openvino nvidia grace

ARMv8 Neoverse-V2 testing with a Pegatron JIMBO P4352 (00022432 BIOS) and ASPEED on Ubuntu 24.04 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 2411240-NE-OPENVINON15
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
November 24
  3 Hours, 33 Minutes
b
November 24
  1 Hour, 4 Minutes
c
November 24
  1 Hour, 4 Minutes
d
November 24
  1 Hour, 4 Minutes
Invert Behavior (Only Show Selected Data)
  1 Hour, 41 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=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-dIwDw0/gcc-13-13.2.0/debian/tmp-nvptx/usr --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto --without-cuda-driver -v
Processor Notes: Scaling Governor: cppc_cpufreq ondemand (Boost: Disabled)
Python Notes: Python 3.12.6
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 + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

b

c

d

Processor: ARMv8 Neoverse-V2 @ 3.47GHz (72 Cores), Motherboard: Pegatron JIMBO P4352 (00022432 BIOS), Memory: 1 x 480GB LPDDR5-6400MT/s NVIDIA 699-2G530-0236-RC1, Disk: 1000GB CT1000T700SSD3, Graphics: ASPEED, Network: 2 x Intel X550

OS: Ubuntu 24.04, Kernel: 6.8.0-49-generic-64k (aarch64), Compiler: GCC 13.2.0 + Clang 18.1.3 + CUDA 11.8, File-System: ext4, Screen Resolution: 1920x1200

openvino nvidia graceOpenBenchmarking.orgPhoronix Test SuiteARMv8 Neoverse-V2 @ 3.47GHz (72 Cores)Pegatron JIMBO P4352 (00022432 BIOS)1 x 480GB LPDDR5-6400MT/s NVIDIA 699-2G530-0236-RC11000GB CT1000T700SSD3ASPEED2 x Intel X550Ubuntu 24.046.8.0-49-generic-64k (aarch64)GCC 13.2.0 + Clang 18.1.3 + CUDA 11.8ext41920x1200ProcessorMotherboardMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen ResolutionOpenvino Nvidia Grace BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-dIwDw0/gcc-13-13.2.0/debian/tmp-nvptx/usr --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto --without-cuda-driver -v - Scaling Governor: cppc_cpufreq ondemand (Boost: Disabled)- Python 3.12.6- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

abcdResult OverviewPhoronix Test Suite100%109%117%126%135%OpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINO GenAIOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINO GenAIOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINO GenAIOpenVINOOpenVINOOpenVINO GenAIOpenVINOOpenVINOOpenVINOOpenVINO GenAIOpenVINO GenAIOpenVINO GenAIOpenVINO GenAIOpenVINO GenAIOpenVINO GenAIOpenVINO GenAIOpenVINO GenAIM.T.E.T.D.F - CPUM.T.E.T.D.F - CPUV.D.F - CPUV.D.F - CPUH.E.R.F - CPUH.E.R.F - CPUF.D.R.F.I - CPUF.D.R.F.I - CPUTinyLlama-1.1B-Chat-v1.0 - CPUN.S.P.L.F - CPUN.S.P.L.F - CPUR.S.A.F - CPUR.S.A.F - CPUW.P.D.F.I - CPUW.P.D.F.I - CPUP.D.F - CPUF.D.F - CPUP.D.F - CPUV.D.F.I - CPUA.G.R.R.0.F.I - CPUA.G.R.R.0.F.I - CPUF.D.F - CPUV.D.F.I - CPUH.E.R.F.I - CPUGemma-7b-int4-ov - CPUP.R.I.R.F - CPUP.R.I.R.F - CPUH.E.R.F.I - CPUP.D.F - CPUW.P.D.F - CPUP.D.F - CPUW.P.D.F - CPUF.D.F.I - CPUR.S.A.F.I - CPUF.D.R.F - CPUF.D.F.I - CPUF.D.R.F - CPUFalcon-7b-instruct-int4-ov - CPUA.G.R.R.0.F - CPUA.G.R.R.0.F - CPUPhi-3-mini-128k-instruct-int4-ov - CPUR.S.A.F.I - CPUP.V.B.D.F - CPUP.V.B.D.F - CPUGemma-7b-int4-ov - CPU - T.T.F.TGemma-7b-int4-ov - CPU - T.P.O.TTinyLlama-1.1B-Chat-v1.0 - CPU - T.T.F.TTinyLlama-1.1B-Chat-v1.0 - CPU - T.P.O.TFalcon-7b-instruct-int4-ov - CPU - T.T.F.TFalcon-7b-instruct-int4-ov - CPU - T.P.O.TPhi-3-mini-128k-instruct-int4-ov - CPU - T.T.F.TPhi-3-mini-128k-instruct-int4-ov - CPU - T.P.O.T

openvino nvidia graceopenvino: 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: Noise Suppression Poconet-Like FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Person Re-Identification Retail 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 - CPUopenvino-genai: Gemma-7b-int4-ov - CPUopenvino-genai: Gemma-7b-int4-ov - CPU - Time To First Tokenopenvino-genai: Gemma-7b-int4-ov - CPU - Time Per Output Tokenopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPUopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time To First Tokenopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time Per Output Tokenopenvino-genai: Falcon-7b-instruct-int4-ov - CPUopenvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time To First Tokenopenvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time Per Output Tokenopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPUopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time To First Tokenopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time Per Output Tokenabcd1.5211430.977.412411.487.452395.8056.57319.461.4312201.72148.41121.1023.67758.8048.08373.2273.61243.99243.7473.7912.811390.97291.6061.6874.32241.68123.10146.01260.4769.0459.29302.9481.55220.28365.7349.1462.80286.07368.6348.7512.0995.0382.7654.9927.9018.1916.5971.8860.2921.5559.8146.401.5211436.57.342437.97.52378.3351.71347.471.4412086.33147.65121.7323.46765.1448.33371.0473.3244.99247.3472.7112.811396.38216.2883.1574.42241.43122.96146.14252.6771.1858.09308.9681.93219.24365.749.1562.64286.88366.3649.0611.9395.9583.8354.9328.0318.216.5772.1760.3621.4659.5146.591.5511238.097.482385.097.462391.0258.55306.891.4412178.49148.02121.4123.81753.9347.52377.9672.75246.92234.6976.6212.771394.95290.5761.8474.63240.74122.93146.21255.6270.3757.5312.4381.75219.68367.7848.8662.93285.46372.9948.1811.9695.8483.6354.1628.1718.4616.5272.460.5521.5559.5946.411.5311360.467.42410.597.412406.8251.73347.41.4312191.22148.66120.8823.18774.0847.81375.4473.48244.38245.2473.3112.831385.22273.7765.6776.19235.84123.43145.61255.6970.3464.04280.2182.57217.55366.5149.0363.41283367.5548.911.9595.6883.7153.2227.9618.7916.4871.8960.6721.5759.646.36OpenBenchmarking.org

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection FP16 - Device: CPUabcd0.34880.69761.04641.39521.744SE +/- 0.01, N = 31.521.521.551.531. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection FP16 - Device: CPUabcd2K4K6K8K10KSE +/- 39.37, N = 311430.9711436.5011238.0911360.46MIN: 3209.44 / MAX: 19663.24MIN: 3430.48 / MAX: 20189.78MIN: 5742.34 / MAX: 19334.45MIN: 6102.91 / MAX: 19090.481. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Detection FP16 - Device: CPUabcd246810SE +/- 0.02, N = 37.417.347.487.401. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Detection FP16 - Device: CPUabcd5001000150020002500SE +/- 5.77, N = 32411.482437.902385.092410.59MIN: 763.2 / MAX: 3338.48MIN: 587.9 / MAX: 3435.18MIN: 815.84 / MAX: 3303.13MIN: 1535.46 / MAX: 3065.841. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Detection FP32 - Device: CPUabcd246810SE +/- 0.04, N = 37.457.507.467.411. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Detection FP32 - Device: CPUabcd5001000150020002500SE +/- 15.17, N = 32395.802378.332391.022406.82MIN: 514.36 / MAX: 3227.94MIN: 553.69 / MAX: 3334.97MIN: 1068.09 / MAX: 3172.91MIN: 1255.43 / MAX: 3054.491. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16 - Device: CPUabcd1326395265SE +/- 1.32, N = 1256.5751.7158.5551.731. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16 - Device: CPUabcd80160240320400SE +/- 7.20, N = 12319.46347.47306.89347.40MIN: 12.87 / MAX: 660.92MIN: 9.85 / MAX: 544.66MIN: 27.01 / MAX: 564.14MIN: 55.22 / MAX: 587.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection FP16-INT8 - Device: CPUabcd0.3240.6480.9721.2961.62SE +/- 0.00, N = 31.431.441.441.431. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection FP16-INT8 - Device: CPUabcd3K6K9K12K15KSE +/- 27.56, N = 312201.7212086.3312178.4912191.22MIN: 5788.57 / MAX: 22002.02MIN: 6158.01 / MAX: 21075.66MIN: 5513.62 / MAX: 21855.35MIN: 5960.92 / MAX: 21866.141. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16 - Device: CPUabcd306090120150SE +/- 0.09, N = 3148.41147.65148.02148.661. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16 - Device: CPUabcd306090120150SE +/- 0.07, N = 3121.10121.73121.41120.88MIN: 3.57 / MAX: 304.56MIN: 4.35 / MAX: 307.93MIN: 3.77 / MAX: 313.66MIN: 4.17 / MAX: 314.741. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16 - Device: CPUabcd612182430SE +/- 0.32, N = 323.6723.4623.8123.181. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16 - Device: CPUabcd170340510680850SE +/- 10.24, N = 3758.80765.14753.93774.08MIN: 66.48 / MAX: 1151.73MIN: 182.49 / MAX: 1221.24MIN: 204.49 / MAX: 1033.25MIN: 188.37 / MAX: 1012.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16-INT8 - Device: CPUabcd1122334455SE +/- 0.07, N = 348.0848.3347.5247.811. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16-INT8 - Device: CPUabcd80160240320400SE +/- 0.53, N = 3373.22371.04377.96375.44MIN: 220.53 / MAX: 676.17MIN: 243.96 / MAX: 665.67MIN: 221.69 / MAX: 694.21MIN: 217.44 / MAX: 655.751. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16 - Device: CPUabcd1632486480SE +/- 0.36, N = 373.6173.3072.7573.481. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16 - Device: CPUabcd50100150200250SE +/- 1.14, N = 3243.99244.99246.92244.38MIN: 5.42 / MAX: 1283.25MIN: 5.59 / MAX: 1049.25MIN: 5.21 / MAX: 971.95MIN: 5.51 / MAX: 1241.971. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16-INT8 - Device: CPUabcd50100150200250SE +/- 2.87, N = 4243.74247.34234.69245.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16-INT8 - Device: CPUabcd20406080100SE +/- 0.89, N = 473.7972.7176.6273.31MIN: 44.4 / MAX: 244.01MIN: 45.7 / MAX: 196.72MIN: 45.48 / MAX: 203.39MIN: 46.02 / MAX: 195.641. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16-INT8 - Device: CPUabcd3691215SE +/- 0.04, N = 312.8112.8112.7712.831. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16-INT8 - Device: CPUabcd30060090012001500SE +/- 3.45, N = 31390.971396.381394.951385.22MIN: 1063.67 / MAX: 2197.21MIN: 1109.87 / MAX: 2180.03MIN: 1054.18 / MAX: 2367.21MIN: 1052.83 / MAX: 2150.81. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Machine Translation EN To DE FP16 - Device: CPUabcd60120180240300SE +/- 0.56, N = 3291.60216.28290.57273.771. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Machine Translation EN To DE FP16 - Device: CPUabcd20406080100SE +/- 0.11, N = 361.6883.1561.8465.67MIN: 51.21 / MAX: 547.97MIN: 51.94 / MAX: 546.99MIN: 51.77 / MAX: 255.72MIN: 51.78 / MAX: 491.381. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16-INT8 - Device: CPUabcd20406080100SE +/- 0.22, N = 374.3274.4274.6376.191. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16-INT8 - Device: CPUabcd50100150200250SE +/- 0.72, N = 3241.68241.43240.74235.84MIN: 19.65 / MAX: 1162.43MIN: 20.7 / MAX: 1204.39MIN: 22.5 / MAX: 1191.14MIN: 20.26 / MAX: 1010.021. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Vehicle Bike Detection FP16 - Device: CPUabcd306090120150SE +/- 0.18, N = 3123.10122.96122.93123.431. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Vehicle Bike Detection FP16 - Device: CPUabcd306090120150SE +/- 0.21, N = 3146.01146.14146.21145.61MIN: 19.5 / MAX: 360.82MIN: 21.38 / MAX: 302.73MIN: 19.85 / MAX: 278.01MIN: 19.49 / MAX: 2861. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Noise Suppression Poconet-Like FP16 - Device: CPUabcd60120180240300SE +/- 0.34, N = 3260.47252.67255.62255.691. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Noise Suppression Poconet-Like FP16 - Device: CPUabcd1632486480SE +/- 0.09, N = 369.0471.1870.3770.34MIN: 47.41 / MAX: 489.69MIN: 49.75 / MAX: 457.8MIN: 61.14 / MAX: 440.12MIN: 49.66 / MAX: 429.381. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16 - Device: CPUabcd1428425670SE +/- 0.65, N = 459.2958.0957.5064.041. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16 - Device: CPUabcd70140210280350SE +/- 3.32, N = 4302.94308.96312.43280.21MIN: 125.62 / MAX: 561.81MIN: 128.04 / MAX: 564.2MIN: 125.63 / MAX: 595.88MIN: 120.84 / MAX: 568.861. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Re-Identification Retail FP16 - Device: CPUabcd20406080100SE +/- 0.09, N = 381.5581.9381.7582.571. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Re-Identification Retail FP16 - Device: CPUabcd50100150200250SE +/- 0.26, N = 3220.28219.24219.68217.55MIN: 7.32 / MAX: 545.95MIN: 7.81 / MAX: 428.59MIN: 7.81 / MAX: 495.32MIN: 7.61 / MAX: 439.281. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUabcd80160240320400SE +/- 0.84, N = 3365.73365.70367.78366.511. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUabcd1122334455SE +/- 0.11, N = 349.1449.1548.8649.03MIN: 0.58 / MAX: 577.11MIN: 0.54 / MAX: 489.68MIN: 0.55 / MAX: 310.19MIN: 0.62 / MAX: 319.491. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16-INT8 - Device: CPUabcd1428425670SE +/- 0.38, N = 362.8062.6462.9363.411. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16-INT8 - Device: CPUabcd60120180240300SE +/- 1.74, N = 3286.07286.88285.46283.00MIN: 149.3 / MAX: 594.08MIN: 148.33 / MAX: 535.79MIN: 156.24 / MAX: 611.64MIN: 146.7 / MAX: 520.891. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUabcd80160240320400SE +/- 0.64, N = 3368.63366.36372.99367.551. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUabcd1122334455SE +/- 0.08, N = 348.7549.0648.1848.90MIN: 0.9 / MAX: 633.89MIN: 0.94 / MAX: 610.85MIN: 0.97 / MAX: 515.24MIN: 0.95 / MAX: 611.441. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO GenAI

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPUabcd3691215SE +/- 0.13, N = 312.0911.9311.9611.95
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPU - Time To First Tokenabcd20406080100SE +/- 0.71, N = 395.0395.9595.8495.68
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Tokenabcd20406080100SE +/- 0.90, N = 382.7683.8383.6383.71

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPUabcd1224364860SE +/- 0.33, N = 354.9954.9354.1653.22
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Tokenabcd714212835SE +/- 0.05, N = 327.9028.0328.1727.96
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Tokenabcd510152025SE +/- 0.11, N = 318.1918.2018.4618.79

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Falcon-7b-instruct-int4-ov - Device: CPUabcd48121620SE +/- 0.02, N = 316.5916.5716.5216.48
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Tokenabcd1632486480SE +/- 0.12, N = 371.8872.1772.4071.89
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Tokenabcd1428425670SE +/- 0.08, N = 360.2960.3660.5560.67

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPUabcd510152025SE +/- 0.04, N = 321.5521.4621.5521.57
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Tokenabcd1326395265SE +/- 0.15, N = 359.8159.5159.5959.60
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Tokenabcd1122334455SE +/- 0.09, N = 346.4046.5946.4146.36

44 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
  Noise Suppression Poconet-Like FP16 - CPU:
    FPS
    ms
  Handwritten English Recognition FP16 - CPU:
    FPS
    ms
  Person Re-Identification Retail 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
OpenVINO GenAI:
  Gemma-7b-int4-ov - CPU
  TinyLlama-1.1B-Chat-v1.0 - CPU
  Falcon-7b-instruct-int4-ov - CPU
  Phi-3-mini-128k-instruct-int4-ov - CPU

a

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-dIwDw0/gcc-13-13.2.0/debian/tmp-nvptx/usr --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto --without-cuda-driver -v
Processor Notes: Scaling Governor: cppc_cpufreq ondemand (Boost: Disabled)
Python Notes: Python 3.12.6
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 + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 24 November 2024 14:36 by user x.

b

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-dIwDw0/gcc-13-13.2.0/debian/tmp-nvptx/usr --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto --without-cuda-driver -v
Processor Notes: Scaling Governor: cppc_cpufreq ondemand (Boost: Disabled)
Python Notes: Python 3.12.6
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 + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 24 November 2024 16:33 by user x.

c

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-dIwDw0/gcc-13-13.2.0/debian/tmp-nvptx/usr --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto --without-cuda-driver -v
Processor Notes: Scaling Governor: cppc_cpufreq ondemand (Boost: Disabled)
Python Notes: Python 3.12.6
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 + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 24 November 2024 17:07 by user x.

d

Processor: ARMv8 Neoverse-V2 @ 3.47GHz (72 Cores), Motherboard: Pegatron JIMBO P4352 (00022432 BIOS), Memory: 1 x 480GB LPDDR5-6400MT/s NVIDIA 699-2G530-0236-RC1, Disk: 1000GB CT1000T700SSD3, Graphics: ASPEED, Network: 2 x Intel X550

OS: Ubuntu 24.04, Kernel: 6.8.0-49-generic-64k (aarch64), Compiler: GCC 13.2.0 + Clang 18.1.3 + CUDA 11.8, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-dIwDw0/gcc-13-13.2.0/debian/tmp-nvptx/usr --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto --without-cuda-driver -v
Processor Notes: Scaling Governor: cppc_cpufreq ondemand (Boost: Disabled)
Python Notes: Python 3.12.6
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 + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 24 November 2024 17:43 by user x.