openvino140-amx-avx

Intel Xeon w9-3495X testing with a ASUS Pro WS W790E-SAGE SE (0705 BIOS) and llvmpipe on Ubuntu 22.04 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 2311131-NE-2311121NE59
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
Disable Color Branding
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Xeon w-3495X AVX512
November 13 2023
  1 Hour, 45 Minutes
Xeon w-3495X AMX
November 13 2023
  3 Hours, 31 Minutes
Invert Behavior (Only Show Selected Data)
  2 Hours, 38 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):


openvino140-amx-avxOpenBenchmarking.orgPhoronix Test SuiteIntel Xeon w9-3495X @ 4.80GHz (56 Cores / 112 Threads)ASUS Pro WS W790E-SAGE SE (0705 BIOS)Intel Device 7aa78 x 32 GB DDR5-4812MT/s Hynix HMCG88AEBRA115N6401GB Micron_9300_MTFDHAL6T4TDR + 4097GB Lexar SSD ARES 4TB + 0GB Virtual HDisk06401GB Micron_9300_MTFDHAL6T4TDR + 0GB Virtual HDisk0llvmpipe (210/405MHz)Realtek ALC12202 x Intel X710 for 10GBASE-TUbuntu 22.046.3.0-060300-generic (x86_64)GNOME Shell 42.9X Server 1.21.1.4NVIDIA 535.129.034.5 Mesa 23.0.4-0ubuntu1~22.04.1 (LLVM 15.0.7 256 bits)OpenCL 3.0 CUDA 12.2.1471.3.242GCC 11.4.0 + CUDA 12.1ext41920x1200ProcessorMotherboardChipsetMemoryDisksGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionOpenvino140-amx-avx BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: intel_pstate powersave (EPP: performance) - CPU Microcode: 0x2b0004b1- Python 3.10.12- 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 / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

Xeon w-3495X AVX512 vs. Xeon w-3495X AMX ComparisonPhoronix Test SuiteBaseline+160%+160%+320%+320%+480%+480%+640%+640%640.1%637.3%529.6%526.4%157.4%152.4%121.1%121.1%120.7%120.4%120.4%97.5%96.7%89.7%82.8%65.9%65.7%64.7%64.6%31.8%30%24%23.9%10.3%W.P.D.F - CPUW.P.D.F - CPUF.D.F - CPUF.D.F - CPUR.S.A.F.I - CPU310.4%V.D.F.I - CPU170.7%A.G.R.R.0.F - CPUA.G.R.R.0.F - CPUP.D.F - CPUP.D.F - CPUP.V.B.D.F - CPUP.D.F - CPUP.D.F - CPUR.S.A.F.I - CPU102.9%W.P.D.F.I - CPUW.P.D.F.I - CPUF.D.R.F - CPUF.D.F.I - CPUH.E.R.F - CPUH.E.R.F - CPUV.D.F - CPUV.D.F - CPUV.D.F.I - CPU35.4%A.G.R.R.0.F.I - CPUA.G.R.R.0.F.I - CPUH.E.R.F.I - CPUH.E.R.F.I - CPUF.D.R.F.I - CPU21.3%F.D.R.F.I - CPU21.2%P.V.B.D.F - CPUF.D.F.I - CPU9.4%F.D.R.F - CPU5.4%R.S.A.F - CPU2.3%OpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOXeon w-3495X AVX512Xeon w-3495X AMX

openvino140-amx-avxopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUXeon w-3495X AVX512Xeon w-3495X AMX12.252268.7790.41309.0436540.921.3983346.630.58131.27213.11131.25213.158914.856.261275.0743.894355.126.421078.6225.941587.2917.623158.518.8511226.314.97844.6466.25884.0763.30541.8651.621187.8723.4777.13362.20165.26338.1692228.810.54108321.980.44289.2896.71290.2396.4017538.093.179400.665.933217.4917.381775.6215.753503.1415.975990.759.339263.516.031401.2339.991095.8651.07545.6952.79585.3596.33OpenBenchmarking.org

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX51220406080100SE +/- 0.06, N = 3SE +/- 0.04, N = 377.1312.251. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX5125001000150020002500SE +/- 0.25, N = 3SE +/- 1.54, N = 3362.202268.77MIN: 119.43 / MAX: 472.79MIN: 1517.57 / MAX: 2563.681. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX5124080120160200SE +/- 0.29, N = 3SE +/- 0.70, N = 3165.2690.411. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUXeon w-3495X AVX512Xeon w-3495X AMX70140210280350SE +/- 2.39, N = 3SE +/- 0.57, N = 3309.04338.16MIN: 163.58 / MAX: 409.95MIN: 127.79 / MAX: 448.451. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX51220K40K60K80K100KSE +/- 84.22, N = 3SE +/- 23.18, N = 392228.8136540.921. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX5120.31280.62560.93841.25121.564SE +/- 0.00, N = 3SE +/- 0.00, N = 30.541.39MIN: 0.24 / MAX: 58.79MIN: 0.75 / MAX: 56.291. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX51220K40K60K80K100KSE +/- 164.95, N = 3SE +/- 161.53, N = 3108321.9883346.631. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX5120.13050.2610.39150.5220.6525SE +/- 0.00, N = 3SE +/- 0.00, N = 30.440.58MIN: 0.22 / MAX: 56.4MIN: 0.31 / MAX: 53.911. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX51260120180240300SE +/- 0.56, N = 3SE +/- 0.09, N = 3289.28131.271. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX51250100150200250SE +/- 0.19, N = 3SE +/- 0.17, N = 396.71213.11MIN: 42.98 / MAX: 223.77MIN: 115.03 / MAX: 293.961. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP32 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX51260120180240300SE +/- 0.48, N = 3SE +/- 0.04, N = 3290.23131.251. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP32 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX51250100150200250SE +/- 0.15, N = 3SE +/- 0.08, N = 396.40213.15MIN: 49.92 / MAX: 186.22MIN: 117.21 / MAX: 284.141. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX5124K8K12K16K20KSE +/- 5.37, N = 3SE +/- 87.78, N = 317538.098914.851. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX512246810SE +/- 0.00, N = 3SE +/- 0.06, N = 33.176.26MIN: 1.39 / MAX: 63.13MIN: 3.38 / MAX: 133.591. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX5122K4K6K8K10KSE +/- 10.11, N = 3SE +/- 0.13, N = 39400.661275.071. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX5121020304050SE +/- 0.00, N = 3SE +/- 0.00, N = 35.9343.89MIN: 2.12 / MAX: 285.01MIN: 22.33 / MAX: 445.641. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUXeon w-3495X AVX512Xeon w-3495X AMX9001800270036004500SE +/- 33.04, N = 3SE +/- 2.70, N = 34355.123217.491. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUXeon w-3495X AVX512Xeon w-3495X AMX48121620SE +/- 0.05, N = 3SE +/- 0.02, N = 36.4217.38MIN: 3.75 / MAX: 71.69MIN: 8.24 / MAX: 103.711. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX512400800120016002000SE +/- 15.27, N = 15SE +/- 0.67, N = 31775.621078.621. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX512612182430SE +/- 0.13, N = 15SE +/- 0.02, N = 315.7525.94MIN: 6.76 / MAX: 103.22MIN: 14.36 / MAX: 99.921. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX5128001600240032004000SE +/- 34.77, N = 6SE +/- 0.49, N = 33503.141587.291. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX51248121620SE +/- 0.15, N = 6SE +/- 0.01, N = 315.9717.62MIN: 8.98 / MAX: 90.98MIN: 11.57 / MAX: 77.451. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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

Xeon w-3495X AVX512: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Xeon w-3495X AMX: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX51213002600390052006500SE +/- 69.64, N = 4SE +/- 2.69, N = 35990.753158.511. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16 - Device: CPUXeon w-3495X AVX512Xeon w-3495X AMX3691215SE +/- 0.01, N = 3SE +/- 0.11, N = 48.859.33MIN: 4.88 / MAX: 68.8MIN: 4.69 / MAX: 283.651. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUXeon w-3495X AVX512Xeon w-3495X AMX2K4K6K8K10KSE +/- 2.05, N = 3SE +/- 83.54, N = 311226.319263.511. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUXeon w-3495X AVX512Xeon w-3495X AMX246810SE +/- 0.00, N = 3SE +/- 0.06, N = 34.976.03MIN: 2.79 / MAX: 62.29MIN: 3.46 / MAX: 82.631. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX51230060090012001500SE +/- 14.65, N = 15SE +/- 0.97, N = 31401.23844.641. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX5121530456075SE +/- 0.40, N = 15SE +/- 0.07, N = 339.9966.25MIN: 21.33 / MAX: 131.88MIN: 40.54 / MAX: 128.11. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX5122004006008001000SE +/- 10.17, N = 6SE +/- 2.31, N = 31095.86884.071. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX5121428425670SE +/- 0.46, N = 6SE +/- 0.17, N = 351.0763.30MIN: 29.37 / MAX: 134.75MIN: 41.81 / MAX: 120.711. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUXeon w-3495X AMXXeon w-3495X AVX512120240360480600SE +/- 28.82, N = 12SE +/- 0.39, N = 3545.69541.861. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUXeon w-3495X AVX512Xeon w-3495X AMX1224364860SE +/- 0.04, N = 3SE +/- 2.69, N = 1251.6252.79MIN: 28.55 / MAX: 117.46MIN: 22.13 / MAX: 170.681. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUXeon w-3495X AVX512Xeon w-3495X AMX30060090012001500SE +/- 0.60, N = 3SE +/- 13.98, N = 151187.87585.351. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUXeon w-3495X AVX512Xeon w-3495X AMX20406080100SE +/- 0.01, N = 3SE +/- 2.35, N = 1523.4796.33MIN: 12.57 / MAX: 82.58MIN: 33.13 / MAX: 263.561. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

CPU Peak Freq (Highest CPU Core Frequency) Monitor

OpenBenchmarking.orgMegahertzCPU Peak Freq (Highest CPU Core Frequency) MonitorPhoronix Test Suite System MonitoringXeon w-3495X AMXXeon w-3495X AVX5128001600240032004000Min: 510 / Avg: 2083.98 / Max: 4517Min: 1900 / Avg: 2590.26 / Max: 4300

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringXeon w-3495X AMXXeon w-3495X AVX512110220330440550Min: 58.72 / Avg: 395.56 / Max: 516.63Min: 92.98 / Avg: 426.33 / Max: 644.43

CPU Temperature Monitor

OpenBenchmarking.orgCelsiusCPU Temperature MonitorPhoronix Test Suite System MonitoringXeon w-3495X AVX512Xeon w-3495X AMX20406080100Min: 31 / Avg: 67.73 / Max: 89Min: 47 / Avg: 79.63 / Max: 90

37 Results Shown

OpenVINO:
  Face Detection FP16 - CPU:
    FPS
    ms
  Face Detection FP16-INT8 - CPU:
    FPS
    ms
  Age Gender Recognition Retail 0013 FP16 - CPU:
    FPS
    ms
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    FPS
    ms
  Person Detection FP16 - CPU:
    FPS
    ms
  Person Detection FP32 - CPU:
    FPS
    ms
  Weld Porosity Detection FP16-INT8 - CPU:
    FPS
    ms
  Weld Porosity Detection FP16 - CPU:
    FPS
    ms
  Vehicle Detection FP16-INT8 - CPU:
    FPS
    ms
  Vehicle Detection FP16 - CPU:
    FPS
    ms
  Person Vehicle Bike Detection FP16 - CPU:
    FPS
    ms
  Face Detection Retail FP16 - CPU:
    FPS
    ms
  Face Detection Retail FP16-INT8 - CPU:
    FPS
    ms
  Handwritten English Recognition FP16 - CPU:
    FPS
    ms
  Handwritten English Recognition FP16-INT8 - CPU:
    FPS
    ms
  Road Segmentation ADAS FP16 - CPU:
    FPS
    ms
  Road Segmentation ADAS FP16-INT8 - CPU:
    FPS
    ms
CPU Peak Freq (Highest CPU Core Frequency) Monitor:
  Phoronix Test Suite System Monitoring:
    Megahertz
    Watts
    Celsius