ngpu.test AMD Ryzen 9 7950X 16-Core testing with a ASUS ProArt X670E-CREATOR WIFI (1004 BIOS) and NVIDIA GeForce RTX 4090 24GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2304087-NE-NGPUTEST677&export=pdf&grs .
ngpu.test Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Vulkan Compiler File-System Screen Resolution pts_nvidia-gpu-compute AMD Ryzen 9 7950X 16-Core @ 4.50GHz (16 Cores / 32 Threads) ASUS ProArt X670E-CREATOR WIFI (1004 BIOS) AMD Device 14d8 2 x 32 GB DDR5-5600MT/s Kingston KF556C40-32 2000GB Samsung SSD 980 PRO 2TB NVIDIA GeForce RTX 4090 24GB NVIDIA Device 22ba LG Ultra HD Intel I225-V + MEDIATEK Device 0616 Ubuntu 22.04 5.19.0-38-generic (x86_64) KDE Plasma 5.24.7 X Server 1.21.1.3 NVIDIA 525.105.17 4.6.0 OpenCL 3.0 CUDA 12.0.151 1.3.224 GCC 11.3.0 xfs 3840x2160 OpenBenchmarking.org - Transparent Huge Pages: madvise - --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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/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-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 - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203 - GLAMOR - BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.02.20.00.03 - GPU Compute Cores: 16384 - Python 3.10.6 - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
ngpu.test neatbench: GPU mandelgpu: GPU indigobench: OpenCL GPU - Supercar indigobench: OpenCL GPU - Bedroom blender: Pabellon Barcelona - NVIDIA OptiX blender: Barbershop - NVIDIA OptiX blender: Fishy Cat - NVIDIA OptiX blender: Classroom - NVIDIA OptiX 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 - vgg16 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU - mobilenet viennacl: OpenCL BLAS - dGEMM-TT viennacl: OpenCL BLAS - dGEMM-TN viennacl: OpenCL BLAS - dGEMM-NT viennacl: OpenCL BLAS - dGEMM-NN viennacl: OpenCL BLAS - dGEMV-T viennacl: OpenCL BLAS - dGEMV-N viennacl: OpenCL BLAS - dDOT viennacl: OpenCL BLAS - dAXPY viennacl: OpenCL BLAS - dCOPY viennacl: OpenCL BLAS - sDOT viennacl: OpenCL BLAS - sAXPY viennacl: OpenCL BLAS - sCOPY viennacl: CPU BLAS - dGEMM-TT viennacl: CPU BLAS - dGEMM-TN viennacl: CPU BLAS - dGEMM-NT viennacl: CPU BLAS - dGEMM-NN viennacl: CPU BLAS - dGEMV-T viennacl: CPU BLAS - dGEMV-N viennacl: CPU BLAS - dDOT viennacl: CPU BLAS - dAXPY viennacl: CPU BLAS - dCOPY viennacl: CPU BLAS - sDOT viennacl: CPU BLAS - sCOPY financebench: Black-Scholes OpenCL luxcorerender: Rainbow Colors and Prism - GPU luxcorerender: LuxCore Benchmark - GPU luxcorerender: Orange Juice - GPU luxcorerender: Danish Mood - GPU luxcorerender: DLSC - GPU arrayfire: Conjugate Gradient OpenCL rodinia: OpenCL Particle Filter lczero: OpenCL clpeak: Global Memory Bandwidth clpeak: Double-Precision Double clpeak: Single-Precision Float clpeak: Integer Compute INT fahbench: octanebench: Total Score vkresample: 2x - Single vkresample: 2x - Double namd-cuda: ATPase Simulation - 327,506 Atoms cl-mem: Write cl-mem: Read cl-mem: Copy shoc: OpenCL - Texture Read Bandwidth shoc: OpenCL - Bus Speed Readback shoc: OpenCL - Bus Speed Download shoc: OpenCL - Max SP Flops shoc: OpenCL - GEMM SGEMM_N shoc: OpenCL - Reduction shoc: OpenCL - MD5 Hash shoc: OpenCL - FFT SP shoc: OpenCL - Triad shoc: OpenCL - S3D hashcat: TrueCrypt RIPEMD160 + XTS hashcat: SHA-512 hashcat: 7-Zip hashcat: SHA1 hashcat: MD5 vkfft: waifu2x-ncnn: 2x - 3 - Yes realsr-ncnn: 4x - Yes realsr-ncnn: 4x - No vkpeak: int16-vec4 vkpeak: int16-scalar vkpeak: int32-vec4 vkpeak: int32-scalar vkpeak: fp64-vec4 vkpeak: fp64-scalar vkpeak: fp16-vec4 vkpeak: fp16-scalar vkpeak: fp32-vec4 vkpeak: fp32-scalar blender: BMW27 - NVIDIA OptiX ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 viennacl: CPU BLAS - sAXPY waifu2x-ncnn: 2x - 3 - No pts_nvidia-gpu-compute 4090 907383065.7 80.072 35.663 8.12 29.75 5.38 7.07 1.99 135.14 1.36 3.43 5.15 2.07 1.99 0.99 1.28 2.68 1357 1310 1290 1167 446 221 730 773 661 451 618 480 111 117 106 110 127 101.8 93.4 88.3 58.7 300 208 2.934 40.94 19.26 17.64 18.84 22.43 0.8731 2.095 46246 870.86 1413.35 78857.40 40863.0 440.4985 1330.491247 7.784 55.387 0.06968 799.4 885.5 411.6 3032.40 26.3967 26.8891 90084.7 28105.9 992.53 93.4700 2778.27 26.3869 646.626 1867900 6389066667 2741600 49962233333 156200000000 63576 2.468 19.116 4.211 39957.84 29976.88 44803.57 45045.95 1419.84 1419.89 89348.10 45059.05 59636.96 45133.99 13.27 1.99 1.47 2.30 0.84 2.27 1.53 1.11 305 OpenBenchmarking.org
NeatBench Acceleration: GPU OpenBenchmarking.org FPS, More Is Better NeatBench 5 Acceleration: GPU pts_nvidia-gpu-compute 900 1800 2700 3600 4500 SE +/- 0.00, N = 3 4090
MandelGPU OpenCL Device: GPU OpenBenchmarking.org Samples/sec, More Is Better MandelGPU 1.3pts1 OpenCL Device: GPU pts_nvidia-gpu-compute 200M 400M 600M 800M 1000M SE +/- 9346262.69, N = 3 907383065.7 1. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL
IndigoBench Acceleration: OpenCL GPU - Scene: Supercar OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Supercar pts_nvidia-gpu-compute 20 40 60 80 100 SE +/- 0.06, N = 3 80.07
IndigoBench Acceleration: OpenCL GPU - Scene: Bedroom OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Bedroom pts_nvidia-gpu-compute 8 16 24 32 40 SE +/- 0.01, N = 3 35.66
Blender Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.5 Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX pts_nvidia-gpu-compute 2 4 6 8 10 SE +/- 0.02, N = 3 8.12
Blender Blend File: Barbershop - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.5 Blend File: Barbershop - Compute: NVIDIA OptiX pts_nvidia-gpu-compute 7 14 21 28 35 SE +/- 0.07, N = 3 29.75
Blender Blend File: Fishy Cat - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.5 Blend File: Fishy Cat - Compute: NVIDIA OptiX pts_nvidia-gpu-compute 1.2105 2.421 3.6315 4.842 6.0525 SE +/- 0.06, N = 13 5.38
Blender Blend File: Classroom - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.5 Blend File: Classroom - Compute: NVIDIA OptiX pts_nvidia-gpu-compute 2 4 6 8 10 SE +/- 0.02, N = 3 7.07
NCNN Target: Vulkan GPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: FastestDet pts_nvidia-gpu-compute 0.4478 0.8956 1.3434 1.7912 2.239 SE +/- 0.05, N = 3 1.99 MIN: 1.42 / MAX: 5.4 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vision_transformer pts_nvidia-gpu-compute 30 60 90 120 150 SE +/- 0.33, N = 3 135.14 MIN: 92.56 / MAX: 193.97 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: regnety_400m pts_nvidia-gpu-compute 0.306 0.612 0.918 1.224 1.53 SE +/- 0.01, N = 3 1.36 MIN: 1.33 / MAX: 4.48 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: squeezenet_ssd pts_nvidia-gpu-compute 0.7718 1.5436 2.3154 3.0872 3.859 SE +/- 0.05, N = 3 3.43 MIN: 2.65 / MAX: 20.72 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: yolov4-tiny pts_nvidia-gpu-compute 1.1588 2.3176 3.4764 4.6352 5.794 SE +/- 0.03, N = 3 5.15 MIN: 4.65 / MAX: 32.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet50 pts_nvidia-gpu-compute 0.4658 0.9316 1.3974 1.8632 2.329 SE +/- 0.06, N = 3 2.07 MIN: 1.44 / MAX: 11.57 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vgg16 pts_nvidia-gpu-compute 0.4478 0.8956 1.3434 1.7912 2.239 SE +/- 0.07, N = 3 1.99 MIN: 1.44 / MAX: 13.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mnasnet pts_nvidia-gpu-compute 0.2228 0.4456 0.6684 0.8912 1.114 SE +/- 0.03, N = 3 0.99 MIN: 0.92 / MAX: 11.68 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: shufflenet-v2 pts_nvidia-gpu-compute 0.288 0.576 0.864 1.152 1.44 SE +/- 0.04, N = 3 1.28 MIN: 1.09 / MAX: 12.49 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mobilenet pts_nvidia-gpu-compute 0.603 1.206 1.809 2.412 3.015 SE +/- 0.04, N = 3 2.68 MIN: 2.45 / MAX: 28.54 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
ViennaCL Test: OpenCL BLAS - dGEMM-TT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TT pts_nvidia-gpu-compute 300 600 900 1200 1500 SE +/- 3.33, N = 3 1357 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dGEMM-TN OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TN pts_nvidia-gpu-compute 300 600 900 1200 1500 SE +/- 0.00, N = 3 1310 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dGEMM-NT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NT pts_nvidia-gpu-compute 300 600 900 1200 1500 SE +/- 0.00, N = 3 1290 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dGEMM-NN OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NN pts_nvidia-gpu-compute 300 600 900 1200 1500 SE +/- 3.33, N = 3 1167 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dGEMV-T OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-T pts_nvidia-gpu-compute 100 200 300 400 500 SE +/- 0.33, N = 3 446 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dGEMV-N OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-N pts_nvidia-gpu-compute 50 100 150 200 250 SE +/- 0.33, N = 3 221 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dDOT OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dDOT pts_nvidia-gpu-compute 160 320 480 640 800 SE +/- 0.00, N = 3 730 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dAXPY pts_nvidia-gpu-compute 170 340 510 680 850 SE +/- 0.33, N = 3 773 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dCOPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dCOPY pts_nvidia-gpu-compute 140 280 420 560 700 SE +/- 0.33, N = 3 661 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - sDOT OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - sDOT pts_nvidia-gpu-compute 100 200 300 400 500 SE +/- 0.00, N = 3 451 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - sAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - sAXPY pts_nvidia-gpu-compute 130 260 390 520 650 SE +/- 0.33, N = 3 618 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - sCOPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - sCOPY pts_nvidia-gpu-compute 100 200 300 400 500 SE +/- 1.20, N = 3 480 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMM-TT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TT pts_nvidia-gpu-compute 20 40 60 80 100 SE +/- 0.67, N = 3 111 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMM-TN OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TN pts_nvidia-gpu-compute 30 60 90 120 150 SE +/- 0.67, N = 3 117 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMM-NT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NT pts_nvidia-gpu-compute 20 40 60 80 100 SE +/- 0.58, N = 3 106 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMM-NN OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NN pts_nvidia-gpu-compute 20 40 60 80 100 SE +/- 0.58, N = 3 110 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMV-T OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-T pts_nvidia-gpu-compute 30 60 90 120 150 SE +/- 1.33, N = 3 127 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMV-N OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-N pts_nvidia-gpu-compute 20 40 60 80 100 SE +/- 2.84, N = 3 101.8 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dDOT OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dDOT pts_nvidia-gpu-compute 20 40 60 80 100 SE +/- 0.09, N = 3 93.4 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dAXPY pts_nvidia-gpu-compute 20 40 60 80 100 SE +/- 1.06, N = 3 88.3 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dCOPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dCOPY pts_nvidia-gpu-compute 13 26 39 52 65 SE +/- 0.52, N = 3 58.7 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - sDOT OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sDOT pts_nvidia-gpu-compute 70 140 210 280 350 SE +/- 4.33, N = 3 300 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - sCOPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sCOPY pts_nvidia-gpu-compute 50 100 150 200 250 SE +/- 2.31, N = 3 208 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
FinanceBench Benchmark: Black-Scholes OpenCL OpenBenchmarking.org ms, Fewer Is Better FinanceBench 2016-07-25 Benchmark: Black-Scholes OpenCL pts_nvidia-gpu-compute 0.6602 1.3204 1.9806 2.6408 3.301 SE +/- 0.004, N = 3 2.934 1. (CXX) g++ options: -O3 -march=native -fopenmp
LuxCoreRender Scene: Rainbow Colors and Prism - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Rainbow Colors and Prism - Acceleration: GPU pts_nvidia-gpu-compute 9 18 27 36 45 SE +/- 0.49, N = 3 40.94 MIN: 36.89 / MAX: 46.01
LuxCoreRender Scene: LuxCore Benchmark - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: LuxCore Benchmark - Acceleration: GPU pts_nvidia-gpu-compute 5 10 15 20 25 SE +/- 0.08, N = 3 19.26 MIN: 7.14 / MAX: 23.35
LuxCoreRender Scene: Orange Juice - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: GPU pts_nvidia-gpu-compute 4 8 12 16 20 SE +/- 0.12, N = 3 17.64 MIN: 15.49 / MAX: 24.67
LuxCoreRender Scene: Danish Mood - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Danish Mood - Acceleration: GPU pts_nvidia-gpu-compute 5 10 15 20 25 SE +/- 0.12, N = 3 18.84 MIN: 6.81 / MAX: 21.85
LuxCoreRender Scene: DLSC - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: DLSC - Acceleration: GPU pts_nvidia-gpu-compute 5 10 15 20 25 SE +/- 0.03, N = 3 22.43 MIN: 21.13 / MAX: 22.71
ArrayFire Test: Conjugate Gradient OpenCL OpenBenchmarking.org ms, Fewer Is Better ArrayFire 3.7 Test: Conjugate Gradient OpenCL pts_nvidia-gpu-compute 0.1964 0.3928 0.5892 0.7856 0.982 SE +/- 0.0009, N = 3 0.8731 1. (CXX) g++ options: -rdynamic
Rodinia Test: OpenCL Particle Filter OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenCL Particle Filter pts_nvidia-gpu-compute 0.4714 0.9428 1.4142 1.8856 2.357 2.095 1. (CXX) g++ options: -O2 -lOpenCL
LeelaChessZero Backend: OpenCL OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: OpenCL pts_nvidia-gpu-compute 10K 20K 30K 40K 50K SE +/- 267.97, N = 3 46246 1. (CXX) g++ options: -flto -pthread
clpeak OpenCL Test: Global Memory Bandwidth OpenBenchmarking.org GBPS, More Is Better clpeak 1.1.2 OpenCL Test: Global Memory Bandwidth pts_nvidia-gpu-compute 200 400 600 800 1000 SE +/- 1.70, N = 3 870.86 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Double-Precision Double OpenBenchmarking.org GFLOPS, More Is Better clpeak 1.1.2 OpenCL Test: Double-Precision Double pts_nvidia-gpu-compute 300 600 900 1200 1500 SE +/- 3.34, N = 3 1413.35 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Single-Precision Float OpenBenchmarking.org GFLOPS, More Is Better clpeak 1.1.2 OpenCL Test: Single-Precision Float pts_nvidia-gpu-compute 20K 40K 60K 80K 100K SE +/- 898.79, N = 4 78857.40 1. (CXX) g++ options: -O3
clpeak OpenCL Test: Integer Compute INT OpenBenchmarking.org GIOPS, More Is Better clpeak 1.1.2 OpenCL Test: Integer Compute INT pts_nvidia-gpu-compute 9K 18K 27K 36K 45K SE +/- 0.27, N = 3 40863.0 1. (CXX) g++ options: -O3
FAHBench OpenBenchmarking.org Ns Per Day, More Is Better FAHBench 2.3.2 pts_nvidia-gpu-compute 100 200 300 400 500 SE +/- 0.83, N = 3 440.50
OctaneBench Total Score OpenBenchmarking.org Score, More Is Better OctaneBench 2020.1 Total Score pts_nvidia-gpu-compute 300 600 900 1200 1500 1330.49
VkResample Upscale: 2x - Precision: Single OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Single pts_nvidia-gpu-compute 2 4 6 8 10 SE +/- 0.007, N = 3 7.784 1. (CXX) g++ options: -O3
VkResample Upscale: 2x - Precision: Double OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Double pts_nvidia-gpu-compute 12 24 36 48 60 SE +/- 0.03, N = 3 55.39 1. (CXX) g++ options: -O3
NAMD CUDA ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD CUDA 2.14 ATPase Simulation - 327,506 Atoms pts_nvidia-gpu-compute 0.0157 0.0314 0.0471 0.0628 0.0785 SE +/- 0.00063, N = 3 0.06968
cl-mem Benchmark: Write OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Write pts_nvidia-gpu-compute 200 400 600 800 1000 SE +/- 0.17, N = 3 799.4 1. (CC) gcc options: -O2 -flto -lOpenCL
cl-mem Benchmark: Read OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Read pts_nvidia-gpu-compute 200 400 600 800 1000 SE +/- 0.07, N = 3 885.5 1. (CC) gcc options: -O2 -flto -lOpenCL
cl-mem Benchmark: Copy OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Copy pts_nvidia-gpu-compute 90 180 270 360 450 SE +/- 0.09, N = 3 411.6 1. (CC) gcc options: -O2 -flto -lOpenCL
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Texture Read Bandwidth OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Texture Read Bandwidth pts_nvidia-gpu-compute 700 1400 2100 2800 3500 SE +/- 2.54, N = 3 3032.40 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Bus Speed Readback OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Readback pts_nvidia-gpu-compute 6 12 18 24 30 SE +/- 0.00, N = 3 26.40 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Bus Speed Download OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Download pts_nvidia-gpu-compute 6 12 18 24 30 SE +/- 0.00, N = 3 26.89 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Max SP Flops OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Max SP Flops pts_nvidia-gpu-compute 20K 40K 60K 80K 100K SE +/- 227.24, N = 3 90084.7 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: GEMM SGEMM_N OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: GEMM SGEMM_N pts_nvidia-gpu-compute 6K 12K 18K 24K 30K SE +/- 278.67, N = 6 28105.9 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Reduction OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Reduction pts_nvidia-gpu-compute 200 400 600 800 1000 SE +/- 11.62, N = 4 992.53 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: MD5 Hash OpenBenchmarking.org GHash/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: MD5 Hash pts_nvidia-gpu-compute 20 40 60 80 100 SE +/- 1.09, N = 15 93.47 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: FFT SP OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: FFT SP pts_nvidia-gpu-compute 600 1200 1800 2400 3000 SE +/- 3.11, N = 3 2778.27 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Triad OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Triad pts_nvidia-gpu-compute 6 12 18 24 30 SE +/- 0.03, N = 3 26.39 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: S3D OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: S3D pts_nvidia-gpu-compute 140 280 420 560 700 SE +/- 0.26, N = 3 646.63 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
Hashcat Benchmark: TrueCrypt RIPEMD160 + XTS OpenBenchmarking.org H/s, More Is Better Hashcat 6.2.4 Benchmark: TrueCrypt RIPEMD160 + XTS pts_nvidia-gpu-compute 400K 800K 1200K 1600K 2000K SE +/- 9691.41, N = 3 1867900
Hashcat Benchmark: SHA-512 OpenBenchmarking.org H/s, More Is Better Hashcat 6.2.4 Benchmark: SHA-512 pts_nvidia-gpu-compute 1400M 2800M 4200M 5600M 7000M SE +/- 484194.63, N = 3 6389066667
Hashcat Benchmark: 7-Zip OpenBenchmarking.org H/s, More Is Better Hashcat 6.2.4 Benchmark: 7-Zip pts_nvidia-gpu-compute 600K 1200K 1800K 2400K 3000K SE +/- 6351.64, N = 3 2741600
Hashcat Benchmark: SHA1 OpenBenchmarking.org H/s, More Is Better Hashcat 6.2.4 Benchmark: SHA1 pts_nvidia-gpu-compute 11000M 22000M 33000M 44000M 55000M SE +/- 63246510.66, N = 3 49962233333
Hashcat Benchmark: MD5 OpenBenchmarking.org H/s, More Is Better Hashcat 6.2.4 Benchmark: MD5 pts_nvidia-gpu-compute 30000M 60000M 90000M 120000M 150000M SE +/- 57735026.92, N = 3 156200000000
VkFFT OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.1.1 pts_nvidia-gpu-compute 14K 28K 42K 56K 70K SE +/- 136.81, N = 3 63576 1. (CXX) g++ options: -O3
Waifu2x-NCNN Vulkan Scale: 2x - Denoise: 3 - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: Yes pts_nvidia-gpu-compute 0.5553 1.1106 1.6659 2.2212 2.7765 SE +/- 0.009, N = 3 2.468
RealSR-NCNN Scale: 4x - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: Yes pts_nvidia-gpu-compute 5 10 15 20 25 SE +/- 0.02, N = 3 19.12
RealSR-NCNN Scale: 4x - TAA: No OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: No pts_nvidia-gpu-compute 0.9475 1.895 2.8425 3.79 4.7375 SE +/- 0.010, N = 3 4.211
vkpeak int16-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int16-vec4 pts_nvidia-gpu-compute 9K 18K 27K 36K 45K SE +/- 30.24, N = 3 39957.84
vkpeak int16-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int16-scalar pts_nvidia-gpu-compute 6K 12K 18K 24K 30K SE +/- 2.60, N = 3 29976.88
vkpeak int32-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int32-vec4 pts_nvidia-gpu-compute 10K 20K 30K 40K 50K SE +/- 78.91, N = 3 44803.57
vkpeak int32-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int32-scalar pts_nvidia-gpu-compute 10K 20K 30K 40K 50K SE +/- 59.05, N = 3 45045.95
vkpeak fp64-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp64-vec4 pts_nvidia-gpu-compute 300 600 900 1200 1500 SE +/- 1.97, N = 3 1419.84
vkpeak fp64-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp64-scalar pts_nvidia-gpu-compute 300 600 900 1200 1500 SE +/- 1.92, N = 3 1419.89
vkpeak fp16-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp16-vec4 pts_nvidia-gpu-compute 20K 40K 60K 80K 100K SE +/- 154.58, N = 3 89348.10
vkpeak fp16-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp16-scalar pts_nvidia-gpu-compute 10K 20K 30K 40K 50K SE +/- 75.33, N = 3 45059.05
vkpeak fp32-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp32-vec4 pts_nvidia-gpu-compute 13K 26K 39K 52K 65K SE +/- 110.07, N = 3 59636.96
vkpeak fp32-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp32-scalar pts_nvidia-gpu-compute 10K 20K 30K 40K 50K SE +/- 114.66, N = 3 45133.99
Blender Blend File: BMW27 - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.5 Blend File: BMW27 - Compute: NVIDIA OptiX pts_nvidia-gpu-compute 3 6 9 12 15 SE +/- 9.84, N = 12 13.27
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: alexnet pts_nvidia-gpu-compute 0.4478 0.8956 1.3434 1.7912 2.239 SE +/- 0.10, N = 3 1.99 MIN: 0.98 / MAX: 15.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet18 pts_nvidia-gpu-compute 0.3308 0.6616 0.9924 1.3232 1.654 SE +/- 0.05, N = 3 1.47 MIN: 1.15 / MAX: 14.14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: googlenet pts_nvidia-gpu-compute 0.5175 1.035 1.5525 2.07 2.5875 SE +/- 0.11, N = 3 2.30 MIN: 1.43 / MAX: 17.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: blazeface pts_nvidia-gpu-compute 0.189 0.378 0.567 0.756 0.945 SE +/- 0.05, N = 3 0.84 MIN: 0.74 / MAX: 17.41 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: efficientnet-b0 pts_nvidia-gpu-compute 0.5108 1.0216 1.5324 2.0432 2.554 SE +/- 0.14, N = 3 2.27 MIN: 1.73 / MAX: 13.33 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 pts_nvidia-gpu-compute 0.3443 0.6886 1.0329 1.3772 1.7215 SE +/- 0.16, N = 3 1.53 MIN: 1.12 / MAX: 11.38 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 pts_nvidia-gpu-compute 0.2498 0.4996 0.7494 0.9992 1.249 SE +/- 0.05, N = 3 1.11 MIN: 0.9 / MAX: 11.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
ViennaCL Test: CPU BLAS - sAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sAXPY pts_nvidia-gpu-compute 70 140 210 280 350 SE +/- 11.06, N = 3 305 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
Phoronix Test Suite v10.8.5