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.

HTML result view exported from: https://openbenchmarking.org/result/2411240-NE-OPENVINON15&sor&grw.

openvino nvidia graceProcessorMotherboardMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen ResolutionabcdARMv8 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 11.8ext41920x1200OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --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 Details- Scaling Governor: cppc_cpufreq ondemand (Boost: Disabled)Python Details- Python 3.12.6Security Details- 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

openvino nvidia graceopenvino-genai: Gemma-7b-int4-ov - CPUopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPUopenvino-genai: Falcon-7b-instruct-int4-ov - CPUopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPUopenvino: 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 - CPU - Time To First Tokenopenvino-genai: Gemma-7b-int4-ov - CPU - Time Per Output Tokenopenvino-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 - CPU - Time To First Tokenopenvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time Per Output Tokenopenvino-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 Tokenabcd12.0954.9916.5921.551.5211430.977.412411.487.452395.8056.57319.461.4312201.72148.41121.1023.67758.8048.08373.2273.61243.99243.7473.7912.811390.97291.6061.6874.32241.68123.10146.01260.4769.0459.29302.9481.55220.28365.7349.1462.80286.07368.6348.7595.0382.7627.9018.1971.8860.2959.8146.4011.9354.9316.5721.461.5211436.57.342437.97.52378.3351.71347.471.4412086.33147.65121.7323.46765.1448.33371.0473.3244.99247.3472.7112.811396.38216.2883.1574.42241.43122.96146.14252.6771.1858.09308.9681.93219.24365.749.1562.64286.88366.3649.0695.9583.8328.0318.272.1760.3659.5146.5911.9654.1616.5221.551.5511238.097.482385.097.462391.0258.55306.891.4412178.49148.02121.4123.81753.9347.52377.9672.75246.92234.6976.6212.771394.95290.5761.8474.63240.74122.93146.21255.6270.3757.5312.4381.75219.68367.7848.8662.93285.46372.9948.1895.8483.6328.1718.4672.460.5559.5946.4111.9553.2216.4821.571.5311360.467.42410.597.412406.8251.73347.41.4312191.22148.66120.8823.18774.0847.81375.4473.48244.38245.2473.3112.831385.22273.7765.6776.19235.84123.43145.61255.6970.3464.04280.2182.57217.55366.5149.0363.41283367.5548.995.6883.7127.9618.7971.8960.6759.646.36OpenBenchmarking.org

OpenVINO GenAI

Model: Gemma-7b-int4-ov - Device: CPU

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPUacdb3691215SE +/- 0.13, N = 312.0911.9611.9511.93

OpenVINO GenAI

Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU

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

OpenVINO GenAI

Model: Falcon-7b-instruct-int4-ov - Device: CPU

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Falcon-7b-instruct-int4-ov - Device: CPUabcd48121620SE +/- 0.02, N = 316.5916.5716.5216.48

OpenVINO GenAI

Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPUdcab510152025SE +/- 0.04, N = 321.5721.5521.5521.46

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection FP16 - Device: CPUcdba0.34880.69761.04641.39521.744SE +/- 0.01, N = 31.551.531.521.521. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection FP16 - Device: CPUcdab2K4K6K8K10KSE +/- 39.37, N = 311238.0911360.4611430.9711436.50MIN: 5742.34 / MAX: 19334.45MIN: 6102.91 / MAX: 19090.48MIN: 3209.44 / MAX: 19663.24MIN: 3430.48 / MAX: 20189.781. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Detection FP16 - Device: CPUcadb246810SE +/- 0.02, N = 37.487.417.407.341. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Detection FP16 - Device: CPUcdab5001000150020002500SE +/- 5.77, N = 32385.092410.592411.482437.90MIN: 815.84 / MAX: 3303.13MIN: 1535.46 / MAX: 3065.84MIN: 763.2 / MAX: 3338.48MIN: 587.9 / MAX: 3435.181. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Detection FP32 - Device: CPUbcad246810SE +/- 0.04, N = 37.507.467.457.411. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Detection FP32 - Device: CPUbcad5001000150020002500SE +/- 15.17, N = 32378.332391.022395.802406.82MIN: 553.69 / MAX: 3334.97MIN: 1068.09 / MAX: 3172.91MIN: 514.36 / MAX: 3227.94MIN: 1255.43 / MAX: 3054.491. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16 - Device: CPUcadb1326395265SE +/- 1.32, N = 1258.5556.5751.7351.711. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16 - Device: CPUcadb80160240320400SE +/- 7.20, N = 12306.89319.46347.40347.47MIN: 27.01 / MAX: 564.14MIN: 12.87 / MAX: 660.92MIN: 55.22 / MAX: 587.24MIN: 9.85 / MAX: 544.661. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection FP16-INT8 - Device: CPUcbda0.3240.6480.9721.2961.62SE +/- 0.00, N = 31.441.441.431.431. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection FP16-INT8 - Device: CPUbcda3K6K9K12K15KSE +/- 27.56, N = 312086.3312178.4912191.2212201.72MIN: 6158.01 / MAX: 21075.66MIN: 5513.62 / MAX: 21855.35MIN: 5960.92 / MAX: 21866.14MIN: 5788.57 / MAX: 22002.021. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection Retail FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16 - Device: CPUdacb306090120150SE +/- 0.09, N = 3148.66148.41148.02147.651. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection Retail FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16 - Device: CPUdacb306090120150SE +/- 0.07, N = 3120.88121.10121.41121.73MIN: 4.17 / MAX: 314.74MIN: 3.57 / MAX: 304.56MIN: 3.77 / MAX: 313.66MIN: 4.35 / MAX: 307.931. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Road Segmentation ADAS FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16 - Device: CPUcabd612182430SE +/- 0.32, N = 323.8123.6723.4623.181. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Road Segmentation ADAS FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16 - Device: CPUcabd170340510680850SE +/- 10.24, N = 3753.93758.80765.14774.08MIN: 204.49 / MAX: 1033.25MIN: 66.48 / MAX: 1151.73MIN: 182.49 / MAX: 1221.24MIN: 188.37 / MAX: 1012.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16-INT8 - Device: CPUbadc1122334455SE +/- 0.07, N = 348.3348.0847.8147.521. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16-INT8 - Device: CPUbadc80160240320400SE +/- 0.53, N = 3371.04373.22375.44377.96MIN: 243.96 / MAX: 665.67MIN: 220.53 / MAX: 676.17MIN: 217.44 / MAX: 655.75MIN: 221.69 / MAX: 694.211. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16 - Device: CPUadbc1632486480SE +/- 0.36, N = 373.6173.4873.3072.751. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16 - Device: CPUadbc50100150200250SE +/- 1.14, N = 3243.99244.38244.99246.92MIN: 5.42 / MAX: 1283.25MIN: 5.51 / MAX: 1241.97MIN: 5.59 / MAX: 1049.25MIN: 5.21 / MAX: 971.951. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection Retail FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16-INT8 - Device: CPUbdac50100150200250SE +/- 2.87, N = 4247.34245.24243.74234.691. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection Retail FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16-INT8 - Device: CPUbdac20406080100SE +/- 0.89, N = 472.7173.3173.7976.62MIN: 45.7 / MAX: 196.72MIN: 46.02 / MAX: 195.64MIN: 44.4 / MAX: 244.01MIN: 45.48 / MAX: 203.391. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Road Segmentation ADAS FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16-INT8 - Device: CPUdbac3691215SE +/- 0.04, N = 312.8312.8112.8112.771. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Road Segmentation ADAS FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16-INT8 - Device: CPUdacb30060090012001500SE +/- 3.45, N = 31385.221390.971394.951396.38MIN: 1052.83 / MAX: 2150.8MIN: 1063.67 / MAX: 2197.21MIN: 1054.18 / MAX: 2367.21MIN: 1109.87 / MAX: 2180.031. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Machine Translation EN To DE FP16 - Device: CPUacdb60120180240300SE +/- 0.56, N = 3291.60290.57273.77216.281. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Machine Translation EN To DE FP16 - Device: CPUacdb20406080100SE +/- 0.11, N = 361.6861.8465.6783.15MIN: 51.21 / MAX: 547.97MIN: 51.77 / MAX: 255.72MIN: 51.78 / MAX: 491.38MIN: 51.94 / MAX: 546.991. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16-INT8 - Device: CPUdcba20406080100SE +/- 0.22, N = 376.1974.6374.4274.321. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16-INT8 - Device: CPUdcba50100150200250SE +/- 0.72, N = 3235.84240.74241.43241.68MIN: 20.26 / MAX: 1010.02MIN: 22.5 / MAX: 1191.14MIN: 20.7 / MAX: 1204.39MIN: 19.65 / MAX: 1162.431. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Vehicle Bike Detection FP16 - Device: CPUdabc306090120150SE +/- 0.18, N = 3123.43123.10122.96122.931. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Vehicle Bike Detection FP16 - Device: CPUdabc306090120150SE +/- 0.21, N = 3145.61146.01146.14146.21MIN: 19.49 / MAX: 286MIN: 19.5 / MAX: 360.82MIN: 21.38 / MAX: 302.73MIN: 19.85 / MAX: 278.011. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Noise Suppression Poconet-Like FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Noise Suppression Poconet-Like FP16 - Device: CPUadcb60120180240300SE +/- 0.34, N = 3260.47255.69255.62252.671. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Noise Suppression Poconet-Like FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Noise Suppression Poconet-Like FP16 - Device: CPUadcb1632486480SE +/- 0.09, N = 369.0470.3470.3771.18MIN: 47.41 / MAX: 489.69MIN: 49.66 / MAX: 429.38MIN: 61.14 / MAX: 440.12MIN: 49.75 / MAX: 457.81. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Handwritten English Recognition FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16 - Device: CPUdabc1428425670SE +/- 0.65, N = 464.0459.2958.0957.501. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Handwritten English Recognition FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16 - Device: CPUdabc70140210280350SE +/- 3.32, N = 4280.21302.94308.96312.43MIN: 120.84 / MAX: 568.86MIN: 125.62 / MAX: 561.81MIN: 128.04 / MAX: 564.2MIN: 125.63 / MAX: 595.881. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Re-Identification Retail FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Re-Identification Retail FP16 - Device: CPUdbca20406080100SE +/- 0.09, N = 382.5781.9381.7581.551. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Re-Identification Retail FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Re-Identification Retail FP16 - Device: CPUdbca50100150200250SE +/- 0.26, N = 3217.55219.24219.68220.28MIN: 7.61 / MAX: 439.28MIN: 7.81 / MAX: 428.59MIN: 7.81 / MAX: 495.32MIN: 7.32 / MAX: 545.951. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUcdab80160240320400SE +/- 0.84, N = 3367.78366.51365.73365.701. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUcdab1122334455SE +/- 0.11, N = 348.8649.0349.1449.15MIN: 0.55 / MAX: 310.19MIN: 0.62 / MAX: 319.49MIN: 0.58 / MAX: 577.11MIN: 0.54 / MAX: 489.681. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Handwritten English Recognition FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16-INT8 - Device: CPUdcab1428425670SE +/- 0.38, N = 363.4162.9362.8062.641. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Handwritten English Recognition FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16-INT8 - Device: CPUdcab60120180240300SE +/- 1.74, N = 3283.00285.46286.07286.88MIN: 146.7 / MAX: 520.89MIN: 156.24 / MAX: 611.64MIN: 149.3 / MAX: 594.08MIN: 148.33 / MAX: 535.791. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUcadb80160240320400SE +/- 0.64, N = 3372.99368.63367.55366.361. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUcadb1122334455SE +/- 0.08, N = 348.1848.7548.9049.06MIN: 0.97 / MAX: 515.24MIN: 0.9 / MAX: 633.89MIN: 0.95 / MAX: 611.44MIN: 0.94 / MAX: 610.851. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO GenAI

Model: Gemma-7b-int4-ov - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPU - Time To First Tokenadcb20406080100SE +/- 0.71, N = 395.0395.6895.8495.95

OpenVINO GenAI

Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Tokenacdb20406080100SE +/- 0.90, N = 382.7683.6383.7183.83

OpenVINO GenAI

Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Tokenadbc714212835SE +/- 0.05, N = 327.9027.9628.0328.17

OpenVINO GenAI

Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Token

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

OpenVINO GenAI

Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Tokenadbc1632486480SE +/- 0.12, N = 371.8871.8972.1772.40

OpenVINO GenAI

Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Token

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

OpenVINO GenAI

Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Tokenbcda1326395265SE +/- 0.15, N = 359.5159.5959.6059.81

OpenVINO GenAI

Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Tokendacb1122334455SE +/- 0.09, N = 346.3646.4046.4146.59

Phoronix Test Suite v10.8.5