openvino-2024

Intel Core Ultra 7 155H testing with a MTL Swift SFG14-72T Coral_MTH (V1.01 BIOS) and Intel Arc MTL 8GB on Ubuntu 23.10 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 2403078-NE-OPENVINO276
Jump To Table - Results

View

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

Statistics

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

Graph Settings

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

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
a
March 06
  6 Hours, 24 Minutes
b
March 07
  41 Minutes
c
March 07
  41 Minutes
d
March 07
  41 Minutes
e
March 07
  7 Hours, 23 Minutes
Invert Behavior (Only Show Selected Data)
  3 Hours, 10 Minutes

Only show results where is faster than
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-2024 OpenBenchmarking.orgPhoronix Test SuiteIntel Core Ultra 7 155H @ 4.80GHz (16 Cores / 22 Threads)MTL Swift SFG14-72T Coral_MTH (V1.01 BIOS)Intel Device 7e7f8 x 2GB DRAM-6400MT/s Micron MT62F1G32D2DS-0261024GB Micron_2550_MTFDKBA1T0TGEIntel Arc MTL 8GB (2250MHz)Intel Meteor Lake-P HD AudioIntel Device 7e40Ubuntu 23.106.8.0-060800rc1daily20240126-generic (x86_64)GNOME Shell 45.2X Server 1.21.1.7 + Wayland4.6 Mesa 24.1~git2401200600.ebcab1~oibaf~m (git-ebcab14 2024-01-20 mantic-oibaf-ppa)GCC 13.2.0ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionOpenvino-2024 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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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: balance_performance) - CPU Microcode: 0x13 - Thermald 2.5.4- Python 3.11.6- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

abcdeResult OverviewPhoronix Test Suite100%103%107%110%113%OpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOP.D.F - CPUP.D.F - CPUV.D.F - CPUV.D.F - CPUP.D.F - CPUP.D.F - CPUF.D.R.F - CPUF.D.R.F - CPUN.S.P.L.F - CPUF.D.F - CPUN.S.P.L.F - CPUF.D.F - CPUM.T.E.T.D.F - CPUM.T.E.T.D.F - CPUW.P.D.F - CPUW.P.D.F - CPUV.D.F.I - CPUV.D.F.I - CPUF.D.F.I - CPUW.P.D.F.I - CPUF.D.F.I - CPUW.P.D.F.I - CPUH.E.R.F - CPUH.E.R.F - CPUR.S.A.F.I - CPUR.S.A.F.I - CPUR.S.A.F - CPUR.S.A.F - CPUP.V.B.D.F - CPUP.V.B.D.F - CPUF.D.R.F.I - CPUF.D.R.F.I - CPUH.E.R.F.I - CPUH.E.R.F.I - CPUP.R.I.R.F - CPUP.R.I.R.F - CPUA.G.R.R.0.F - CPUA.G.R.R.0.F - CPUA.G.R.R.0.F.I - CPUA.G.R.R.0.F.I - CPU

openvino-2024 openvino: Face Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Face Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUabcde1.8220.4719.97146.156.33454.1966.70280.81173.861002.41118.8119.67643.51230.73323.3190.88256.364823.26108.7112466.993797.30341.26349.7847.861099.3315.36104.8624.8897.4316.5558.84355.6126.0130.2952.32186.7127.243.31156.101.271.9122.0121.43163.566.82501.5371.39304.16189.191059.77127.221.39693.74246.61345.9695.15265.614958.11111.612915.873557.43317.45325.8242.721021.7613.997.922.9589.3615.6354.94326.624.128.3148.8178.2426.283.23152.021.221.9521.9721.41163.336.76506.7671.56304.5188.181058.96127.721.45693.66246.59348.6995.34267.314962.19112.2112894.543543.9318.02326.3842.781023.4413.7597.6722.9389.9415.6554.73325.624.0928.3248.42177.8126.123.22151.191.221.9121.6821.07159.696.74493.1470.24299.19185.521045.93125.6420.94682.02243.84337.2992.52257.644908.52111.2912467.63562.54321.69331.4843.751030.0814.1399.5223.3391.1915.8255.6333.5124.4928.6450.08183.2827.093.26152.481.261.7619.4619.10145.056.30455.7467.33282.22176.09996.96119.7419.86653.79231.80315.3888.60252.964709.82105.7012467.503912.27359.37366.1048.221103.1215.31103.8824.7596.1616.6458.38351.7325.5930.1353.70191.3627.613.39160.661.27OpenBenchmarking.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 2024.0Model: Face Detection FP16 - Device: CPUedcba0.43880.87761.31641.75522.194SE +/- 0.01, N = 15SE +/- 0.02, N = 81.761.911.951.911.821. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUedcba510152025SE +/- 0.20, N = 15SE +/- 0.23, N = 319.4621.6821.9722.0120.471. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUedcba510152025SE +/- 0.21, N = 15SE +/- 0.27, N = 319.1021.0721.4121.4319.971. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUedcba4080120160200SE +/- 1.21, N = 15SE +/- 1.22, N = 15145.05159.69163.33163.56146.151. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUedcba246810SE +/- 0.04, N = 13SE +/- 0.05, N = 156.306.746.766.826.331. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUedcba110220330440550SE +/- 3.85, N = 15SE +/- 4.97, N = 5455.74493.14506.76501.53454.191. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUedcba1632486480SE +/- 0.68, N = 6SE +/- 0.75, N = 467.3370.2471.5671.3966.701. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUedcba70140210280350SE +/- 2.03, N = 15SE +/- 2.21, N = 15282.22299.19304.50304.16280.811. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUedcba4080120160200SE +/- 1.26, N = 12SE +/- 1.41, N = 15176.09185.52188.18189.19173.861. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUedcba2004006008001000SE +/- 7.15, N = 15SE +/- 6.75, N = 15996.961045.931058.961059.771002.411. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUedcba306090120150SE +/- 1.39, N = 4SE +/- 1.16, N = 6119.74125.64127.70127.20118.811. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUedcba510152025SE +/- 0.15, N = 15SE +/- 0.20, N = 1519.8620.9421.4521.3919.671. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUedcba150300450600750SE +/- 5.14, N = 10SE +/- 5.15, N = 15653.79682.02693.66693.74643.511. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUedcba50100150200250SE +/- 1.91, N = 3SE +/- 1.67, N = 15231.80243.84246.59246.61230.731. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUedcba80160240320400SE +/- 3.89, N = 15SE +/- 2.66, N = 15315.38337.29348.69345.96323.311. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUedcba20406080100SE +/- 0.61, N = 3SE +/- 0.70, N = 1088.6092.5295.3495.1590.881. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUedcba60120180240300SE +/- 2.45, N = 6SE +/- 2.88, N = 4252.96257.64267.31265.61256.361. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUedcba11002200330044005500SE +/- 46.64, N = 6SE +/- 39.34, N = 34709.824908.524962.194958.114823.261. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUedcba306090120150SE +/- 0.83, N = 15SE +/- 1.48, N = 3105.70111.29112.21111.60108.711. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUedcba3K6K9K12K15KSE +/- 146.93, N = 3SE +/- 151.02, N = 412467.5012467.6012894.5412915.8712466.991. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUedcba8001600240032004000SE +/- 31.91, N = 15SE +/- 32.88, N = 83912.273562.543543.903557.433797.30MIN: 2798.1 / MAX: 5581.53MIN: 1816.87 / MAX: 5174.72MIN: 2743.85 / MAX: 5185.69MIN: 2757.58 / MAX: 5221.58MIN: 1742.11 / MAX: 5264.591. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUedcba80160240320400SE +/- 3.72, N = 15SE +/- 3.98, N = 3359.37321.69318.02317.45341.26MIN: 181.92 / MAX: 496.2MIN: 228.05 / MAX: 462.91MIN: 175.18 / MAX: 464.55MIN: 224.7 / MAX: 464.25MIN: 177.09 / MAX: 488.591. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUedcba80160240320400SE +/- 3.98, N = 15SE +/- 4.98, N = 3366.10331.48326.38325.82349.78MIN: 173.32 / MAX: 500.3MIN: 221.77 / MAX: 461.89MIN: 225.82 / MAX: 460.08MIN: 220.85 / MAX: 464.29MIN: 176.64 / MAX: 492.351. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUedcba1122334455SE +/- 0.40, N = 15SE +/- 0.40, N = 1548.2243.7542.7842.7247.86MIN: 21.22 / MAX: 118.95MIN: 23.92 / MAX: 118.28MIN: 19.12 / MAX: 66.42MIN: 23.22 / MAX: 67.87MIN: 18.18 / MAX: 104.891. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUedcba2004006008001000SE +/- 7.33, N = 13SE +/- 9.38, N = 151103.121030.081023.441021.761099.33MIN: 406.78 / MAX: 1728.53MIN: 733.36 / MAX: 1612.47MIN: 727.38 / MAX: 1604.26MIN: 721.29 / MAX: 1599.18MIN: 459.81 / MAX: 1740.171. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUedcba48121620SE +/- 0.13, N = 15SE +/- 0.17, N = 515.3114.1313.7513.9015.36MIN: 6.83 / MAX: 39.1MIN: 8.44 / MAX: 37.62MIN: 7.71 / MAX: 30.86MIN: 7.85 / MAX: 35.11MIN: 6.94 / MAX: 39.471. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUedcba20406080100SE +/- 1.04, N = 6SE +/- 1.16, N = 4103.8899.5297.6797.90104.86MIN: 44.02 / MAX: 396.62MIN: 39.25 / MAX: 383.84MIN: 51.53 / MAX: 347.08MIN: 37.33 / MAX: 376.3MIN: 43.38 / MAX: 358.761. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUedcba612182430SE +/- 0.18, N = 15SE +/- 0.20, N = 1524.7523.3322.9322.9524.88MIN: 11.42 / MAX: 47.13MIN: 13.63 / MAX: 40.97MIN: 11.91 / MAX: 43.96MIN: 11.9 / MAX: 43.97MIN: 12.66 / MAX: 47.231. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUedcba20406080100SE +/- 0.70, N = 12SE +/- 0.81, N = 1596.1691.1989.9489.3697.43MIN: 45.85 / MAX: 157.97MIN: 46.11 / MAX: 142.48MIN: 46.46 / MAX: 140.34MIN: 46.01 / MAX: 136.05MIN: 46.27 / MAX: 163.71. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUedcba48121620SE +/- 0.12, N = 15SE +/- 0.11, N = 1516.6415.8215.6515.6316.55MIN: 7.02 / MAX: 37.41MIN: 6.52 / MAX: 29.45MIN: 7.08 / MAX: 26.33MIN: 7.37 / MAX: 26.39MIN: 6.65 / MAX: 34.711. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUedcba1326395265SE +/- 0.67, N = 4SE +/- 0.58, N = 658.3855.6054.7354.9458.84MIN: 25.03 / MAX: 96.63MIN: 32.5 / MAX: 89.87MIN: 32.28 / MAX: 86.23MIN: 32.3 / MAX: 87.41MIN: 28.65 / MAX: 92.741. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUedcba80160240320400SE +/- 2.64, N = 15SE +/- 3.64, N = 15351.73333.51325.60326.60355.61MIN: 137.63 / MAX: 624.33MIN: 227.46 / MAX: 479.39MIN: 217.98 / MAX: 455.75MIN: 127.63 / MAX: 466.63MIN: 163.07 / MAX: 515.111. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUedcba612182430SE +/- 0.20, N = 10SE +/- 0.21, N = 1525.5924.4924.0924.1026.01MIN: 12.13 / MAX: 55.42MIN: 12.24 / MAX: 41.08MIN: 11.69 / MAX: 42.69MIN: 12.07 / MAX: 40.91MIN: 10.92 / MAX: 57.131. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUedcba714212835SE +/- 0.25, N = 3SE +/- 0.22, N = 1530.1328.6428.3228.3130.29MIN: 14.67 / MAX: 57.69MIN: 16.72 / MAX: 56.71MIN: 17.27 / MAX: 57.04MIN: 17.01 / MAX: 55.63MIN: 13.26 / MAX: 59.591. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUedcba1224364860SE +/- 0.67, N = 15SE +/- 0.44, N = 1553.7050.0848.4248.8052.32MIN: 24.32 / MAX: 89.77MIN: 24.33 / MAX: 73.52MIN: 24.4 / MAX: 71.85MIN: 24.49 / MAX: 74.38MIN: 24.2 / MAX: 79.71. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUedcba4080120160200SE +/- 1.32, N = 3SE +/- 1.41, N = 10191.36183.28177.81178.24186.71MIN: 101.79 / MAX: 268.9MIN: 101.8 / MAX: 248.36MIN: 102.85 / MAX: 239.14MIN: 101.95 / MAX: 247.18MIN: 101.83 / MAX: 274.051. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUedcba612182430SE +/- 0.27, N = 6SE +/- 0.31, N = 427.6127.0926.1226.2827.24MIN: 11.88 / MAX: 54.33MIN: 15.78 / MAX: 43.25MIN: 15.46 / MAX: 41.86MIN: 16.16 / MAX: 43.57MIN: 15.08 / MAX: 47.911. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUedcba0.76281.52562.28843.05123.814SE +/- 0.03, N = 6SE +/- 0.03, N = 33.393.263.223.233.31MIN: 1.06 / MAX: 14.99MIN: 1.04 / MAX: 8MIN: 1.04 / MAX: 15.36MIN: 1.1 / MAX: 8.44MIN: 1.1 / MAX: 12.431. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUedcba4080120160200SE +/- 1.27, N = 15SE +/- 2.14, N = 3160.66152.48151.19152.02156.10MIN: 88.95 / MAX: 239.44MIN: 89.77 / MAX: 219.3MIN: 89.51 / MAX: 211.52MIN: 88.01 / MAX: 226.83MIN: 89.74 / MAX: 233.971. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUedcba0.28580.57160.85741.14321.429SE +/- 0.01, N = 3SE +/- 0.02, N = 41.271.261.221.221.27MIN: 0.38 / MAX: 12.95MIN: 0.4 / MAX: 6.52MIN: 0.4 / MAX: 5.49MIN: 0.39 / MAX: 6.57MIN: 0.38 / MAX: 11.641. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

40 Results Shown

OpenVINO:
  Face Detection FP16 - CPU
  Person Detection FP16 - CPU
  Person Detection FP32 - CPU
  Vehicle Detection FP16 - CPU
  Face Detection FP16-INT8 - CPU
  Face Detection Retail FP16 - CPU
  Road Segmentation ADAS FP16 - CPU
  Vehicle Detection FP16-INT8 - CPU
  Weld Porosity Detection FP16 - CPU
  Face Detection Retail FP16-INT8 - CPU
  Road Segmentation ADAS FP16-INT8 - CPU
  Machine Translation EN To DE FP16 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
  Person Vehicle Bike Detection FP16 - CPU
  Noise Suppression Poconet-Like FP16 - CPU
  Handwritten English Recognition FP16 - CPU
  Person Re-Identification Retail FP16 - CPU
  Age Gender Recognition Retail 0013 FP16 - CPU
  Handwritten English Recognition FP16-INT8 - CPU
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU
  Face Detection FP16 - CPU
  Person Detection FP16 - CPU
  Person Detection FP32 - CPU
  Vehicle Detection FP16 - CPU
  Face Detection FP16-INT8 - CPU
  Face Detection Retail FP16 - CPU
  Road Segmentation ADAS FP16 - CPU
  Vehicle Detection FP16-INT8 - CPU
  Weld Porosity Detection FP16 - CPU
  Face Detection Retail FP16-INT8 - CPU
  Road Segmentation ADAS FP16-INT8 - CPU
  Machine Translation EN To DE FP16 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
  Person Vehicle Bike Detection FP16 - CPU
  Noise Suppression Poconet-Like FP16 - CPU
  Handwritten English Recognition FP16 - CPU
  Person Re-Identification Retail FP16 - CPU
  Age Gender Recognition Retail 0013 FP16 - CPU
  Handwritten English Recognition FP16-INT8 - CPU
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU