AMD Ryzen 5 4500U versus Ice Lake on Ubuntu Linux performance.
Ryzen 5 4500U Processor: AMD Ryzen 5 4500U @ 2.38GHz (6 Cores), Motherboard: LENOVO LNVNB161216 (EECN20WW BIOS), Chipset: AMD Renoir Root Complex, Memory: 16GB, Disk: 256GB SKHynix_HFM256GDHTNI-87A0B, Graphics: AMD Renoir 512MB (1500/400MHz), Audio: AMD Device 1637, Network: Realtek RTL8822CE 802.11ac PCIe
OS: Ubuntu 20.04, Kernel: 5.9.0-050900rc7daily20201002-generic (x86_64) 20201001, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 20.3.0-devel (git-57b4f60 2020-10-02 focal-oibaf-ppa) (LLVM 10.0.1), Vulkan: 1.2.145, Compiler: GCC 9.3.0 + Clang 10.0.1-1~oibaf~fTarget:, File-System: ext4, Screen Resolution: 1920x1080
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8600102Python Notes: Python 3.8.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Core i7 1065G7 Processor: Intel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads) , Motherboard: Dell 06CDVY (1.0.9 BIOS) , Chipset: Intel Device 34ef , Memory: 16GB, Disk: KBG40ZPZ512G NVMe TOSHIBA 512GB , Graphics: Intel Iris Plus G7 3GB (1100MHz) , Audio: Realtek ALC289 , Network: Intel Killer Wi-Fi 6 AX1650i 160MHz
OS: Ubuntu 20.04, Kernel: 5.9.0-050900rc7daily20201003-generic (x86_64) 20201002, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 20.3.0-devel (git-81cd4c8 2020-10-03 focal-oibaf-ppa), Vulkan: 1.2.145, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1200
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --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 -vProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x78Python Notes: Python 3.8.2Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Renoir vs. Icelake Benchmarks Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution Ryzen 5 4500U Core i7 1065G7 AMD Ryzen 5 4500U @ 2.38GHz (6 Cores) LENOVO LNVNB161216 (EECN20WW BIOS) AMD Renoir Root Complex 16GB 256GB SKHynix_HFM256GDHTNI-87A0B AMD Renoir 512MB (1500/400MHz) AMD Device 1637 Realtek RTL8822CE 802.11ac PCIe Ubuntu 20.04 5.9.0-050900rc7daily20201002-generic (x86_64) 20201001 GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 4.6 Mesa 20.3.0-devel (git-57b4f60 2020-10-02 focal-oibaf-ppa) (LLVM 10.0.1) 1.2.145 GCC 9.3.0 + Clang 10.0.1-1~oibaf~fTarget: ext4 1920x1080 Intel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads) Dell 06CDVY (1.0.9 BIOS) Intel Device 34ef KBG40ZPZ512G NVMe TOSHIBA 512GB Intel Iris Plus G7 3GB (1100MHz) Realtek ALC289 Intel Killer Wi-Fi 6 AX1650i 160MHz 5.9.0-050900rc7daily20201003-generic (x86_64) 20201002 4.6 Mesa 20.3.0-devel (git-81cd4c8 2020-10-03 focal-oibaf-ppa) GCC 9.3.0 1920x1200 OpenBenchmarking.org Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --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 - Ryzen 5 4500U: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8600102 - Core i7 1065G7: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x78 Python Details - Python 3.8.2 Security Details - Ryzen 5 4500U: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected - Core i7 1065G7: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Ryzen 5 4500U vs. Core i7 1065G7 Comparison Phoronix Test Suite Baseline +39.5% +39.5% +79% +79% +118.5% +118.5% +158% +158% 53.5% 46.7% 45.7% 39.6% 38.8% 35% 34.4% 31.9% 30.6% 29.2% 28% 27.4% 26.7% 26.4% 25.2% 23.4% 23% 22.3% 21.8% 21.5% 19.9% 18.8% 18.5% 17.2% 17% 16.7% 15.9% 15.3% 14.9% 14.4% 13.4% 13.1% 11.7% 11.3% 11.1% 11% 10.4% 9.9% 9.9% 8.9% 8.2% 7.5% 7% 6.1% 2.9% 2.3% Vulkan GPU - shufflenet-v2 158.1% Vulkan GPU - mnasnet 108.3% Resizing 105.7% mobilenet-v1-1.0 95.3% Vulkan GPU - resnet18 93.8% I.R.V 91.7% Inception V4 91.3% Enhanced 91.2% Mobilenet Float 90.7% Vulkan GPU - resnet50 88.3% Vulkan GPU-v2-v2 - mobilenet-v2 87.9% SqueezeNet 87.3% Mobilenet Quant 86.1% Vulkan GPU-v3-v3 - mobilenet-v3 85% resnet-v2-50 83.9% Sharpen 75.6% NASNet Mobile 74.3% Thorough 69.3% Swirl 66.9% Disney Material 64.4% 1920 x 1080 63.6% inception-v3 62.3% R.C.a.P 60.8% Noise-Gaussian 60.3% V.P.M 59.9% Vulkan GPU - googlenet 59.1% DLSC 58.7% 2 58.6% Medium 56.4% 55.5% BMW27 - CPU-Only 55% B.B.B.S.1 - Software Only 54.6% Vulkan GPU - vgg16 54.6% HWB Color Space 54.4% T.T.F.S.S 54.1% CPU - vgg16 Rhodopsin Protein 53% Many Spheres - 1920 x 1080 52.3% Many Spheres - 1920 x 1080 52.2% B.B.B.S.4 - Software Only 52.1% Time To Compile 48.9% Material Tester 47.3% Rotate P.6.P.P.D 46.4% CoreMark Size 666 - I.P.S 46.1% StyleBench - Firefox D.I.S 45.4% Time To Compile 44.4% Time To Compile 42.1% SqueezeNetV1.0 40.9% Speedometer - Firefox C.S.T H.2.1.V.E 38% CPU-v3-v3 - mobilenet-v3 Vulkan GPU - yolov4-tiny 34.6% 19 T.B.T 31.3% 3 30.3% CPU - MobileNet v2 29.3% vklBenchmark Pathtracer - Crown 28.4% Enc Mode 4 - 1080p 27.5% Wavelet Contour - 1920 x 1080 27.5% Wavelet Contour - 1920 x 1080 27.5% CPU - shufflenet-v2 Vulkan GPU - efficientnet-b0 27.3% CPU - googlenet Timed Time - Size 1,000 CPU - SqueezeNet v1.1 25.7% CPU Server Room - CPU-only 25.1% SVG Files To PNG Device AI Score 23.1% CPU - resnet18 Basemark - Firefox CanvasMark - Firefox CPU-v2-v2 - mobilenet-v2 Scale 21.3% P.P.A.S.T 21.1% Vulkan GPU - mobilenet 20.6% 8 20.5% 2.D.T.P 18.8% T.F.A.T.T Vulkan GPU - blazeface 18.5% Pod2html C.S.T 17.3% PSPDFKit WASM - Firefox Summer Nature 4K 17% WebXPRT - Firefox CPU - mobilenet 17% Maze Solver - Firefox Enc Mode 8 - 1080p 16.1% GoogleNet - CPU - 200 16% Octane - Firefox 10 15.7% 1920 x 1080 - Fullscreen - Low - OpenGL 15.3% Q.1.L Masskrug - CPU-only 15% AlexNet - CPU - 200 14.9% Jetstream - Firefox Vulkan GPU - alexnet 14.4% Interpreter Enc Mode 0 - 1080p 14.3% Wavelet Volume - 1920 x 1080 14.2% Wavelet Volume - 1920 x 1080 14.2% Vulkan GPU - squeezenet Jetstream 2 - Firefox P.P.B 12.8% Vulkan - 1920 x 1080 - High 11.8% Memorial CPU - squeezenet 11.3% Server Rack - CPU-only CPU - alexnet S.N.1 Pathtracer ISPC - Crown 10.4% CPU ARES-6 - Firefox CPU - yolov4-tiny Crop 9.2% T.T.O.7.I WAV To FLAC 8.8% MobileNetV2_224 8.6% P.P.S Fast 8.2% Kraken - Firefox T.T.S.S T.T.C.C.G.C Q.1.L.H.C 5.9% 1920 x 1080 - Fullscreen - Medium - OpenGL 5.8% CPU - resnet50 5.2% D.T.S 5.1% Default 4.1% W.i - Firefox 4.1% W.c - Firefox 4.1% Rotate 90 Degrees 4.1% Vulkan - 1920 x 1080 - Medium 3.9% Quality 100 2.9% CPU - efficientnet-b0 Antialias 2.9% N.2.3.C.F.R 2.4% CPU - mnasnet NCNN NCNN GraphicsMagick Mobile Neural Network NCNN TensorFlow Lite TensorFlow Lite GraphicsMagick TensorFlow Lite NCNN NCNN TensorFlow Lite TensorFlow Lite NCNN Mobile Neural Network GraphicsMagick TensorFlow Lite ASTC Encoder GraphicsMagick Appleseed GLmark2 Mobile Neural Network LuxCoreRender GraphicsMagick BRL-CAD NCNN LuxCoreRender libavif avifenc ASTC Encoder libavif avifenc Blender MPV NCNN GraphicsMagick YafaRay NCNN LAMMPS Molecular Dynamics Simulator ParaView ParaView MPV Timed FFmpeg Compilation Appleseed GraphicsMagick OCRMyPDF Coremark Selenium AI Benchmark Alpha Build2 Timed Linux Kernel Compilation Mobile Neural Network Selenium ctx_clock x265 NCNN NCNN Zstd Compression GNU Octave Benchmark RawTherapee Zstd Compression RNNoise TNN OpenVKL Embree Numpy Benchmark SVT-AV1 ParaView ParaView NCNN NCNN NCNN SQLite Speedtest TNN NeatBench Darktable Inkscape AI Benchmark Alpha NCNN Selenium Selenium NCNN GEGL Hugin NCNN libavif avifenc LibreOffice WireGuard + Linux Networking Stack Stress Test PyBench NCNN Perl Benchmarks 7-Zip Compression Selenium dav1d Selenium NCNN Selenium SVT-AV1 Caffe Selenium libavif avifenc Unigine Superposition WebP Image Encode Darktable Caffe Selenium NCNN Perl Benchmarks SVT-AV1 ParaView ParaView NCNN Selenium LibRaw Basemark GPU Intel Open Image Denoise NCNN Darktable NCNN dav1d Embree DeepSpeech Selenium NCNN GEGL Tesseract OCR FLAC Audio Encoding Mobile Neural Network Himeno Benchmark ASTC Encoder Selenium eSpeak-NG Speech Engine Git WebP Image Encode Unigine Superposition NCNN AI Benchmark Alpha WebP Image Encode Selenium Selenium GEGL Basemark GPU WebP Image Encode NCNN GEGL FFTE NCNN Ryzen 5 4500U Core i7 1065G7
Renoir vs. Icelake Benchmarks ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU - mnasnet graphics-magick: Resizing mnn: mobilenet-v1-1.0 ncnn: Vulkan GPU - resnet18 tensorflow-lite: Inception ResNet V2 tensorflow-lite: Inception V4 graphics-magick: Enhanced tensorflow-lite: Mobilenet Float ncnn: Vulkan GPU - resnet50 tensorflow-lite: SqueezeNet tensorflow-lite: Mobilenet Quant ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 mnn: resnet-v2-50 graphics-magick: Sharpen tensorflow-lite: NASNet Mobile astcenc: Thorough graphics-magick: Swirl appleseed: Disney Material glmark2: 1920 x 1080 mnn: inception-v3 luxcorerender: Rainbow Colors and Prism graphics-magick: Noise-Gaussian brl-cad: VGR Performance Metric ncnn: Vulkan GPU - googlenet luxcorerender: DLSC avifenc: 2 astcenc: Medium avifenc: 0 blender: BMW27 - CPU-Only mpv: Big Buck Bunny Sunflower 1080p - Software Only ncnn: Vulkan GPU - vgg16 graphics-magick: HWB Color Space yafaray: Total Time For Sample Scene ncnn: CPU - vgg16 paraview: Many Spheres - 1920 x 1080 paraview: Many Spheres - 1920 x 1080 mpv: Big Buck Bunny Sunflower 4K - Software Only build-ffmpeg: Time To Compile appleseed: Material Tester graphics-magick: Rotate ocrmypdf: Processing 60 Page PDF Document coremark: CoreMark Size 666 - Iterations Per Second selenium: StyleBench - Firefox ai-benchmark: Device Inference Score build2: Time To Compile build-linux-kernel: Time To Compile mnn: SqueezeNetV1.0 selenium: Speedometer - Firefox ctx-clock: Context Switch Time x265: H.265 1080p Video Encoding ncnn: Vulkan GPU - yolov4-tiny compress-zstd: 19 octave-benchmark: rawtherapee: Total Benchmark Time compress-zstd: 3 rnnoise: tnn: CPU - MobileNet v2 openvkl: vklBenchmark embree: Pathtracer - Crown numpy: svt-av1: Enc Mode 4 - 1080p ncnn: Vulkan GPU - efficientnet-b0 sqlite-speedtest: Timed Time - Size 1,000 tnn: CPU - SqueezeNet v1.1 neatbench: CPU inkscape: SVG Files To PNG ai-benchmark: Device AI Score ncnn: CPU - resnet18 selenium: Basemark - Firefox selenium: CanvasMark - Firefox gegl: Scale hugin: Panorama Photo Assistant + Stitching Time ncnn: Vulkan GPU - mobilenet avifenc: 8 libreoffice: 20 Documents To PDF wireguard: pybench: Total For Average Test Times perl-benchmark: Pod2html compress-7zip: Compress Speed Test selenium: PSPDFKit WASM - Firefox dav1d: Summer Nature 4K selenium: WebXPRT - Firefox ncnn: CPU - mobilenet selenium: Maze Solver - Firefox svt-av1: Enc Mode 8 - 1080p caffe: GoogleNet - CPU - 200 selenium: Octane - Firefox avifenc: 10 unigine-super: 1920 x 1080 - Fullscreen - Low - OpenGL webp: Quality 100, Lossless darktable: Masskrug - CPU-only caffe: AlexNet - CPU - 200 selenium: Jetstream - Firefox ncnn: Vulkan GPU - alexnet perl-benchmark: Interpreter svt-av1: Enc Mode 0 - 1080p paraview: Wavelet Volume - 1920 x 1080 paraview: Wavelet Volume - 1920 x 1080 ncnn: Vulkan GPU - squeezenet selenium: Jetstream 2 - Firefox libraw: Post-Processing Benchmark basemark: Vulkan - 1920 x 1080 - High oidn: Memorial ncnn: CPU - squeezenet darktable: Server Rack - CPU-only ncnn: CPU - alexnet embree: Pathtracer ISPC - Crown deepspeech: CPU selenium: ARES-6 - Firefox ncnn: CPU - yolov4-tiny gegl: Crop tesseract-ocr: Time To OCR 7 Images himeno: Poisson Pressure Solver astcenc: Fast selenium: Kraken - Firefox espeak: Text-To-Speech Synthesis git: Time To Complete Common Git Commands webp: Quality 100, Lossless, Highest Compression unigine-super: 1920 x 1080 - Fullscreen - Medium - OpenGL ncnn: CPU - resnet50 ai-benchmark: Device Training Score webp: Default selenium: WASM imageConvolute - Firefox selenium: WASM collisionDetection - Firefox gegl: Rotate 90 Degrees basemark: Vulkan - 1920 x 1080 - Medium webp: Quality 100 gegl: Antialias encode-mp3: WAV To MP3 gegl: Color Enhance webp: Quality 100, Highest Compression gegl: Tile Glass gegl: Cartoon dolfyn: Computational Fluid Dynamics gegl: Wavelet Blur gegl: Reflect vkfft: paraview: Wavelet Contour - 1920 x 1080 paraview: Wavelet Contour - 1920 x 1080 ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: CPU - googlenet ncnn: CPU - blazeface ncnn: CPU - efficientnet-b0 ncnn: CPU - mnasnet ncnn: CPU - shufflenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU-v2-v2 - mobilenet-v2 mnn: MobileNetV2_224 lammps: Rhodopsin Protein ffte: N=256, 3D Complex FFT Routine encode-flac: WAV To FLAC dav1d: Summer Nature 1080p darktable: Server Room - CPU-only darktable: Boat - CPU-only Ryzen 5 4500U Core i7 1065G7 4.13 5.20 576 4.831 8.83 4332290 4793913 109 221797 19.02 334171 226773 6.34 32.106 72 261175 59.08 247 523.471454 1661 44.581 0.82 125 50866 11.74 0.73 96.768 8.44 165.972 399.89 683.98 62.04 806 349.325 109.85 8.77 878.797 259.13 121.308 532.122345 606 44.604 167307.980014 59.5 676 243.860 200.772 8.745 63.51 118 30.56 31.24 16.0 8.944 87.388 2424.2 19.772 260.427 59.67 3.8048 282.20 1.312 13.18 74.752 256.238 8.15 28.035 1279 27.79 449.51 9794 6.498 65.381 18.12 6.995 7.976 276.870 994 0.12838271 22912 1768 77.55 206 28.38 6.3 10.613 295400 30445 6.405 22.6 21.525 9.817 113117 176.33 14.49 0.00105822 0.072 942.191 58.89 24.72 84.037 28.44 22.59 4.52 25.31 0.267 22.86 3.6294 73.51014 47.63 48.06 9.069 25.618 4155.741971 7.21 892.3 33.140 55.614 45.926 11.0 49.95 603 1.556 29.3 400.7 44.131 105.98 2.424 41.878 7.813 61.569 7.568 33.634 96.512 18.772 66.105 33.040 2580 536.719 51.50 1.89 5.69 33.23 2.38 12.91 7.52 6.79 9.22 9.26 4.800 4.041 22192.970247223 8.614 238.68 6.420 16.838 10.66 10.83 280 9.433 17.11 8303800 9170150 57 422984 35.82 626064 421963 11.73 59.027 41 455216 100.05 148 860.340601 1015 72.373 0.51 78 31812 18.68 0.46 153.449 13.20 258.151 619.67 442.46 95.90 522 538.414 71.56 5.76 577.239 170.38 180.686 783.823337 889 65.278 114477.279309 86.7 465 352.192 285.251 12.325 88.67 85 22.14 42.06 21.5 6.781 114.773 3165.4 25.764 336.738 77.11 2.9628 361.15 1.029 16.78 59.157 321.966 10.2 22.713 1039 22.59 549.84 11926 7.884 79.160 21.85 8.429 6.653 328.947 837 0.10834320 19534 1509 66.28 241 33.20 5.4 9.140 342564 35275 7.411 19.6 18.675 11.291 129988 202.57 16.58 0.00092512 0.063 825.224 51.58 21.79 95.073 25.21 20.21 5.05 28.16 0.240 20.57 3.2869 66.58825 43.33 43.75 9.903 23.519 4496.690725 7.80 830.1 30.976 52.397 48.633 10.4 52.54 574 1.620 30.5 417.1 45.937 101.98 2.494 43.073 7.957 62.407 7.488 33.406 95.913 18.661 66.375 33.099 421.003 40.40 2.24 10.69 26.22 2.42 12.55 7.35 5.33 6.83 7.62 5.215 2.641 21665.391928848 9.371 265.01 8.031 17.015 OpenBenchmarking.org
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: shufflenet-v2 Ryzen 5 4500U Core i7 1065G7 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.35, N = 3 4.13 10.66 MIN: 3.8 / MAX: 5.21 MIN: 10.08 / MAX: 12.18 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: mnasnet Ryzen 5 4500U Core i7 1065G7 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 5.20 10.83 MIN: 4.9 / MAX: 11.7 MIN: 10.5 / MAX: 14.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Mobile Neural Network MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by ALibaba. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: mobilenet-v1-1.0 Ryzen 5 4500U Core i7 1065G7 3 6 9 12 15 SE +/- 0.029, N = 3 SE +/- 0.013, N = 3 4.831 9.433 MIN: 4.3 / MAX: 21.97 MIN: 8.89 / MAX: 15.49 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: resnet18 Ryzen 5 4500U Core i7 1065G7 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 8.83 17.11 MIN: 8.54 / MAX: 10.22 MIN: 16.81 / MAX: 17.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: resnet50 Ryzen 5 4500U Core i7 1065G7 8 16 24 32 40 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 19.02 35.82 MIN: 18.55 / MAX: 20.08 MIN: 35.58 / MAX: 36.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 Ryzen 5 4500U Core i7 1065G7 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.36, N = 3 6.34 11.73 MIN: 5.92 / MAX: 23.58 MIN: 10.88 / MAX: 14.69 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Mobile Neural Network MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by ALibaba. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: resnet-v2-50 Ryzen 5 4500U Core i7 1065G7 13 26 39 52 65 SE +/- 0.21, N = 3 SE +/- 0.35, N = 3 32.11 59.03 MIN: 29.79 / MAX: 51.51 MIN: 56.05 / MAX: 82.31 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: googlenet Ryzen 5 4500U Core i7 1065G7 5 10 15 20 25 SE +/- 0.10, N = 3 SE +/- 0.02, N = 3 11.74 18.68 MIN: 11.01 / MAX: 30 MIN: 18.52 / MAX: 19.07 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: vgg16 Ryzen 5 4500U Core i7 1065G7 20 40 60 80 100 SE +/- 0.27, N = 3 SE +/- 0.03, N = 3 62.04 95.90 MIN: 60.99 / MAX: 81.46 MIN: 93.54 / MAX: 96.72 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: vgg16 Ryzen 5 4500U Core i7 1065G7 20 40 60 80 100 SE +/- 0.42, N = 3 SE +/- 0.02, N = 3 109.85 71.56 MIN: 107.76 / MAX: 158.7 MIN: 70.12 / MAX: 87.59 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread