new tests jan

AMD Ryzen 7 4700U testing with a LENOVO LNVNB161216 (DTCN18WWV1.04 BIOS) and AMD Renoir 512MB on Ubuntu 22.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2301054-NE-NEWTESTSJ91&grs&rdt.

new tests janProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionabcAMD Ryzen 7 4700U @ 2.00GHz (8 Cores)LENOVO LNVNB161216 (DTCN18WWV1.04 BIOS)AMD Renoir/Cezanne16GB512GB SAMSUNG MZALQ512HALU-000L2AMD Renoir 512MB (1600/400MHz)AMD Renoir Radeon HD AudioIntel Wi-Fi 6 AX200Ubuntu 22.045.18.8-051808-generic (x86_64)GNOME Shell 42.2X Server + Wayland4.6 Mesa 22.0.5 (LLVM 13.0.1 DRM 3.46)1.3.204GCC 11.3.0ext41920x1080OpenBenchmarking.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-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/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 schedutil (Boost: Enabled) - Platform Profile: balanced - CPU Microcode: 0x8600102 - ACPI Profile: balanced Python Details- Python 3.10.6Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: 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 Retpolines IBPB: conditional IBRS_FW STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

new tests janonednn: IP Shapes 3D - f32 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUkvazaar: Bosphorus 4K - Mediumopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUuvg266: Bosphorus 4K - Slowopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUkvazaar: Bosphorus 1080p - Ultra Fastonednn: Deconvolution Batch shapes_3d - f32 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUbrl-cad: VGR Performance Metriconednn: Recurrent Neural Network Inference - u8s8f32 - CPUkvazaar: Bosphorus 4K - Slowonednn: Recurrent Neural Network Training - f32 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Person Detection FP32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUopenvino: Person Detection FP32 - CPUuvg266: Bosphorus 1080p - Slowuvg266: Bosphorus 1080p - Very Fastuvg266: Bosphorus 4K - Mediumkvazaar: Bosphorus 1080p - Super Fastonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUuvg266: Bosphorus 4K - Super Fastkvazaar: Bosphorus 4K - Super Fastuvg266: Bosphorus 1080p - Ultra Fastkvazaar: Bosphorus 1080p - Very Fastonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: IP Shapes 1D - f32 - CPUuvg266: Bosphorus 4K - Very Fastuvg266: Bosphorus 1080p - Super Fastkvazaar: Bosphorus 4K - Very Fastonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUuvg266: Bosphorus 1080p - Mediumopenvino: Weld Porosity Detection FP16-INT8 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUkvazaar: Bosphorus 1080p - Slowuvg266: Bosphorus 4K - Ultra Fastopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUkvazaar: Bosphorus 4K - Ultra Fastonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUkvazaar: Bosphorus 1080p - Mediumopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUonednn: IP Shapes 1D - bf16bf16bf16 - CPUabc13.9667272.114.684.594065.090.972.782530.411.5883.9810.275496.5241.4790404270.535.416535.7525.98153.814214.1430.61794.509957.584514309.90.9414.3641.033.0862.884.166899.213.9350.751.164316.0310.55928.8942.1111.226718.943.2576238.4916.27207.623.4793723.4411.123336.192.3618.786.442183531.3733.00476720.6629.47135.651932.845.18882197.920.1824.392.222.0711.726254.6915.684.923885.831.022.92436.541.6486.9410.393794.0242.5810614228.735.496430.4325.76155.134187.8730.28034.499917.506344268.920.9514.5141.23.163.484.130589.2713.8350.9351.234281.7610.47678.9442.4211.186671.523.2450438.2316.29209.013.4566623.3111.163348.872.3518.756.421163539.932.94046709.7629.51135.461929.355.17662198.2520.1524.372.222.0711.7815276.4914.454.884097.160.972.862536.171.5885.210.632996.2841.5804244330.135.56507.4425.59156.154155.4430.68224.552677.500314314.770.9514.4641.453.1163.324.138959.2813.9551.1351.594289.1610.49998.9642.3411.266697.783.2355438.2416.38208.993.4669723.3511.173350.492.3518.826.441133528.9433.04046729.5129.43135.821927.865.1863198.0120.1724.392.222.07OpenBenchmarking.org

oneDNN

Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUabc4812162013.9711.7311.78MIN: 13.24MIN: 11.34MIN: 11.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUabc60120180240300272.10254.69276.49MIN: 218.74 / MAX: 296.69MIN: 203.79 / MAX: 289.9MIN: 189.01 / MAX: 300.811. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUabc4812162014.6815.6814.451. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Medium

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Mediumabc1.1072.2143.3214.4285.5354.594.924.881. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUabc90018002700360045004065.093885.834097.16MIN: 3620.71 / MAX: 4385.17MIN: 3467.55 / MAX: 4401.5MIN: 3675.56 / MAX: 4343.581. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUabc0.22950.4590.68850.9181.14750.971.020.971. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

uvg266

Video Input: Bosphorus 4K - Video Preset: Slow

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Slowabc0.65251.3051.95752.613.26252.782.902.86

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPUabc50010001500200025002530.412436.542536.17MIN: 2449.14 / MAX: 2675.68MIN: 2357.22 / MAX: 2630.77MIN: 2449.59 / MAX: 2652.11. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPUabc0.3690.7381.1071.4761.8451.581.641.581. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Ultra Fastabc2040608010083.9886.9485.201. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUabc369121510.2810.3910.63MIN: 8.83MIN: 9.22MIN: 9.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUabc2040608010096.5294.0296.281. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUabc102030405041.442.541.5MIN: 31.23 / MAX: 63.72MIN: 27.02 / MAX: 107.55MIN: 23.58 / MAX: 63.781. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

BRL-CAD

VGR Performance Metric

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.34VGR Performance Metricabc20K40K60K80K100K7904081061804241. (CXX) g++ options: -std=c++14 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lregex_brl -lz_brl -lnetpbm -ldl -lm -ltk8.6

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUabc90018002700360045004270.534228.734330.13MIN: 4249.56MIN: 4206.73MIN: 4299.11. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Slow

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Slowabc1.23752.4753.71254.956.18755.415.495.501. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

oneDNN

Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUabc140028004200560070006535.756430.436507.44MIN: 6490.41MIN: 6374.21MIN: 6454.121. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUabc61218243025.9825.7625.59MIN: 18.73 / MAX: 85.18MIN: 19.71 / MAX: 48.6MIN: 17.81 / MAX: 49.851. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUabc306090120150153.81155.13156.151. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPUabc90018002700360045004214.144187.874155.44MIN: 3752.16 / MAX: 4441.98MIN: 3773.91 / MAX: 4439.08MIN: 3613.62 / MAX: 4551.41. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUabc71421283530.6230.2830.68MIN: 29.86MIN: 29.58MIN: 29.951. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUabc1.02442.04883.07324.09765.1224.509954.499914.55267MIN: 4.28MIN: 4.32MIN: 4.21. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUabc2468107.584517.506347.50031MIN: 6.81MIN: 6.8MIN: 6.751. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUabc90018002700360045004309.904268.924314.77MIN: 4290.44MIN: 4246.65MIN: 4294.781. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPUabc0.21380.42760.64140.85521.0690.940.950.951. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

uvg266

Video Input: Bosphorus 1080p - Video Preset: Slow

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Slowabc4812162014.3614.5114.46

uvg266

Video Input: Bosphorus 1080p - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Very Fastabc91827364541.0341.2041.45

uvg266

Video Input: Bosphorus 4K - Video Preset: Medium

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Mediumabc0.69981.39962.09942.79923.4993.083.103.11

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Super Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Super Fastabc142842567062.8863.4863.321. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUabc0.93761.87522.81283.75044.6884.166894.130584.13895MIN: 3.87MIN: 3.88MIN: 3.891. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

uvg266

Video Input: Bosphorus 4K - Video Preset: Super Fast

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super Fastabc36912159.209.279.28

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Super Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super Fastabc4812162013.9313.8313.951. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

uvg266

Video Input: Bosphorus 1080p - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Ultra Fastabc122436486050.7050.9351.13

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Very Fastabc122436486051.1651.2351.591. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUabc90018002700360045004316.034281.764289.16MIN: 4298.56MIN: 4260.68MIN: 4269.171. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUabc369121510.5610.4810.50MIN: 10.04MIN: 9.9MIN: 101. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

uvg266

Video Input: Bosphorus 4K - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very Fastabc36912158.898.948.96

uvg266

Video Input: Bosphorus 1080p - Video Preset: Super Fast

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Super Fastabc102030405042.1142.4242.34

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very Fastabc369121511.2211.1811.261. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

oneDNN

Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUabc140028004200560070006718.946671.526697.78MIN: 6697.51MIN: 6654.15MIN: 6676.081. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUabc0.7331.4662.1992.9323.6653.257623.245043.23554MIN: 3.11MIN: 2.86MIN: 3.071. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUabc91827364538.4938.2338.24MIN: 28.2 / MAX: 63.19MIN: 28.03 / MAX: 79.55MIN: 28.23 / MAX: 65.711. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

uvg266

Video Input: Bosphorus 1080p - Video Preset: Medium

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Mediumabc4812162016.2716.2916.38

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUabc50100150200250207.62209.01208.991. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

oneDNN

Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUabc0.78291.56582.34873.13163.91453.479373.456663.46697MIN: 3.39MIN: 3.37MIN: 3.391. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Slow

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Slowabc61218243023.4423.3123.351. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

uvg266

Video Input: Bosphorus 4K - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra Fastabc369121511.1211.1611.17

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUabc70014002100280035003336.193348.873350.491. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUabc0.5311.0621.5932.1242.6552.362.352.35MIN: 1.6 / MAX: 18.58MIN: 1.49 / MAX: 19.15MIN: 1.66 / MAX: 17.911. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra Fastabc51015202518.7818.7518.821. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUabc2468106.442186.421166.44113MIN: 6.3MIN: 6.31MIN: 6.321. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUabc80016002400320040003531.373539.903528.941. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUabc81624324033.0032.9433.04MIN: 32.72MIN: 32.5MIN: 32.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUabc140028004200560070006720.666709.766729.51MIN: 6699.87MIN: 6685.23MIN: 6706.131. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUabc71421283529.4729.5129.43MIN: 20.29 / MAX: 55.95MIN: 20.02 / MAX: 45.76MIN: 21.25 / MAX: 56.161. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUabc306090120150135.65135.46135.821. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUabc4008001200160020001932.841929.351927.86MIN: 1873.21 / MAX: 1964.73MIN: 1860.58 / MAX: 1965.05MIN: 1879.04 / MAX: 1962.331. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUabc1.16752.3353.50254.675.83755.188825.176625.18630MIN: 4.7MIN: 4.87MIN: 4.691. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUabc4080120160200197.90198.25198.011. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUabc51015202520.1820.1520.17MIN: 16.21 / MAX: 32.87MIN: 16.59 / MAX: 34.39MIN: 12.54 / MAX: 39.191. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Medium

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Mediumabc61218243024.3924.3724.391. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUabc0.49950.9991.49851.9982.49752.222.222.22MIN: 1.51 / MAX: 19.63MIN: 1.62 / MAX: 18.78MIN: 1.65 / MAX: 17.561. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUabc0.46580.93161.39741.86322.3292.072.072.071. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared


Phoronix Test Suite v10.8.5