openvino-1.4.0-amx

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 2311114-NE-2311110NE81
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

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
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
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
AVX512_CORE_AMX
November 11 2023
  1 Hour, 45 Minutes
AVX512_CORE
November 12 2023
  1 Hour, 45 Minutes
Invert Hiding All Results Option
  1 Hour, 45 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):


openvino-1.4.0-amxOpenBenchmarking.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 + 0GB Virtual HDisk06401GB Micron_9300_MTFDHAL6T4TDR + 4097GB Lexar SSD ARES 4TB + 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 ResolutionOpenvino-1.4.0-amx 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

AVX512_CORE_AMX vs. AVX512_CORE ComparisonPhoronix Test SuiteBaseline+160.2%+160.2%+320.4%+320.4%+480.6%+480.6%159.5%111%29.6%11.7%11.5%5.2%4.1%W.P.D.F - CPU640.8%W.P.D.F - CPU639.3%F.D.F - CPU529.2%F.D.F - CPU526.7%V.D.F.I - CPUA.G.R.R.0.F - CPU159.3%A.G.R.R.0.F - CPU152.7%P.V.B.D.F - CPU130.1%P.D.F - CPU120.4%P.D.F - CPU120.3%P.D.F - CPU117.7%P.D.F - CPU117.7%R.S.A.F.I - CPUF.D.R.F - CPU109.6%W.P.D.F.I - CPU106%W.P.D.F.I - CPU105.4%F.D.F.I - CPU92.3%H.E.R.F - CPU89.2%H.E.R.F - CPU89.1%V.D.F - CPU78.6%V.D.F - CPU78.4%R.S.A.F - CPU49.4%R.S.A.F - CPU49.3%H.E.R.F.I - CPU40.4%H.E.R.F.I - CPU40.4%A.G.R.R.0.F.I - CPU31.8%A.G.R.R.0.F.I - CPU30.2%V.D.F.I - CPUP.V.B.D.F - CPU15.1%F.D.R.F.I - CPUF.D.R.F.I - CPUR.S.A.F.I - CPUF.D.R.F - CPU5%F.D.F.I - CPUOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOAVX512_CORE_AMXAVX512_CORE

openvino-1.4.0-amxopenvino: 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 - CPUAVX512_CORE_AMXAVX512_CORE77.14362.17165.65337.4991906.180.54108977.140.44289.5796.62289.8996.5217523.903.189417.385.933234.9717.281921.7814.543661.1215.276610.968.4510083.575.541597.4735.031244.3644.97807.4634.621129.4149.5212.262269.7086.16324.2136370.461.483670.380.58131.41212.82133.14210.108530.816.551273.7843.934193.976.661077.2825.971591.0317.583153.698.8711238.544.96844.5966.26886.1463.15540.6951.731187.7523.47OpenBenchmarking.org

CPU Peak Freq (Highest CPU Core Frequency) Monitor

OpenBenchmarking.orgMegahertzCPU Peak Freq (Highest CPU Core Frequency) MonitorPhoronix Test Suite System MonitoringAVX512_COREAVX512_CORE_AMX8001600240032004000Min: 1900 / Avg: 2564.64 / Max: 4586Min: 1900 / Avg: 2523.31 / Max: 4355

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringAVX512_COREAVX512_CORE_AMX110220330440550Min: 48.23 / Avg: 428.13 / Max: 642.82Min: 54.4 / Avg: 407.76 / Max: 507.26

CPU Temperature Monitor

OpenBenchmarking.orgCelsiusCPU Temperature MonitorPhoronix Test Suite System MonitoringAVX512_COREAVX512_CORE_AMX1632486480Min: 36 / Avg: 69.48 / Max: 85Min: 36 / Avg: 68.03 / Max: 78

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: CPUAVX512_COREAVX512_CORE_AMX20406080100SE +/- 0.01, N = 3SE +/- 0.08, N = 312.2677.141. (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 - Device: CPUAVX512_COREAVX512_CORE_AMX1530456075Min: 12.25 / Avg: 12.26 / Max: 12.28Min: 76.99 / Avg: 77.14 / Max: 77.271. (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: CPUAVX512_COREAVX512_CORE_AMX5001000150020002500SE +/- 0.78, N = 3SE +/- 0.35, N = 32269.70362.17MIN: 1653.74 / MAX: 2733.95MIN: 125.7 / MAX: 443.521. (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: CPUAVX512_COREAVX512_CORE_AMX400800120016002000Min: 2268.56 / Avg: 2269.7 / Max: 2271.19Min: 361.6 / Avg: 362.17 / Max: 362.811. (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: CPUAVX512_COREAVX512_CORE_AMX4080120160200SE +/- 0.43, N = 3SE +/- 0.07, N = 386.16165.651. (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 FP16-INT8 - Device: CPUAVX512_COREAVX512_CORE_AMX306090120150Min: 85.72 / Avg: 86.16 / Max: 87.01Min: 165.54 / Avg: 165.65 / Max: 165.781. (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: CPUAVX512_COREAVX512_CORE_AMX70140210280350SE +/- 1.55, N = 3SE +/- 0.16, N = 3324.21337.49MIN: 173.46 / MAX: 419.38MIN: 123.15 / MAX: 428.331. (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: CPUAVX512_COREAVX512_CORE_AMX60120180240300Min: 321.12 / Avg: 324.21 / Max: 325.81Min: 337.19 / Avg: 337.49 / Max: 337.731. (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: CPUAVX512_COREAVX512_CORE_AMX20K40K60K80K100KSE +/- 31.52, N = 3SE +/- 56.21, N = 336370.4691906.181. (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: CPUAVX512_COREAVX512_CORE_AMX16K32K48K64K80KMin: 36315.23 / Avg: 36370.46 / Max: 36424.38Min: 91824.27 / Avg: 91906.18 / Max: 92013.811. (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: CPUAVX512_COREAVX512_CORE_AMX0.3150.630.9451.261.575SE +/- 0.00, N = 3SE +/- 0.00, N = 31.400.54MIN: 0.74 / MAX: 52.71MIN: 0.24 / MAX: 55.371. (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: CPUAVX512_COREAVX512_CORE_AMX246810Min: 1.4 / Avg: 1.4 / Max: 1.4Min: 0.54 / Avg: 0.54 / Max: 0.541. (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: CPUAVX512_COREAVX512_CORE_AMX20K40K60K80K100KSE +/- 99.28, N = 3SE +/- 222.39, N = 383670.38108977.141. (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: CPUAVX512_COREAVX512_CORE_AMX20K40K60K80K100KMin: 83473.09 / Avg: 83670.38 / Max: 83788.47Min: 108645.2 / Avg: 108977.14 / Max: 109399.51. (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: CPUAVX512_COREAVX512_CORE_AMX0.13050.2610.39150.5220.6525SE +/- 0.00, N = 3SE +/- 0.00, N = 30.580.44MIN: 0.31 / MAX: 50.67MIN: 0.22 / MAX: 54.331. (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: CPUAVX512_COREAVX512_CORE_AMX246810Min: 0.58 / Avg: 0.58 / Max: 0.58Min: 0.43 / Avg: 0.44 / Max: 0.441. (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: CPUAVX512_COREAVX512_CORE_AMX60120180240300SE +/- 0.03, N = 3SE +/- 0.19, N = 3131.41289.571. (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: CPUAVX512_COREAVX512_CORE_AMX50100150200250Min: 131.36 / Avg: 131.41 / Max: 131.46Min: 289.19 / Avg: 289.57 / Max: 289.831. (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: CPUAVX512_COREAVX512_CORE_AMX50100150200250SE +/- 0.06, N = 3SE +/- 0.07, N = 3212.8296.62MIN: 114.27 / MAX: 308.21MIN: 31.84 / MAX: 1901. (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: CPUAVX512_COREAVX512_CORE_AMX4080120160200Min: 212.74 / Avg: 212.82 / Max: 212.93Min: 96.53 / Avg: 96.62 / Max: 96.751. (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: CPUAVX512_COREAVX512_CORE_AMX60120180240300SE +/- 1.70, N = 3SE +/- 0.35, N = 3133.14289.891. (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: CPUAVX512_COREAVX512_CORE_AMX50100150200250Min: 131.42 / Avg: 133.14 / Max: 136.55Min: 289.39 / Avg: 289.89 / Max: 290.551. (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: CPUAVX512_COREAVX512_CORE_AMX50100150200250SE +/- 2.67, N = 3SE +/- 0.11, N = 3210.1096.52MIN: 115.17 / MAX: 637.54MIN: 34.11 / MAX: 190.761. (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: CPUAVX512_COREAVX512_CORE_AMX4080120160200Min: 204.77 / Avg: 210.1 / Max: 212.79Min: 96.3 / Avg: 96.52 / Max: 96.681. (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: CPUAVX512_COREAVX512_CORE_AMX4K8K12K16K20KSE +/- 120.35, N = 3SE +/- 19.41, N = 38530.8117523.901. (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: CPUAVX512_COREAVX512_CORE_AMX3K6K9K12K15KMin: 8341.06 / Avg: 8530.81 / Max: 8753.95Min: 17485.88 / Avg: 17523.9 / Max: 17549.691. (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: CPUAVX512_COREAVX512_CORE_AMX246810SE +/- 0.09, N = 3SE +/- 0.00, N = 36.553.18MIN: 3.46 / MAX: 460.84MIN: 1.4 / MAX: 68.791. (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: CPUAVX512_COREAVX512_CORE_AMX3691215Min: 6.38 / Avg: 6.55 / Max: 6.69Min: 3.17 / Avg: 3.18 / Max: 3.181. (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: CPUAVX512_COREAVX512_CORE_AMX2K4K6K8K10KSE +/- 0.25, N = 3SE +/- 1.68, N = 31273.789417.381. (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: CPUAVX512_COREAVX512_CORE_AMX16003200480064008000Min: 1273.34 / Avg: 1273.78 / Max: 1274.2Min: 9414.69 / Avg: 9417.38 / Max: 9420.481. (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: CPUAVX512_COREAVX512_CORE_AMX1020304050SE +/- 0.01, N = 3SE +/- 0.00, N = 343.935.93MIN: 22.22 / MAX: 112.86MIN: 2.16 / MAX: 72.841. (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: CPUAVX512_COREAVX512_CORE_AMX918273645Min: 43.92 / Avg: 43.93 / Max: 43.95Min: 5.93 / Avg: 5.93 / Max: 5.931. (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: CPUAVX512_COREAVX512_CORE_AMX9001800270036004500SE +/- 56.25, N = 3SE +/- 4.47, N = 34193.973234.971. (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: CPUAVX512_COREAVX512_CORE_AMX7001400210028003500Min: 4095.33 / Avg: 4193.97 / Max: 4290.15Min: 3226.15 / Avg: 3234.97 / Max: 3240.681. (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: CPUAVX512_COREAVX512_CORE_AMX48121620SE +/- 0.09, N = 3SE +/- 0.02, N = 36.6617.28MIN: 3.76 / MAX: 73.82MIN: 8.29 / MAX: 106.971. (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: CPUAVX512_COREAVX512_CORE_AMX48121620Min: 6.51 / Avg: 6.66 / Max: 6.82Min: 17.25 / Avg: 17.28 / Max: 17.331. (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: CPUAVX512_COREAVX512_CORE_AMX400800120016002000SE +/- 0.86, N = 3SE +/- 0.57, N = 31077.281921.781. (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: CPUAVX512_COREAVX512_CORE_AMX30060090012001500Min: 1075.65 / Avg: 1077.28 / Max: 1078.56Min: 1920.66 / Avg: 1921.78 / Max: 1922.551. (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: CPUAVX512_COREAVX512_CORE_AMX612182430SE +/- 0.02, N = 3SE +/- 0.01, N = 325.9714.54MIN: 14.87 / MAX: 84.67MIN: 6.89 / MAX: 93.431. (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: CPUAVX512_COREAVX512_CORE_AMX612182430Min: 25.94 / Avg: 25.97 / Max: 26.01Min: 14.53 / Avg: 14.54 / Max: 14.551. (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: CPUAVX512_COREAVX512_CORE_AMX8001600240032004000SE +/- 0.66, N = 3SE +/- 7.35, N = 31591.033661.121. (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: CPUAVX512_COREAVX512_CORE_AMX6001200180024003000Min: 1589.78 / Avg: 1591.03 / Max: 1592.05Min: 3646.68 / Avg: 3661.12 / Max: 3670.731. (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: CPUAVX512_COREAVX512_CORE_AMX48121620SE +/- 0.01, N = 3SE +/- 0.03, N = 317.5815.27MIN: 11.53 / MAX: 73.39MIN: 8.47 / MAX: 83.391. (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: CPUAVX512_COREAVX512_CORE_AMX48121620Min: 17.57 / Avg: 17.58 / Max: 17.6Min: 15.23 / Avg: 15.27 / Max: 15.331. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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

AVX512_CORE_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.

AVX512_CORE: 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: CPUAVX512_COREAVX512_CORE_AMX14002800420056007000SE +/- 3.93, N = 3SE +/- 6.91, N = 33153.696610.961. (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 - Device: CPUAVX512_COREAVX512_CORE_AMX11002200330044005500Min: 3149.08 / Avg: 3153.69 / Max: 3161.52Min: 6602.02 / Avg: 6610.96 / Max: 6624.561. (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: CPUAVX512_COREAVX512_CORE_AMX246810SE +/- 0.01, N = 3SE +/- 0.01, N = 38.878.45MIN: 4.92 / MAX: 63.24MIN: 4.69 / MAX: 315.081. (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: CPUAVX512_COREAVX512_CORE_AMX3691215Min: 8.85 / Avg: 8.87 / Max: 8.88Min: 8.43 / Avg: 8.45 / Max: 8.461. (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: CPUAVX512_COREAVX512_CORE_AMX2K4K6K8K10KSE +/- 15.03, N = 3SE +/- 4.26, N = 311238.5410083.571. (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: CPUAVX512_COREAVX512_CORE_AMX2K4K6K8K10KMin: 11215.29 / Avg: 11238.54 / Max: 11266.67Min: 10079.21 / Avg: 10083.57 / Max: 10092.091. (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: CPUAVX512_COREAVX512_CORE_AMX1.24652.4933.73954.9866.2325SE +/- 0.01, N = 3SE +/- 0.00, N = 34.965.54MIN: 2.8 / MAX: 86.65MIN: 3.48 / MAX: 64.431. (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: CPUAVX512_COREAVX512_CORE_AMX246810Min: 4.95 / Avg: 4.96 / Max: 4.97Min: 5.54 / Avg: 5.54 / Max: 5.541. (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: CPUAVX512_COREAVX512_CORE_AMX30060090012001500SE +/- 0.11, N = 3SE +/- 2.41, N = 3844.591597.471. (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: CPUAVX512_COREAVX512_CORE_AMX30060090012001500Min: 844.46 / Avg: 844.59 / Max: 844.81Min: 1593.42 / Avg: 1597.47 / Max: 1601.751. (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: CPUAVX512_COREAVX512_CORE_AMX1530456075SE +/- 0.01, N = 3SE +/- 0.05, N = 366.2635.03MIN: 40.67 / MAX: 120.74MIN: 20.47 / MAX: 91.061. (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: CPUAVX512_COREAVX512_CORE_AMX1326395265Min: 66.24 / Avg: 66.26 / Max: 66.27Min: 34.94 / Avg: 35.03 / Max: 35.121. (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: CPUAVX512_COREAVX512_CORE_AMX30060090012001500SE +/- 3.11, N = 3SE +/- 1.40, N = 3886.141244.361. (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: CPUAVX512_COREAVX512_CORE_AMX2004006008001000Min: 880 / Avg: 886.14 / Max: 890.01Min: 1242.17 / Avg: 1244.36 / Max: 1246.981. (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: CPUAVX512_COREAVX512_CORE_AMX1428425670SE +/- 0.22, N = 3SE +/- 0.05, N = 363.1544.97MIN: 48.78 / MAX: 123.42MIN: 27.58 / MAX: 116.581. (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: CPUAVX512_COREAVX512_CORE_AMX1224364860Min: 62.88 / Avg: 63.15 / Max: 63.59Min: 44.87 / Avg: 44.97 / Max: 45.051. (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: CPUAVX512_COREAVX512_CORE_AMX2004006008001000SE +/- 0.17, N = 3SE +/- 0.30, N = 3540.69807.461. (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: CPUAVX512_COREAVX512_CORE_AMX140280420560700Min: 540.36 / Avg: 540.69 / Max: 540.87Min: 807.05 / Avg: 807.46 / Max: 808.051. (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: CPUAVX512_COREAVX512_CORE_AMX1224364860SE +/- 0.02, N = 3SE +/- 0.01, N = 351.7334.62MIN: 27.75 / MAX: 106.93MIN: 18.6 / MAX: 100.861. (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: CPUAVX512_COREAVX512_CORE_AMX1020304050Min: 51.71 / Avg: 51.73 / Max: 51.76Min: 34.59 / Avg: 34.62 / Max: 34.631. (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: CPUAVX512_COREAVX512_CORE_AMX30060090012001500SE +/- 0.84, N = 3SE +/- 1.67, N = 31187.751129.411. (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: CPUAVX512_COREAVX512_CORE_AMX2004006008001000Min: 1186.08 / Avg: 1187.75 / Max: 1188.74Min: 1126.84 / Avg: 1129.41 / Max: 1132.531. (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: CPUAVX512_COREAVX512_CORE_AMX1122334455SE +/- 0.01, N = 3SE +/- 0.07, N = 323.4749.52MIN: 13.03 / MAX: 80.04MIN: 25.16 / MAX: 117.591. (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: CPUAVX512_COREAVX512_CORE_AMX1020304050Min: 23.46 / Avg: 23.47 / Max: 23.5Min: 49.39 / Avg: 49.52 / Max: 49.631. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

37 Results Shown

CPU Peak Freq (Highest CPU Core Frequency) Monitor:
  Phoronix Test Suite System Monitoring:
    Megahertz
    Watts
    Celsius
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