ai

2 x Intel Xeon Max 9468 testing with a Supermicro X13DEM v1.10 (1.3 BIOS) and ASPEED on Ubuntu 23.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2306210-NE-AI780463786&sor&grr.

aiProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen Resolutionabcd2 x Intel Xeon Max 9468 @ 3.50GHz (96 Cores / 192 Threads)Supermicro X13DEM v1.10 (1.3 BIOS)Intel Device 1bce512GB7682GB INTEL SSDPF2KX076TZASPEEDVE2282 x Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb/200GbUbuntu 23.046.2.0-20-generic (x86_64)GNOME Shell 44.0X Server 1.21.1.7GCC 12.2.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-Pa930Z/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Pa930Z/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x2c0001d1Python Details- Python 3.11.2Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

aitensorflow: CPU - 512 - ResNet-50tensorflow: CPU - 256 - ResNet-50tensorflow: CPU - 512 - GoogLeNetopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUtensorflow: CPU - 256 - GoogLeNettensorflow: CPU - 64 - GoogLeNettensorflow: CPU - 64 - ResNet-50tensorflow: CPU - 32 - ResNet-50tensorflow: CPU - 512 - AlexNetopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUtensorflow: CPU - 256 - AlexNetopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUtensorflow: CPU - 16 - GoogLeNetopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUtensorflow: CPU - 16 - ResNet-50tensorflow: CPU - 32 - GoogLeNettensorflow: CPU - 16 - AlexNettensorflow: CPU - 64 - AlexNettensorflow: CPU - 32 - AlexNetabcd72.670.97232.36149.92159.92209.53159.0557.6950.86685.25294.46325.25585.7615.256280.34700.1634.12696.1734.3217.025630.2937.24643.455.9715718.162.9631933.23104.391.1268911.420.4110460.518.192922.3840.35129.13240431.07373.5476.9669.57234.35151.35158.39200.6154.8959.2347.79671.22294.87324.86593.2715.196303.6703.8533.97696.7734.35175637.8137.36641.215.9415755.632.9532169.37105.391.1369578.860.4111897.598.182926.3140.64138.1229.08450.94361.2577.7770.31237.48158.88151.47206.53157.3157.1750.61666.10293.86325.91609.8015.276270.57699.3834.20709.0733.7017.035628.2037.41640.395.9415763.432.9632075.69104.261.1369611.400.4112093.028.192920.1040.35136.99240.69445.77356.6977.7671.32235.21150.66159.12206.7152.9257.1250.58679.84293.13326.61599.6815.346240.17693.1434.48715.4433.416.935661.2637.37641.235.9415797.22.9532249.87101.541.1366799.280.4112095.528.162931.8340.5140.15229.92453.77347.6OpenBenchmarking.org

TensorFlow

Device: CPU - Batch Size: 512 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: ResNet-50cdba20406080100SE +/- 0.46, N = 377.7777.7676.9672.60

TensorFlow

Device: CPU - Batch Size: 256 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: ResNet-50dacb1632486480SE +/- 0.46, N = 371.3270.9770.3169.57

TensorFlow

Device: CPU - Batch Size: 512 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: GoogLeNetcdba50100150200250SE +/- 2.29, N = 3237.48235.21234.35232.36

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPUadbc4080120160200SE +/- 2.76, N = 15149.92150.66151.35158.88MIN: 119.1 / MAX: 310.39MIN: 119.46 / MAX: 358.12MIN: 120.35 / MAX: 358.51MIN: 113.05 / MAX: 433.031. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPUadbc4080120160200SE +/- 2.51, N = 15159.92159.12158.39151.471. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

TensorFlow

Device: CPU - Batch Size: 256 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: GoogLeNetadcb50100150200250SE +/- 2.48, N = 4209.53206.70206.53200.60

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: GoogLeNetacbd4080120160200SE +/- 1.59, N = 15159.05157.31154.89152.92

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: ResNet-50bacd1326395265SE +/- 0.48, N = 359.2357.6957.1757.12

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: ResNet-50acdb1122334455SE +/- 0.52, N = 550.8650.6150.5847.79

TensorFlow

Device: CPU - Batch Size: 512 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: AlexNetadbc150300450600750SE +/- 1.85, N = 3685.25679.84671.22666.10

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUdcab60120180240300SE +/- 0.27, N = 3293.13293.86294.46294.87MIN: 263.72 / MAX: 522.86MIN: 243.71 / MAX: 469.02MIN: 247.31 / MAX: 419.59MIN: 226.08 / MAX: 443.681. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUdcab70140210280350SE +/- 0.30, N = 3326.61325.91325.25324.861. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

TensorFlow

Device: CPU - Batch Size: 256 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: AlexNetcdba130260390520650SE +/- 5.92, N = 6609.80599.68593.27585.76

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUbacd48121620SE +/- 0.04, N = 315.1915.2515.2715.34MIN: 12.88 / MAX: 123.19MIN: 12.68 / MAX: 103.08MIN: 12.18 / MAX: 108.89MIN: 12.8 / MAX: 110.561. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUbacd14002800420056007000SE +/- 17.13, N = 36303.606280.346270.576240.171. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUdcab150300450600750SE +/- 4.13, N = 3693.14699.38700.16703.85MIN: 410.77 / MAX: 1590.99MIN: 514.52 / MAX: 1681.15MIN: 452.33 / MAX: 1789.1MIN: 448.43 / MAX: 1668.721. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUdcab816243240SE +/- 0.19, N = 334.4834.2034.1233.971. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPUabcd150300450600750SE +/- 4.23, N = 3696.17696.77709.07715.44MIN: 486.45 / MAX: 1616.8MIN: 507.9 / MAX: 1821.8MIN: 484.14 / MAX: 1950.13MIN: 545.06 / MAX: 1928.171. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPUbacd816243240SE +/- 0.21, N = 334.3534.3233.7033.401. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUdbac48121620SE +/- 0.03, N = 316.9317.0017.0217.03MIN: 13.05 / MAX: 111.31MIN: 12.73 / MAX: 119.86MIN: 12.75 / MAX: 119.51MIN: 12.56 / MAX: 127.181. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUdbac12002400360048006000SE +/- 10.49, N = 35661.265637.815630.295628.201. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUabdc918273645SE +/- 0.07, N = 337.2437.3637.3737.41MIN: 29.9 / MAX: 223.47MIN: 29.38 / MAX: 311.72MIN: 29.21 / MAX: 165.63MIN: 30.15 / MAX: 313.151. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUadbc140280420560700SE +/- 1.24, N = 3643.45641.23641.21640.391. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUbcda1.34332.68664.02995.37326.7165SE +/- 0.02, N = 35.945.945.945.97MIN: 4.34 / MAX: 46.22MIN: 4.05 / MAX: 48.91MIN: 4.16 / MAX: 39.51MIN: 4.29 / MAX: 50.421. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUdcba3K6K9K12K15KSE +/- 46.70, N = 315797.2015763.4315755.6315718.161. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUbdac0.6661.3321.9982.6643.33SE +/- 0.01, N = 32.952.952.962.96MIN: 2.31 / MAX: 64.16MIN: 2.37 / MAX: 60.04MIN: 2.39 / MAX: 71.74MIN: 2.36 / MAX: 80.41. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUdbca7K14K21K28K35KSE +/- 77.08, N = 332249.8732169.3732075.6931933.231. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: GoogLeNetbacd20406080100SE +/- 1.06, N = 15105.39104.39104.26101.54

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: CPUabcd0.25430.50860.76291.01721.2715SE +/- 0.00, N = 31.121.131.131.13MIN: 0.81 / MAX: 35.87MIN: 0.78 / MAX: 30.57MIN: 0.8 / MAX: 39.35MIN: 0.78 / MAX: 28.191. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

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: CPUcbad15K30K45K60K75KSE +/- 696.32, N = 369611.4069578.8668911.4266799.281. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUabcd0.090.180.270.360.45SE +/- 0.00, N = 30.40.40.40.4MIN: 0.31 / MAX: 24.44MIN: 0.33 / MAX: 23.94MIN: 0.31 / MAX: 37.77MIN: 0.32 / MAX: 28.361. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUdcba20K40K60K80K100KSE +/- 450.23, N = 3112095.52112093.02111897.59110460.511. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUdbac246810SE +/- 0.01, N = 38.168.188.198.19MIN: 6.73 / MAX: 68.57MIN: 6.61 / MAX: 66.24MIN: 6.68 / MAX: 62.91MIN: 6.58 / MAX: 70.461. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUdbac6001200180024003000SE +/- 4.50, N = 32931.832926.312922.382920.101. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50bdca918273645SE +/- 0.34, N = 340.6440.5040.3540.35

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: GoogLeNetdbca306090120150SE +/- 1.50, N = 4140.15138.10136.99129.13

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: AlexNetcadb50100150200250SE +/- 2.42, N = 15240.69240.00229.92229.08

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: AlexNetdbca100200300400500SE +/- 5.55, N = 4453.77450.94445.77431.07

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: AlexNetabcd80160240320400SE +/- 3.63, N = 3373.54361.25356.69347.60

Phoronix Test Suite v10.8.4