icelake 2023 Tests for a future article. Intel Core i7-1065G7 testing with a Dell 06CDVY (1.0.9 BIOS) and Intel Iris Plus ICL GT2 16GB on Ubuntu 23.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2310252-NE-ICELAKE2057&grr .
icelake 2023 Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL OpenCL Compiler File-System Screen Resolution a b Intel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads) Dell 06CDVY (1.0.9 BIOS) Intel Ice Lake-LP DRAM 16GB Toshiba KBG40ZPZ512G NVMe 512GB Intel Iris Plus ICL GT2 16GB (1100MHz) Realtek ALC289 Intel Ice Lake-LP PCH CNVi WiFi Ubuntu 23.04 6.2.0-24-generic (x86_64) GNOME Shell 44.0 X Server + Wayland 4.6 Mesa 23.0.4-0ubuntu1~23.04.1 OpenCL 3.0 GCC 12.3.0 ext4 1920x1200 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-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-12-DAPbBt/gcc-12-12.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-DAPbBt/gcc-12-12.3.0/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: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xb8 - Thermald 2.5.2 Security Details - itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Mitigation of Microcode + tsx_async_abort: Not affected
icelake 2023 openradioss: Chrysler Neon 1M openradioss: INIVOL and Fluid Structure Interaction Drop Container fluidx3d: FP32-FP16C openradioss: Bird Strike on Windshield openradioss: Rubber O-Ring Seal Installation fluidx3d: FP32-FP32 oidn: RTLightmap.hdr.4096x4096 - CPU-Only easywave: e2Asean Grid + BengkuluSept2007 Source - 2400 avifenc: 0 openradioss: Bumper Beam fluidx3d: FP32-FP16S openradioss: Cell Phone Drop Test oidn: RT.ldr_alb_nrm.3840x2160 - CPU-Only oidn: RT.hdr_alb_nrm.3840x2160 - CPU-Only embree: Pathtracer - Crown embree: Pathtracer ISPC - Crown embree: Pathtracer - Asian Dragon Obj avifenc: 2 embree: Pathtracer ISPC - Asian Dragon Obj embree: Pathtracer - Asian Dragon easywave: e2Asean Grid + BengkuluSept2007 Source - 1200 svt-av1: Preset 4 - Bosphorus 4K embree: Pathtracer ISPC - Asian Dragon ncnn: CPU - FastestDet ncnn: CPU - vision_transformer ncnn: CPU - regnety_400m ncnn: CPU - squeezenet_ssd ncnn: CPU - yolov4-tiny ncnn: CPU - resnet50 ncnn: CPU - alexnet ncnn: CPU - resnet18 ncnn: CPU - vgg16 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 ncnn: CPU - mobilenet ncnn: Vulkan GPU - FastestDet ncnn: Vulkan GPU - vision_transformer ncnn: Vulkan GPU - regnety_400m ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU - mobilenet onednn: Recurrent Neural Network Training - u8s8f32 - CPU onednn: Recurrent Neural Network Training - f32 - CPU onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Recurrent Neural Network Inference - u8s8f32 - CPU quantlib: Multi-Threaded svt-av1: Preset 8 - Bosphorus 4K svt-av1: Preset 4 - Bosphorus 1080p avifenc: 6, Lossless stress-ng: Cloning stress-ng: Vector Shuffle stress-ng: Wide Vector Math quantlib: Single-Threaded avifenc: 6 aom-av1: Speed 9 Realtime - Bosphorus 4K svt-av1: Preset 8 - Bosphorus 1080p onednn: Deconvolution Batch shapes_1d - f32 - CPU onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU svt-av1: Preset 12 - Bosphorus 4K aom-av1: Speed 10 Realtime - Bosphorus 4K svt-av1: Preset 13 - Bosphorus 4K aom-av1: Speed 11 Realtime - Bosphorus 4K onednn: IP Shapes 1D - f32 - CPU onednn: IP Shapes 1D - u8s8f32 - CPU easywave: e2Asean Grid + BengkuluSept2007 Source - 240 avifenc: 10, Lossless onednn: IP Shapes 3D - f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - f32 - CPU aom-av1: Speed 9 Realtime - Bosphorus 1080p aom-av1: Speed 10 Realtime - Bosphorus 1080p aom-av1: Speed 11 Realtime - Bosphorus 1080p svt-av1: Preset 12 - Bosphorus 1080p onednn: Deconvolution Batch shapes_3d - f32 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU svt-av1: Preset 13 - Bosphorus 1080p onednn: IP Shapes 1D - bf16bf16bf16 - CPU a b 2917.08 1818.21 210 921.19 693.04 257 0.04 560.794 581.559 512.2 500 337.47 0.09 0.09 2.5641 2.8093 2.9828 257.08 3.2088 3.2657 225.678 0.727 3.6724 5.15 267.05 11.97 13.81 32.22 34.19 10.3 12.98 70.08 17.18 1.15 10.72 5.83 4.33 3.54 4.37 24.14 5.64 268.47 11.95 13.89 32.2 34.28 10.38 13.06 70.21 17.19 1.17 10.78 5.24 2.71 3.54 4.35 24.15 14373.9 14396.7 14376.4 7398.63 7400.64 7378.4 7472.8 9.095 2.726 39.912 641.54 2156.51 88229.8 2898.3 28.757 34.32 25.293 21.4405 9.48511 27.939 34.32 30.093 33.21 13.3903 6.00177 11.91 13.14 9.05715 3.81175 17.715 13.1328 146.87 144.8 150.75 191.279 15.1772 8.16222 255.397 2947.38 1824.13 209 953.64 694.01 264 0.05 560.991 540.786 516.66 496 338.36 0.10 0.10 2.6409 2.8357 3.035 238.246 3.3091 3.2676 225.755 0.769 3.8233 5.25 254.37 11.26 13.15 30.62 31.55 9.61 11.81 65.36 16.11 1.05 10.23 4.02 2.73 3.54 4.46 22.94 4.84 251.88 11.33 13.12 30.66 32.25 9.57 11.79 65.22 16.13 1.08 10.14 3.6 2.79 3.48 4.47 22.83 13583.8 12976.6 12945.5 6677.03 6701.8 6648.27 7336.6 9.974 2.989 36.845 702.93 2306.11 96693.23 2894.4 26.309 34.37 28.357 12.9325 8.47414 31.483 35.13 32.582 33.31 10.7302 4.91146 11.933 12.02 8.04914 3.0439 15.4635 13.1309 147.01 143.67 150.93 190.598 15.0825 8.149 252.158 OpenBenchmarking.org
OpenRadioss Model: Chrysler Neon 1M OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Chrysler Neon 1M a b 600 1200 1800 2400 3000 2917.08 2947.38
OpenRadioss Model: INIVOL and Fluid Structure Interaction Drop Container OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: INIVOL and Fluid Structure Interaction Drop Container a b 400 800 1200 1600 2000 1818.21 1824.13
FluidX3D Test: FP32-FP16C OpenBenchmarking.org MLUPs/s, More Is Better FluidX3D 2.9 Test: FP32-FP16C a b 50 100 150 200 250 210 209
OpenRadioss Model: Bird Strike on Windshield OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Bird Strike on Windshield a b 200 400 600 800 1000 921.19 953.64
OpenRadioss Model: Rubber O-Ring Seal Installation OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Rubber O-Ring Seal Installation a b 150 300 450 600 750 693.04 694.01
FluidX3D Test: FP32-FP32 OpenBenchmarking.org MLUPs/s, More Is Better FluidX3D 2.9 Test: FP32-FP32 a b 60 120 180 240 300 257 264
Intel Open Image Denoise Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.1 Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only a b 0.0113 0.0226 0.0339 0.0452 0.0565 0.04 0.05
easyWave Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400 OpenBenchmarking.org Seconds, Fewer Is Better easyWave r34 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400 a b 120 240 360 480 600 560.79 560.99 1. (CXX) g++ options: -O3 -fopenmp
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 0 a b 130 260 390 520 650 581.56 540.79 1. (CXX) g++ options: -O3 -fPIC -lm
OpenRadioss Model: Bumper Beam OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Bumper Beam a b 110 220 330 440 550 512.20 516.66
FluidX3D Test: FP32-FP16S OpenBenchmarking.org MLUPs/s, More Is Better FluidX3D 2.9 Test: FP32-FP16S a b 110 220 330 440 550 500 496
OpenRadioss Model: Cell Phone Drop Test OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Cell Phone Drop Test a b 70 140 210 280 350 337.47 338.36
Intel Open Image Denoise Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.1 Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only a b 0.0225 0.045 0.0675 0.09 0.1125 0.09 0.10
Intel Open Image Denoise Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.1 Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only a b 0.0225 0.045 0.0675 0.09 0.1125 0.09 0.10
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer - Model: Crown a b 0.5942 1.1884 1.7826 2.3768 2.971 2.5641 2.6409 MIN: 2.54 / MAX: 2.62 MIN: 2.53 / MAX: 2.86
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Crown a b 0.638 1.276 1.914 2.552 3.19 2.8093 2.8357 MIN: 2.78 / MAX: 2.89 MIN: 2.76 / MAX: 3.16
Embree Binary: Pathtracer - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer - Model: Asian Dragon Obj a b 0.6829 1.3658 2.0487 2.7316 3.4145 2.9828 3.0350 MIN: 2.96 / MAX: 3.03 MIN: 2.95 / MAX: 3.29
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 2 a b 60 120 180 240 300 257.08 238.25 1. (CXX) g++ options: -O3 -fPIC -lm
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Obj a b 0.7445 1.489 2.2335 2.978 3.7225 3.2088 3.3091 MIN: 3.18 / MAX: 3.26 MIN: 3.19 / MAX: 3.62
Embree Binary: Pathtracer - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer - Model: Asian Dragon a b 0.7352 1.4704 2.2056 2.9408 3.676 3.2657 3.2676 MIN: 3.23 / MAX: 3.33 MIN: 3.2 / MAX: 3.53
easyWave Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200 OpenBenchmarking.org Seconds, Fewer Is Better easyWave r34 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200 a b 50 100 150 200 250 225.68 225.76 1. (CXX) g++ options: -O3 -fopenmp
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K a b 0.173 0.346 0.519 0.692 0.865 0.727 0.769 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon a b 0.8602 1.7204 2.5806 3.4408 4.301 3.6724 3.8233 MIN: 3.64 / MAX: 3.74 MIN: 3.66 / MAX: 4.13
NCNN Target: CPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: FastestDet a b 1.1813 2.3626 3.5439 4.7252 5.9065 5.15 5.25 MIN: 4.89 / MAX: 15.82 MIN: 5.09 / MAX: 12.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vision_transformer a b 60 120 180 240 300 267.05 254.37 MIN: 261.81 / MAX: 284.75 MIN: 245.85 / MAX: 753.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: regnety_400m a b 3 6 9 12 15 11.97 11.26 MIN: 11.19 / MAX: 23.34 MIN: 10.71 / MAX: 22.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: squeezenet_ssd a b 4 8 12 16 20 13.81 13.15 MIN: 13.11 / MAX: 25.08 MIN: 12.51 / MAX: 24.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: yolov4-tiny a b 7 14 21 28 35 32.22 30.62 MIN: 30.8 / MAX: 42.97 MIN: 29.78 / MAX: 41.83 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet50 a b 8 16 24 32 40 34.19 31.55 MIN: 32.53 / MAX: 48.47 MIN: 30.01 / MAX: 42.43 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: alexnet a b 3 6 9 12 15 10.30 9.61 MIN: 8.89 / MAX: 20.31 MIN: 8.48 / MAX: 20.48 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet18 a b 3 6 9 12 15 12.98 11.81 MIN: 12.11 / MAX: 25.94 MIN: 11.4 / MAX: 27.26 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vgg16 a b 16 32 48 64 80 70.08 65.36 MIN: 66.44 / MAX: 80.57 MIN: 62.97 / MAX: 77.5 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: googlenet a b 4 8 12 16 20 17.18 16.11 MIN: 16 / MAX: 29.65 MIN: 15.41 / MAX: 27.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: blazeface a b 0.2588 0.5176 0.7764 1.0352 1.294 1.15 1.05 MIN: 1.08 / MAX: 7.24 MIN: 0.98 / MAX: 5.03 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: efficientnet-b0 a b 3 6 9 12 15 10.72 10.23 MIN: 10.17 / MAX: 21.68 MIN: 9.49 / MAX: 21.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mnasnet a b 1.3118 2.6236 3.9354 5.2472 6.559 5.83 4.02 MIN: 5.4 / MAX: 19 MIN: 3.47 / MAX: 16.72 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: shufflenet-v2 a b 0.9743 1.9486 2.9229 3.8972 4.8715 4.33 2.73 MIN: 3.92 / MAX: 15.31 MIN: 2.61 / MAX: 12.22 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 a b 0.7965 1.593 2.3895 3.186 3.9825 3.54 3.54 MIN: 3.4 / MAX: 13.43 MIN: 3.39 / MAX: 13.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 a b 1.0035 2.007 3.0105 4.014 5.0175 4.37 4.46 MIN: 4.21 / MAX: 13.61 MIN: 4.22 / MAX: 14.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mobilenet a b 6 12 18 24 30 24.14 22.94 MIN: 22.95 / MAX: 34.8 MIN: 21.77 / MAX: 34.37 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: FastestDet a b 1.269 2.538 3.807 5.076 6.345 5.64 4.84 MIN: 5.29 / MAX: 16.11 MIN: 4.59 / MAX: 13.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer a b 60 120 180 240 300 268.47 251.88 MIN: 262.87 / MAX: 279.73 MIN: 245.57 / MAX: 275.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m a b 3 6 9 12 15 11.95 11.33 MIN: 11.17 / MAX: 23.16 MIN: 10.77 / MAX: 21.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd a b 4 8 12 16 20 13.89 13.12 MIN: 13.1 / MAX: 28.84 MIN: 12.52 / MAX: 24.8 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny a b 7 14 21 28 35 32.20 30.66 MIN: 31.01 / MAX: 43.29 MIN: 29.83 / MAX: 42 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet50 a b 8 16 24 32 40 34.28 32.25 MIN: 32.55 / MAX: 45.96 MIN: 30.03 / MAX: 45.13 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: alexnet a b 3 6 9 12 15 10.38 9.57 MIN: 8.85 / MAX: 21.96 MIN: 8.44 / MAX: 19.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet18 a b 3 6 9 12 15 13.06 11.79 MIN: 12.51 / MAX: 26 MIN: 11.39 / MAX: 25.81 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vgg16 a b 16 32 48 64 80 70.21 65.22 MIN: 66.55 / MAX: 80.56 MIN: 63.02 / MAX: 76.03 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: googlenet a b 4 8 12 16 20 17.19 16.13 MIN: 15.97 / MAX: 28.67 MIN: 15.44 / MAX: 27.07 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: blazeface a b 0.2633 0.5266 0.7899 1.0532 1.3165 1.17 1.08 MIN: 1.07 / MAX: 10.59 MIN: 1.03 / MAX: 5.53 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 a b 3 6 9 12 15 10.78 10.14 MIN: 10.21 / MAX: 21.92 MIN: 8.56 / MAX: 21.18 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mnasnet a b 1.179 2.358 3.537 4.716 5.895 5.24 3.60 MIN: 3.48 / MAX: 17.52 MIN: 3.47 / MAX: 8.6 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 a b 0.6278 1.2556 1.8834 2.5112 3.139 2.71 2.79 MIN: 2.62 / MAX: 12.47 MIN: 2.62 / MAX: 12.19 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 a b 0.7965 1.593 2.3895 3.186 3.9825 3.54 3.48 MIN: 3.4 / MAX: 13.64 MIN: 3.4 / MAX: 7.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 a b 1.0058 2.0116 3.0174 4.0232 5.029 4.35 4.47 MIN: 4.2 / MAX: 14.21 MIN: 4.2 / MAX: 14.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mobilenet a b 6 12 18 24 30 24.15 22.83 MIN: 22.83 / MAX: 34.07 MIN: 21.89 / MAX: 33.08 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU a b 3K 6K 9K 12K 15K 14373.9 13583.8 MIN: 14132.5 MIN: 13104.3 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU a b 3K 6K 9K 12K 15K 14396.7 12976.6 MIN: 14160.6 MIN: 12797.4 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU a b 3K 6K 9K 12K 15K 14376.4 12945.5 MIN: 14135.6 MIN: 12762.5 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU a b 1600 3200 4800 6400 8000 7398.63 6677.03 MIN: 7210.77 MIN: 6521.21 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU a b 1600 3200 4800 6400 8000 7400.64 6701.80 MIN: 7186.27 MIN: 6511.57 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU a b 1600 3200 4800 6400 8000 7378.40 6648.27 MIN: 7171.27 MIN: 6485.23 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
QuantLib Configuration: Multi-Threaded OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Multi-Threaded a b 1600 3200 4800 6400 8000 7472.8 7336.6 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K a b 3 6 9 12 15 9.095 9.974 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 1080p a b 0.6725 1.345 2.0175 2.69 3.3625 2.726 2.989 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
libavif avifenc Encoder Speed: 6, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6, Lossless a b 9 18 27 36 45 39.91 36.85 1. (CXX) g++ options: -O3 -fPIC -lm
Stress-NG Test: Cloning OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Cloning a b 150 300 450 600 750 641.54 702.93 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lmpfr -lpthread -lrt -lz
Stress-NG Test: Vector Shuffle OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Shuffle a b 500 1000 1500 2000 2500 2156.51 2306.11 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lmpfr -lpthread -lrt -lz
Stress-NG Test: Wide Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Wide Vector Math a b 20K 40K 60K 80K 100K 88229.80 96693.23 1. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lmpfr -lpthread -lrt -lz
QuantLib Configuration: Single-Threaded OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Single-Threaded a b 600 1200 1800 2400 3000 2898.3 2894.4 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
libavif avifenc Encoder Speed: 6 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6 a b 7 14 21 28 35 28.76 26.31 1. (CXX) g++ options: -O3 -fPIC -lm
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.7 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K a b 8 16 24 32 40 34.32 34.37 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 1080p a b 7 14 21 28 35 25.29 28.36 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU a b 5 10 15 20 25 21.44 12.93 MIN: 17.2 MIN: 11.01 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU a b 3 6 9 12 15 9.48511 8.47414 MIN: 8.16 MIN: 7.22 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 4K a b 7 14 21 28 35 27.94 31.48 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
AOM AV1 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.7 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K a b 8 16 24 32 40 34.32 35.13 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 4K a b 8 16 24 32 40 30.09 32.58 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
AOM AV1 Encoder Mode: Speed 11 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.7 Encoder Mode: Speed 11 Realtime - Input: Bosphorus 4K a b 8 16 24 32 40 33.21 33.31 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU a b 3 6 9 12 15 13.39 10.73 MIN: 7.71 MIN: 7.53 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU a b 2 4 6 8 10 6.00177 4.91146 MIN: 3.57 MIN: 3.5 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
easyWave Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240 OpenBenchmarking.org Seconds, Fewer Is Better easyWave r34 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240 a b 3 6 9 12 15 11.91 11.93 1. (CXX) g++ options: -O3 -fopenmp
libavif avifenc Encoder Speed: 10, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 10, Lossless a b 3 6 9 12 15 13.14 12.02 1. (CXX) g++ options: -O3 -fPIC -lm
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU a b 3 6 9 12 15 9.05715 8.04914 MIN: 7.61 MIN: 7.4 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU a b 0.8576 1.7152 2.5728 3.4304 4.288 3.81175 3.04390 MIN: 2.41 MIN: 2.19 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU a b 4 8 12 16 20 17.72 15.46 MIN: 14.78 MIN: 14.77 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU a b 3 6 9 12 15 13.13 13.13 MIN: 12.76 MIN: 12.68 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.7 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p a b 30 60 90 120 150 146.87 147.01 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
AOM AV1 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.7 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p a b 30 60 90 120 150 144.80 143.67 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
AOM AV1 Encoder Mode: Speed 11 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.7 Encoder Mode: Speed 11 Realtime - Input: Bosphorus 1080p a b 30 60 90 120 150 150.75 150.93 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 1080p a b 40 80 120 160 200 191.28 190.60 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU a b 4 8 12 16 20 15.18 15.08 MIN: 14.54 MIN: 14.35 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU a b 2 4 6 8 10 8.16222 8.14900 MIN: 7.27 MIN: 7.2 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 1080p a b 60 120 180 240 300 255.40 252.16 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Phoronix Test Suite v10.8.5