab0.46350.9271.39051.8542.31752.062.051. (CXX) g++ options: -O3 -lrt

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: PartialTweetsab369121512.4212.391. (CXX) g++ options: -O3 -lrt

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 3.10Throughput Test: DistinctUserIDab369121513.3712.731. (CXX) g++ options: -O3 -lrt

ACES DGEMM

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point Rateab306090120150144.48144.971. (CC) gcc options: -ffast-math -mavx2 -O3 -fopenmp -lopenblas

Intel Open Image Denoise

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.3Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Onlyab0.15530.31060.46590.62120.77650.690.69

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.3Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Onlyab0.15530.31060.46590.62120.77650.690.69

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.3Run: RTLightmap.hdr.4096x4096 - Device: CPU-Onlyab0.07430.14860.22290.29720.37150.330.33

ONNX Runtime

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: GPT-2 - Device: CPU - Executor: Parallelab122436486051.7552.891. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: GPT-2 - Device: CPU - Executor: Standardab306090120150140.54140.901. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: yolov4 - Device: CPU - Executor: Parallelab2468108.495708.416171. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: yolov4 - Device: CPU - Executor: Standardab4812162015.1415.321. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ZFNet-512 - Device: CPU - Executor: Parallelab132639526554.9757.161. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ZFNet-512 - Device: CPU - Executor: Standardab306090120150113.38114.771. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: T5 Encoder - Device: CPU - Executor: Parallelab153045607566.1364.841. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: T5 Encoder - Device: CPU - Executor: Standardab4080120160200163.54161.521. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: bertsquad-12 - Device: CPU - Executor: Parallelab369121512.7212.561. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: bertsquad-12 - Device: CPU - Executor: Standardab61218243026.9727.121. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallelab4080120160200173.53172.471. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: CaffeNet 12-int8 - Device: CPU - Executor: Standardab2004006008001000869.33865.221. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: fcn-resnet101-11 - Device: CPU - Executor: Parallelab0.36790.73581.10371.47161.83951.614851.635281. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: fcn-resnet101-11 - Device: CPU - Executor: Standardab0.63491.26981.90472.53963.17452.808982.821951. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallelab61218243023.4024.081. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ArcFace ResNet-100 - Device: CPU - Executor: Standardab122436486052.0852.041. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallelab306090120150131.25132.981. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standardab120240360480600536.30533.491. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: super-resolution-10 - Device: CPU - Executor: Parallelab153045607567.8967.481. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: super-resolution-10 - Device: CPU - Executor: Standardab50100150200250205.49206.731. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Parallelab0.19490.38980.58470.77960.97450.8663410.8640631. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: ResNet101_DUC_HDC-12 - Device: CPU - Executor: Standardab0.29460.58920.88381.17841.4731.305681.309311. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallelab91827364539.0638.811. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.19Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standardab132639526559.5058.991. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.2Benchmark: particle_volume/ao/real_timeab1.06692.13383.20074.26765.33454.741954.72912

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.2Benchmark: particle_volume/scivis/real_timeab1.06982.13963.20944.27925.3494.754884.75153

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.2Benchmark: particle_volume/pathtracer/real_timeab4080120160200184.85183.84

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.2Benchmark: gravity_spheres_volume/dim_512/ao/real_timeab0.86511.73022.59533.46044.32553.835413.84506

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.2Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeab0.84361.68722.53083.37444.2183.749143.74053

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.2Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeab0.98471.96942.95413.93884.92354.376394.36447

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagickOperation: Swirlab3060901201501261251. GraphicsMagick 1.3.42 2023-09-23 Q16 http://www.GraphicsMagick.org/

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagickOperation: Rotateab501001502002502122001. GraphicsMagick 1.3.42 2023-09-23 Q16 http://www.GraphicsMagick.org/

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagickOperation: Sharpenab51015202519191. GraphicsMagick 1.3.42 2023-09-23 Q16 http://www.GraphicsMagick.org/

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagickOperation: Enhancedab112233445550501. GraphicsMagick 1.3.42 2023-09-23 Q16 http://www.GraphicsMagick.org/

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagickOperation: Resizingab601201802403002832351. GraphicsMagick 1.3.42 2023-09-23 Q16 http://www.GraphicsMagick.org/

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagickOperation: Noise-Gaussianab153045607568671. GraphicsMagick 1.3.42 2023-09-23 Q16 http://www.GraphicsMagick.org/

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagickOperation: HWB Color Spaceab601201802403002572521. GraphicsMagick 1.3.42 2023-09-23 Q16 http://www.GraphicsMagick.org/

BYTE Unix Benchmark

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 5.1.3-gitComputational Test: Pipeab10M20M30M40M50M44538458.444695866.61. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 5.1.3-gitComputational Test: Dhrystone 2ab200M400M600M800M1000M781175751.0780130318.11. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 5.1.3-gitComputational Test: System Callab9M18M27M36M45M43927689.443955081.61. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm

LZ4 Compression

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.10Compression Level: 1 - Compression Speedab20040060080010001033.441029.671. (CC) gcc options: -O3 -pthread

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.10Compression Level: 1 - Decompression Speedab140028004200560070006687.66700.21. (CC) gcc options: -O3 -pthread

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.10Compression Level: 2 - Compression Speedab100200300400500474.96476.471. (CC) gcc options: -O3 -pthread

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.10Compression Level: 2 - Decompression Speedab130026003900520065005923.85922.11. (CC) gcc options: -O3 -pthread

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.10Compression Level: 3 - Compression Speedab4080120160200168.65168.611. (CC) gcc options: -O3 -pthread

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.10Compression Level: 3 - Decompression Speedab130026003900520065006167.86174.21. (CC) gcc options: -O3 -pthread

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.10Compression Level: 9 - Compression Speedab142842567060.4960.471. (CC) gcc options: -O3 -pthread

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.10Compression Level: 9 - Decompression Speedab140028004200560070006446.96478.61. (CC) gcc options: -O3 -pthread

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.10Compression Level: 12 - Compression Speedab51015202520.7420.701. (CC) gcc options: -O3 -pthread

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.10Compression Level: 12 - Decompression Speedab140028004200560070006644.36643.31. (CC) gcc options: -O3 -pthread

Etcpak

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 2.0Benchmark: Multi-Threaded - Configuration: ETC2ab60120180240300291.96294.201. (CXX) g++ options: -flto -pthread

BYTE Unix Benchmark

OpenBenchmarking.orgMWIPS, More Is BetterBYTE Unix Benchmark 5.1.3-gitComputational Test: Whetstone Doubleab30K60K90K120K150K149214.7149060.01. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm

LeelaChessZero

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.31.1Backend: BLASab901802703604503953721. (CXX) g++ options: -flto -pthread

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.31.1Backend: Eigenab601201802403002962771. (CXX) g++ options: -flto -pthread

Stockfish

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 17Chess Benchmarkab6M12M18M24M30M26172950214880821. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfishChess Benchmarkab4M8M12M16M20M20554668203866021. Stockfish 16 by the Stockfish developers (see AUTHORS file)

GROMACS

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

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bareab0.39220.78441.17661.56881.9611.7411.7431. (CXX) g++ options: -O3 -lm

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACSInput: water_GMX50_bareab0.23850.4770.71550.9541.19251.0601.0561. GROMACS version: 2023.3-Ubuntu_2023.3_1ubuntu3

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: nasnetab0.98031.96062.94093.92124.90154.3574.352MIN: 3.81 / MAX: 13.67MIN: 3.84 / MAX: 9.481. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: mobilenetV3ab0.13210.26420.39630.52840.66050.5870.556MIN: 0.55 / MAX: 1.28MIN: 0.53 / MAX: 1.251. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: squeezenetv1.1ab0.21380.42760.64140.85521.0690.9500.926MIN: 0.87 / MAX: 1.67MIN: 0.87 / MAX: 1.741. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: resnet-v2-50ab2468106.9046.837MIN: 6.1 / MAX: 16.18MIN: 6.05 / MAX: 16.691. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: SqueezeNetV1.0ab0.33980.67961.01941.35921.6991.4911.510MIN: 1.37 / MAX: 2.7MIN: 1.37 / MAX: 2.631. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: MobileNetV2_224ab0.24350.4870.73050.9741.21751.0791.082MIN: 0.98 / MAX: 4.28MIN: 0.97 / MAX: 2.171. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: mobilenet-v1-1.0ab0.27410.54820.82231.09641.37051.2181.214MIN: 1.13 / MAX: 2.19MIN: 1.14 / MAX: 2.171. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: inception-v3ab369121511.1710.86MIN: 10.11 / MAX: 20.26MIN: 8.94 / MAX: 20.251. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

Z3 Theorem Prover

OpenBenchmarking.orgSeconds, Fewer Is BetterZ3 Theorem Prover 4.12.1SMT File: 1.smt2ab4812162016.4017.811. (CXX) g++ options: -lpthread -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -O3 -fPIC

OpenBenchmarking.orgSeconds, Fewer Is BetterZ3 Theorem Prover 4.12.1SMT File: 2.smt2ab91827364536.9938.081. (CXX) g++ options: -lpthread -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -O3 -fPIC

Build2

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.17Time To Compileab4080120160200163.78164.21

Y-Cruncher

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.5Pi Digits To Calculate: 1Bab61218243023.4223.65

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.5Pi Digits To Calculate: 500Mab369121510.0889.946

POV-Ray

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-RayTrace Timeab91827364538.0638.071. POV-Ray 3.7.0.10.unofficial

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: BMW27 - Compute: CPU-Onlyab306090120150113.20112.43

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Junkshop - Compute: CPU-Onlyab4080120160200159.46160.26

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Classroom - Compute: CPU-Onlyab70140210280350317.03316.58

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Fishy Cat - Compute: CPU-Onlyab4080120160200159.34160.43

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Barbershop - Compute: CPU-Onlyab20040060080010001128.791129.22

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Pabellon Barcelona - Compute: CPU-Onlyab80160240320400357.14356.68

Whisperfile

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisperfile 20Aug24Model Size: Tinyab81624324032.8832.88

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisperfile 20Aug24Model Size: Smallab306090120150156.75156.83

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisperfile 20Aug24Model Size: Mediumab90180270360450424.17423.65

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP32MobileNetV2ab20040060080010008468491. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP32MobileNetV3Largeab2004006008001000104010251. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP32MobileNetV3Smallab701402102803503013021. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP16MobileNetV2ab30060090012001500125212511. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP16MobileNetV3Largeab30060090012001500119811931. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP16MobileNetV3Smallab1002003004005004784821. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: QU8MobileNetV2ab1302603905206505895941. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: QU8MobileNetV3Largeab1302603905206506046051. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: QU8MobileNetV3Smallab601201802403002902901. (CXX) g++ options: -O3 -lrt -lm

113 Results Shown

SVT-AV1:
  Preset 3 - Bosphorus 4K
  Preset 5 - Bosphorus 4K
  Preset 8 - Bosphorus 4K
  Preset 13 - Bosphorus 4K
  Preset 3 - Bosphorus 1080p
  Preset 5 - Bosphorus 1080p
  Preset 8 - Bosphorus 1080p
  Preset 13 - Bosphorus 1080p
  Preset 3 - Beauty 4K 10-bit
  Preset 5 - Beauty 4K 10-bit
  Preset 8 - Beauty 4K 10-bit
  Preset 13 - Beauty 4K 10-bit
x265:
  Bosphorus 4K
  Bosphorus 1080p
simdjson:
  Kostya
  TopTweet
  LargeRand
  PartialTweets
  DistinctUserID
ACES DGEMM
Intel Open Image Denoise:
  RT.hdr_alb_nrm.3840x2160 - CPU-Only
  RT.ldr_alb_nrm.3840x2160 - CPU-Only
  RTLightmap.hdr.4096x4096 - CPU-Only
ONNX Runtime:
  GPT-2 - CPU - Parallel
  GPT-2 - CPU - Standard
  yolov4 - CPU - Parallel
  yolov4 - CPU - Standard
  ZFNet-512 - CPU - Parallel
  ZFNet-512 - CPU - Standard
  T5 Encoder - CPU - Parallel
  T5 Encoder - CPU - Standard
  bertsquad-12 - CPU - Parallel
  bertsquad-12 - CPU - Standard
  CaffeNet 12-int8 - CPU - Parallel
  CaffeNet 12-int8 - CPU - Standard
  fcn-resnet101-11 - CPU - Parallel
  fcn-resnet101-11 - CPU - Standard
  ArcFace ResNet-100 - CPU - Parallel
  ArcFace ResNet-100 - CPU - Standard
  ResNet50 v1-12-int8 - CPU - Parallel
  ResNet50 v1-12-int8 - CPU - Standard
  super-resolution-10 - CPU - Parallel
  super-resolution-10 - CPU - Standard
  ResNet101_DUC_HDC-12 - CPU - Parallel
  ResNet101_DUC_HDC-12 - CPU - Standard
  Faster R-CNN R-50-FPN-int8 - CPU - Parallel
  Faster R-CNN R-50-FPN-int8 - CPU - Standard
OSPRay:
  particle_volume/ao/real_time
  particle_volume/scivis/real_time
  particle_volume/pathtracer/real_time
  gravity_spheres_volume/dim_512/ao/real_time
  gravity_spheres_volume/dim_512/scivis/real_time
  gravity_spheres_volume/dim_512/pathtracer/real_time
GraphicsMagick:
  Swirl
  Rotate
  Sharpen
  Enhanced
  Resizing
  Noise-Gaussian
  HWB Color Space
BYTE Unix Benchmark:
  Pipe
  Dhrystone 2
  System Call
LZ4 Compression:
  1 - Compression Speed
  1 - Decompression Speed
  2 - Compression Speed
  2 - Decompression Speed
  3 - Compression Speed
  3 - Decompression Speed
  9 - Compression Speed
  9 - Decompression Speed
  12 - Compression Speed
  12 - Decompression Speed
Etcpak
BYTE Unix Benchmark
LeelaChessZero:
  BLAS
  Eigen
Stockfish
Stockfish
GROMACS
GROMACS
Mobile Neural Network:
  nasnet
  mobilenetV3
  squeezenetv1.1
  resnet-v2-50
  SqueezeNetV1.0
  MobileNetV2_224
  mobilenet-v1-1.0
  inception-v3
Z3 Theorem Prover:
  1.smt2
  2.smt2
Build2
Y-Cruncher:
  1B
  500M
POV-Ray
Blender:
  BMW27 - CPU-Only
  Junkshop - CPU-Only
  Classroom - CPU-Only
  Fishy Cat - CPU-Only
  Barbershop - CPU-Only
  Pabellon Barcelona - CPU-Only
Whisperfile:
  Tiny
  Small
  Medium
XNNPACK:
  FP32MobileNetV2
  FP32MobileNetV3Large
  FP32MobileNetV3Small
  FP16MobileNetV2
  FP16MobileNetV3Large
  FP16MobileNetV3Small
  QU8MobileNetV2
  QU8MobileNetV3Large
  QU8MobileNetV3Small