ddddai AMD Ryzen 7 7840HS testing with a Framework Laptop 16 (AMD Ryzen 7040 ) FRANMZCP07 (03.01 BIOS) and AMD Radeon 780M 512MB on Ubuntu 24.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2411253-NE-DDDDAI39404&grt .
ddddai Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution a b c d AMD Ryzen 7 7840HS @ 5.29GHz (8 Cores / 16 Threads) Framework Laptop 16 (AMD Ryzen 7040 ) FRANMZCP07 (03.01 BIOS) AMD Device 14e8 2 x 8GB DDR5-5600MT/s A-DATA AD5S56008G-B 512GB Western Digital PC SN810 SDCPNRY-512G AMD Radeon 780M 512MB AMD Navi 31 HDMI/DP MEDIATEK MT7922 802.11ax PCI Ubuntu 24.04 6.8.0-48-generic (x86_64) GNOME Shell 46.0 X Server + Wayland 4.6 Mesa 24.2~git2406200600.0ac0fb~oibaf~n (git-0ac0fbc 2024-06-20 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57) GCC 13.2.0 ext4 2560x1600 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --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-backtrace --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-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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 Details - Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - Platform Profile: balanced - CPU Microcode: 0xa704103 - ACPI Profile: balanced Python Details - Python 3.12.3 Security 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: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
ddddai llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128 llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512 llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024 llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048 llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128 llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512 llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024 llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048 llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128 llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512 llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024 llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048 openvino: Face Detection FP16 - CPU openvino: Face Detection FP16 - CPU openvino: Person Detection FP16 - CPU openvino: Person Detection FP16 - CPU openvino: Person Detection FP32 - CPU openvino: Person Detection FP32 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection Retail FP16 - CPU openvino: Face Detection Retail FP16 - CPU openvino: Road Segmentation ADAS FP16 - CPU openvino: Road Segmentation ADAS FP16 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU openvino: Person Re-Identification Retail FP16 - CPU openvino: Person Re-Identification Retail FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino-genai: Gemma-7b-int4-ov - CPU openvino-genai: Gemma-7b-int4-ov - CPU - Time To First Token openvino-genai: Gemma-7b-int4-ov - CPU - Time Per Output Token openvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU openvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time To First Token openvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time Per Output Token openvino-genai: Falcon-7b-instruct-int4-ov - CPU openvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time To First Token openvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time Per Output Token openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time To First Token openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time Per Output Token a b c d 7.25 44.83 43.62 41.38 7.64 45.71 44.22 41.49 54.63 166.26 155.44 142.47 5.87 679.69 37.22 107.33 36.86 108.46 247.14 16.13 11.5 347.2 1343.56 2.96 105.69 37.78 590.67 6.74 590.41 13.47 1908.38 4.13 182.16 21.9 56.36 70.89 1121.63 7.04 550.99 7.23 543.71 14.59 292.71 27.28 768.99 5.17 15348.57 0.48 335.59 23.79 21199.7 0.35 9.65 188.15 103.63 24.81 43.01 40.31 13.23 139.06 75.56 19.03 86.75 52.53 7.25 45.25 43.88 41.1 7.63 44.58 43.45 41.38 54.64 162.09 152.29 146.13 5.93 673.29 37.23 107.36 37.15 107.56 245.32 16.25 11.69 341.61 1332.62 2.98 108.9 36.67 588.27 6.76 583.92 13.62 1909.12 4.14 188.79 21.13 56.23 71.09 1112.06 7.09 554.98 7.18 536.31 14.78 290.66 27.45 783.6 5.08 15326.37 0.49 338.64 23.58 21264.05 0.35 9.8 182.66 102.09 24.74 43.2 40.41 13.34 138.66 74.97 19.09 86.94 52.38 7.25 44.76 44.06 41.61 7.63 45.05 43.56 41.42 54.46 166.8 161.8 146.86 5.88 677.43 37.98 105.19 36.94 108.21 244.42 16.31 11.77 339 1330.69 2.98 103.29 38.66 586.59 6.79 586.2 13.58 1916.74 4.12 189.59 21.05 55.77 71.68 1116.04 7.07 551.35 7.23 549.16 14.45 300.37 26.58 777.34 5.12 15335.47 0.49 335.54 23.79 21235.24 0.35 9.77 183.34 102.37 24.77 43.16 40.37 13.36 138.41 74.87 19.15 86.87 52.23 7.25 45.09 44.34 41.71 7.63 45.2 43.77 41.76 54.69 178.14 155.83 150.4 5.89 678.48 37.45 106.71 37.08 107.74 250.01 15.95 11.78 339.14 1327.47 2.99 104.27 38.29 590.33 6.74 587.52 13.54 1893.54 4.17 189.49 21.06 56.39 70.85 1120.88 7.05 558.37 7.14 546.6 14.51 299.44 26.66 777.18 5.12 15342.91 0.49 334.86 23.84 21253.78 0.35 9.79 183.33 102.13 24.74 43.12 40.42 13.39 135.36 74.66 19.02 86.74 52.58 OpenBenchmarking.org
Llama.cpp Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128 a b c d 2 4 6 8 10 7.25 7.25 7.25 7.25 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llama.cpp Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512 a b c d 10 20 30 40 50 44.83 45.25 44.76 45.09 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llama.cpp Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024 a b c d 10 20 30 40 50 43.62 43.88 44.06 44.34 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llama.cpp Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048 a b c d 10 20 30 40 50 41.38 41.10 41.61 41.71 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llama.cpp Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128 a b c d 2 4 6 8 10 7.64 7.63 7.63 7.63 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llama.cpp Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512 a b c d 10 20 30 40 50 45.71 44.58 45.05 45.20 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llama.cpp Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024 a b c d 10 20 30 40 50 44.22 43.45 43.56 43.77 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llama.cpp Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048 a b c d 10 20 30 40 50 41.49 41.38 41.42 41.76 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llama.cpp Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128 a b c d 12 24 36 48 60 54.63 54.64 54.46 54.69 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llama.cpp Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512 a b c d 40 80 120 160 200 166.26 162.09 166.80 178.14 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llama.cpp Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024 a b c d 40 80 120 160 200 155.44 152.29 161.80 155.83 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Llama.cpp Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048 a b c d 30 60 90 120 150 142.47 146.13 146.86 150.40 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU a b c d 1.3343 2.6686 4.0029 5.3372 6.6715 5.87 5.93 5.88 5.89 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU a b c d 150 300 450 600 750 679.69 673.29 677.43 678.48 MIN: 580.15 / MAX: 722.06 MIN: 532.22 / MAX: 728.48 MIN: 534.91 / MAX: 720.64 MIN: 630.81 / MAX: 719.79 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU a b c d 9 18 27 36 45 37.22 37.23 37.98 37.45 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU a b c d 20 40 60 80 100 107.33 107.36 105.19 106.71 MIN: 73.05 / MAX: 128.28 MIN: 82.65 / MAX: 126.62 MIN: 66.55 / MAX: 124.75 MIN: 79.08 / MAX: 125.81 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Person Detection FP32 - Device: CPU a b c d 9 18 27 36 45 36.86 37.15 36.94 37.08 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Detection FP32 - Device: CPU a b c d 20 40 60 80 100 108.46 107.56 108.21 107.74 MIN: 97.43 / MAX: 123.44 MIN: 92 / MAX: 128.48 MIN: 87.24 / MAX: 135.83 MIN: 72.67 / MAX: 125.1 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU a b c d 50 100 150 200 250 247.14 245.32 244.42 250.01 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU a b c d 4 8 12 16 20 16.13 16.25 16.31 15.95 MIN: 6.02 / MAX: 30.47 MIN: 5.96 / MAX: 31.79 MIN: 8.43 / MAX: 24.38 MIN: 7.05 / MAX: 40.34 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU a b c d 3 6 9 12 15 11.50 11.69 11.77 11.78 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU a b c d 80 160 240 320 400 347.20 341.61 339.00 339.14 MIN: 328.58 / MAX: 367.27 MIN: 280.81 / MAX: 366.89 MIN: 277.9 / MAX: 378.86 MIN: 267.44 / MAX: 367.02 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU a b c d 300 600 900 1200 1500 1343.56 1332.62 1330.69 1327.47 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU a b c d 0.6728 1.3456 2.0184 2.6912 3.364 2.96 2.98 2.98 2.99 MIN: 1.62 / MAX: 18.15 MIN: 1.63 / MAX: 18.79 MIN: 1.57 / MAX: 13.93 MIN: 1.59 / MAX: 20.62 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU a b c d 20 40 60 80 100 105.69 108.90 103.29 104.27 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU a b c d 9 18 27 36 45 37.78 36.67 38.66 38.29 MIN: 21.12 / MAX: 62.56 MIN: 21.89 / MAX: 57.54 MIN: 18.34 / MAX: 55.37 MIN: 23.43 / MAX: 50.13 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16-INT8 - Device: CPU a b c d 130 260 390 520 650 590.67 588.27 586.59 590.33 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16-INT8 - Device: CPU a b c d 2 4 6 8 10 6.74 6.76 6.79 6.74 MIN: 3.45 / MAX: 21.71 MIN: 3.47 / MAX: 21.86 MIN: 3.68 / MAX: 19.59 MIN: 3.52 / MAX: 22.15 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16 - Device: CPU a b c d 130 260 390 520 650 590.41 583.92 586.20 587.52 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16 - Device: CPU a b c d 4 8 12 16 20 13.47 13.62 13.58 13.54 MIN: 6.83 / MAX: 27.16 MIN: 6.92 / MAX: 32.75 MIN: 7.9 / MAX: 33.7 MIN: 7.03 / MAX: 28.23 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU a b c d 400 800 1200 1600 2000 1908.38 1909.12 1916.74 1893.54 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU a b c d 0.9383 1.8766 2.8149 3.7532 4.6915 4.13 4.14 4.12 4.17 MIN: 2.29 / MAX: 20.89 MIN: 2.29 / MAX: 20.49 MIN: 2.35 / MAX: 19.27 MIN: 2.27 / MAX: 18.49 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU a b c d 40 80 120 160 200 182.16 188.79 189.59 189.49 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU a b c d 5 10 15 20 25 21.90 21.13 21.05 21.06 MIN: 11.04 / MAX: 33.55 MIN: 9.47 / MAX: 37.68 MIN: 12.4 / MAX: 37.33 MIN: 13.96 / MAX: 30.73 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU a b c d 13 26 39 52 65 56.36 56.23 55.77 56.39 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU a b c d 16 32 48 64 80 70.89 71.09 71.68 70.85 MIN: 37.61 / MAX: 98.63 MIN: 51.22 / MAX: 99.72 MIN: 56.84 / MAX: 84.14 MIN: 58.01 / MAX: 93.11 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16-INT8 - Device: CPU a b c d 200 400 600 800 1000 1121.63 1112.06 1116.04 1120.88 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16-INT8 - Device: CPU a b c d 2 4 6 8 10 7.04 7.09 7.07 7.05 MIN: 3.53 / MAX: 22.7 MIN: 3.5 / MAX: 21.97 MIN: 3.6 / MAX: 18.81 MIN: 3.49 / MAX: 23.46 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU a b c d 120 240 360 480 600 550.99 554.98 551.35 558.37 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU a b c d 2 4 6 8 10 7.23 7.18 7.23 7.14 MIN: 3.93 / MAX: 20.09 MIN: 4.63 / MAX: 12.96 MIN: 3.75 / MAX: 22.65 MIN: 4.43 / MAX: 19.5 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU a b c d 120 240 360 480 600 543.71 536.31 549.16 546.60 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU a b c d 4 8 12 16 20 14.59 14.78 14.45 14.51 MIN: 9.75 / MAX: 32.36 MIN: 8.51 / MAX: 40.64 MIN: 10.48 / MAX: 32.75 MIN: 8.59 / MAX: 31.16 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU a b c d 70 140 210 280 350 292.71 290.66 300.37 299.44 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU a b c d 6 12 18 24 30 27.28 27.45 26.58 26.66 MIN: 18.02 / MAX: 55.02 MIN: 20.22 / MAX: 47.25 MIN: 20.89 / MAX: 46.91 MIN: 19.28 / MAX: 42.41 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU a b c d 200 400 600 800 1000 768.99 783.60 777.34 777.18 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU a b c d 1.1633 2.3266 3.4899 4.6532 5.8165 5.17 5.08 5.12 5.12 MIN: 3 / MAX: 19.43 MIN: 3.14 / MAX: 20.29 MIN: 3.05 / MAX: 20.31 MIN: 3.01 / MAX: 17.88 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b c d 3K 6K 9K 12K 15K 15348.57 15326.37 15335.47 15342.91 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b c d 0.1103 0.2206 0.3309 0.4412 0.5515 0.48 0.49 0.49 0.49 MIN: 0.24 / MAX: 10.6 MIN: 0.25 / MAX: 15.34 MIN: 0.25 / MAX: 15.13 MIN: 0.25 / MAX: 19.36 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU a b c d 70 140 210 280 350 335.59 338.64 335.54 334.86 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU a b c d 6 12 18 24 30 23.79 23.58 23.79 23.84 MIN: 19.25 / MAX: 39.59 MIN: 18.58 / MAX: 36.81 MIN: 19.11 / MAX: 38.65 MIN: 18.36 / MAX: 40.79 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b c d 5K 10K 15K 20K 25K 21199.70 21264.05 21235.24 21253.78 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b c d 0.0788 0.1576 0.2364 0.3152 0.394 0.35 0.35 0.35 0.35 MIN: 0.19 / MAX: 13.04 MIN: 0.19 / MAX: 16.89 MIN: 0.19 / MAX: 12.19 MIN: 0.19 / MAX: 13.37 1. (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 OpenBenchmarking.org tokens/s, More Is Better OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU a b c d 3 6 9 12 15 9.65 9.80 9.77 9.79
OpenVINO GenAI Model: Gemma-7b-int4-ov - Device: CPU - Time To First Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU - Time To First Token a b c d 40 80 120 160 200 188.15 182.66 183.34 183.33
OpenVINO GenAI Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Token a b c d 20 40 60 80 100 103.63 102.09 102.37 102.13
OpenVINO GenAI Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU OpenBenchmarking.org tokens/s, More Is Better OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU a b c d 6 12 18 24 30 24.81 24.74 24.77 24.74
OpenVINO GenAI Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Token a b c d 10 20 30 40 50 43.01 43.20 43.16 43.12
OpenVINO GenAI Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Token a b c d 9 18 27 36 45 40.31 40.41 40.37 40.42
OpenVINO GenAI Model: Falcon-7b-instruct-int4-ov - Device: CPU OpenBenchmarking.org tokens/s, More Is Better OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU a b c d 3 6 9 12 15 13.23 13.34 13.36 13.39
OpenVINO GenAI Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Token a b c d 30 60 90 120 150 139.06 138.66 138.41 135.36
OpenVINO GenAI Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Token a b c d 20 40 60 80 100 75.56 74.97 74.87 74.66
OpenVINO GenAI Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU OpenBenchmarking.org tokens/s, More Is Better OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU a b c d 5 10 15 20 25 19.03 19.09 19.15 19.02
OpenVINO GenAI Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Token a b c d 20 40 60 80 100 86.75 86.94 86.87 86.74
OpenVINO GenAI Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Token a b c d 12 24 36 48 60 52.53 52.38 52.23 52.58
Phoronix Test Suite v10.8.5