ngc rtx 3090 AMD Ryzen 9 5900X 12-Core testing with a ASUS ROG CROSSHAIR VIII HERO (3402 BIOS) and NVIDIA GeForce RTX 3090 24GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2104059-IB-NGCRTX30939&sor&grs .
ngc rtx 3090 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Vulkan Compiler File-System Screen Resolution 1 2 3 AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads) ASUS ROG CROSSHAIR VIII HERO (3402 BIOS) AMD Starship/Matisse 16GB 1000GB Sabrent Rocket 4.0 Plus + 2000GB NVIDIA GeForce RTX 3090 24GB NVIDIA Device 1aef ASUS VP28U Realtek RTL8125 2.5GbE + Intel I211 Ubuntu 20.04 5.8.0-48-generic (x86_64) GNOME Shell 3.36.7 X Server 1.20.9 NVIDIA 460.67 4.6.0 OpenCL 1.2 CUDA 11.2.162 1.2.155 GCC 9.3.0 + CUDA 11.2 ext4 3840x2160 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise 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=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,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: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201009 OpenCL Details - GPU Compute Cores: 10496 Python Details - 1: Python 3.8.5 Security Details - 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: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
ngc rtx 3090 vkfft: ncnn: Vulkan GPU - resnet18 namd-cuda: ATPase Simulation - 327,506 Atoms ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU - vgg16 viennacl: CPU BLAS - sDOT viennacl: CPU BLAS - dDOT viennacl: CPU BLAS - dCOPY ncnn: Vulkan GPU - mobilenet arrayfire: Conjugate Gradient OpenCL shoc: OpenCL - GEMM SGEMM_N betsy: ETC1 - Highest ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 luxcorerender-cl: Rainbow Colors and Prism blender: Classroom - NVIDIA OptiX ncnn: Vulkan GPU - resnet50 viennacl: CPU BLAS - dGEMM-NN luxcorerender-cl: LuxCore Benchmark viennacl: OpenCL BLAS - sCOPY shoc: OpenCL - MD5 Hash viennacl: OpenCL BLAS - dGEMV-T financebench: Black-Scholes OpenCL mandelgpu: GPU luxcorerender-cl: Food hashcat: 7-Zip clpeak: Global Memory Bandwidth indigobench: OpenCL GPU - Supercar hashcat: TrueCrypt RIPEMD160 + XTS lczero: OpenCL viennacl: CPU BLAS - dGEMV-N ncnn: Vulkan GPU - googlenet realsr-ncnn: 4x - No rodinia: OpenCL Particle Filter shoc: OpenCL - S3D hashcat: SHA1 viennacl: CPU BLAS - dGEMM-TT viennacl: CPU BLAS - dGEMM-TN shoc: OpenCL - Reduction v-ray: NVIDIA RTX GPU clpeak: Double-Precision Double fahbench: ncnn: Vulkan GPU - yolov4-tiny shoc: OpenCL - Max SP Flops hashcat: MD5 viennacl: CPU BLAS - dAXPY gromacs-gpu: Water Benchmark luxcorerender-cl: DLSC viennacl: OpenCL BLAS - sDOT shoc: OpenCL - FFT SP hashcat: SHA-512 ncnn: Vulkan GPU - shufflenet-v2 viennacl: OpenCL BLAS - sAXPY blender: Barbershop - CUDA ncnn: Vulkan GPU - alexnet viennacl: OpenCL BLAS - dGEMM-TN viennacl: OpenCL BLAS - dGEMM-NN realsr-ncnn: 4x - Yes viennacl: OpenCL BLAS - dGEMM-NT clpeak: Integer Compute INT cl-mem: Write viennacl: CPU BLAS - sCOPY viennacl: OpenCL BLAS - dDOT waifu2x-ncnn: 2x - 3 - Yes cl-mem: Copy betsy: ETC2 RGB - Highest viennacl: CPU BLAS - dGEMV-T shoc: OpenCL - Texture Read Bandwidth viennacl: CPU BLAS - sAXPY shoc: OpenCL - Bus Speed Readback blender: BMW27 - NVIDIA OptiX clpeak: Single-Precision Float blender: Pabellon Barcelona - NVIDIA OptiX octanebench: Total Score cl-mem: Read vkresample: 2x - Double ncnn: Vulkan GPU - regnety_400m blender: BMW27 - CUDA shoc: OpenCL - Triad blender: Fishy Cat - NVIDIA OptiX blender: Fishy Cat - CUDA indigobench: OpenCL GPU - Bedroom vkresample: 2x - Single blender: Pabellon Barcelona - CUDA blender: Barbershop - NVIDIA OptiX shoc: OpenCL - Bus Speed Download viennacl: OpenCL BLAS - dGEMM-TT v-ray: NVIDIA CUDA GPU blender: Classroom - CUDA viennacl: OpenCL BLAS - dGEMV-N viennacl: OpenCL BLAS - dAXPY viennacl: OpenCL BLAS - dCOPY viennacl: CPU BLAS - dGEMM-NT redshift: ncnn: Vulkan GPU - blazeface mixbench: OpenCL - Single Precision mixbench: OpenCL - Double Precision mixbench: OpenCL - Integer 1 2 3 43686 13.98 0.12884 5.69 4.12 14.93 4.11 55.24 136 43.8 22.8 12.78 1.477 8202.75 3.040 4.42 26.12 30.52 24.75 53.5 9.08 366 44.1934 378 6.234 466253751.5 4.70 1149333 810.12 52.929 846967 39148 77.8 13.16 5.866 3.743 428.916 22583233333 55.3 56.7 390.957 2601 654.89 343.6182 21.92 39924.9 66413233333 33.4 9.643 11.20 375 2347.21 2853033333 4.78 504 373.50 11.06 601 603 29.623 605 17922.35 742.0 62.6 650 3.439 363.5 4.054 83.2 2224.01 91.6 26.3585 9.76 35173.57 46.68 680.723023 825.3 122.795 16.75 18.35 25.4764 20.43 34.60 20.865 9.282 120.48 335.89 26.3101 1963 51.42 237 722 607 52.9 141 1.88 34053.47 496.29 20685.77 43194 13.65 0.12599 5.57 4.04 15.19 4.18 56.10 138 43.2 22.5 12.92 1.491 8272.77 3.015 4.45 26.29 30.33 24.60 53.2 9.13 364 43.9588 376 6.265 468356717.8 4.68 1144667 813.37 52.720 845867 38996 78.1 13.11 5.867 3.729 430.512 22585700000 55.1 56.5 389.899 2610 657.03 344.7206 21.99 39799.6 66432866667 33.3 9.670 11.17 374 2342.08 2851266667 4.77 503 374.21 11.08 600 602 29.598 604 17951.73 740.8 62.5 651 3.444 363.0 4.049 83.1 2226.47 91.5 26.3873 9.77 35204.07 46.72 680.186086 825.9 122.873 16.74 18.36 25.4634 20.42 34.61 20.870 9.284 120.49 335.87 26.3106 605 1963 51.42 237 722 607 52.9 141 1.83 34079.35 467.53 19683.19 44750 8229.33 44.0181 1147133 849167 5.845 429.952 22665866667 391.275 66617033333 2344.26 2857366667 29.574 3.440 25.4698 35867.33 459.26 20677.83 OpenBenchmarking.org
VkFFT OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.1.1 3 1 2 10K 20K 30K 40K 50K SE +/- 562.76, N = 3 SE +/- 463.57, N = 5 SE +/- 334.75, N = 3 44750 43686 43194 1. (CXX) g++ options: -O3 -pthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: resnet18 2 1 4 8 12 16 20 SE +/- 0.16, N = 3 SE +/- 0.05, N = 3 13.65 13.98 MIN: 12.7 / MAX: 30.04 MIN: 12.86 / MAX: 46.72 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NAMD CUDA ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD CUDA 2.14 ATPase Simulation - 327,506 Atoms 2 1 0.029 0.058 0.087 0.116 0.145 SE +/- 0.00057, N = 3 SE +/- 0.00063, N = 3 0.12599 0.12884
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: efficientnet-b0 2 1 1.2803 2.5606 3.8409 5.1212 6.4015 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 5.57 5.69 MIN: 5.16 / MAX: 23.76 MIN: 5.25 / MAX: 7.81 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: mnasnet 2 1 0.927 1.854 2.781 3.708 4.635 SE +/- 0.13, N = 3 SE +/- 0.00, N = 3 4.04 4.12 MIN: 3.67 / MAX: 25.57 MIN: 3.76 / MAX: 27.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: squeezenet_ssd 1 2 4 8 12 16 20 SE +/- 0.18, N = 3 SE +/- 0.13, N = 3 14.93 15.19 MIN: 13.47 / MAX: 53.36 MIN: 13.88 / MAX: 66.94 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 1 2 0.9405 1.881 2.8215 3.762 4.7025 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 4.11 4.18 MIN: 3.79 / MAX: 6 MIN: 3.89 / MAX: 28.81 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: vgg16 1 2 13 26 39 52 65 SE +/- 0.23, N = 3 SE +/- 0.20, N = 3 55.24 56.10 MIN: 51.44 / MAX: 87.52 MIN: 51.69 / MAX: 136.04 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
ViennaCL Test: CPU BLAS - sDOT OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sDOT 2 1 30 60 90 120 150 SE +/- 3.18, N = 3 SE +/- 1.67, N = 3 138 136 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 1 2 10 20 30 40 50 SE +/- 0.84, N = 3 SE +/- 1.32, N = 3 43.8 43.2 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 1 2 5 10 15 20 25 SE +/- 0.17, N = 3 SE +/- 0.63, N = 3 22.8 22.5 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: mobilenet 1 2 3 6 9 12 15 SE +/- 0.14, N = 3 SE +/- 0.09, N = 3 12.78 12.92 MIN: 11.91 / MAX: 28.97 MIN: 12.1 / MAX: 29.15 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
ArrayFire Test: Conjugate Gradient OpenCL OpenBenchmarking.org ms, Fewer Is Better ArrayFire 3.7 Test: Conjugate Gradient OpenCL 1 2 0.3355 0.671 1.0065 1.342 1.6775 SE +/- 0.003, N = 3 SE +/- 0.003, N = 3 1.477 1.491 1. (CXX) g++ options: -rdynamic
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 2 3 1 2K 4K 6K 8K 10K SE +/- 86.21, N = 4 SE +/- 65.52, N = 3 SE +/- 88.75, N = 4 8272.77 8229.33 8202.75 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
Betsy GPU Compressor Codec: ETC1 - Quality: Highest OpenBenchmarking.org Seconds, Fewer Is Better Betsy GPU Compressor 1.1 Beta Codec: ETC1 - Quality: Highest 2 1 0.684 1.368 2.052 2.736 3.42 SE +/- 0.016, N = 3 SE +/- 0.014, N = 3 3.015 3.040 1. (CXX) g++ options: -O3 -O2 -lpthread -ldl
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 1 2 1.0013 2.0026 3.0039 4.0052 5.0065 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 4.42 4.45 MIN: 4.08 / MAX: 17.92 MIN: 4.12 / MAX: 6.86 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
LuxCoreRender OpenCL Scene: Rainbow Colors and Prism OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender OpenCL 2.3 Scene: Rainbow Colors and Prism 2 1 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 26.29 26.12 MIN: 23.57 / MAX: 27.71 MIN: 23.66 / MAX: 27.71
Blender Blend File: Classroom - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Classroom - Compute: NVIDIA OptiX 2 1 7 14 21 28 35 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 30.33 30.52
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: resnet50 2 1 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.24, N = 3 24.60 24.75 MIN: 23.3 / MAX: 51.24 MIN: 22.52 / MAX: 45.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
ViennaCL Test: CPU BLAS - dGEMM-NN OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NN 1 2 12 24 36 48 60 SE +/- 0.64, N = 3 SE +/- 0.75, N = 3 53.5 53.2 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
LuxCoreRender OpenCL Scene: LuxCore Benchmark OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender OpenCL 2.3 Scene: LuxCore Benchmark 2 1 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 9.13 9.08 MIN: 0.23 / MAX: 10.53 MIN: 0.23 / MAX: 10.56
ViennaCL Test: OpenCL BLAS - sCOPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - sCOPY 1 2 80 160 240 320 400 SE +/- 0.67, N = 3 366 364 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
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 1 3 2 10 20 30 40 50 SE +/- 0.12, N = 3 SE +/- 0.18, N = 3 SE +/- 0.00, N = 3 44.19 44.02 43.96 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
ViennaCL Test: OpenCL BLAS - dGEMV-T OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-T 1 2 80 160 240 320 400 SE +/- 0.67, N = 3 378 376 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 1 2 2 4 6 8 10 SE +/- 0.020, N = 3 SE +/- 0.003, N = 3 6.234 6.265 1. (CXX) g++ options: -O3 -march=native -fopenmp
MandelGPU OpenCL Device: GPU OpenBenchmarking.org Samples/sec, More Is Better MandelGPU 1.3pts1 OpenCL Device: GPU 2 1 100M 200M 300M 400M 500M SE +/- 4569465.07, N = 5 SE +/- 4478729.17, N = 3 468356717.8 466253751.5 1. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL
LuxCoreRender OpenCL Scene: Food OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender OpenCL 2.3 Scene: Food 1 2 1.0575 2.115 3.1725 4.23 5.2875 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 4.70 4.68 MIN: 0.33 / MAX: 5.9 MIN: 0.3 / MAX: 5.88
Hashcat Benchmark: 7-Zip OpenBenchmarking.org H/s, More Is Better Hashcat 6.1.1 Benchmark: 7-Zip 1 3 2 200K 400K 600K 800K 1000K SE +/- 1071.34, N = 3 SE +/- 3069.38, N = 3 SE +/- 3483.45, N = 3 1149333 1147133 1144667
clpeak OpenCL Test: Global Memory Bandwidth OpenBenchmarking.org GBPS, More Is Better clpeak OpenCL Test: Global Memory Bandwidth 2 1 200 400 600 800 1000 SE +/- 0.07, N = 3 SE +/- 3.33, N = 3 813.37 810.12 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
IndigoBench Acceleration: OpenCL GPU - Scene: Supercar OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Supercar 1 2 12 24 36 48 60 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 52.93 52.72
Hashcat Benchmark: TrueCrypt RIPEMD160 + XTS OpenBenchmarking.org H/s, More Is Better Hashcat 6.1.1 Benchmark: TrueCrypt RIPEMD160 + XTS 3 1 2 200K 400K 600K 800K 1000K SE +/- 883.80, N = 3 SE +/- 1168.09, N = 3 SE +/- 88.19, N = 3 849167 846967 845867
LeelaChessZero Backend: OpenCL OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: OpenCL 1 2 8K 16K 24K 32K 40K SE +/- 165.32, N = 3 SE +/- 192.20, N = 3 39148 38996 1. (CXX) g++ options: -flto -pthread
ViennaCL Test: CPU BLAS - dGEMV-N OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-N 2 1 20 40 60 80 100 SE +/- 0.26, N = 3 SE +/- 0.26, N = 3 78.1 77.8 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: googlenet 2 1 3 6 9 12 15 SE +/- 0.08, N = 3 SE +/- 0.18, N = 3 13.11 13.16 MIN: 11.82 / MAX: 48.41 MIN: 12.01 / MAX: 35.57 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
RealSR-NCNN Scale: 4x - TAA: No OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: No 3 1 2 1.3201 2.6402 3.9603 5.2804 6.6005 SE +/- 0.079, N = 3 SE +/- 0.079, N = 3 SE +/- 0.071, N = 4 5.845 5.866 5.867
Rodinia Test: OpenCL Particle Filter OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenCL Particle Filter 2 1 0.8422 1.6844 2.5266 3.3688 4.211 SE +/- 0.012, N = 3 SE +/- 0.027, N = 3 3.729 3.743 1. (CXX) g++ options: -m64 -lm -lcuda -lcudart -lcudadevrt -lcudart_static -lrt -lpthread -ldl
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 2 3 1 90 180 270 360 450 SE +/- 0.47, N = 3 SE +/- 1.17, N = 3 SE +/- 0.34, N = 3 430.51 429.95 428.92 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
Hashcat Benchmark: SHA1 OpenBenchmarking.org H/s, More Is Better Hashcat 6.1.1 Benchmark: SHA1 3 2 1 5000M 10000M 15000M 20000M 25000M SE +/- 19772062.22, N = 3 SE +/- 18693403.47, N = 3 SE +/- 20398229.77, N = 3 22665866667 22585700000 22583233333
ViennaCL Test: CPU BLAS - dGEMM-TT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TT 1 2 12 24 36 48 60 SE +/- 0.06, N = 3 SE +/- 0.15, N = 3 55.3 55.1 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 1 2 13 26 39 52 65 SE +/- 0.06, N = 3 SE +/- 0.15, N = 3 56.7 56.5 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
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 3 1 2 80 160 240 320 400 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 391.28 390.96 389.90 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
Chaos Group V-RAY Mode: NVIDIA RTX GPU OpenBenchmarking.org vrays, More Is Better Chaos Group V-RAY 5 Mode: NVIDIA RTX GPU 2 1 600 1200 1800 2400 3000 SE +/- 8.62, N = 3 SE +/- 6.17, N = 3 2610 2601
clpeak OpenCL Test: Double-Precision Double OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Double-Precision Double 2 1 140 280 420 560 700 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 657.03 654.89 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
FAHBench OpenBenchmarking.org Ns Per Day, More Is Better FAHBench 2.3.2 2 1 70 140 210 280 350 SE +/- 0.21, N = 3 SE +/- 0.11, N = 3 344.72 343.62
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: yolov4-tiny 1 2 5 10 15 20 25 SE +/- 0.28, N = 3 SE +/- 0.08, N = 3 21.92 21.99 MIN: 19.58 / MAX: 55.4 MIN: 19.81 / MAX: 50.11 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
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 1 2 9K 18K 27K 36K 45K SE +/- 222.52, N = 3 SE +/- 353.13, N = 3 39924.9 39799.6 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
Hashcat Benchmark: MD5 OpenBenchmarking.org H/s, More Is Better Hashcat 6.1.1 Benchmark: MD5 3 2 1 14000M 28000M 42000M 56000M 70000M SE +/- 55041388.47, N = 3 SE +/- 75053099.72, N = 3 SE +/- 73641979.27, N = 3 66617033333 66432866667 66413233333
ViennaCL Test: CPU BLAS - dAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dAXPY 1 2 8 16 24 32 40 SE +/- 1.09, N = 3 SE +/- 0.90, N = 3 33.4 33.3 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
GROMACS Water Benchmark OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2020.3 Water Benchmark 2 1 3 6 9 12 15 SE +/- 0.017, N = 3 SE +/- 0.061, N = 3 9.670 9.643 1. (CXX) g++ options: -O3 -lpthread -ldl -lrt -lm
LuxCoreRender OpenCL Scene: DLSC OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender OpenCL 2.3 Scene: DLSC 1 2 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 11.20 11.17 MIN: 10.85 / MAX: 11.44 MIN: 10.84 / MAX: 11.33
ViennaCL Test: OpenCL BLAS - sDOT OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - sDOT 1 2 80 160 240 320 400 SE +/- 0.88, N = 3 375 374 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
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 1 3 2 500 1000 1500 2000 2500 SE +/- 1.05, N = 3 SE +/- 2.35, N = 3 SE +/- 1.31, N = 3 2347.21 2344.26 2342.08 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
Hashcat Benchmark: SHA-512 OpenBenchmarking.org H/s, More Is Better Hashcat 6.1.1 Benchmark: SHA-512 3 1 2 600M 1200M 1800M 2400M 3000M SE +/- 2834509.56, N = 3 SE +/- 3284475.27, N = 3 SE +/- 2406472.75, N = 3 2857366667 2853033333 2851266667
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: shufflenet-v2 2 1 1.0755 2.151 3.2265 4.302 5.3775 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 4.77 4.78 MIN: 4.53 / MAX: 6.88 MIN: 4.44 / MAX: 5.97 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
ViennaCL Test: OpenCL BLAS - sAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - sAXPY 1 2 110 220 330 440 550 504 503 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
Blender Blend File: Barbershop - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Barbershop - Compute: CUDA 1 2 80 160 240 320 400 SE +/- 0.19, N = 3 SE +/- 0.37, N = 3 373.50 374.21
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: alexnet 1 2 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 11.06 11.08 MIN: 10.13 / MAX: 35.54 MIN: 10.15 / MAX: 28.07 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
ViennaCL Test: OpenCL BLAS - dGEMM-TN OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TN 1 2 130 260 390 520 650 SE +/- 1.33, N = 3 SE +/- 1.53, N = 3 601 600 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 1 2 130 260 390 520 650 SE +/- 1.67, N = 3 SE +/- 1.20, N = 3 603 602 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
RealSR-NCNN Scale: 4x - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: Yes 3 2 1 7 14 21 28 35 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 29.57 29.60 29.62
ViennaCL Test: OpenCL BLAS - dGEMM-NT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NT 1 2 130 260 390 520 650 SE +/- 1.53, N = 3 SE +/- 1.67, N = 3 605 604 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
clpeak OpenCL Test: Integer Compute INT OpenBenchmarking.org GIOPS, More Is Better clpeak OpenCL Test: Integer Compute INT 2 1 4K 8K 12K 16K 20K SE +/- 168.52, N = 7 SE +/- 138.19, N = 3 17951.73 17922.35 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
cl-mem Benchmark: Write OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Write 1 2 160 320 480 640 800 SE +/- 0.38, N = 3 SE +/- 0.75, N = 3 742.0 740.8 1. (CC) gcc options: -O2 -flto -lOpenCL
ViennaCL Test: CPU BLAS - sCOPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sCOPY 1 2 14 28 42 56 70 SE +/- 0.49, N = 3 SE +/- 0.61, N = 3 62.6 62.5 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 2 1 140 280 420 560 700 SE +/- 0.33, N = 3 651 650 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
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 1 3 2 0.7749 1.5498 2.3247 3.0996 3.8745 SE +/- 0.007, N = 3 SE +/- 0.008, N = 3 SE +/- 0.013, N = 3 3.439 3.440 3.444
cl-mem Benchmark: Copy OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Copy 1 2 80 160 240 320 400 SE +/- 0.20, N = 3 SE +/- 0.17, N = 3 363.5 363.0 1. (CC) gcc options: -O2 -flto -lOpenCL
Betsy GPU Compressor Codec: ETC2 RGB - Quality: Highest OpenBenchmarking.org Seconds, Fewer Is Better Betsy GPU Compressor 1.1 Beta Codec: ETC2 RGB - Quality: Highest 2 1 0.9122 1.8244 2.7366 3.6488 4.561 SE +/- 0.017, N = 3 SE +/- 0.029, N = 3 4.049 4.054 1. (CXX) g++ options: -O3 -O2 -lpthread -ldl
ViennaCL Test: CPU BLAS - dGEMV-T OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-T 1 2 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 0.47, N = 3 83.2 83.1 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -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 2 1 500 1000 1500 2000 2500 SE +/- 2.17, N = 3 SE +/- 2.03, N = 3 2226.47 2224.01 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
ViennaCL Test: CPU BLAS - sAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sAXPY 1 2 20 40 60 80 100 SE +/- 2.08, N = 3 SE +/- 2.72, N = 3 91.6 91.5 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
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 2 1 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 26.39 26.36 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
Blender Blend File: BMW27 - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: NVIDIA OptiX 1 2 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 9.76 9.77
clpeak OpenCL Test: Single-Precision Float OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Single-Precision Float 2 1 8K 16K 24K 32K 40K SE +/- 21.78, N = 3 SE +/- 51.98, N = 3 35204.07 35173.57 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
Blender Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX 1 2 11 22 33 44 55 SE +/- 0.12, N = 3 SE +/- 0.08, N = 3 46.68 46.72
OctaneBench Total Score OpenBenchmarking.org Score, More Is Better OctaneBench 2020.1 Total Score 1 2 150 300 450 600 750 680.72 680.19
cl-mem Benchmark: Read OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Read 2 1 200 400 600 800 1000 SE +/- 0.67, N = 3 SE +/- 0.52, N = 3 825.9 825.3 1. (CC) gcc options: -O2 -flto -lOpenCL
VkResample Upscale: 2x - Precision: Double OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Double 1 2 30 60 90 120 150 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 122.80 122.87 1. (CXX) g++ options: -O3 -pthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: regnety_400m 2 1 4 8 12 16 20 SE +/- 0.16, N = 3 SE +/- 0.29, N = 3 16.74 16.75 MIN: 15.52 / MAX: 52.59 MIN: 15.48 / MAX: 39.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Blender Blend File: BMW27 - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: CUDA 1 2 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 18.35 18.36
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 1 3 2 6 12 18 24 30 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 25.48 25.47 25.46 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
Blender Blend File: Fishy Cat - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Fishy Cat - Compute: NVIDIA OptiX 2 1 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 20.42 20.43
Blender Blend File: Fishy Cat - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Fishy Cat - Compute: CUDA 1 2 8 16 24 32 40 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 34.60 34.61
IndigoBench Acceleration: OpenCL GPU - Scene: Bedroom OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Bedroom 2 1 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 20.87 20.87
VkResample Upscale: 2x - Precision: Single OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Single 1 2 3 6 9 12 15 SE +/- 0.006, N = 3 SE +/- 0.005, N = 3 9.282 9.284 1. (CXX) g++ options: -O3 -pthread
Blender Blend File: Pabellon Barcelona - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Pabellon Barcelona - Compute: CUDA 1 2 30 60 90 120 150 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 120.48 120.49
Blender Blend File: Barbershop - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Barbershop - Compute: NVIDIA OptiX 2 1 70 140 210 280 350 SE +/- 0.22, N = 3 SE +/- 0.72, N = 3 335.87 335.89
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 2 1 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 26.31 26.31 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
ViennaCL Test: OpenCL BLAS - dGEMM-TT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TT 2 130 260 390 520 650 SE +/- 0.50, N = 2 605 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
Chaos Group V-RAY Mode: NVIDIA CUDA GPU OpenBenchmarking.org vpaths, More Is Better Chaos Group V-RAY 5 Mode: NVIDIA CUDA GPU 2 1 400 800 1200 1600 2000 1963 1963
Blender Blend File: Classroom - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Classroom - Compute: CUDA 1 2 12 24 36 48 60 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 51.42 51.42
ViennaCL Test: OpenCL BLAS - dGEMV-N OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-N 2 1 50 100 150 200 250 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 237 237 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 2 1 160 320 480 640 800 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 722 722 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 2 1 130 260 390 520 650 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 607 607 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 2 1 12 24 36 48 60 SE +/- 0.18, N = 3 SE +/- 0.34, N = 3 52.9 52.9 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
RedShift Demo OpenBenchmarking.org Seconds, Fewer Is Better RedShift Demo 3.0 1 2 30 60 90 120 150 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 141 141
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: blazeface 2 1 0.423 0.846 1.269 1.692 2.115 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 1.83 1.88 MIN: 1.72 / MAX: 2.92 MIN: 1.74 / MAX: 3.19 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Mixbench Backend: OpenCL - Benchmark: Single Precision OpenBenchmarking.org GFLOPS, More Is Better Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Single Precision 3 2 1 8K 16K 24K 32K 40K SE +/- 623.98, N = 15 SE +/- 17.98, N = 3 SE +/- 22.01, N = 3 35867.33 34079.35 34053.47 1. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
Mixbench Backend: OpenCL - Benchmark: Double Precision OpenBenchmarking.org GFLOPS, More Is Better Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Double Precision 1 2 3 110 220 330 440 550 SE +/- 9.28, N = 15 SE +/- 0.00, N = 3 SE +/- 5.63, N = 3 496.29 467.53 459.26 1. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
Mixbench Backend: OpenCL - Benchmark: Integer OpenBenchmarking.org GIOPS, More Is Better Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Integer 1 3 2 4K 8K 12K 16K 20K SE +/- 8.12, N = 3 SE +/- 13.56, N = 3 SE +/- 404.51, N = 12 20685.77 20677.83 19683.19 1. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
Phoronix Test Suite v10.8.5