RTX 3090 Compute AMD Ryzen 9 5900X 12-Core testing with a ASUS ROG CROSSHAIR VIII HERO (3801 BIOS) and NVIDIA GeForce RTX 3090 24GB on Ubuntu 21.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2108296-TJ-RTX3090CO87&sro .
RTX 3090 Compute Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Vulkan Compiler File-System Screen Resolution RTX 3090 2 3 AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads) ASUS ROG CROSSHAIR VIII HERO (3801 BIOS) AMD Starship/Matisse 16GB 1000GB Western Digital WD_BLACK SN850 1TB + 2000GB NVIDIA GeForce RTX 3090 24GB NVIDIA GA102 HD Audio ASUS VP28U Realtek RTL8125 2.5GbE + Intel I211 Ubuntu 21.10 5.13.0-14-generic (x86_64) GNOME Shell 40.2 X Server 1.20.11 NVIDIA 470.63.01 4.6.0 OpenCL 3.0 CUDA 11.4.112 1.2.175 GCC 11.2.0 ext4 3840x2160 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --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-M6DaQn/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-M6DaQn/gcc-11-11.2.0/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 Processor Details - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016 OpenCL Details - GPU Compute Cores: 10496 Python Details - RTX 3090: Python 3.9.6 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
RTX 3090 Compute vkpeak: fp32-scalar vkpeak: fp32-vec4 vkpeak: fp16-scalar vkpeak: fp16-vec4 vkpeak: fp64-scalar vkpeak: fp64-vec4 vkpeak: int32-scalar vkpeak: int32-vec4 vkpeak: int16-scalar vkpeak: int16-vec4 realsr-ncnn: 4x - No realsr-ncnn: 4x - Yes waifu2x-ncnn: 2x - 3 - Yes vkfft: hashcat: MD5 hashcat: SHA1 hashcat: 7-Zip hashcat: SHA-512 hashcat: TrueCrypt RIPEMD160 + XTS shoc: OpenCL - S3D shoc: OpenCL - Triad shoc: OpenCL - FFT SP shoc: OpenCL - MD5 Hash shoc: OpenCL - Reduction shoc: OpenCL - GEMM SGEMM_N shoc: OpenCL - Max SP Flops shoc: OpenCL - Bus Speed Download shoc: OpenCL - Bus Speed Readback shoc: OpenCL - Texture Read Bandwidth cl-mem: Copy cl-mem: Read cl-mem: Write namd-cuda: ATPase Simulation - 327,506 Atoms vkresample: 2x - Double vkresample: 2x - Single octanebench: Total Score redshift: fahbench: lczero: OpenCL rodinia: OpenCL Particle Filter arrayfire: Conjugate Gradient OpenCL luxcorerender: DLSC - GPU luxcorerender: Danish Mood - GPU luxcorerender: Orange Juice - GPU luxcorerender: LuxCore Benchmark - GPU luxcorerender: Rainbow Colors and Prism - GPU financebench: Black-Scholes OpenCL viennacl: CPU BLAS - sCOPY viennacl: CPU BLAS - sAXPY viennacl: CPU BLAS - sDOT viennacl: CPU BLAS - dCOPY viennacl: CPU BLAS - dAXPY viennacl: CPU BLAS - dDOT viennacl: CPU BLAS - dGEMV-N viennacl: CPU BLAS - dGEMV-T viennacl: CPU BLAS - dGEMM-NN viennacl: CPU BLAS - dGEMM-NT viennacl: CPU BLAS - dGEMM-TN viennacl: CPU BLAS - dGEMM-TT viennacl: OpenCL BLAS - sCOPY viennacl: OpenCL BLAS - sAXPY viennacl: OpenCL BLAS - sDOT viennacl: OpenCL BLAS - dCOPY viennacl: OpenCL BLAS - dAXPY viennacl: OpenCL BLAS - dDOT viennacl: OpenCL BLAS - dGEMV-N viennacl: OpenCL BLAS - dGEMV-T viennacl: OpenCL BLAS - dGEMM-NN viennacl: OpenCL BLAS - dGEMM-NT viennacl: OpenCL BLAS - dGEMM-TN viennacl: OpenCL BLAS - dGEMM-TT 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 ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - regnety_400m indigobench: OpenCL GPU - Bedroom indigobench: OpenCL GPU - Supercar blender: BMW27 - CUDA blender: Classroom - CUDA blender: Fishy Cat - CUDA blender: Barbershop - CUDA blender: BMW27 - NVIDIA OptiX blender: Classroom - NVIDIA OptiX blender: Fishy Cat - NVIDIA OptiX blender: Barbershop - NVIDIA OptiX blender: Pabellon Barcelona - CUDA blender: Pabellon Barcelona - NVIDIA OptiX mandelgpu: GPU clpeak: Integer Compute INT clpeak: Single-Precision Float clpeak: Double-Precision Double clpeak: Global Memory Bandwidth v-ray: NVIDIA RTX GPU v-ray: NVIDIA CUDA GPU RTX 3090 2 3 20910.29 27572.34 20776.35 40572.58 653.53 653.50 20763.65 20652.47 13670.44 16931.70 5.592 28.508 3.306 43351 66726633333 22839700000 1153133 2879033333 854867 430.301 25.4664 2349.20 44.5445 391.546 8329.86 40181.1 26.3155 27.0998 2236.38 363.8 827.3 740.1 0.12056 119.648 9.272 681.17956 138 345.3526 53955 3.730 1.472 11.50 8.93 10.38 11.01 32.61 6.271 67.9 102 155 24.3 36.3 47.5 82.1 89.1 53.2 53.7 58.4 56.6 363 499 372 593 721 658 240 377 602 605 600 603 4.18 1.86 2.10 1.69 1.96 3.11 0.91 4.21 4.06 1.56 1.78 3.44 6.75 4.16 2.41 20.935 53.168 18.31 51.31 34.53 373.96 12.20 28.60 21.66 315.25 120.33 43.45 483619873.6 18162.91 35211.37 657.71 810.35 2941 2115 21142.21 27739.81 20950.52 40867.15 658.57 658.55 20924.81 20673.05 13709.9 17004.32 5.523 28.245 3.277 43413 66914300000 22860600000 1160100 2884800000 860700 430.156 25.4781 2352 44.2953 390.914 8432.96 40013.3 26.338 27.1248 2237.75 363.7 827.3 739 0.12076 119.394 9.271 682.731009 139 343.5447 53950 3.672 1.483 11.5 8.66 10.36 10.93 32.81 6.271 69.4 105 156 24.7 36.9 47.8 81.7 89.8 53.3 53.8 58.2 56.7 363 499 370 592 720 658 239 376 600 602 597 601 4.16 1.84 2.1 1.68 1.95 3.13 0.92 3.9 4.04 1.55 1.81 3.44 6.77 4 2.41 20.987 53.39 18.33 51.07 34.44 372.81 9.5 28.58 18.94 314.61 120.54 43.51 483164709 18313.8 35226 656.4 813.51 2939 2116 20946.96 27428.37 20725.45 40257.04 648.73 648.72 20614.05 20517.61 13608.26 16875.09 5.573 28.299 3.287 42399 66706700000 22821000000 1157500 2882500000 855400 429.423 25.4707 2348.03 44.1942 390.293 8278.67 39723.3 26.2982 27.0876 2241.48 363.6 827.7 737.6 0.12115 119.107 9.286 682.901259 138 344.8072 53598 3.675 1.473 11.5 8.86 10.42 10.97 32.87 6.263 67.2 101 152 24.6 36.8 47.5 82.2 89.8 54.6 53.8 58.4 56.6 367 498 371 607 724 660 240 377 605 607 602 4.13 1.85 2.1 1.69 1.96 3.12 0.91 3.85 4.1 1.55 1.8 3.43 6.68 3.99 2.41 20.976 53.414 18.36 51.13 34.5 373.1 9.51 28.97 18.99 317.94 120.48 43.55 485737287.8 18533.09 35183.92 658.23 813.54 2959 2116 OpenBenchmarking.org
vkpeak fp32-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp32-scalar 2 3 RTX 3090 5K 10K 15K 20K 25K SE +/- 144.67, N = 3 21142.21 20946.96 20910.29
vkpeak fp32-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp32-vec4 2 3 RTX 3090 6K 12K 18K 24K 30K SE +/- 183.95, N = 3 27739.81 27428.37 27572.34
vkpeak fp16-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp16-scalar 2 3 RTX 3090 4K 8K 12K 16K 20K SE +/- 67.18, N = 3 20950.52 20725.45 20776.35
vkpeak fp16-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp16-vec4 2 3 RTX 3090 9K 18K 27K 36K 45K SE +/- 147.11, N = 3 40867.15 40257.04 40572.58
vkpeak fp64-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp64-scalar 2 3 RTX 3090 140 280 420 560 700 SE +/- 2.50, N = 3 658.57 648.73 653.53
vkpeak fp64-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp64-vec4 2 3 RTX 3090 140 280 420 560 700 SE +/- 2.55, N = 3 658.55 648.72 653.50
vkpeak int32-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int32-scalar 2 3 RTX 3090 4K 8K 12K 16K 20K SE +/- 81.20, N = 3 20924.81 20614.05 20763.65
vkpeak int32-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int32-vec4 2 3 RTX 3090 4K 8K 12K 16K 20K SE +/- 55.18, N = 3 20673.05 20517.61 20652.47
vkpeak int16-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int16-scalar 2 3 RTX 3090 3K 6K 9K 12K 15K SE +/- 20.28, N = 3 13709.90 13608.26 13670.44
vkpeak int16-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int16-vec4 2 3 RTX 3090 4K 8K 12K 16K 20K SE +/- 41.21, N = 3 17004.32 16875.09 16931.70
RealSR-NCNN Scale: 4x - TAA: No OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: No 2 3 RTX 3090 1.2582 2.5164 3.7746 5.0328 6.291 SE +/- 0.008, N = 3 5.523 5.573 5.592
RealSR-NCNN Scale: 4x - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: Yes 2 3 RTX 3090 7 14 21 28 35 SE +/- 0.04, N = 3 28.25 28.30 28.51
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 2 3 RTX 3090 0.7439 1.4878 2.2317 2.9756 3.7195 SE +/- 0.016, N = 3 3.277 3.287 3.306
VkFFT OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.1.1 2 3 RTX 3090 9K 18K 27K 36K 45K SE +/- 375.64, N = 3 43413 42399 43351 1. (CXX) g++ options: -O3 -pthread
Hashcat Benchmark: MD5 OpenBenchmarking.org H/s, More Is Better Hashcat 6.1.1 Benchmark: MD5 2 3 RTX 3090 14000M 28000M 42000M 56000M 70000M SE +/- 4511220.58, N = 3 66914300000 66706700000 66726633333
Hashcat Benchmark: SHA1 OpenBenchmarking.org H/s, More Is Better Hashcat 6.1.1 Benchmark: SHA1 2 3 RTX 3090 5000M 10000M 15000M 20000M 25000M SE +/- 24017979.38, N = 3 22860600000 22821000000 22839700000
Hashcat Benchmark: 7-Zip OpenBenchmarking.org H/s, More Is Better Hashcat 6.1.1 Benchmark: 7-Zip 2 3 RTX 3090 200K 400K 600K 800K 1000K SE +/- 1017.08, N = 3 1160100 1157500 1153133
Hashcat Benchmark: SHA-512 OpenBenchmarking.org H/s, More Is Better Hashcat 6.1.1 Benchmark: SHA-512 2 3 RTX 3090 600M 1200M 1800M 2400M 3000M SE +/- 3299158.14, N = 3 2884800000 2882500000 2879033333
Hashcat Benchmark: TrueCrypt RIPEMD160 + XTS OpenBenchmarking.org H/s, More Is Better Hashcat 6.1.1 Benchmark: TrueCrypt RIPEMD160 + XTS 2 3 RTX 3090 200K 400K 600K 800K 1000K SE +/- 1741.97, N = 3 860700 855400 854867
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 RTX 3090 90 180 270 360 450 SE +/- 0.25, N = 3 430.16 429.42 430.30 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -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 2 3 RTX 3090 6 12 18 24 30 SE +/- 0.02, N = 3 25.48 25.47 25.47 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -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 2 3 RTX 3090 500 1000 1500 2000 2500 SE +/- 1.26, N = 3 2352.00 2348.03 2349.20 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -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 2 3 RTX 3090 10 20 30 40 50 SE +/- 0.00, N = 3 44.30 44.19 44.54 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -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 2 3 RTX 3090 80 160 240 320 400 SE +/- 0.20, N = 3 390.91 390.29 391.55 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -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 2 3 RTX 3090 2K 4K 6K 8K 10K SE +/- 56.22, N = 3 8432.96 8278.67 8329.86 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -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 2 3 RTX 3090 9K 18K 27K 36K 45K SE +/- 475.87, N = 3 40013.3 39723.3 40181.1 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -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 2 3 RTX 3090 6 12 18 24 30 SE +/- 0.03, N = 3 26.34 26.30 26.32 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -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 2 3 RTX 3090 6 12 18 24 30 SE +/- 0.01, N = 3 27.12 27.09 27.10 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
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 3 RTX 3090 500 1000 1500 2000 2500 SE +/- 5.62, N = 3 2237.75 2241.48 2236.38 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
cl-mem Benchmark: Copy OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Copy 2 3 RTX 3090 80 160 240 320 400 SE +/- 0.15, N = 3 363.7 363.6 363.8 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 2 3 RTX 3090 200 400 600 800 1000 SE +/- 0.42, N = 3 827.3 827.7 827.3 1. (CC) gcc options: -O2 -flto -lOpenCL
cl-mem Benchmark: Write OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Write 2 3 RTX 3090 160 320 480 640 800 SE +/- 0.23, N = 3 739.0 737.6 740.1 1. (CC) gcc options: -O2 -flto -lOpenCL
NAMD CUDA ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD CUDA 2.14 ATPase Simulation - 327,506 Atoms 2 3 RTX 3090 0.0273 0.0546 0.0819 0.1092 0.1365 SE +/- 0.00027, N = 3 0.12076 0.12115 0.12056
VkResample Upscale: 2x - Precision: Double OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Double 2 3 RTX 3090 30 60 90 120 150 SE +/- 0.14, N = 3 119.39 119.11 119.65 1. (CXX) g++ options: -O3 -pthread
VkResample Upscale: 2x - Precision: Single OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Single 2 3 RTX 3090 3 6 9 12 15 SE +/- 0.015, N = 3 9.271 9.286 9.272 1. (CXX) g++ options: -O3 -pthread
OctaneBench Total Score OpenBenchmarking.org Score, More Is Better OctaneBench 2020.1 Total Score 2 3 RTX 3090 150 300 450 600 750 682.73 682.90 681.18
RedShift Demo OpenBenchmarking.org Seconds, Fewer Is Better RedShift Demo 3.0 2 3 RTX 3090 30 60 90 120 150 SE +/- 0.33, N = 3 139 138 138
FAHBench OpenBenchmarking.org Ns Per Day, More Is Better FAHBench 2.3.2 2 3 RTX 3090 80 160 240 320 400 SE +/- 0.17, N = 3 343.54 344.81 345.35
LeelaChessZero Backend: OpenCL OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: OpenCL 2 3 RTX 3090 12K 24K 36K 48K 60K SE +/- 24.25, N = 3 53950 53598 53955 1. (CXX) g++ options: -flto -pthread
Rodinia Test: OpenCL Particle Filter OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenCL Particle Filter 2 3 RTX 3090 0.8393 1.6786 2.5179 3.3572 4.1965 SE +/- 0.044, N = 4 3.672 3.675 3.730 1. (CXX) g++ options: -O2 -lOpenCL
ArrayFire Test: Conjugate Gradient OpenCL OpenBenchmarking.org ms, Fewer Is Better ArrayFire 3.7 Test: Conjugate Gradient OpenCL 2 3 RTX 3090 0.3337 0.6674 1.0011 1.3348 1.6685 SE +/- 0.001, N = 3 1.483 1.473 1.472 1. (CXX) g++ options: -rdynamic
LuxCoreRender Scene: DLSC - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: DLSC - Acceleration: GPU 2 3 RTX 3090 3 6 9 12 15 SE +/- 0.01, N = 3 11.50 11.50 11.50 MIN: 11.34 / MAX: 11.68 MIN: 11.35 / MAX: 11.71 MIN: 11.31 / MAX: 11.72
LuxCoreRender Scene: Danish Mood - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Danish Mood - Acceleration: GPU 2 3 RTX 3090 2 4 6 8 10 SE +/- 0.13, N = 3 8.66 8.86 8.93 MIN: 2.96 / MAX: 10.52 MIN: 3.16 / MAX: 10.65 MIN: 2.97 / MAX: 10.79
LuxCoreRender Scene: Orange Juice - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Orange Juice - Acceleration: GPU 2 3 RTX 3090 3 6 9 12 15 SE +/- 0.03, N = 3 10.36 10.42 10.38 MIN: 8.48 / MAX: 13.54 MIN: 8.51 / MAX: 13.74 MIN: 8.42 / MAX: 13.74
LuxCoreRender Scene: LuxCore Benchmark - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: LuxCore Benchmark - Acceleration: GPU 2 3 RTX 3090 3 6 9 12 15 SE +/- 0.03, N = 3 10.93 10.97 11.01 MIN: 3.29 / MAX: 12.95 MIN: 3.33 / MAX: 13.02 MIN: 3.31 / MAX: 13.09
LuxCoreRender Scene: Rainbow Colors and Prism - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Rainbow Colors and Prism - Acceleration: GPU 2 3 RTX 3090 8 16 24 32 40 SE +/- 0.18, N = 3 32.81 32.87 32.61 MIN: 30.72 / MAX: 35.61 MIN: 30.74 / MAX: 35.64 MIN: 29.7 / MAX: 35.64
FinanceBench Benchmark: Black-Scholes OpenCL OpenBenchmarking.org ms, Fewer Is Better FinanceBench 2016-07-25 Benchmark: Black-Scholes OpenCL 2 3 RTX 3090 2 4 6 8 10 SE +/- 0.001, N = 3 6.271 6.263 6.271 1. (CXX) g++ options: -O3 -march=native -fopenmp
ViennaCL Test: CPU BLAS - sCOPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sCOPY 2 3 RTX 3090 15 30 45 60 75 SE +/- 0.06, N = 3 69.4 67.2 67.9 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - sAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sAXPY 2 3 RTX 3090 20 40 60 80 100 SE +/- 0.33, N = 3 105 101 102 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 2 3 RTX 3090 30 60 90 120 150 SE +/- 0.67, N = 3 156 152 155 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 2 3 RTX 3090 6 12 18 24 30 SE +/- 0.09, N = 3 24.7 24.6 24.3 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 2 3 RTX 3090 8 16 24 32 40 SE +/- 0.25, N = 3 36.9 36.8 36.3 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 2 3 RTX 3090 11 22 33 44 55 SE +/- 0.23, N = 3 47.8 47.5 47.5 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 2 3 RTX 3090 20 40 60 80 100 SE +/- 0.10, N = 3 81.7 82.2 82.1 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 2 3 RTX 3090 20 40 60 80 100 SE +/- 0.03, N = 3 89.8 89.8 89.1 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 2 3 RTX 3090 12 24 36 48 60 SE +/- 0.52, N = 3 53.3 54.6 53.2 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 3 RTX 3090 12 24 36 48 60 SE +/- 0.07, N = 3 53.8 53.8 53.7 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 2 3 RTX 3090 13 26 39 52 65 SE +/- 0.09, N = 3 58.2 58.4 58.4 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 2 3 RTX 3090 13 26 39 52 65 SE +/- 0.09, N = 3 56.7 56.6 56.6 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 2 3 RTX 3090 80 160 240 320 400 SE +/- 0.58, N = 3 363 364 363 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 2 3 RTX 3090 110 220 330 440 550 SE +/- 0.33, N = 3 499 498 499 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 2 3 RTX 3090 80 160 240 320 400 SE +/- 0.33, N = 3 370 371 372 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 3 RTX 3090 130 260 390 520 650 SE +/- 0.33, N = 3 592 607 593 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 3 RTX 3090 160 320 480 640 800 SE +/- 0.33, N = 3 720 724 721 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 3 RTX 3090 140 280 420 560 700 SE +/- 0.67, N = 3 658 660 658 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 2 3 RTX 3090 50 100 150 200 250 SE +/- 0.33, N = 3 239 240 240 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 2 3 RTX 3090 80 160 240 320 400 SE +/- 0.33, N = 3 376 377 377 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 2 3 RTX 3090 130 260 390 520 650 SE +/- 1.67, N = 3 600 605 602 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 2 3 RTX 3090 130 260 390 520 650 SE +/- 1.33, N = 3 602 607 605 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 2 3 RTX 3090 130 260 390 520 650 SE +/- 1.53, N = 3 597 602 600 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: OpenCL BLAS - dGEMM-TT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TT 2 RTX 3090 130 260 390 520 650 SE +/- 1.67, N = 3 601 603 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mobilenet 2 3 RTX 3090 0.9405 1.881 2.8215 3.762 4.7025 SE +/- 0.00, N = 3 4.16 4.13 4.18 MIN: 4.11 / MAX: 4.52 MIN: 4.09 / MAX: 4.58 MIN: 4.11 / MAX: 4.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 2 3 RTX 3090 0.4185 0.837 1.2555 1.674 2.0925 SE +/- 0.00, N = 3 1.84 1.85 1.86 MIN: 1.82 / MAX: 2.57 MIN: 1.83 / MAX: 3.41 MIN: 1.82 / MAX: 5.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 2 3 RTX 3090 0.4725 0.945 1.4175 1.89 2.3625 SE +/- 0.01, N = 3 2.10 2.10 2.10 MIN: 2.08 / MAX: 3.15 MIN: 2.08 / MAX: 2.65 MIN: 2.07 / MAX: 3.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: shufflenet-v2 2 3 RTX 3090 0.3803 0.7606 1.1409 1.5212 1.9015 SE +/- 0.01, N = 3 1.68 1.69 1.69 MIN: 1.67 / MAX: 2.34 MIN: 1.67 / MAX: 2.42 MIN: 1.67 / MAX: 3.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mnasnet 2 3 RTX 3090 0.441 0.882 1.323 1.764 2.205 SE +/- 0.01, N = 3 1.95 1.96 1.96 MIN: 1.94 / MAX: 2.45 MIN: 1.94 / MAX: 2.95 MIN: 1.94 / MAX: 3.05 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: efficientnet-b0 2 3 RTX 3090 0.7043 1.4086 2.1129 2.8172 3.5215 SE +/- 0.01, N = 3 3.11 3.12 3.11 MIN: 3.1 / MAX: 3.23 MIN: 3.1 / MAX: 4.74 MIN: 3.09 / MAX: 4.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: blazeface 2 3 RTX 3090 0.207 0.414 0.621 0.828 1.035 SE +/- 0.01, N = 3 0.91 0.91 0.91 MIN: 0.89 / MAX: 1.76 MIN: 0.9 / MAX: 2.07 MIN: 0.89 / MAX: 1.96 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: googlenet 2 3 RTX 3090 0.9473 1.8946 2.8419 3.7892 4.7365 SE +/- 0.06, N = 3 3.87 3.85 4.21 MIN: 3.62 / MAX: 14.75 MIN: 3.62 / MAX: 14.78 MIN: 3.58 / MAX: 15.09 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: vgg16 2 3 RTX 3090 0.9225 1.845 2.7675 3.69 4.6125 SE +/- 0.01, N = 3 4.04 4.10 4.06 MIN: 4.02 / MAX: 4.12 MIN: 4.01 / MAX: 14.21 MIN: 4.01 / MAX: 10.61 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet18 2 3 RTX 3090 0.351 0.702 1.053 1.404 1.755 SE +/- 0.02, N = 3 1.55 1.55 1.56 MIN: 1.52 / MAX: 1.82 MIN: 1.54 / MAX: 1.85 MIN: 1.52 / MAX: 10.44 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: alexnet 2 3 RTX 3090 0.4073 0.8146 1.2219 1.6292 2.0365 SE +/- 0.01, N = 3 1.78 1.80 1.78 MIN: 1.76 / MAX: 1.96 MIN: 1.77 / MAX: 1.97 MIN: 1.75 / MAX: 2.11 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet50 2 3 RTX 3090 0.7763 1.5526 2.3289 3.1052 3.8815 SE +/- 0.01, N = 3 3.44 3.43 3.44 MIN: 3.43 / MAX: 3.55 MIN: 3.42 / MAX: 3.7 MIN: 3.42 / MAX: 3.57 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: yolov4-tiny 2 3 RTX 3090 2 4 6 8 10 SE +/- 0.03, N = 3 6.77 6.68 6.75 MIN: 6.42 / MAX: 8.75 MIN: 6.33 / MAX: 7.23 MIN: 6.39 / MAX: 7.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: squeezenet_ssd 2 3 RTX 3090 0.936 1.872 2.808 3.744 4.68 SE +/- 0.12, N = 2 4.00 3.99 4.16 MIN: 3.92 / MAX: 4.17 MIN: 3.91 / MAX: 4.27 MIN: 3.94 / MAX: 5.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: regnety_400m 2 3 RTX 3090 0.5423 1.0846 1.6269 2.1692 2.7115 SE +/- 0.01, N = 3 2.40 2.41 2.41 MIN: 2.39 / MAX: 2.53 MIN: 2.39 / MAX: 3.92 MIN: 2.37 / MAX: 3.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
IndigoBench Acceleration: OpenCL GPU - Scene: Bedroom OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Bedroom 2 3 RTX 3090 5 10 15 20 25 SE +/- 0.05, N = 3 20.99 20.98 20.94
IndigoBench Acceleration: OpenCL GPU - Scene: Supercar OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Supercar 2 3 RTX 3090 12 24 36 48 60 SE +/- 0.06, N = 3 53.39 53.41 53.17
Blender Blend File: BMW27 - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: CUDA 2 3 RTX 3090 5 10 15 20 25 SE +/- 0.01, N = 3 18.33 18.36 18.31
Blender Blend File: Classroom - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Classroom - Compute: CUDA 2 3 RTX 3090 12 24 36 48 60 SE +/- 0.05, N = 3 51.07 51.13 51.31
Blender Blend File: Fishy Cat - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Fishy Cat - Compute: CUDA 2 3 RTX 3090 8 16 24 32 40 SE +/- 0.01, N = 3 34.44 34.50 34.53
Blender Blend File: Barbershop - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Barbershop - Compute: CUDA 2 3 RTX 3090 80 160 240 320 400 SE +/- 0.27, N = 3 372.81 373.10 373.96
Blender Blend File: BMW27 - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: NVIDIA OptiX 2 3 RTX 3090 3 6 9 12 15 SE +/- 2.70, N = 15 9.50 9.51 12.20
Blender Blend File: Classroom - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Classroom - Compute: NVIDIA OptiX 2 3 RTX 3090 7 14 21 28 35 SE +/- 0.04, N = 3 28.58 28.97 28.60
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 3 RTX 3090 5 10 15 20 25 SE +/- 2.66, N = 15 18.94 18.99 21.66
Blender Blend File: Barbershop - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Barbershop - Compute: NVIDIA OptiX 2 3 RTX 3090 70 140 210 280 350 SE +/- 0.18, N = 3 314.61 317.94 315.25
Blender Blend File: Pabellon Barcelona - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Pabellon Barcelona - Compute: CUDA 2 3 RTX 3090 30 60 90 120 150 SE +/- 0.05, N = 3 120.54 120.48 120.33
Blender Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX 2 3 RTX 3090 10 20 30 40 50 SE +/- 0.09, N = 3 43.51 43.55 43.45
MandelGPU OpenCL Device: GPU OpenBenchmarking.org Samples/sec, More Is Better MandelGPU 1.3pts1 OpenCL Device: GPU 2 3 RTX 3090 100M 200M 300M 400M 500M SE +/- 222116.26, N = 3 483164709.0 485737287.8 483619873.6 1. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL
clpeak OpenCL Test: Integer Compute INT OpenBenchmarking.org GIOPS, More Is Better clpeak OpenCL Test: Integer Compute INT 2 3 RTX 3090 4K 8K 12K 16K 20K SE +/- 148.97, N = 9 18313.80 18533.09 18162.91 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
clpeak OpenCL Test: Single-Precision Float OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Single-Precision Float 2 3 RTX 3090 8K 16K 24K 32K 40K SE +/- 13.13, N = 3 35226.00 35183.92 35211.37 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
clpeak OpenCL Test: Double-Precision Double OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Double-Precision Double 2 3 RTX 3090 140 280 420 560 700 SE +/- 0.02, N = 3 656.40 658.23 657.71 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
clpeak OpenCL Test: Global Memory Bandwidth OpenBenchmarking.org GBPS, More Is Better clpeak OpenCL Test: Global Memory Bandwidth 2 3 RTX 3090 200 400 600 800 1000 SE +/- 3.03, N = 3 813.51 813.54 810.35 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
Chaos Group V-RAY Mode: NVIDIA RTX GPU OpenBenchmarking.org vrays, More Is Better Chaos Group V-RAY 5 Mode: NVIDIA RTX GPU 2 3 RTX 3090 600 1200 1800 2400 3000 SE +/- 11.15, N = 3 2939 2959 2941
Chaos Group V-RAY Mode: NVIDIA CUDA GPU OpenBenchmarking.org vpaths, More Is Better Chaos Group V-RAY 5 Mode: NVIDIA CUDA GPU 2 3 RTX 3090 500 1000 1500 2000 2500 SE +/- 0.88, N = 3 2116 2116 2115
Phoronix Test Suite v10.8.4