Intel Core i9-9900K testing with a ASRock Z390M Pro4 (P4.20 BIOS) and Intel UHD 630 3GB on Ubuntu 20.04 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2009261-FI-9900KWIES08 9900k-wiesn - Phoronix Test Suite 9900k-wiesn Intel Core i9-9900K testing with a ASRock Z390M Pro4 (P4.20 BIOS) and Intel UHD 630 3GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2009261-FI-9900KWIES08&grt&sor .
9900k-wiesn Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Compiler File-System Screen Resolution 1 2 3 3a Intel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads) ASRock Z390M Pro4 (P4.20 BIOS) Intel Cannon Lake PCH 16GB 240GB Corsair Force MP510 Intel UHD 630 3GB (1200MHz) Realtek ALC892 G237HL Intel I219-V Ubuntu 20.04 5.9.0-050900rc1daily20200819-generic (x86_64) 20200818 GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 4.6 Mesa 20.0.4 OpenCL 2.1 GCC 9.3.0 ext4 1920x1080 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 - Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6 Python Details - Python 2.7.18rc1 + Python 3.8.2 Security Details - itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Vulnerable; SMT vulnerable + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled + srbds: Vulnerable + tsx_async_abort: Vulnerable
9900k-wiesn ai-benchmark: Device Inference Score ai-benchmark: Device Training Score ai-benchmark: Device AI Score aom-av1: Speed 0 Two-Pass couchdb: 100 - 1000 - 24 dcraw: RAW To PPM Image Conversion espeak: Text-To-Speech Synthesis glmark2: 1920 x 1080 gpaw: Carbon Nanotube incompact3d: Cylinder influxdb: 4 - 10000 - 2,5000,1 - 10000 influxdb: 64 - 10000 - 2,5000,1 - 10000 influxdb: 1024 - 10000 - 2,5000,1 - 10000 lammps: 20k Atoms lammps: Rhodopsin Protein lczero: BLAS lczero: Eigen lczero: OpenCL libraw: Post-Processing Benchmark mnn: SqueezeNetV1.0 mnn: resnet-v2-50 mnn: MobileNetV2_224 mnn: mobilenet-v1-1.0 mnn: inception-v3 mocassin: Dust 2D tau100.0 ncnn: CPU - squeezenet ncnn: CPU - mobilenet ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU - shufflenet-v2 ncnn: CPU - mnasnet ncnn: CPU - efficientnet-b0 ncnn: CPU - blazeface ncnn: CPU - googlenet ncnn: CPU - vgg16 ncnn: CPU - resnet18 ncnn: CPU - alexnet ncnn: CPU - resnet50 ncnn: CPU - yolov4-tiny ncnn: Vulkan GPU - squeezenet ncnn: Vulkan GPU - mobilenet ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - yolov4-tiny opencv: Features 2D opencv: Object Detection opencv: DNN - Deep Neural Network realsr-ncnn: 4x - No system-decompress-gzip: tnn: CPU - MobileNet v2 tnn: CPU - SqueezeNet v1.1 webp: Default webp: Quality 100 webp: Quality 100, Lossless webp: Quality 100, Highest Compression webp: Quality 100, Lossless, Highest Compression 1 2 3 3a 0.33 754 367.892863 6.134 6.850 38.82 192 253.485 1.366 2.113 15.537 6.322 33.012 1181 1139 2320 75.749 33.290 24.995 744 343.004 367.039266 1623050.5 1631004.7 1635245.9 6.149 6.856 860 786 327 39.20 5.795 34.634 2.966 6.350 37.704 191 15.50 17.78 4.99 3.98 2.90 3.78 6.22 1.54 15.34 66.00 14.80 15.80 27.34 26.41 39.52 34.76 11.30 12.64 7.95 11.78 23.60 1.98 32.35 185.11 28.50 46.77 68.69 70.98 109975 37985 24960 253.416 2.566 285.030 268.092 1.356 2.110 15.555 6.325 33.040 762 365.954091 6.132 6.831 39.21 191 253.359 1.350 2.109 15.256 6.346 32.939 1183 1143 2326 0.33 73.534 33.278 24.995 781 343.647 365.685353 1623988.5 1633876.8 1635905.7 6.143 6.849 859 784 321 38.99 5.817 34.813 2.967 6.320 37.875 191 15.45 17.79 4.98 3.98 2.87 3.76 6.28 1.60 15.33 66.07 14.66 15.73 27.01 26.44 39.57 34.51 11.29 12.64 7.95 11.77 23.58 1.94 32.34 184.87 28.51 46.02 68.71 70.65 110406 37334 17734 253.444 2.568 288.317 268.222 1.364 2.111 15.423 6.326 32.650 OpenBenchmarking.org
AI Benchmark Alpha Device Inference Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Inference Score 3a 2 300 600 900 1200 1500 1183 1181
AI Benchmark Alpha Device Training Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Training Score 3a 2 200 400 600 800 1000 1143 1139
AI Benchmark Alpha Device AI Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device AI Score 3a 2 500 1000 1500 2000 2500 2326 2320
AOM AV1 Encoder Mode: Speed 0 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 0 Two-Pass 3a 1 0.0743 0.1486 0.2229 0.2972 0.3715 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.33 0.33 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Apache CouchDB Bulk Size: 100 - Inserts: 1000 - Rounds: 24 OpenBenchmarking.org Seconds, Fewer Is Better Apache CouchDB 3.1.1 Bulk Size: 100 - Inserts: 1000 - Rounds: 24 3a 2 20 40 60 80 100 SE +/- 0.64, N = 3 SE +/- 0.88, N = 6 73.53 75.75 1. (CXX) g++ options: -std=c++14 -lmozjs-68 -lm -lerl_interface -lei -fPIC -MMD
dcraw RAW To PPM Image Conversion OpenBenchmarking.org Seconds, Fewer Is Better dcraw RAW To PPM Image Conversion 3a 2 8 16 24 32 40 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 33.28 33.29 1. (CC) gcc options: -lm
eSpeak-NG Speech Engine Text-To-Speech Synthesis OpenBenchmarking.org Seconds, Fewer Is Better eSpeak-NG Speech Engine 20200907 Text-To-Speech Synthesis 2 3a 6 12 18 24 30 SE +/- 0.31, N = 5 SE +/- 0.11, N = 4 25.00 25.00 1. (CC) gcc options: -O2 -std=c99
GLmark2 Resolution: 1920 x 1080 OpenBenchmarking.org Score, More Is Better GLmark2 2020.04 Resolution: 1920 x 1080 3a 3 1 2 200 400 600 800 1000 781 762 754 744
GPAW Input: Carbon Nanotube OpenBenchmarking.org Seconds, Fewer Is Better GPAW 20.1 Input: Carbon Nanotube 2 3a 70 140 210 280 350 SE +/- 0.64, N = 3 SE +/- 0.63, N = 3 343.00 343.65 1. (CC) gcc options: -pthread -shared -fwrapv -O2 -lxc -lblas -lmpi
Incompact3D Input: Cylinder OpenBenchmarking.org Seconds, Fewer Is Better Incompact3D 2020-09-17 Input: Cylinder 3a 3 2 1 80 160 240 320 400 SE +/- 2.62, N = 3 SE +/- 1.96, N = 3 SE +/- 2.28, N = 3 SE +/- 0.57, N = 3 365.69 365.95 367.04 367.89 1. (F9X) gfortran options: -cpp -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
InfluxDB Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 3a 2 300K 600K 900K 1200K 1500K SE +/- 1945.61, N = 3 SE +/- 6010.29, N = 3 1623988.5 1623050.5
InfluxDB Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 3a 2 300K 600K 900K 1200K 1500K SE +/- 3347.24, N = 3 SE +/- 8331.21, N = 3 1633876.8 1631004.7
InfluxDB Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 3a 2 400K 800K 1200K 1600K 2000K SE +/- 6241.14, N = 3 SE +/- 6268.22, N = 3 1635905.7 1635245.9
LAMMPS Molecular Dynamics Simulator Model: 20k Atoms OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 24Aug2020 Model: 20k Atoms 2 3a 1 3 2 4 6 8 10 SE +/- 0.015, N = 3 SE +/- 0.021, N = 3 SE +/- 0.022, N = 3 SE +/- 0.010, N = 3 6.149 6.143 6.134 6.132 1. (CXX) g++ options: -O3 -pthread -lm
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 24Aug2020 Model: Rhodopsin Protein 2 1 3a 3 2 4 6 8 10 SE +/- 0.005, N = 3 SE +/- 0.021, N = 3 SE +/- 0.020, N = 3 SE +/- 0.047, N = 14 6.856 6.850 6.849 6.831 1. (CXX) g++ options: -O3 -pthread -lm
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: BLAS 2 3a 200 400 600 800 1000 SE +/- 4.91, N = 3 SE +/- 5.51, N = 3 860 859 1. (CXX) g++ options: -flto -pthread
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: Eigen 2 3a 200 400 600 800 1000 SE +/- 2.67, N = 3 SE +/- 2.31, N = 3 786 784 1. (CXX) g++ options: -flto -pthread
LeelaChessZero Backend: OpenCL OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: OpenCL 2 3a 70 140 210 280 350 SE +/- 2.08, N = 3 SE +/- 3.28, N = 3 327 321 1. (CXX) g++ options: -flto -pthread
LibRaw Post-Processing Benchmark OpenBenchmarking.org Mpix/sec, More Is Better LibRaw 0.20 Post-Processing Benchmark 3 2 3a 1 9 18 27 36 45 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.13, N = 3 SE +/- 0.10, N = 3 39.21 39.20 38.99 38.82 1. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: SqueezeNetV1.0 2 3a 1.3088 2.6176 3.9264 5.2352 6.544 SE +/- 0.010, N = 3 SE +/- 0.037, N = 3 5.795 5.817 MIN: 4.83 / MAX: 8.79 MIN: 4.84 / MAX: 7.67 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
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: resnet-v2-50 2 3a 8 16 24 32 40 SE +/- 0.04, N = 3 SE +/- 0.14, N = 3 34.63 34.81 MIN: 34.27 / MAX: 46.39 MIN: 34.32 / MAX: 47.37 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
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: MobileNetV2_224 2 3a 0.6676 1.3352 2.0028 2.6704 3.338 SE +/- 0.014, N = 3 SE +/- 0.015, N = 3 2.966 2.967 MIN: 2.8 / MAX: 4.26 MIN: 2.8 / MAX: 5.23 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
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: mobilenet-v1-1.0 3a 2 2 4 6 8 10 SE +/- 0.006, N = 3 SE +/- 0.011, N = 3 6.320 6.350 MIN: 6.11 / MAX: 18.61 MIN: 6.12 / MAX: 18.43 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
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: inception-v3 2 3a 9 18 27 36 45 SE +/- 0.17, N = 3 SE +/- 0.24, N = 3 37.70 37.88 MIN: 37.16 / MAX: 50.83 MIN: 37.33 / MAX: 50.76 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
Monte Carlo Simulations of Ionised Nebulae Input: Dust 2D tau100.0 OpenBenchmarking.org Seconds, Fewer Is Better Monte Carlo Simulations of Ionised Nebulae 2019-03-24 Input: Dust 2D tau100.0 2 3 3a 1 40 80 120 160 200 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 191 191 191 192 1. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O3 -O2 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
NCNN Target: CPU - Model: squeezenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: squeezenet 3a 2 4 8 12 16 20 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 15.45 15.50 MIN: 15.24 / MAX: 17.65 MIN: 15.25 / MAX: 15.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mobilenet 2 3a 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 17.78 17.79 MIN: 17.4 / MAX: 27.55 MIN: 17.55 / MAX: 18.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU-v2-v2 - Model: mobilenet-v2 3a 2 1.1228 2.2456 3.3684 4.4912 5.614 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 4.98 4.99 MIN: 4.84 / MAX: 6.09 MIN: 4.89 / MAX: 6.06 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU-v3-v3 - Model: mobilenet-v3 2 3a 0.8955 1.791 2.6865 3.582 4.4775 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 3.98 3.98 MIN: 3.94 / MAX: 5.33 MIN: 3.89 / MAX: 5.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: shufflenet-v2 3a 2 0.6525 1.305 1.9575 2.61 3.2625 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 2.87 2.90 MIN: 2.83 / MAX: 4.99 MIN: 2.86 / MAX: 3.81 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mnasnet 3a 2 0.8505 1.701 2.5515 3.402 4.2525 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 3.76 3.78 MIN: 3.71 / MAX: 4.81 MIN: 3.74 / MAX: 5.84 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: efficientnet-b0 2 3a 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 6.22 6.28 MIN: 6.1 / MAX: 7.57 MIN: 6.18 / MAX: 7.41 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: blazeface 2 3a 0.36 0.72 1.08 1.44 1.8 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 1.54 1.60 MIN: 1.47 / MAX: 1.61 MIN: 1.41 / MAX: 1.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: googlenet 3a 2 4 8 12 16 20 SE +/- 0.55, N = 3 SE +/- 0.05, N = 3 15.33 15.34 MIN: 14.36 / MAX: 17 MIN: 15.08 / MAX: 17.87 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: vgg16 2 3a 15 30 45 60 75 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 66.00 66.07 MIN: 65.76 / MAX: 67.3 MIN: 65.79 / MAX: 75.74 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet18 3a 2 4 8 12 16 20 SE +/- 0.43, N = 3 SE +/- 0.14, N = 3 14.66 14.80 MIN: 13.92 / MAX: 15.7 MIN: 13.9 / MAX: 17.22 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: alexnet 3a 2 4 8 12 16 20 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 15.73 15.80 MIN: 15.51 / MAX: 17.29 MIN: 15.51 / MAX: 17.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet50 3a 2 6 12 18 24 30 SE +/- 0.44, N = 3 SE +/- 0.32, N = 3 27.01 27.34 MIN: 25.53 / MAX: 36.96 MIN: 26.56 / MAX: 28.64 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: yolov4-tiny 2 3a 6 12 18 24 30 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 26.41 26.44 MIN: 26.01 / MAX: 33.84 MIN: 26.12 / MAX: 27.6 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: squeezenet 2 3a 9 18 27 36 45 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 39.52 39.57 MIN: 39.13 / MAX: 39.75 MIN: 39.18 / MAX: 41.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: mobilenet 3a 2 8 16 24 32 40 SE +/- 0.19, N = 3 SE +/- 0.01, N = 3 34.51 34.76 MIN: 32.42 / MAX: 40.99 MIN: 34.52 / MAX: 36.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 3a 2 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 11.29 11.30 MIN: 10.74 / MAX: 11.56 MIN: 11.05 / MAX: 11.53 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 2 3a 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 12.64 12.64 MIN: 12.43 / MAX: 12.85 MIN: 12.41 / MAX: 13.06 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: shufflenet-v2 2 3a 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 7.95 7.95 MIN: 6.98 / MAX: 8.33 MIN: 7.07 / MAX: 8.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: mnasnet 3a 2 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 11.77 11.78 MIN: 11.72 / MAX: 11.93 MIN: 11.17 / MAX: 11.96 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: efficientnet-b0 3a 2 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 23.58 23.60 MIN: 23.23 / MAX: 23.65 MIN: 23.24 / MAX: 23.69 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: blazeface 3a 2 0.4455 0.891 1.3365 1.782 2.2275 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 1.94 1.98 MIN: 1.92 / MAX: 2.09 MIN: 1.92 / MAX: 2.14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: googlenet 3a 2 8 16 24 32 40 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 32.34 32.35 MIN: 31.91 / MAX: 32.6 MIN: 31.8 / MAX: 32.72 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: vgg16 3a 2 40 80 120 160 200 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 184.87 185.11 MIN: 182.78 / MAX: 186.8 MIN: 183.53 / MAX: 187.24 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: resnet18 2 3a 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 28.50 28.51 MIN: 27.98 / MAX: 28.88 MIN: 27.98 / MAX: 28.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: alexnet 3a 2 11 22 33 44 55 SE +/- 0.93, N = 3 SE +/- 0.09, N = 3 46.02 46.77 MIN: 42.37 / MAX: 50.33 MIN: 44.26 / MAX: 49.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: resnet50 2 3a 15 30 45 60 75 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 68.69 68.71 MIN: 67.71 / MAX: 69.23 MIN: 68.1 / MAX: 68.95 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: yolov4-tiny 3a 2 16 32 48 64 80 SE +/- 0.38, N = 3 SE +/- 0.06, N = 3 70.65 70.98 MIN: 64.15 / MAX: 74 MIN: 65.18 / MAX: 91.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenCV Test: Features 2D OpenBenchmarking.org ms, Fewer Is Better OpenCV 4.4 Test: Features 2D 2 3a 20K 40K 60K 80K 100K SE +/- 869.68, N = 15 SE +/- 807.78, N = 3 109975 110406 1. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt
OpenCV Test: Object Detection OpenBenchmarking.org ms, Fewer Is Better OpenCV 4.4 Test: Object Detection 3a 2 8K 16K 24K 32K 40K SE +/- 754.41, N = 15 SE +/- 401.74, N = 7 37334 37985 1. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt
OpenCV Test: DNN - Deep Neural Network OpenBenchmarking.org ms, Fewer Is Better OpenCV 4.4 Test: DNN - Deep Neural Network 3a 2 5K 10K 15K 20K 25K SE +/- 161.00, N = 3 SE +/- 7385.79, N = 15 17734 24960 1. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt
RealSR-NCNN Scale: 4x - TAA: No OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: No 3 2 3a 1 60 120 180 240 300 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 253.36 253.42 253.44 253.49
System GZIP Decompression OpenBenchmarking.org Seconds, Fewer Is Better System GZIP Decompression 2 3a 0.5778 1.1556 1.7334 2.3112 2.889 SE +/- 0.018, N = 3 SE +/- 0.019, N = 3 2.566 2.568
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.2.3 Target: CPU - Model: MobileNet v2 2 3a 60 120 180 240 300 SE +/- 0.24, N = 3 SE +/- 0.91, N = 3 285.03 288.32 MIN: 283.65 / MAX: 286.48 MIN: 286.2 / MAX: 293.83 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.2.3 Target: CPU - Model: SqueezeNet v1.1 2 3a 60 120 180 240 300 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 268.09 268.22 MIN: 267.46 / MAX: 270.33 MIN: 267.71 / MAX: 269.21 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
WebP Image Encode Encode Settings: Default OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Default 3 2 3a 1 0.3074 0.6148 0.9222 1.2296 1.537 SE +/- 0.001, N = 3 SE +/- 0.005, N = 3 SE +/- 0.015, N = 3 SE +/- 0.015, N = 3 1.350 1.356 1.364 1.366 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
WebP Image Encode Encode Settings: Quality 100 OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100 3 2 3a 1 0.4754 0.9508 1.4262 1.9016 2.377 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 2.109 2.110 2.111 2.113 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
WebP Image Encode Encode Settings: Quality 100, Lossless OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless 3 3a 1 2 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 15.26 15.42 15.54 15.56 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
WebP Image Encode Encode Settings: Quality 100, Highest Compression OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Highest Compression 1 2 3a 3 2 4 6 8 10 SE +/- 0.006, N = 3 SE +/- 0.010, N = 3 SE +/- 0.008, N = 3 SE +/- 0.039, N = 3 6.322 6.325 6.326 6.346 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
WebP Image Encode Encode Settings: Quality 100, Lossless, Highest Compression OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless, Highest Compression 3a 3 1 2 8 16 24 32 40 SE +/- 0.10, N = 3 SE +/- 0.16, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 32.65 32.94 33.01 33.04 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
Phoronix Test Suite v10.8.4