openvino 2023 ryzen

AMD Ryzen 9 7950X 16-Core testing with a ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS) and AMD Radeon RX 7900 XTX 24GB on Ubuntu 23.04 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 2309298-PTS-OPENVINO16
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
Performance Per
Dollar
Date
Run
  Test
  Duration
a
September 29 2023
  1 Hour, 49 Minutes
b
September 29 2023
  2 Hours, 18 Minutes
c
September 29 2023
  1 Hour, 49 Minutes
d
September 29 2023
  1 Hour, 49 Minutes
Invert Behavior (Only Show Selected Data)
  1 Hour, 56 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-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: performance) - CPU Microcode: 0xa601203
Python Notes: Python 3.11.4
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: Mitigation of 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

d

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: 32GB, Disk: Western Digital WD_BLACK SN850X 1000GB + 4001GB Western Digital WD_BLACK SN850X 4000GB, Graphics: AMD Radeon RX 7900 XTX 24GB (2304/1249MHz), Audio: AMD Device ab30, Monitor: ASUS MG28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411

OS: Ubuntu 23.04, Kernel: 6.6.0-060600rc1daily20230915-generic (x86_64), Desktop: GNOME Shell 44.3, Display Server: X Server 1.21.1.7 + Wayland, OpenGL: 4.6 Mesa 23.3~git2309150600.b73ebc~oibaf~l (git-b73ebc6 2023-09-15 lunar-oibaf-ppa) (LLVM 15.0.7 DRM 3.54), Compiler: GCC 12.3.0, File-System: ext4, Screen Resolution: 3840x2160

openvino 2023 ryzenOpenBenchmarking.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 14d832GBWestern Digital WD_BLACK SN850X 1000GB + 4001GB Western Digital WD_BLACK SN850X 4000GBAMD Radeon RX 7900 XTX 24GB (2304/1249MHz)AMD Device ab30ASUS MG28UIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 23.046.6.0-060600rc1daily20230915-generic (x86_64)GNOME Shell 44.3X Server 1.21.1.7 + Wayland4.6 Mesa 23.3~git2309150600.b73ebc~oibaf~l (git-b73ebc6 2023-09-15 lunar-oibaf-ppa) (LLVM 15.0.7 DRM 3.54)GCC 12.3.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionOpenvino 2023 Ryzen BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: amd-pstate-epp powersave (EPP: performance) - CPU Microcode: 0xa601203- Python 3.11.4- 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: Mitigation of 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

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

openvino 2023 ryzenopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUabcd14.44551.6394.4084.6793.9085.13775.8610.2728.05284.843275.162.35314.1325.381741.104.561461.9710.924856.053.22509.6315.63140.2256.962834.155.61644.974.84754.6321.1736592.000.39638.6425.0251738.410.2714.48550.3895.7383.5295.7383.49777.6610.2428.10284.223283.212.35319.4124.971739.674.561462.5510.924851.363.22513.3715.52141.1656.572832.565.601634.024.87756.9521.1036637.930.39628.8125.4551802.940.2714.45551.8296.3782.9594.2084.83788.4810.1028.06284.723285.232.34315.7325.251742.064.561462.7310.914845.873.22510.0215.62140.7556.742832.555.601637.514.86753.4821.1936618.960.39639.2325.0051736.910.2714.44552.1093.9385.0994.7984.35788.1910.1128.20283.183286.372.35315.5825.271738.354.571463.0210.914861.843.21508.9015.65140.7356.82830.095.601648.164.83752.4121.2336655.670.39644.7224.7851783.420.27OpenBenchmarking.org

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Face Detection FP16 - Device: CPUabcd48121620SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 314.4414.4814.4514.441. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Face Detection FP16 - Device: CPUabcd120240360480600SE +/- 0.68, N = 3SE +/- 1.41, N = 3SE +/- 0.39, N = 3SE +/- 0.06, N = 3551.63550.38551.82552.10MIN: 494.18 / MAX: 577.07MIN: 277.83 / MAX: 573.87MIN: 489.13 / MAX: 574.74MIN: 498.67 / MAX: 579.191. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Person Detection FP16 - Device: CPUabcd20406080100SE +/- 0.59, N = 3SE +/- 0.97, N = 5SE +/- 0.87, N = 3SE +/- 0.42, N = 394.4095.7396.3793.931. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Person Detection FP16 - Device: CPUabcd20406080100SE +/- 0.53, N = 3SE +/- 0.86, N = 5SE +/- 0.74, N = 3SE +/- 0.38, N = 384.6783.5282.9585.09MIN: 57.93 / MAX: 118.94MIN: 55.18 / MAX: 114.03MIN: 63.4 / MAX: 115.79MIN: 57.13 / MAX: 115.961. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Person Detection FP32 - Device: CPUabcd20406080100SE +/- 0.27, N = 3SE +/- 0.60, N = 3SE +/- 0.44, N = 3SE +/- 1.32, N = 393.9095.7394.2094.791. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Person Detection FP32 - Device: CPUabcd20406080100SE +/- 0.24, N = 3SE +/- 0.52, N = 3SE +/- 0.40, N = 3SE +/- 1.15, N = 385.1383.4984.8384.35MIN: 58.25 / MAX: 116.82MIN: 60.81 / MAX: 115.9MIN: 62.75 / MAX: 116.36MIN: 35.39 / MAX: 114.461. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Vehicle Detection FP16 - Device: CPUabcd2004006008001000SE +/- 5.37, N = 3SE +/- 1.96, N = 3SE +/- 4.18, N = 3SE +/- 3.84, N = 3775.86777.66788.48788.191. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Vehicle Detection FP16 - Device: CPUabcd3691215SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 310.2710.2410.1010.11MIN: 3.83 / MAX: 23.02MIN: 3.93 / MAX: 17.98MIN: 3.86 / MAX: 20.61MIN: 4.23 / MAX: 19.81. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Face Detection FP16-INT8 - Device: CPUabcd714212835SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 328.0528.1028.0628.201. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Face Detection FP16-INT8 - Device: CPUabcd60120180240300SE +/- 0.19, N = 3SE +/- 0.46, N = 3SE +/- 0.15, N = 3SE +/- 0.81, N = 3284.84284.22284.72283.18MIN: 272.17 / MAX: 293.27MIN: 272.33 / MAX: 290.91MIN: 253.14 / MAX: 292.23MIN: 148.13 / MAX: 297.231. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Face Detection Retail FP16 - Device: CPUabcd7001400210028003500SE +/- 3.86, N = 3SE +/- 1.36, N = 3SE +/- 3.35, N = 3SE +/- 3.83, N = 33275.163283.213285.233286.371. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Face Detection Retail FP16 - Device: CPUabcd0.52881.05761.58642.11522.644SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.352.352.342.35MIN: 1.23 / MAX: 9.23MIN: 1.23 / MAX: 9.49MIN: 1.23 / MAX: 9.27MIN: 1.24 / MAX: 11.051. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Road Segmentation ADAS FP16 - Device: CPUabcd70140210280350SE +/- 0.83, N = 3SE +/- 3.12, N = 3SE +/- 0.75, N = 3SE +/- 0.82, N = 3314.13319.41315.73315.581. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Road Segmentation ADAS FP16 - Device: CPUabcd612182430SE +/- 0.07, N = 3SE +/- 0.24, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 325.3824.9725.2525.27MIN: 8.89 / MAX: 35.26MIN: 9.41 / MAX: 42.14MIN: 9.11 / MAX: 36.02MIN: 10.71 / MAX: 33.351. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Vehicle Detection FP16-INT8 - Device: CPUabcd400800120016002000SE +/- 4.42, N = 3SE +/- 3.38, N = 3SE +/- 1.78, N = 3SE +/- 0.90, N = 31741.101739.671742.061738.351. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Vehicle Detection FP16-INT8 - Device: CPUabcd1.02832.05663.08494.11325.1415SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34.564.564.564.57MIN: 2.63 / MAX: 13.84MIN: 2.61 / MAX: 12.41MIN: 2.62 / MAX: 12.29MIN: 2.62 / MAX: 12.31. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Weld Porosity Detection FP16 - Device: CPUabcd30060090012001500SE +/- 0.32, N = 3SE +/- 0.07, N = 3SE +/- 0.42, N = 3SE +/- 0.14, N = 31461.971462.551462.731463.021. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Weld Porosity Detection FP16 - Device: CPUabcd3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 310.9210.9210.9110.91MIN: 5.58 / MAX: 19.13MIN: 5.73 / MAX: 22.33MIN: 6.03 / MAX: 18.7MIN: 5.64 / MAX: 18.961. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Face Detection Retail FP16-INT8 - Device: CPUabcd10002000300040005000SE +/- 6.39, N = 3SE +/- 11.64, N = 3SE +/- 12.42, N = 3SE +/- 9.80, N = 34856.054851.364845.874861.841. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Face Detection Retail FP16-INT8 - Device: CPUabcd0.72451.4492.17352.8983.6225SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.223.223.223.21MIN: 1.78 / MAX: 10.8MIN: 1.8 / MAX: 10.48MIN: 1.8 / MAX: 10.23MIN: 1.79 / MAX: 10.711. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Road Segmentation ADAS FP16-INT8 - Device: CPUabcd110220330440550SE +/- 1.73, N = 3SE +/- 3.27, N = 3SE +/- 2.09, N = 3SE +/- 1.95, N = 3509.63513.37510.02508.901. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Road Segmentation ADAS FP16-INT8 - Device: CPUabcd48121620SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 315.6315.5215.6215.65MIN: 8.4 / MAX: 22.84MIN: 8.31 / MAX: 21.58MIN: 8.29 / MAX: 22.27MIN: 8.48 / MAX: 22.91. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Machine Translation EN To DE FP16 - Device: CPUabcd306090120150SE +/- 0.07, N = 3SE +/- 0.51, N = 3SE +/- 0.19, N = 3SE +/- 0.32, N = 3140.22141.16140.75140.731. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Machine Translation EN To DE FP16 - Device: CPUabcd1326395265SE +/- 0.03, N = 3SE +/- 0.20, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 356.9656.5756.7456.80MIN: 30.93 / MAX: 74.12MIN: 27.28 / MAX: 65.55MIN: 26.01 / MAX: 65.6MIN: 33.66 / MAX: 70.031. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Weld Porosity Detection FP16-INT8 - Device: CPUabcd6001200180024003000SE +/- 0.44, N = 3SE +/- 1.40, N = 3SE +/- 1.63, N = 3SE +/- 2.25, N = 32834.152832.562832.552830.091. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Weld Porosity Detection FP16-INT8 - Device: CPUabcd1.262.523.785.046.3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 35.605.605.605.60MIN: 2.92 / MAX: 13.06MIN: 2.92 / MAX: 12.76MIN: 2.93 / MAX: 13.03MIN: 2.92 / MAX: 12.351. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Person Vehicle Bike Detection FP16 - Device: CPUabcd400800120016002000SE +/- 8.79, N = 3SE +/- 0.66, N = 3SE +/- 3.33, N = 3SE +/- 3.31, N = 31644.971634.021637.511648.161. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Person Vehicle Bike Detection FP16 - Device: CPUabcd1.09582.19163.28744.38325.479SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 34.844.874.864.83MIN: 3.28 / MAX: 13.19MIN: 3.19 / MAX: 12.27MIN: 3.2 / MAX: 16.94MIN: 3.16 / MAX: 12.351. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Handwritten English Recognition FP16 - Device: CPUabcd160320480640800SE +/- 4.96, N = 3SE +/- 1.00, N = 3SE +/- 1.25, N = 3SE +/- 3.65, N = 3754.63756.95753.48752.411. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Handwritten English Recognition FP16 - Device: CPUabcd510152025SE +/- 0.14, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 321.1721.1021.1921.23MIN: 12.98 / MAX: 34.35MIN: 13.13 / MAX: 31.96MIN: 15.94 / MAX: 31.78MIN: 13.16 / MAX: 31.241. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUabcd8K16K24K32K40KSE +/- 42.09, N = 3SE +/- 35.30, N = 3SE +/- 25.78, N = 3SE +/- 29.05, N = 336592.0036637.9336618.9636655.671. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUabcd0.08780.17560.26340.35120.439SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.390.390.390.39MIN: 0.2 / MAX: 7.21MIN: 0.2 / MAX: 6.72MIN: 0.2 / MAX: 6.68MIN: 0.2 / MAX: 7.131. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Handwritten English Recognition FP16-INT8 - Device: CPUabcd140280420560700SE +/- 1.40, N = 3SE +/- 6.41, N = 15SE +/- 2.06, N = 3SE +/- 1.78, N = 3638.64628.81639.23644.721. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Handwritten English Recognition FP16-INT8 - Device: CPUabcd612182430SE +/- 0.06, N = 3SE +/- 0.27, N = 15SE +/- 0.08, N = 3SE +/- 0.07, N = 325.0225.4525.0024.78MIN: 16.53 / MAX: 35.6MIN: 16.19 / MAX: 35.92MIN: 16.35 / MAX: 34.49MIN: 16.23 / MAX: 33.371. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUabcd11K22K33K44K55KSE +/- 15.29, N = 3SE +/- 90.98, N = 3SE +/- 62.15, N = 3SE +/- 111.48, N = 351738.4151802.9451736.9151783.421. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUabcd0.06080.12160.18240.24320.304SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.270.270.270.27MIN: 0.15 / MAX: 6.43MIN: 0.15 / MAX: 7.1MIN: 0.15 / MAX: 6.59MIN: 0.15 / MAX: 6.591. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

36 Results Shown

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

a

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: performance) - CPU Microcode: 0xa601203
Python Notes: Python 3.11.4
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: Mitigation of 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 29 September 2023 10:16 by user pts.

b

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: performance) - CPU Microcode: 0xa601203
Python Notes: Python 3.11.4
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: Mitigation of 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 29 September 2023 11:39 by user pts.

c

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: performance) - CPU Microcode: 0xa601203
Python Notes: Python 3.11.4
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: Mitigation of 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 29 September 2023 12:54 by user pts.

d

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: 32GB, Disk: Western Digital WD_BLACK SN850X 1000GB + 4001GB Western Digital WD_BLACK SN850X 4000GB, Graphics: AMD Radeon RX 7900 XTX 24GB (2304/1249MHz), Audio: AMD Device ab30, Monitor: ASUS MG28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411

OS: Ubuntu 23.04, Kernel: 6.6.0-060600rc1daily20230915-generic (x86_64), Desktop: GNOME Shell 44.3, Display Server: X Server 1.21.1.7 + Wayland, OpenGL: 4.6 Mesa 23.3~git2309150600.b73ebc~oibaf~l (git-b73ebc6 2023-09-15 lunar-oibaf-ppa) (LLVM 15.0.7 DRM 3.54), Compiler: GCC 12.3.0, 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-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: performance) - CPU Microcode: 0xa601203
Python Notes: Python 3.11.4
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: Mitigation of 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 29 September 2023 13:55 by user pts.