openvino 2024

AMD Ryzen 9 7950X 16-Core testing with a ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS) and NVIDIA GeForce RTX 4090 24GB 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 2403069-PTS-OPENVINO90
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

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
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
March 06
  2 Hours, 4 Minutes
b
March 06
  2 Hours, 2 Minutes
c
March 06
  2 Hours, 2 Minutes
Invert Hiding All Results Option
  2 Hours, 2 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):

a

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203
Python Notes: Python 3.11.6
Security Notes: 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: Vulnerable: Safe RET no microcode + 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 STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

b

c

Processor: AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 16GB DRAM-6000MT/s G Skill F5-6000J3038F16G, Disk: 2000GB Samsung SSD 980 PRO 2TB + 4001GB Western Digital WD_BLACK SN850X 4000GB, Graphics: NVIDIA GeForce RTX 4090 24GB, Audio: NVIDIA AD102 HD Audio, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411

OS: Ubuntu 23.10, Kernel: 6.7.0-060700-generic (x86_64), Desktop: GNOME Shell 45.2, Display Server: X Server 1.21.1.7, Display Driver: NVIDIA 550.54.14, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.4.89, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160

openvino 2024OpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads)ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS)AMD Device 14d82 x 16GB DRAM-6000MT/s G Skill F5-6000J3038F16G2000GB Samsung SSD 980 PRO 2TB + 4001GB Western Digital WD_BLACK SN850X 4000GBNVIDIA GeForce RTX 4090 24GBNVIDIA AD102 HD AudioDELL U2723QEIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 23.106.7.0-060700-generic (x86_64)GNOME Shell 45.2X Server 1.21.1.7NVIDIA 550.54.144.6.0OpenCL 3.0 CUDA 12.4.89GCC 13.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-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: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203- 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: Vulnerable: Safe RET no microcode + 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 STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

abcResult OverviewPhoronix Test Suite100%101%101%102%102%OpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOR.S.A.F - CPUR.S.A.F - CPUP.D.F - CPUP.V.B.D.F - CPUP.V.B.D.F - CPUP.D.F - CPUP.D.F - CPUP.D.F - CPUV.D.F - CPUV.D.F - CPUF.D.F - CPUM.T.E.T.D.F - CPUM.T.E.T.D.F - CPUR.S.A.F.I - CPUR.S.A.F.I - CPUF.D.F - CPUF.D.R.F - CPUP.R.I.R.F - CPUP.R.I.R.F - CPUF.D.R.F.I - CPUF.D.R.F - CPUW.P.D.F.I - CPUF.D.F.I - CPUF.D.F.I - CPUF.D.R.F.I - CPUW.P.D.F - CPUW.P.D.F - CPUA.G.R.R.0.F - CPUH.E.R.F.I - CPUH.E.R.F.I - CPUW.P.D.F.I - CPUH.E.R.F - CPUH.E.R.F - CPUV.D.F.I - CPUA.G.R.R.0.F.I - CPUN.S.P.L.F - CPUA.G.R.R.0.F.I - CPUA.G.R.R.0.F - CPUN.S.P.L.F - CPUV.D.F.I - CPU

openvino 2024openvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Face Detection FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUabc284.7728.0291.175.331494.1587.6887.3091.57762.8810.4513.33135.4258.97452.3417.63597.873082.024.231883.104479.952.526.18314.0525.433.501316.1312.1334012.2020.85765.512577.45711.3022.461596.8648218.141591.110.290.429.874.99282.7328.2292.165.341492.3486.7687.1891.68765.0910.4213.37134.7359.27455.4617.51597.063095.794.221887.224496.752.516.17313.4325.483.501316.7312.1234014.5720.90763.842578.49710.1622.491594.1648211.961592.230.290.429.874.99278.1928.6790.775.261514.6588.0486.1892.75770.5910.3513.27135.7058.85455.0517.52600.093080.884.211891.574498.332.516.16313.0525.513.491319.5012.1034096.4120.86765.232583.01711.5722.451596.0348255.241591.450.290.429.874.99OpenBenchmarking.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: Road Segmentation ADAS FP16 - Device: CPUabc60120180240300SE +/- 1.37, N = 3SE +/- 1.82, N = 3SE +/- 2.46, N = 3284.77282.73278.191. (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: CPUabc714212835SE +/- 0.13, N = 3SE +/- 0.18, N = 3SE +/- 0.25, N = 328.0228.2228.67MIN: 16.22 / MAX: 40.02MIN: 10.53 / MAX: 44.58MIN: 10.75 / MAX: 39.131. (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: CPUabc20406080100SE +/- 1.05, N = 3SE +/- 1.15, N = 3SE +/- 0.40, N = 391.1792.1690.771. (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: CPUabc1.20152.4033.60454.8066.0075SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 35.335.345.26MIN: 3.57 / MAX: 11.48MIN: 3.39 / MAX: 15.51MIN: 3.33 / MAX: 14.21. (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: CPUabc30060090012001500SE +/- 10.51, N = 3SE +/- 9.79, N = 3SE +/- 5.79, N = 31494.151492.341514.651. (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: CPUabc20406080100SE +/- 1.01, N = 3SE +/- 1.07, N = 3SE +/- 0.38, N = 387.6886.7688.04MIN: 61.79 / MAX: 115.55MIN: 60.41 / MAX: 118.86MIN: 47.09 / MAX: 117.981. (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: CPUabc20406080100SE +/- 0.76, N = 3SE +/- 0.65, N = 3SE +/- 0.70, N = 387.3087.1886.18MIN: 65.54 / MAX: 119.07MIN: 65.19 / MAX: 115.17MIN: 36.72 / MAX: 118.141. (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: CPUabc20406080100SE +/- 0.79, N = 3SE +/- 0.68, N = 3SE +/- 0.76, N = 391.5791.6892.751. (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: CPUabc170340510680850SE +/- 3.80, N = 3SE +/- 1.79, N = 3SE +/- 0.96, N = 3762.88765.09770.591. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUabc3691215SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 310.4510.4210.35MIN: 4.01 / MAX: 16.6MIN: 4.87 / MAX: 26.31MIN: 4.05 / MAX: 16.441. (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 - Device: CPUabc3691215SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 313.3313.3713.271. (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: CPUabc306090120150SE +/- 0.20, N = 3SE +/- 0.51, N = 3SE +/- 0.24, N = 3135.42134.73135.701. (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: CPUabc1326395265SE +/- 0.08, N = 3SE +/- 0.22, N = 3SE +/- 0.10, N = 358.9759.2758.85MIN: 29.49 / MAX: 98.18MIN: 26.39 / MAX: 68.68MIN: 29.03 / MAX: 79.531. (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: CPUabc100200300400500SE +/- 1.47, N = 3SE +/- 0.95, N = 3SE +/- 1.99, N = 3452.34455.46455.051. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUabc48121620SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 317.6317.5117.52MIN: 8.66 / MAX: 23.81MIN: 8.99 / MAX: 24.3MIN: 11.31 / MAX: 25.021. (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: CPUabc130260390520650SE +/- 3.84, N = 3SE +/- 3.67, N = 3SE +/- 3.92, N = 3597.87597.06600.09MIN: 542.54 / MAX: 619.98MIN: 543.04 / MAX: 622.56MIN: 549.16 / MAX: 622.691. (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: CPUabc7001400210028003500SE +/- 6.57, N = 3SE +/- 16.74, N = 3SE +/- 1.12, N = 33082.023095.793080.881. (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: CPUabc0.95181.90362.85543.80724.759SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 34.234.224.21MIN: 2.57 / MAX: 14.29MIN: 2.4 / MAX: 13.52MIN: 2.44 / MAX: 13.771. (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: CPUabc400800120016002000SE +/- 1.28, N = 3SE +/- 2.36, N = 3SE +/- 2.78, N = 31883.101887.221891.571. (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: CPUabc10002000300040005000SE +/- 8.16, N = 3SE +/- 7.60, N = 3SE +/- 6.41, N = 34479.954496.754498.331. (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: CPUabc0.5671.1341.7012.2682.835SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 32.522.512.51MIN: 1.27 / MAX: 13.33MIN: 1.26 / MAX: 11.44MIN: 1.25 / MAX: 7.611. (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: CPUabc246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 36.186.176.16MIN: 3.15 / MAX: 15.54MIN: 3.14 / MAX: 14.86MIN: 3.1 / MAX: 15.041. (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: CPUabc70140210280350SE +/- 0.27, N = 3SE +/- 0.51, N = 3SE +/- 0.26, N = 3314.05313.43313.05MIN: 275.97 / MAX: 320.83MIN: 274.87 / MAX: 322.79MIN: 276.27 / MAX: 334.961. (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: CPUabc612182430SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 325.4325.4825.511. (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: CPUabc0.78751.5752.36253.153.9375SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.503.503.49MIN: 1.84 / MAX: 12.79MIN: 1.78 / MAX: 12.34MIN: 1.83 / MAX: 13.541. (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: CPUabc30060090012001500SE +/- 1.63, N = 3SE +/- 1.26, N = 3SE +/- 1.80, N = 31316.131316.731319.501. (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: CPUabc3691215SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 312.1312.1212.10MIN: 6.43 / MAX: 22.51MIN: 6.67 / MAX: 25.3MIN: 6.14 / MAX: 22.631. (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: CPUabc7K14K21K28K35KSE +/- 24.86, N = 3SE +/- 53.39, N = 3SE +/- 8.14, N = 334012.2034014.5734096.411. (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: CPUabc510152025SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 320.8520.9020.86MIN: 13.74 / MAX: 31.31MIN: 13.77 / MAX: 84.15MIN: 14.51 / MAX: 33.161. (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: CPUabc170340510680850SE +/- 1.58, N = 3SE +/- 3.20, N = 3SE +/- 1.63, N = 3765.51763.84765.231. (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: CPUabc6001200180024003000SE +/- 2.84, N = 3SE +/- 2.74, N = 3SE +/- 2.42, N = 32577.452578.492583.011. (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: CPUabc150300450600750SE +/- 2.20, N = 3SE +/- 3.16, N = 3SE +/- 5.94, N = 3711.30710.16711.571. (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: CPUabc510152025SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.19, N = 322.4622.4922.45MIN: 14.61 / MAX: 35.03MIN: 14.38 / MAX: 34.89MIN: 15.95 / MAX: 35.141. (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: CPUabc30060090012001500SE +/- 4.44, N = 3SE +/- 0.27, N = 3SE +/- 2.29, N = 31596.861594.161596.031. (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: CPUabc10K20K30K40K50KSE +/- 65.78, N = 3SE +/- 56.28, N = 3SE +/- 83.63, N = 348218.1448211.9648255.241. (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: CPUabc30060090012001500SE +/- 2.77, N = 3SE +/- 1.35, N = 3SE +/- 1.16, N = 31591.111592.231591.451. (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: CPUabc0.06530.13060.19590.26120.3265SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.290.290.29MIN: 0.16 / MAX: 8.36MIN: 0.16 / MAX: 11.72MIN: 0.16 / MAX: 6.851. (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: CPUabc0.09450.1890.28350.3780.4725SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.420.420.42MIN: 0.21 / MAX: 4.47MIN: 0.21 / MAX: 7.93MIN: 0.21 / MAX: 51. (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: CPUabc3691215SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 39.879.879.87MIN: 6.5 / MAX: 20.17MIN: 5.43 / MAX: 16.47MIN: 5.37 / MAX: 15.941. (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: CPUabc1.12282.24563.36844.49125.614SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 34.994.994.99MIN: 2.85 / MAX: 14.42MIN: 2.8 / MAX: 15.08MIN: 2.65 / MAX: 13.941. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

40 Results Shown

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

a

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203
Python Notes: Python 3.11.6
Security Notes: 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: Vulnerable: Safe RET no microcode + 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 STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 6 March 2024 20:21 by user pts.

b

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203
Python Notes: Python 3.11.6
Security Notes: 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: Vulnerable: Safe RET no microcode + 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 STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 6 March 2024 21:39 by user pts.

c

Processor: AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 16GB DRAM-6000MT/s G Skill F5-6000J3038F16G, Disk: 2000GB Samsung SSD 980 PRO 2TB + 4001GB Western Digital WD_BLACK SN850X 4000GB, Graphics: NVIDIA GeForce RTX 4090 24GB, Audio: NVIDIA AD102 HD Audio, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411

OS: Ubuntu 23.10, Kernel: 6.7.0-060700-generic (x86_64), Desktop: GNOME Shell 45.2, Display Server: X Server 1.21.1.7, Display Driver: NVIDIA 550.54.14, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.4.89, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203
Python Notes: Python 3.11.6
Security Notes: 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: Vulnerable: Safe RET no microcode + 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 STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 6 March 2024 22:52 by user pts.