ai ryzen

AMD Ryzen AI 9 HX 370 testing with a ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS) and AMD Radeon 512MB on Ubuntu 24.10 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 2411250-NE-AIRYZEN4682
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 25
  1 Hour, 26 Minutes
b
November 25
  1 Hour, 26 Minutes
c
November 25
  1 Hour, 26 Minutes
d
November 25
  1 Hour, 27 Minutes
e
November 25
  1 Hour, 26 Minutes
Invert Behavior (Only Show Selected Data)
  1 Hour, 26 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):


ai ryzenOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen AI 9 HX 370 @ 4.37GHz (12 Cores / 24 Threads)ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS)AMD Device 15074 x 8GB LPDDR5-7500MT/s Samsung K3KL9L90CM-MGCT1024GB MTFDKBA1T0QFM-1BD1AABGBAMD Radeon 512MBAMD Rembrandt Radeon HD AudioMEDIATEK Device 7925Ubuntu 24.106.11.0-rc6-phx (x86_64)GNOME Shell 47.0X Server + Wayland4.6 Mesa 24.2.3-1ubuntu1 (LLVM 19.1.0 DRM 3.58)GCC 14.2.0ext42880x1800ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionAi Ryzen BenchmarksSystem Logs- amdgpu.dcdebugmask=0x600 - 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,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --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-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/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 (Boost: Enabled EPP: balance_performance) - Platform Profile: balanced - CPU Microcode: 0xb204011 - ACPI Profile: balanced - Python 3.12.7- 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 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; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

abcdeResult OverviewPhoronix Test Suite100%102%105%107%110%OpenVINOLlama.cppOpenVINO GenAI

ai ryzenopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048openvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024openvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512openvino: Face Detection Retail FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUllama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048openvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512openvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino-genai: Falcon-7b-instruct-int4-ov - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128openvino-genai: Gemma-7b-int4-ov - CPUopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPUopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPUllama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time Per Output Tokenopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time To First Tokenopenvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time Per Output Tokenopenvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time To First Tokenopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time Per Output Tokenopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time To First Tokenopenvino-genai: Gemma-7b-int4-ov - CPU - Time Per Output Tokenopenvino-genai: Gemma-7b-int4-ov - CPU - Time To First Tokenabcde5.061169.64568.110.5316.35365.4751.79115.72129.985.441100.13154.3115.1252.06206.9628.9445.08132.877.24138.561640.6254.73109.5647.98249.42208.9957.28444.3113.4510.06593.2330.05422.2528.290.9411718.1119.11621.4416399.530.6633.3214.1844.9311.36497.681231.813332.0555.1910.018.3717.0428.4410.3230.0958.68109.7188.04182.3435.1639.22119.42231.136.83870.25787.267.622.45266.5644.21135.46132.335.271134.91140.01117.9250.83183.6432.6146.67128.347.97140.611490.6149.22121.8250.13238.7200.6659.65468.312.7610.58564.2831.77404.4729.531.0110945.6119.82599.6116390.570.6632.8314.94798.0111.81490.5112.1831.7532.3831.9854.069.998.3317.0228.4310.2930.1358.77109.0484.7177.435.1839.1120.03235.335.871010.95736.38.1222.32268.0740.96146.29120.584.551309.47149.21131.3845.61193.7830.9141.81143.258.08127.481471.5852.5114.1847.74250.62190.2462.92458.9113.0210.62561.630.11392.6130.410.9711406.7519.61606.0116445.830.6632.7114.39828.1111.66492.2912.1431.5932.7231.5255.189.968.2417.1628.4810.4129.9758.28110.7885.8178.5235.1138.84121.37237.724.861215.99569.9810.516.42363.7351.35116.71113.935.381106.04124.44116.3451.53197.5930.3142.53140.797.79126.061524.9953.59111.8448.22248.2193.2761.93429.2413.9210.89548.1629.51401.729.730.9911135.820.13590.5116126.970.6731.3914.63814.7711.72486.6512.2831.4232.0631.1954.039.838.216.9728.1510.2829.958.92110.5385.32181.5435.5239.2121.97242.385.781025.5722.788.2722272.0340.18149.1142.424.381365.09135.17140.6642.62194.830.7543.16138.777.78137.031527.7652.41114.3545.56262.58201.0959.53466.6112.810.31578.7629.76415.8528.710.9511583.8618.81631.3717219.190.6332.7214.25836.2312.01508.3711.7632.6733.2631.9354.6610.048.2816.8628.0310.4330.2259.3111.483.23180.0735.6739.5120.84239.26OpenBenchmarking.org

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16 - Device: CPUbcead2468106.835.875.785.064.86MIN: 2.29 / MAX: 34.8MIN: 1.99 / MAX: 12.29MIN: 2.33 / MAX: 32.64MIN: 2.16 / MAX: 28.7MIN: 2.06 / MAX: 12.471. (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: CPUbcead30060090012001500870.251010.951025.501169.641215.991. (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: CPUbceda2004006008001000787.26736.30722.78569.98568.10MIN: 478.62 / MAX: 927.26MIN: 465.09 / MAX: 873.8MIN: 461.99 / MAX: 871.97MIN: 425.76 / MAX: 663.66MIN: 422.58 / MAX: 660.471. (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: CPUbceda36912157.608.128.2710.5010.531. (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: Vehicle Detection FP16 - Device: CPUbceda51015202522.4522.3222.0016.4216.35MIN: 8.5 / MAX: 58.21MIN: 9.5 / MAX: 47.65MIN: 9.07 / MAX: 50.66MIN: 7.99 / MAX: 46.8MIN: 7.58 / MAX: 37.931. (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: CPUbceda80160240320400266.56268.07272.03363.73365.471. (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: CPUecbda122436486040.1840.9644.2151.3551.791. (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: CPUecbda306090120150149.10146.29135.46116.71115.72MIN: 77.68 / MAX: 189.75MIN: 76.74 / MAX: 191.8MIN: 77.49 / MAX: 190.4MIN: 77.42 / MAX: 154.46MIN: 49.3 / MAX: 152.181. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048dcabe306090120150113.93120.58129.98132.33142.421. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection FP16 - Device: CPUecbda1.2242.4483.6724.8966.124.384.555.275.385.441. (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: CPUecbda300600900120015001365.091309.471134.911106.041100.13MIN: 976.08 / MAX: 1622.06MIN: 965.54 / MAX: 1588.7MIN: 848.07 / MAX: 1328.82MIN: 758.52 / MAX: 1296.59MIN: 811.7 / MAX: 1287.951. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024debca306090120150124.44135.17140.01149.21154.301. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Detection FP16 - Device: CPUecbda306090120150140.66131.38117.92116.34115.12MIN: 76.65 / MAX: 180.47MIN: 76.97 / MAX: 173.31MIN: 79.25 / MAX: 157.07MIN: 46.65 / MAX: 154.31MIN: 48.31 / MAX: 154.811. (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: CPUecbda122436486042.6245.6150.8351.5352.061. (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: CPUbceda50100150200250183.64193.78194.80197.59206.961. (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: CPUbceda81624324032.6130.9130.7530.3128.94MIN: 15.72 / MAX: 59.5MIN: 17.1 / MAX: 60.15MIN: 16.84 / MAX: 49.25MIN: 14.12 / MAX: 57.43MIN: 17 / MAX: 46.111. (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: CPUbaedc112233445546.6745.0843.1642.5341.81MIN: 20.3 / MAX: 70.08MIN: 21.35 / MAX: 65.19MIN: 20.2 / MAX: 76.04MIN: 21.12 / MAX: 71.63MIN: 20.59 / MAX: 75.641. (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 - Device: CPUbaedc306090120150128.34132.87138.77140.79143.251. (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: CPUcbdea2468108.087.977.797.787.24MIN: 3.47 / MAX: 33.22MIN: 3.64 / MAX: 30.64MIN: 3.43 / MAX: 27.36MIN: 3.49 / MAX: 31.56MIN: 3.16 / MAX: 33.461. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512dceab306090120150126.06127.48137.03138.56140.611. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16-INT8 - Device: CPUcbdea4008001200160020001471.581490.611524.991527.761640.621. (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: CPUbecda122436486049.2252.4152.5053.5954.731. (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: Machine Translation EN To DE FP16 - Device: CPUbecda306090120150121.82114.35114.18111.84109.56MIN: 54.14 / MAX: 185.91MIN: 64.06 / MAX: 181.31MIN: 50.2 / MAX: 164.4MIN: 64.41 / MAX: 165.62MIN: 67.71 / MAX: 161.261. (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: CPUbdace112233445550.1348.2247.9847.7445.56MIN: 24.55 / MAX: 82.9MIN: 24.48 / MAX: 89.36MIN: 23.83 / MAX: 88.63MIN: 23.33 / MAX: 68.32MIN: 22.94 / MAX: 73.941. (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: CPUbdace60120180240300238.70248.20249.42250.62262.581. (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: CPUcdbea50100150200250190.24193.27200.66201.09208.991. (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: CPUcdbea142842567062.9261.9359.6559.5357.28MIN: 24.39 / MAX: 102.66MIN: 24.49 / MAX: 98.31MIN: 24.08 / MAX: 103.1MIN: 24.24 / MAX: 99.13MIN: 24.02 / MAX: 80.181. (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: CPUdaceb100200300400500429.24444.31458.91466.61468.301. (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: CPUdaceb4812162013.9213.4513.0212.8012.76MIN: 6 / MAX: 37.95MIN: 5.98 / MAX: 41.66MIN: 5.11 / MAX: 39.66MIN: 5.83 / MAX: 34.19MIN: 5.15 / MAX: 25.451. (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: CPUdcbea369121510.8910.6210.5810.3110.06MIN: 5.09 / MAX: 22.22MIN: 4.86 / MAX: 20.14MIN: 4.84 / MAX: 42.87MIN: 5.18 / MAX: 40.85MIN: 4.77 / MAX: 36.661. (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: CPUdcbea130260390520650548.16561.60564.28578.76593.231. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048deacb71421283529.5129.7630.0530.1131.771. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16 - Device: CPUcdbea90180270360450392.61401.70404.47415.85422.251. (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: CPUcdbea71421283530.4129.7329.5328.7128.29MIN: 15.23 / MAX: 61.34MIN: 11.69 / MAX: 58.97MIN: 15.09 / MAX: 60.98MIN: 15.77 / MAX: 58.92MIN: 11.58 / MAX: 67.821. (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: CPUbdcea0.22730.45460.68190.90921.13651.010.990.970.950.94MIN: 0.31 / MAX: 25.04MIN: 0.3 / MAX: 21.06MIN: 0.29 / MAX: 22.42MIN: 0.3 / MAX: 25.77MIN: 0.29 / MAX: 27.161. (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: CPUbdcea3K6K9K12K15K10945.6111135.8011406.7511583.8611718.111. (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: CPUdbcae51015202520.1319.8219.6119.1118.81MIN: 10.26 / MAX: 51.88MIN: 10.2 / MAX: 44.89MIN: 10.56 / MAX: 41.5MIN: 9.86 / MAX: 40.24MIN: 10.58 / MAX: 26.341. (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: CPUdbcae140280420560700590.51599.61606.01621.44631.371. (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: CPUdbace4K8K12K16K20K16126.9716390.5716399.5316445.8317219.191. (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: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUdcbae0.15080.30160.45240.60320.7540.670.660.660.660.63MIN: 0.22 / MAX: 22.2MIN: 0.22 / MAX: 25.66MIN: 0.22 / MAX: 25.15MIN: 0.22 / MAX: 24.64MIN: 0.22 / MAX: 19.871. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512dceba81624324031.3932.7132.7232.8333.321. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16-INT8 - Device: CPUbdcea4812162014.9414.6314.3914.2514.10MIN: 6.41 / MAX: 43.15MIN: 6.84 / MAX: 43.93MIN: 6.79 / MAX: 37.8MIN: 6.16 / MAX: 44.46MIN: 7.61 / MAX: 41.691. (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: CPUbdcea2004006008001000798.01814.77828.11836.23844.931. (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: Falcon-7b-instruct-int4-ov - Device: CPUacdbe369121511.3611.6611.7211.8112.01

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Vehicle Bike Detection FP16 - Device: CPUdbcae110220330440550486.65490.51492.29497.68508.371. (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: CPUdbcae369121512.2812.1812.1412.0011.76MIN: 5.68 / MAX: 23.33MIN: 5.99 / MAX: 21.81MIN: 6.13 / MAX: 34.85MIN: 5.96 / MAX: 39.02MIN: 5.94 / MAX: 21.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024dcbae81624324031.4231.5931.7531.8132.671. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512dbcae81624324032.0632.3832.7233.0033.261. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024dceba71421283531.1931.5231.9331.9832.051. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128dbeca122436486054.0354.0654.6655.1855.191. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128dcbae36912159.839.969.9910.0110.041. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenVINO GenAI

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPUdceba2468108.208.248.288.338.37

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPUedbac4812162016.8616.9717.0217.0417.16

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPUedbac71421283528.0328.1528.4328.4428.48

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128dbace369121510.2810.2910.3210.4110.431. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048dcabe71421283529.9029.9730.0930.1330.221. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

56 Results Shown

OpenVINO:
  Face Detection Retail FP16 - CPU:
    ms
    FPS
  Face Detection FP16-INT8 - CPU:
    ms
    FPS
  Vehicle Detection FP16 - CPU:
    ms
    FPS
  Person Detection FP32 - CPU:
    FPS
    ms
Llama.cpp
OpenVINO:
  Face Detection FP16 - CPU:
    FPS
    ms
Llama.cpp
OpenVINO:
  Person Detection FP16 - CPU:
    ms
    FPS
  Road Segmentation ADAS FP16-INT8 - CPU:
    FPS
    ms
  Road Segmentation ADAS FP16 - CPU:
    ms
    FPS
  Face Detection Retail FP16-INT8 - CPU:
    ms
Llama.cpp
OpenVINO:
  Face Detection Retail FP16-INT8 - CPU
  Machine Translation EN To DE FP16 - CPU
  Machine Translation EN To DE FP16 - CPU
  Handwritten English Recognition FP16-INT8 - CPU
  Handwritten English Recognition FP16-INT8 - CPU
  Handwritten English Recognition FP16 - CPU
  Handwritten English Recognition FP16 - CPU
  Vehicle Detection FP16-INT8 - CPU
  Vehicle Detection FP16-INT8 - CPU
  Person Re-Identification Retail FP16 - CPU
  Person Re-Identification Retail FP16 - CPU
Llama.cpp
OpenVINO:
  Weld Porosity Detection FP16 - CPU:
    FPS
    ms
  Age Gender Recognition Retail 0013 FP16 - CPU:
    ms
    FPS
  Noise Suppression Poconet-Like FP16 - CPU:
    ms
    FPS
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    FPS
    ms
Llama.cpp
OpenVINO:
  Weld Porosity Detection FP16-INT8 - CPU:
    ms
    FPS
OpenVINO GenAI
OpenVINO:
  Person Vehicle Bike Detection FP16 - CPU:
    FPS
    ms
Llama.cpp:
  CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024
  CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128
  CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128
OpenVINO GenAI:
  Gemma-7b-int4-ov - CPU
  Phi-3-mini-128k-instruct-int4-ov - CPU
  TinyLlama-1.1B-Chat-v1.0 - CPU
Llama.cpp:
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128
  CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048