sunny Testss for a future article. Intel Core Ultra 7 256V testing with a ASUS Zenbook S 14 UX5406SA_UX5406SA UX5406SA v1.0 (UX5406SA.300 BIOS) and ASUS Intel LNL 7GB on Ubuntu 24.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2411248-NE-SUNNY040284&grs .
sunny Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL OpenCL Compiler File-System Screen Resolution a b Intel Core Ultra 7 256V @ 4.70GHz (8 Cores) ASUS Zenbook S 14 UX5406SA_UX5406SA UX5406SA v1.0 (UX5406SA.300 BIOS) Intel Device a87f 8 x 2GB LPDDR5-8533MT/s Samsung 1024GB Western Digital WD PC SN560 SDDPNQE-1T00-1102 ASUS Intel LNL 7GB Intel Lunar Lake-M HD Audio Intel Device a840 Ubuntu 24.10 6.12.0-rc3-phx-aipt (x86_64) GNOME Shell 47.0 X Server + Wayland 4.6 Mesa 24.3~git2410200600.4bc2d2~oibaf~o (git-4bc2d22 2024-10-20 oracular-oibaf-pp OpenCL 3.0 GCC 14.2.0 ext4 2880x1800 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --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 Processor Details - Scaling Governor: intel_pstate powersave (EPP: balance_performance) - Platform Profile: balanced - CPU Microcode: 0x114 - Thermald 2.5.8 - ACPI Profile: balanced Java Details - OpenJDK Runtime Environment (build 21.0.5+11-Ubuntu-1ubuntu124.10) Python Details - Python 3.12.7 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: 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; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
sunny openvino: Face Detection Retail FP16-INT8 - CPU 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 - Text Generation 128 renaissance: In-Memory Database Shootout renaissance: Akka Unbalanced Cobwebbed Tree renaissance: Scala Dotty renaissance: Apache Spark Bayes openvino: Road Segmentation ADAS FP16 - CPU openvino: Road Segmentation ADAS FP16 - CPU llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128 openvino: Face Detection Retail FP16-INT8 - CPU renaissance: Rand Forest openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512 blender: Junkshop - CPU-Only llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512 openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU 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 - Prompt Processing 2048 renaissance: Apache Spark PageRank openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU renaissance: Savina Reactors.IO openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048 blender: Classroom - CPU-Only renaissance: ALS Movie Lens renaissance: Finagle HTTP Requests llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024 renaissance: Gaussian Mixture Model openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024 openvino: Weld Porosity Detection FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU blender: Pabellon Barcelona - CPU-Only openvino: Person Re-Identification Retail FP16 - CPU blender: BMW27 - CPU-Only openvino: Person Re-Identification Retail FP16 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU blender: Barbershop - CPU-Only llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128 openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU blender: Fishy Cat - CPU-Only llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512 vkpeak: int16-vec4 openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Face Detection Retail FP16 - CPU openvino: Face Detection FP16 - CPU openvino: Face Detection Retail FP16 - CPU openvino: Person Detection FP16 - CPU primesieve: 1e12 openvino: Person Detection FP32 - CPU openvino: Person Detection FP32 - CPU openvino: Person Detection FP16 - CPU primesieve: 1e13 renaissance: Genetic Algorithm Using Jenetics + Futures vkpeak: int32-scalar vkpeak: fp64-vec4 vkpeak: fp32-scalar vkpeak: int32-vec4 vkpeak: int16-scalar vkpeak: fp64-scalar vkpeak: fp16-scalar vkpeak: fp32-vec4 vkpeak: fp16-vec4 openvino: Age Gender Recognition Retail 0013 FP16 - CPU renaissance: Apache Spark ALS a b 5.82 22.02 8.18 3666.0 4680.4 504.9 576.1 64.03 62.38 36.91 1026.9 530.0 219.73 18.14 25.04 325.79 82.4 33.06 120.7 23.46 23.32 2499.1 0.51 5040.0 11199.94 66.4 640.15 11841.5 1603.6 74.15 3998.5 91.93 65.18 6.1 1.61 21.38 78.37 25.33 38.57 155.06 76.47 186.74 836.92 16.22 222.76 245.22 31.3 127.48 653.94 2528.85 8.69 4019.35 316.02 12.58 10.42 340.45 25.77 3616.14 284.72 20.99 571.4 9.53 2484.8 416.85 17.53 24.633 229.63 17.39 227.74 375.354 1345.6 826.97 213.37 1989.85 848.97 3189.67 218.71 6201.56 2928.03 6532.13 1.43 4.02 25.22 8.99 3960.0 5048.7 535.0 548.5 66.75 59.84 38.36 988.82 549.0 212.79 18.73 25.84 334.36 84.56 32.23 123.8 24.01 23.86 2555.2 0.52 4962.2 11036.01 65.53 632.33 11978.1 1620.8 74.85 3964.1 91.16 65.73 6.06 1.6 21.25 77.92 25.19 38.78 154.23 76.88 187.74 841.4 16.3 221.76 244.2 31.43 126.97 656.46 2538.07 8.66 4033.01 315 12.62 10.45 339.5 25.7 3625.91 283.97 21.04 570.08 9.55 2479.73 416.05 17.56 24.599 229.9 17.37 227.5 375.683 1344.7 827.21 213.43 1990.33 849.17 3190.35 218.75 6202.63 2928.51 6532.63 1.43 OpenBenchmarking.org
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 1.3095 2.619 3.9285 5.238 6.5475 5.82 4.02 MIN: 4.19 / MAX: 15.87 MIN: 2.26 / MAX: 10.32 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
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 6 12 18 24 30 22.02 25.22 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 3 6 9 12 15 8.18 8.99 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: In-Memory Database Shootout a b 800 1600 2400 3200 4000 3666.0 3960.0 MIN: 3310.92 / MAX: 4011.42 MIN: 3506.06 / MAX: 4250.74
Renaissance Test: Akka Unbalanced Cobwebbed Tree OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Akka Unbalanced Cobwebbed Tree a b 1100 2200 3300 4400 5500 4680.4 5048.7 MAX: 6368.49 MIN: 5048.68 / MAX: 6733.71
Renaissance Test: Scala Dotty OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Scala Dotty a b 120 240 360 480 600 504.9 535.0 MIN: 414.43 / MAX: 1051.65 MIN: 423.09 / MAX: 1208.18
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Apache Spark Bayes a b 120 240 360 480 600 576.1 548.5 MIN: 487.72 / MAX: 639.08 MIN: 479.93 / MAX: 622.49
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 15 30 45 60 75 64.03 66.75 MIN: 38.34 / MAX: 92.38 MIN: 37.15 / MAX: 103.09 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 14 28 42 56 70 62.38 59.84 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
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 9 18 27 36 45 36.91 38.36 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
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 200 400 600 800 1000 1026.90 988.82 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Random Forest a b 120 240 360 480 600 530.0 549.0 MIN: 433.94 / MAX: 631.56 MIN: 432.9 / MAX: 695.6
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 50 100 150 200 250 219.73 212.79 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 5 10 15 20 25 18.14 18.73 MIN: 10.6 / MAX: 32.58 MIN: 10.83 / MAX: 30.37 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
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 6 12 18 24 30 25.04 25.84 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Blender Blend File: Junkshop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Junkshop - Compute: CPU-Only a b 70 140 210 280 350 325.79 334.36
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 20 40 60 80 100 82.40 84.56 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU a b 8 16 24 32 40 33.06 32.23 MIN: 18.51 / MAX: 45.41 MIN: 18.43 / MAX: 42.01 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 FPS, More Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU a b 30 60 90 120 150 120.7 123.8 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
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 6 12 18 24 30 23.46 24.01 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 6 12 18 24 30 23.32 23.86 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Renaissance Test: Apache Spark PageRank OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Apache Spark PageRank a b 500 1000 1500 2000 2500 2499.1 2555.2 MIN: 2241.43 MIN: 2311.16 / MAX: 2555.25
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 0.117 0.234 0.351 0.468 0.585 0.51 0.52 MIN: 0.31 / MAX: 4.69 MIN: 0.32 / MAX: 5.59 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Savina Reactors.IO a b 1100 2200 3300 4400 5500 5040.0 4962.2 MAX: 6798.06 MAX: 6756.71
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 2K 4K 6K 8K 10K 11199.94 11036.01 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
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 15 30 45 60 75 66.40 65.53 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Classroom - Compute: CPU-Only a b 140 280 420 560 700 640.15 632.33
Renaissance Test: ALS Movie Lens OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: ALS Movie Lens a b 3K 6K 9K 12K 15K 11841.5 11978.1 MIN: 11513.13 / MAX: 11841.51 MIN: 11444.74 / MAX: 12030.59
Renaissance Test: Finagle HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Finagle HTTP Requests a b 300 600 900 1200 1500 1603.6 1620.8 MIN: 1387.17 / MAX: 1649.09 MIN: 1416.42 / MAX: 1684.8
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 20 40 60 80 100 74.15 74.85 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Renaissance Test: Gaussian Mixture Model OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Gaussian Mixture Model a b 900 1800 2700 3600 4500 3998.5 3964.1 MIN: 3952.45 / MAX: 4600.23 MIN: 3964.09 / MAX: 4527.22
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 20 40 60 80 100 91.93 91.16 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-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU a b 15 30 45 60 75 65.18 65.73 MIN: 44.34 / MAX: 92.86 MIN: 45.14 / MAX: 93.91 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 2 4 6 8 10 6.10 6.06 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 FPS, More Is Better OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU a b 0.3623 0.7246 1.0869 1.4492 1.8115 1.61 1.60 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 5 10 15 20 25 21.38 21.25 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 20 40 60 80 100 78.37 77.92 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
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 6 12 18 24 30 25.33 25.19 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
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 9 18 27 36 45 38.57 38.78 MIN: 24.14 / MAX: 62.33 MIN: 24.36 / MAX: 58.4 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 30 60 90 120 150 155.06 154.23 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 20 40 60 80 100 76.47 76.88 MIN: 50.95 / MAX: 112.21 MIN: 50.85 / MAX: 128.2 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 40 80 120 160 200 186.74 187.74 MIN: 124.74 / MAX: 224.64 MIN: 124.83 / MAX: 225.14 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Pabellon Barcelona - Compute: CPU-Only a b 200 400 600 800 1000 836.92 841.40
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 4 8 12 16 20 16.22 16.30 MIN: 9.29 / MAX: 27.06 MIN: 9.29 / MAX: 25.68 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: BMW27 - Compute: CPU-Only a b 50 100 150 200 250 222.76 221.76
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 50 100 150 200 250 245.22 244.20 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 7 14 21 28 35 31.30 31.43 MIN: 17.4 / MAX: 41.91 MIN: 17.6 / MAX: 52.95 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 30 60 90 120 150 127.48 126.97 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 140 280 420 560 700 653.94 656.46 MIN: 449.53 / MAX: 748.39 MIN: 441.08 / MAX: 743.39 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Barbershop - Compute: CPU-Only a b 500 1000 1500 2000 2500 2528.85 2538.07
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 2 4 6 8 10 8.69 8.66 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
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 900 1800 2700 3600 4500 4019.35 4033.01 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-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16-INT8 - Device: CPU a b 70 140 210 280 350 316.02 315.00 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 3 6 9 12 15 12.58 12.62 MIN: 6.7 / MAX: 20.64 MIN: 6.68 / MAX: 20.14 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 3 6 9 12 15 10.42 10.45 MIN: 6.3 / MAX: 24.72 MIN: 6.31 / MAX: 23.39 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Fishy Cat - Compute: CPU-Only a b 70 140 210 280 350 340.45 339.50
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 6 12 18 24 30 25.77 25.70 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
vkpeak int16-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20240505 int16-vec4 a b 800 1600 2400 3200 4000 3616.14 3625.91
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 60 120 180 240 300 284.72 283.97 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 5 10 15 20 25 20.99 21.04 MIN: 14.56 / MAX: 36.4 MIN: 14.56 / MAX: 37.55 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 120 240 360 480 600 571.40 570.08 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 3 6 9 12 15 9.53 9.55 MIN: 5.45 / MAX: 17.12 MIN: 5.49 / MAX: 23.25 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 500 1000 1500 2000 2500 2484.80 2479.73 MIN: 1667.39 / MAX: 2664.08 MIN: 1667.31 / MAX: 2739.54 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 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU a b 90 180 270 360 450 416.85 416.05 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 4 8 12 16 20 17.53 17.56 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
Primesieve Length: 1e12 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.6 Length: 1e12 a b 6 12 18 24 30 24.63 24.60 1. (CXX) g++ options: -O3
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Detection FP32 - Device: CPU a b 50 100 150 200 250 229.63 229.90 MIN: 151.86 / MAX: 275.83 MIN: 150.52 / MAX: 280.47 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 4 8 12 16 20 17.39 17.37 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 50 100 150 200 250 227.74 227.50 MIN: 148.49 / MAX: 268.77 MIN: 150.76 / MAX: 266.09 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
Primesieve Length: 1e13 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.6 Length: 1e13 a b 80 160 240 320 400 375.35 375.68 1. (CXX) g++ options: -O3
Renaissance Test: Genetic Algorithm Using Jenetics + Futures OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Genetic Algorithm Using Jenetics + Futures a b 300 600 900 1200 1500 1345.6 1344.7 MIN: 1290.39 / MAX: 1379.78 MIN: 1309.34 / MAX: 1413.55
vkpeak int32-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20240505 int32-scalar a b 200 400 600 800 1000 826.97 827.21
vkpeak fp64-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20240505 fp64-vec4 a b 50 100 150 200 250 213.37 213.43
vkpeak fp32-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20240505 fp32-scalar a b 400 800 1200 1600 2000 1989.85 1990.33
vkpeak int32-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20240505 int32-vec4 a b 200 400 600 800 1000 848.97 849.17
vkpeak int16-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20240505 int16-scalar a b 700 1400 2100 2800 3500 3189.67 3190.35
vkpeak fp64-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20240505 fp64-scalar a b 50 100 150 200 250 218.71 218.75
vkpeak fp16-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20240505 fp16-scalar a b 1300 2600 3900 5200 6500 6201.56 6202.63
vkpeak fp32-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20240505 fp32-vec4 a b 600 1200 1800 2400 3000 2928.03 2928.51
vkpeak fp16-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20240505 fp16-vec4 a b 1400 2800 4200 5600 7000 6532.13 6532.63
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 0.3218 0.6436 0.9654 1.2872 1.609 1.43 1.43 MIN: 0.89 / MAX: 5.19 MIN: 0.89 / MAX: 6.95 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
Phoronix Test Suite v10.8.5