NVIDIA GeForce RTX 3090 AMD Ryzen 9 7950X 16-Core testing with a ASUS TUF GAMING X670E-PLUS WIFI (0613 BIOS) and Gigabyte NVIDIA GeForce RTX 4090 24GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2210139-SADD-211206987&rdt&grr .
NVIDIA GeForce 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads) ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3801 BIOS) AMD Starship/Matisse 32GB 1000GB Sabrent Rocket 4.0 Plus NVIDIA GeForce RTX 3090 24GB NVIDIA GA102 HD Audio ASUS MG28U Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 21.10 5.13.0-22-generic (x86_64) GNOME Shell 40.5 X Server 1.20.13 NVIDIA 495.44 4.6.0 OpenCL 3.0 CUDA 11.5.100 1.2.186 GCC 11.2.0 + Clang 13.0.0-2 ext4 3840x2160 AMD Ryzen 9 7950X 16-Core @ 4.50GHz (16 Cores / 32 Threads) ASUS TUF GAMING X670E-PLUS WIFI (0613 BIOS) AMD Device 14d8 2048GB XPG GAMMIX S70 BLADE + 4001GB SSD 870 QVO 4TB Gigabyte NVIDIA GeForce RTX 4090 24GB NVIDIA Device 22ba PI-KVM Video Realtek RTL8125 2.5GbE + MEDIATEK Device 0608 Ubuntu 22.04 5.15.0-25-generic (x86_64) GNOME Shell 42.4 X Server 1.21.1.3 NVIDIA 520.56.06 OpenCL 3.0 CUDA 11.8.87 1.3.205 GCC 13.0.0 20221013 + Clang 14.0.0-1ubuntu1 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - RTX 3090: --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-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/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 - NVIDIA RTX 3090: --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-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/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 - NVIDIA 3090: --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-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/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 - RTX 4090: --build=x86_64-linux-gnu --disable-multilib --enable-checking=release --enable-languages=c,c++ --host=x86_64-linux-gnu --target=x86_64-linux-gnu -v Processor Details - RTX 3090: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201016 - NVIDIA RTX 3090: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201016 - NVIDIA 3090: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201016 - RTX 4090: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203 Graphics Details - RTX 3090: BAR1 / Visible vRAM Size: 32768 MiB - NVIDIA RTX 3090: BAR1 / Visible vRAM Size: 32768 MiB - NVIDIA 3090: BAR1 / Visible vRAM Size: 32768 MiB - RTX 4090: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.02.18.00.d2 OpenCL Details - RTX 3090: GPU Compute Cores: 10496 - NVIDIA RTX 3090: GPU Compute Cores: 10496 - NVIDIA 3090: GPU Compute Cores: 10496 - RTX 4090: GPU Compute Cores: 16384 Python Details - RTX 3090: Python 3.9.7 - NVIDIA RTX 3090: Python 3.9.7 - NVIDIA 3090: Python 3.9.7 - RTX 4090: Python 3.10.6 Security Details - RTX 3090: 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 - NVIDIA RTX 3090: 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 - NVIDIA 3090: 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 4090: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
NVIDIA GeForce RTX 3090 shoc: OpenCL - Max SP Flops vkfft: etlegacy: 3840 x 2160 vkpeak: fp64-vec4 vkpeak: int16-vec4 vkpeak: int16-scalar vkpeak: int32-vec4 vkpeak: int32-scalar vkpeak: fp64-scalar vkpeak: fp16-vec4 vkpeak: fp16-scalar vkpeak: fp32-vec4 vkpeak: fp32-scalar lczero: OpenCL octanebench: Total Score warsow: 1920 x 1080 fahbench: warsow: 1920 x 1200 warsow: 2560 x 1440 warsow: 3840 x 2160 luxcorerender: DLSC - GPU blender: Barbershop - CUDA luxcorerender: LuxCore Benchmark - GPU v-ray: NVIDIA RTX GPU v-ray: NVIDIA CUDA GPU luxcorerender: Orange Juice - GPU indigobench: OpenCL GPU - Bedroom indigobench: OpenCL GPU - Supercar luxcorerender: Danish Mood - GPU namd-cuda: ATPase Simulation - 327,506 Atoms blender: Barbershop - NVIDIA OptiX unvanquished: 2560 x 1440 - Ultra ncnn: Vulkan GPU - regnety_400m ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU - mobilenet blender: Pabellon Barcelona - CUDA clpeak: Double-Precision Double xonotic: 3840 x 2160 - Ultimate blender: BMW27 - CUDA unvanquished: 1920 x 1080 - Ultra realsr-ncnn: 4x - Yes xonotic: 3840 x 2160 - Ultra unvanquished: 3840 x 2160 - Ultra unvanquished: 1920 x 1200 - Ultra unvanquished: 1920 x 1080 - High unvanquished: 3840 x 2160 - High unvanquished: 2560 x 1440 - High unvanquished: 1920 x 1200 - High xonotic: 3840 x 2160 - High vkresample: 2x - Double 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 - sAXPY viennacl: CPU BLAS - sCOPY unvanquished: 2560 x 1440 - Medium unvanquished: 3840 x 2160 - Medium unvanquished: 1920 x 1200 - Medium unvanquished: 1920 x 1080 - Medium blender: Fishy Cat - CUDA 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 blender: Classroom - CUDA xonotic: 3840 x 2160 - Low blender: Fishy Cat - NVIDIA OptiX paraview: Many Spheres - 3840 x 2160 paraview: Many Spheres - 3840 x 2160 paraview: Many Spheres - 1920 x 1080 paraview: Many Spheres - 1920 x 1080 paraview: Many Spheres - 1920 x 1200 paraview: Many Spheres - 1920 x 1200 paraview: Many Spheres - 2560 x 1440 paraview: Many Spheres - 2560 x 1440 shoc: OpenCL - Texture Read Bandwidth blender: Pabellon Barcelona - NVIDIA OptiX blender: Classroom - NVIDIA OptiX etlegacy: 2560 x 1440 blender: BMW27 - NVIDIA OptiX etlegacy: 1920 x 1080 etlegacy: 1920 x 1200 vkresample: 2x - Single paraview: Wavelet Contour - 3840 x 2160 paraview: Wavelet Contour - 3840 x 2160 hashcat: SHA-512 paraview: Wavelet Volume - 3840 x 2160 paraview: Wavelet Volume - 3840 x 2160 paraview: Wavelet Contour - 2560 x 1440 paraview: Wavelet Contour - 2560 x 1440 paraview: Wavelet Contour - 1920 x 1200 paraview: Wavelet Contour - 1920 x 1200 paraview: Wavelet Contour - 1920 x 1080 paraview: Wavelet Contour - 1920 x 1080 hashcat: SHA1 hashcat: MD5 hashcat: TrueCrypt RIPEMD160 + XTS luxcorerender: Rainbow Colors and Prism - GPU paraview: Wavelet Volume - 2560 x 1440 paraview: Wavelet Volume - 2560 x 1440 paraview: Wavelet Volume - 1920 x 1200 paraview: Wavelet Volume - 1920 x 1200 paraview: Wavelet Volume - 1920 x 1080 paraview: Wavelet Volume - 1920 x 1080 realsr-ncnn: 4x - No rodinia: OpenCL Particle Filter hashcat: 7-Zip arrayfire: Conjugate Gradient OpenCL shoc: OpenCL - Bus Speed Readback waifu2x-ncnn: 2x - 3 - Yes cl-mem: Copy cl-mem: Read cl-mem: Write shoc: OpenCL - GEMM SGEMM_N mandelgpu: GPU shoc: OpenCL - S3D shoc: OpenCL - Bus Speed Download shoc: OpenCL - Triad clpeak: Integer Compute INT shoc: OpenCL - FFT SP shoc: OpenCL - Reduction shoc: OpenCL - MD5 Hash clpeak: Single-Precision Float clpeak: Global Memory Bandwidth financebench: Black-Scholes OpenCL neatbench: GPU mixbench: NVIDIA CUDA - Integer RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 40753.9 45831 648.4 16885.79 13708.58 20672.19 20769.27 653.61 41184.89 20949.64 27806.74 20927.99 22739 686.231258 984.3 353.8915 984.8 984.7 960.8 91.13 2856 2119 10.45 20.961 53.438 9.18 0.12792 56.19 461.7 2.54 15.96 7.02 3.55 1.91 1.67 4.17 5.85 1.06 3.26 2.08 1.94 3.17 1.98 4.28 48.11 658.16 374.4286255 11.04 470.8 28.949 499.2632615 456.8 463 482 463.6 469 464.9 556.9297001 117.817 91.9 93.8 88.4 81.5 76.1 68.1 42.4 34.9 23.3 140 99.6 66.1 492.5 490.1 473.6 496.1 22.86 602 599 604 601 377 239 660 722 606 375 503 368 22.76 655.142588 11.22 9169.636 91.46 9419.399 93.95 9414.686 93.91 9343.817 93.2 2246.17 17.96 17.4 640.2 6.94 652.3 645.3 9.272 4134.488 396.74 2887000000 6157.361 384.84 5366.18 514.93 5849.675 561.32 6274.519 602.09 22599300000 71446900000 846100 32.33 8944.746 559.05 10151.478 634.47 10874.708 679.67 5.621 3.843 1138500 1.47 27.1252 3.313 364.1 794.6 743.1 8102.38 481322759.6 429.082 26.3342 25.4781 17725.14 2100.51 391.209 44.1932 35227.21 813.42 6.259 40238.8 44252 638.7 651.17 16880.01 13657.36 20594.78 20689.72 649.53 40926.17 20717.31 27457.90 20826.66 22711 685.109656 975.5 353.3272 980.3 985.7 980.7 11.57 91.29 11.20 2856 2112 10.41 20.951 53.500 9.20 0.12912 56.35 452.5 2.53 17.31 6.72 3.55 1.92 1.67 4.18 6.07 1.03 3.25 2.08 1.8 2.24 1.97 4.22 48.18 657.71 369.9242194 11.02 469.5 29.064 492.4660277 461.2 469.8 479.0 471.0 467.6 478.3 567.7214300 118.517 90.7 92.5 84.4 81.9 75.5 67.1 41.6 34.7 23.2 137 98.2 65.5 488.5 485.6 488.5 487.3 22.87 601 601 605 600 377 240 657 722 605 371 501 364 22.69 659.9059394 11.32 9217.228 91.94 9429.536 94.05 9451.903 94.28 9356.710 93.33 2240.09 18.00 17.43 647.6 6.91 654.5 659.1 9.292 4070.881 390.64 2884666667 6028.366 376.77 5374.983 515.78 5867.721 563.05 6206.035 595.52 22678500000 71411366667 825633 32.60 8719.750 544.98 10300.044 643.75 11036.994 689.81 5.715 3.694 1140100 1.470 27.1252 3.362 364.2 794.3 744.7 8336.71 475794831.7 430.347 26.3282 25.4840 18044.25 2101.08 391.573 44.5453 35136.60 813.45 6.258 40566.2 44147 635.5 658.51 17012.23 13709.41 20672.21 20924.98 658.5 41496.68 20953.72 27806.55 20960.25 23029 681.126108 984.8 354.4623 984.9 985.5 978.6 11.61 90.36 11.22 2829 2115 10.43 20.943 53.6 9.01 0.12779 56.34 466.6 2.53 19.73 7.43 3.56 1.9 1.7 4.17 5.75 1.05 3.42 2.08 1.8 2.24 1.97 4.23 48.09 658.16 367.1052632 11.09 474.5 28.891 490.2778714 469.7 471.1 440 472.9 475.7 474.6 566.1228693 119.073 90.8 92.8 86.8 82.6 75.4 67.5 42.2 34.3 23.2 137 98.3 65.3 481.2 483 484 491.9 22.78 605 602 606 604 377 237 637 723 608 371 500 364 22.64 645.8515908 11.22 9226.854 92.03 9402.63 93.79 9236.629 92.13 9380.932 93.57 2245.23 17.96 17.98 643.7 6.92 659.8 657.8 9.291 4081.298 391.63 2892900000 6107.065 381.69 5430.386 521.09 5836.216 560.03 6247.735 599.52 22813100000 71436200000 816300 32.25 9049.543 565.6 10497.894 656.12 11143.486 696.47 5.673 3.627 1141500 1.485 27.0904 3.318 362.8 795.2 742.8 8098.46 472928214.8 430.279 26.3202 25.4505 18742.7 2101.82 392.03 44.5358 35225.4 813.47 6.256 88132.7 76599 219.3 1410.44 39651.75 29775.38 44563.49 44768.16 1409.19 88463.01 44666.11 59114.75 44774.48 1300.965825 971.1 425.8766 973.0 980.1 985.4 21.38 49.31 18.31 17.47 33.044 74.728 17.39 0.16788 33.55 608.2 1.64 3.43 4.80 2.81 1.87 1.13 3.68 2.69 0.78 2.11 1.32 1.25 1.5 1.27 3.05 22.22 1408.89 457.4973315 10.25 611.3 18.731 586.6807687 597.3 615.4 620.3 607.3 618.8 628.5 701.8573748 55.371 114 118 107 111 133 93.8 96.9 87.6 58.0 332 311 206 637.5 636.9 638.9 640.1 12.59 1350 1297 1283 1160 441 221 720 771 659 447 575 452 13.30 830.0198846 6.05 17496.043 174.52 17448.869 174.04 17473.094 174.29 17441.984 173.98 2939.59 11.06 11.13 799.7 4.48 794.0 811.4 7.760 8296.768 796.14 6300233333 18202.541 1137.66 8282.332 794.76 8344.584 800.73 8320.030 798.37 49722966667 151433333333 1827614 35.74 18033.644 1127.10 17621.059 1101.32 17786.529 1111.66 4.166 2.055 2547700 0.9347 3.3579 2.506 411.7 887.9 804.3 27192.4 587587462.0 646.062 3.3878 3.3663 41856.42 2787.07 953.251 94.6195 81211.79 870.62 2.953 4090 OpenBenchmarking.org
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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 20K 40K 60K 80K 100K SE +/- 297.72, N = 3 SE +/- 781.51, N = 3 40753.9 40238.8 40566.2 88132.7 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
VkFFT OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.1.1 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 16K 32K 48K 64K 80K SE +/- 384.18, N = 9 SE +/- 489.60, N = 3 45831 44252 44147 76599 1. (CXX) g++ options: -O3
ET: Legacy Resolution: 3840 x 2160 OpenBenchmarking.org Frames Per Second, More Is Better ET: Legacy 2.78 Resolution: 3840 x 2160 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 140 280 420 560 700 SE +/- 6.04, N = 3 SE +/- 113.10, N = 6 648.4 638.7 635.5 219.3
vkpeak fp64-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp64-vec4 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 300 600 900 1200 1500 SE +/- 1.42, N = 3 SE +/- 1.24, N = 3 651.17 658.51 1410.44
vkpeak int16-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int16-vec4 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 8K 16K 24K 32K 40K SE +/- 2.98, N = 3 SE +/- 18.88, N = 3 16885.79 16880.01 17012.23 39651.75
vkpeak int16-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int16-scalar RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 6K 12K 18K 24K 30K SE +/- 29.87, N = 3 SE +/- 36.89, N = 3 13708.58 13657.36 13709.41 29775.38
vkpeak int32-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int32-vec4 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 10K 20K 30K 40K 50K SE +/- 44.80, N = 3 SE +/- 2.83, N = 3 20672.19 20594.78 20672.21 44563.49
vkpeak int32-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int32-scalar RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 10K 20K 30K 40K 50K SE +/- 44.97, N = 3 SE +/- 1.91, N = 3 20769.27 20689.72 20924.98 44768.16
vkpeak fp64-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp64-scalar RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 300 600 900 1200 1500 SE +/- 0.83, N = 3 SE +/- 0.03, N = 3 653.61 649.53 658.50 1409.19
vkpeak fp16-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp16-vec4 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 20K 40K 60K 80K 100K SE +/- 52.39, N = 3 SE +/- 3.14, N = 3 41184.89 40926.17 41496.68 88463.01
vkpeak fp16-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp16-scalar RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 10K 20K 30K 40K 50K SE +/- 45.34, N = 3 SE +/- 58.62, N = 3 20949.64 20717.31 20953.72 44666.11
vkpeak fp32-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp32-vec4 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 13K 26K 39K 52K 65K SE +/- 69.31, N = 3 SE +/- 88.56, N = 3 27806.74 27457.90 27806.55 59114.75
vkpeak fp32-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp32-scalar RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 10K 20K 30K 40K 50K SE +/- 65.72, N = 3 SE +/- 61.65, N = 3 20927.99 20826.66 20960.25 44774.48
LeelaChessZero Backend: OpenCL OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: OpenCL RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 5K 10K 15K 20K 25K SE +/- 98.83, N = 3 22739 22711 23029 1. (CXX) g++ options: -flto -pthread
OctaneBench Total Score OpenBenchmarking.org Score, More Is Better OctaneBench 2020.1 Total Score RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 300 600 900 1200 1500 686.23 685.11 681.13 1300.97
Warsow Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better Warsow 2.5 Beta Resolution: 1920 x 1080 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 5.54, N = 3 SE +/- 7.67, N = 10 984.3 975.5 984.8 971.1
FAHBench OpenBenchmarking.org Ns Per Day, More Is Better FAHBench 2.3.2 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 90 180 270 360 450 SE +/- 0.32, N = 3 SE +/- 1.01, N = 3 353.89 353.33 354.46 425.88
Warsow Resolution: 1920 x 1200 OpenBenchmarking.org Frames Per Second, More Is Better Warsow 2.5 Beta Resolution: 1920 x 1200 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 5.60, N = 3 SE +/- 4.70, N = 3 984.8 980.3 984.9 973.0
Warsow Resolution: 2560 x 1440 OpenBenchmarking.org Frames Per Second, More Is Better Warsow 2.5 Beta Resolution: 2560 x 1440 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 0.35, N = 3 SE +/- 5.45, N = 3 984.7 985.7 985.5 980.1
Warsow Resolution: 3840 x 2160 OpenBenchmarking.org Frames Per Second, More Is Better Warsow 2.5 Beta Resolution: 3840 x 2160 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 0.78, N = 3 SE +/- 0.07, N = 3 960.8 980.7 978.6 985.4
LuxCoreRender Scene: DLSC - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: DLSC - Acceleration: GPU NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 11.57 11.61 21.38 MIN: 11.39 / MAX: 11.73 MIN: 11.41 / MAX: 11.72 MIN: 18.47 / MAX: 21.85
Blender Blend File: Barbershop - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Barbershop - Compute: CUDA RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 20 40 60 80 100 SE +/- 0.17, N = 3 SE +/- 0.17, N = 3 91.13 91.29 90.36 49.31
LuxCoreRender Scene: LuxCore Benchmark - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: LuxCore Benchmark - Acceleration: GPU NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.09, N = 3 11.20 11.22 18.31 MIN: 3.54 / MAX: 13.16 MIN: 3.57 / MAX: 13.17 MIN: 7.1 / MAX: 23.24
Chaos Group V-RAY Mode: NVIDIA RTX GPU OpenBenchmarking.org vrays, More Is Better Chaos Group V-RAY 5 Mode: NVIDIA RTX GPU RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 600 1200 1800 2400 3000 SE +/- 11.72, N = 3 2856 2856 2829
Chaos Group V-RAY Mode: NVIDIA CUDA GPU OpenBenchmarking.org vpaths, More Is Better Chaos Group V-RAY 5 Mode: NVIDIA CUDA GPU RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 500 1000 1500 2000 2500 SE +/- 0.33, N = 3 2119 2112 2115
LuxCoreRender Scene: Orange Juice - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Orange Juice - Acceleration: GPU RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 4 8 12 16 20 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 10.45 10.41 10.43 17.47 MIN: 8.53 / MAX: 13.8 MIN: 8.47 / MAX: 13.76 MIN: 8.54 / MAX: 13.75 MIN: 0.39 / MAX: 25.03
IndigoBench Acceleration: OpenCL GPU - Scene: Bedroom OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Bedroom RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 8 16 24 32 40 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 20.96 20.95 20.94 33.04
IndigoBench Acceleration: OpenCL GPU - Scene: Supercar OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Supercar RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 20 40 60 80 100 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 53.44 53.50 53.60 74.73
LuxCoreRender Scene: Danish Mood - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Danish Mood - Acceleration: GPU RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 4 8 12 16 20 SE +/- 0.08, N = 3 SE +/- 0.20, N = 3 9.18 9.20 9.01 17.39 MIN: 3.53 / MAX: 10.86 MIN: 3.03 / MAX: 10.91 MIN: 3.3 / MAX: 10.77 MIN: 0.07 / MAX: 21.12
NAMD CUDA ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD CUDA 2.14 ATPase Simulation - 327,506 Atoms RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.0378 0.0756 0.1134 0.1512 0.189 SE +/- 0.00047, N = 3 SE +/- 0.00009, N = 3 0.12792 0.12912 0.12779 0.16788
Blender Blend File: Barbershop - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Barbershop - Compute: NVIDIA OptiX RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 13 26 39 52 65 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 56.19 56.35 56.34 33.55
Unvanquished Resolution: 2560 x 1440 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 2560 x 1440 - Effects Quality: Ultra RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 130 260 390 520 650 SE +/- 14.16, N = 12 SE +/- 0.07, N = 3 461.7 452.5 466.6 608.2
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: regnety_400m RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.5715 1.143 1.7145 2.286 2.8575 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 2.54 2.53 2.53 1.64 MIN: 2.5 / MAX: 3.7 MIN: 2.49 / MAX: 3.64 MIN: 2.51 / MAX: 2.76 MIN: 1.61 / MAX: 2.15 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: squeezenet_ssd RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 5 10 15 20 25 SE +/- 1.24, N = 3 SE +/- 0.03, N = 3 15.96 17.31 19.73 3.43 MIN: 5.77 / MAX: 36.07 MIN: 5.63 / MAX: 36.32 MIN: 7.36 / MAX: 35.55 MIN: 3.34 / MAX: 4.06 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: yolov4-tiny RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 2 4 6 8 10 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 7.02 6.72 7.43 4.80 MIN: 6.34 / MAX: 30.81 MIN: 6.3 / MAX: 19.53 MIN: 6.36 / MAX: 36.74 MIN: 4.73 / MAX: 5.37 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet50 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.801 1.602 2.403 3.204 4.005 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.55 3.55 3.56 2.81 MIN: 3.52 / MAX: 3.69 MIN: 3.52 / MAX: 3.75 MIN: 3.53 / MAX: 3.69 MIN: 2.79 / MAX: 3.38 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: alexnet RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.432 0.864 1.296 1.728 2.16 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 1.91 1.92 1.90 1.87 MIN: 1.86 / MAX: 9.04 MIN: 1.87 / MAX: 7.42 MIN: 1.87 / MAX: 2.6 MIN: 1.83 / MAX: 2.45 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet18 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.3825 0.765 1.1475 1.53 1.9125 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 1.67 1.67 1.70 1.13 MIN: 1.64 / MAX: 1.9 MIN: 1.64 / MAX: 4.75 MIN: 1.65 / MAX: 9.46 MIN: 1.11 / MAX: 1.43 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: vgg16 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.9405 1.881 2.8215 3.762 4.7025 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 4.17 4.18 4.17 3.68 MIN: 4.12 / MAX: 4.86 MIN: 4.12 / MAX: 11.44 MIN: 4.13 / MAX: 4.34 MIN: 3.66 / MAX: 4.19 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: googlenet RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 2 4 6 8 10 SE +/- 0.26, N = 3 SE +/- 0.03, N = 3 5.85 6.07 5.75 2.69 MIN: 3.71 / MAX: 29.49 MIN: 3.71 / MAX: 31.52 MIN: 3.72 / MAX: 31 MIN: 2.2 / MAX: 4.95 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: blazeface RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.2385 0.477 0.7155 0.954 1.1925 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 1.06 1.03 1.05 0.78 MIN: 1.02 / MAX: 2.12 MIN: 1 / MAX: 2.07 MIN: 1.01 / MAX: 2.18 MIN: 0.76 / MAX: 1.68 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: efficientnet-b0 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.7695 1.539 2.3085 3.078 3.8475 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.26 3.25 3.42 2.11 MIN: 3.23 / MAX: 3.42 MIN: 3.22 / MAX: 4.42 MIN: 3.24 / MAX: 4.26 MIN: 2.09 / MAX: 2.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mnasnet RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.468 0.936 1.404 1.872 2.34 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 2.08 2.08 2.08 1.32 MIN: 2.06 / MAX: 2.29 MIN: 2.05 / MAX: 3.23 MIN: 2.06 / MAX: 2.51 MIN: 1.31 / MAX: 2 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: shufflenet-v2 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.4365 0.873 1.3095 1.746 2.1825 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.94 1.80 1.80 1.25 MIN: 1.78 / MAX: 2.28 MIN: 1.76 / MAX: 3 MIN: 1.77 / MAX: 2.69 MIN: 1.23 / MAX: 2.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.7133 1.4266 2.1399 2.8532 3.5665 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.17 2.24 2.24 1.50 MIN: 2.21 / MAX: 20.43 MIN: 2.21 / MAX: 3.37 MIN: 2.21 / MAX: 4.61 MIN: 1.47 / MAX: 2.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.4455 0.891 1.3365 1.782 2.2275 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.98 1.97 1.97 1.27 MIN: 1.94 / MAX: 6.06 MIN: 1.94 / MAX: 3.15 MIN: 1.94 / MAX: 2.26 MIN: 1.25 / MAX: 2.23 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mobilenet RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.963 1.926 2.889 3.852 4.815 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 4.28 4.22 4.23 3.05 MIN: 4.15 / MAX: 15.44 MIN: 4.13 / MAX: 4.48 MIN: 4.16 / MAX: 4.41 MIN: 3.02 / MAX: 4.05 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Blender Blend File: Pabellon Barcelona - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Pabellon Barcelona - Compute: CUDA RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 11 22 33 44 55 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 48.11 48.18 48.09 22.22
clpeak OpenCL Test: Double-Precision Double OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Double-Precision Double RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 300 600 900 1200 1500 SE +/- 0.03, N = 3 SE +/- 0.23, N = 3 658.16 657.71 658.16 1408.89 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
Xonotic Resolution: 3840 x 2160 - Effects Quality: Ultimate OpenBenchmarking.org Frames Per Second, More Is Better Xonotic 0.8.2 Resolution: 3840 x 2160 - Effects Quality: Ultimate RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 100 200 300 400 500 SE +/- 1.53, N = 3 SE +/- 0.84, N = 3 374.43 369.92 367.11 457.50 MIN: 65 / MAX: 751 MIN: 58 / MAX: 764 MIN: 65 / MAX: 749 MIN: 72 / MAX: 1128
Blender Blend File: BMW27 - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: BMW27 - Compute: CUDA RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 3.94, N = 15 11.04 11.02 11.09 10.25
Unvanquished Resolution: 1920 x 1080 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1080 - Effects Quality: Ultra RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 130 260 390 520 650 SE +/- 1.10, N = 3 SE +/- 0.91, N = 3 470.8 469.5 474.5 611.3
RealSR-NCNN Scale: 4x - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: Yes RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 7 14 21 28 35 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 28.95 29.06 28.89 18.73
Xonotic Resolution: 3840 x 2160 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Xonotic 0.8.2 Resolution: 3840 x 2160 - Effects Quality: Ultra RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 130 260 390 520 650 SE +/- 1.15, N = 3 SE +/- 0.80, N = 3 499.26 492.47 490.28 586.68 MIN: 117 / MAX: 913 MIN: 93 / MAX: 902 MIN: 122 / MAX: 891 MIN: 218 / MAX: 1144
Unvanquished Resolution: 3840 x 2160 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 3840 x 2160 - Effects Quality: Ultra RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 130 260 390 520 650 SE +/- 4.41, N = 3 SE +/- 1.07, N = 3 456.8 461.2 469.7 597.3
Unvanquished Resolution: 1920 x 1200 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1200 - Effects Quality: Ultra RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 130 260 390 520 650 SE +/- 5.55, N = 3 SE +/- 0.79, N = 3 463.0 469.8 471.1 615.4
Unvanquished Resolution: 1920 x 1080 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1080 - Effects Quality: High RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 130 260 390 520 650 SE +/- 2.19, N = 3 SE +/- 1.32, N = 3 482.0 479.0 440.0 620.3
Unvanquished Resolution: 3840 x 2160 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 3840 x 2160 - Effects Quality: High RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 130 260 390 520 650 SE +/- 3.53, N = 3 SE +/- 1.30, N = 3 463.6 471.0 472.9 607.3
Unvanquished Resolution: 2560 x 1440 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 2560 x 1440 - Effects Quality: High RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 130 260 390 520 650 SE +/- 2.97, N = 3 SE +/- 1.30, N = 3 469.0 467.6 475.7 618.8
Unvanquished Resolution: 1920 x 1200 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1200 - Effects Quality: High RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 140 280 420 560 700 SE +/- 4.62, N = 3 SE +/- 3.34, N = 3 464.9 478.3 474.6 628.5
Xonotic Resolution: 3840 x 2160 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Xonotic 0.8.2 Resolution: 3840 x 2160 - Effects Quality: High RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 150 300 450 600 750 SE +/- 1.97, N = 3 SE +/- 3.30, N = 3 556.93 567.72 566.12 701.86 MIN: 114 / MAX: 1122 MIN: 91 / MAX: 1163 MIN: 113 / MAX: 1151 MIN: 193 / MAX: 1442
VkResample Upscale: 2x - Precision: Double OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Double RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 30 60 90 120 150 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 117.82 118.52 119.07 55.37 1. (CXX) g++ options: -O3
ViennaCL Test: CPU BLAS - dGEMM-TT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TT RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 30 60 90 120 150 SE +/- 0.26, N = 3 91.9 90.7 90.8 114.0 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 30 60 90 120 150 SE +/- 0.32, N = 3 SE +/- 0.67, N = 3 93.8 92.5 92.8 118.0 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 20 40 60 80 100 SE +/- 0.12, N = 3 88.4 84.4 86.8 107.0 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 20 40 60 80 100 SE +/- 0.18, N = 3 81.5 81.9 82.6 111.0 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 30 60 90 120 150 SE +/- 0.36, N = 3 76.1 75.5 75.4 133.0 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 20 40 60 80 100 SE +/- 0.17, N = 3 SE +/- 9.12, N = 3 68.1 67.1 67.5 93.8 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 20 40 60 80 100 SE +/- 0.42, N = 3 SE +/- 0.12, N = 3 42.4 41.6 42.2 96.9 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 34.9 34.7 34.3 87.6 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 13 26 39 52 65 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 23.3 23.2 23.2 58.0 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 70 140 210 280 350 SE +/- 0.67, N = 3 SE +/- 2.67, N = 3 140 137 137 332 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 70 140 210 280 350 SE +/- 0.68, N = 3 SE +/- 1.45, N = 3 99.6 98.2 98.3 311.0 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 50 100 150 200 250 SE +/- 0.09, N = 3 SE +/- 0.88, N = 3 66.1 65.5 65.3 206.0 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
Unvanquished Resolution: 2560 x 1440 - Effects Quality: Medium OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 2560 x 1440 - Effects Quality: Medium RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 140 280 420 560 700 SE +/- 3.75, N = 3 SE +/- 0.49, N = 3 492.5 488.5 481.2 637.5
Unvanquished Resolution: 3840 x 2160 - Effects Quality: Medium OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 3840 x 2160 - Effects Quality: Medium RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 140 280 420 560 700 SE +/- 2.17, N = 3 SE +/- 6.63, N = 3 490.1 485.6 483.0 636.9
Unvanquished Resolution: 1920 x 1200 - Effects Quality: Medium OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1200 - Effects Quality: Medium RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 140 280 420 560 700 SE +/- 1.98, N = 3 SE +/- 2.89, N = 3 473.6 488.5 484.0 638.9
Unvanquished Resolution: 1920 x 1080 - Effects Quality: Medium OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1080 - Effects Quality: Medium RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 140 280 420 560 700 SE +/- 3.91, N = 3 SE +/- 5.77, N = 3 496.1 487.3 491.9 640.1
Blender Blend File: Fishy Cat - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Fishy Cat - Compute: CUDA RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 22.86 22.87 22.78 12.59
ViennaCL Test: OpenCL BLAS - dGEMM-TT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TT RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 300 600 900 1200 1500 602 601 605 1350 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 300 600 900 1200 1500 SE +/- 1.33, N = 3 SE +/- 3.33, N = 3 599 601 602 1297 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 300 600 900 1200 1500 SE +/- 1.67, N = 3 SE +/- 3.33, N = 3 604 605 606 1283 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 601 600 604 1160 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 100 200 300 400 500 SE +/- 0.33, N = 3 377 377 377 441 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 50 100 150 200 250 SE +/- 0.33, N = 3 239 240 237 221 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 160 320 480 640 800 SE +/- 0.58, N = 3 660 657 637 720 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 170 340 510 680 850 SE +/- 0.00, N = 3 SE +/- 0.58, N = 3 722 722 723 771 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 140 280 420 560 700 SE +/- 0.33, N = 3 606 605 608 659 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 100 200 300 400 500 SE +/- 0.58, N = 3 375 371 371 447 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 120 240 360 480 600 SE +/- 0.33, N = 3 503 501 500 575 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 100 200 300 400 500 SE +/- 0.88, N = 3 368 364 364 452 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
Blender Blend File: Classroom - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Classroom - Compute: CUDA RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 22.76 22.69 22.64 13.30
Xonotic Resolution: 3840 x 2160 - Effects Quality: Low OpenBenchmarking.org Frames Per Second, More Is Better Xonotic 0.8.2 Resolution: 3840 x 2160 - Effects Quality: Low RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 0.55, N = 3 SE +/- 2.14, N = 3 655.14 659.91 645.85 830.02 MIN: 103 / MAX: 1300 MIN: 109 / MAX: 1303 MIN: 117 / MAX: 1283 MIN: 217 / MAX: 1735
Blender Blend File: Fishy Cat - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Fishy Cat - Compute: NVIDIA OptiX RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 3 6 9 12 15 SE +/- 0.09, N = 3 SE +/- 0.05, N = 13 11.22 11.32 11.22 6.05
ParaView Test: Many Spheres - Resolution: 3840 x 2160 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.9 Test: Many Spheres - Resolution: 3840 x 2160 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 4K 8K 12K 16K 20K SE +/- 6.01, N = 3 SE +/- 24.18, N = 3 9169.64 9217.23 9226.85 17496.04
ParaView Test: Many Spheres - Resolution: 3840 x 2160 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Many Spheres - Resolution: 3840 x 2160 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 40 80 120 160 200 SE +/- 0.06, N = 3 SE +/- 0.24, N = 3 91.46 91.94 92.03 174.52
ParaView Test: Many Spheres - Resolution: 1920 x 1080 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.9 Test: Many Spheres - Resolution: 1920 x 1080 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 4K 8K 12K 16K 20K SE +/- 4.72, N = 3 SE +/- 9.92, N = 3 9419.40 9429.54 9402.63 17448.87
ParaView Test: Many Spheres - Resolution: 1920 x 1080 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Many Spheres - Resolution: 1920 x 1080 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 40 80 120 160 200 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 93.95 94.05 93.79 174.04
ParaView Test: Many Spheres - Resolution: 1920 x 1200 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.9 Test: Many Spheres - Resolution: 1920 x 1200 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 4K 8K 12K 16K 20K SE +/- 5.73, N = 3 SE +/- 25.11, N = 3 9414.69 9451.90 9236.63 17473.09
ParaView Test: Many Spheres - Resolution: 1920 x 1200 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Many Spheres - Resolution: 1920 x 1200 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 40 80 120 160 200 SE +/- 0.06, N = 3 SE +/- 0.25, N = 3 93.91 94.28 92.13 174.29
ParaView Test: Many Spheres - Resolution: 2560 x 1440 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.9 Test: Many Spheres - Resolution: 2560 x 1440 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 4K 8K 12K 16K 20K SE +/- 7.77, N = 3 SE +/- 2.22, N = 3 9343.82 9356.71 9380.93 17441.98
ParaView Test: Many Spheres - Resolution: 2560 x 1440 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Many Spheres - Resolution: 2560 x 1440 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 40 80 120 160 200 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 93.20 93.33 93.57 173.98
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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 600 1200 1800 2400 3000 SE +/- 3.07, N = 3 SE +/- 0.34, N = 3 2246.17 2240.09 2245.23 2939.59 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
Blender Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 17.96 18.00 17.96 11.06
Blender Blend File: Classroom - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Classroom - Compute: NVIDIA OptiX RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 17.40 17.43 17.98 11.13
ET: Legacy Resolution: 2560 x 1440 OpenBenchmarking.org Frames Per Second, More Is Better ET: Legacy 2.78 Resolution: 2560 x 1440 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 7.88, N = 4 SE +/- 6.23, N = 3 640.2 647.6 643.7 799.7
Blender Blend File: BMW27 - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: BMW27 - Compute: NVIDIA OptiX RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.04, N = 15 6.94 6.91 6.92 4.48
ET: Legacy Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better ET: Legacy 2.78 Resolution: 1920 x 1080 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 3.73, N = 3 SE +/- 3.83, N = 3 652.3 654.5 659.8 794.0
ET: Legacy Resolution: 1920 x 1200 OpenBenchmarking.org Frames Per Second, More Is Better ET: Legacy 2.78 Resolution: 1920 x 1200 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 2.46, N = 3 SE +/- 0.47, N = 3 645.3 659.1 657.8 811.4
VkResample Upscale: 2x - Precision: Single OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Single RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 3 6 9 12 15 SE +/- 0.003, N = 3 SE +/- 0.002, N = 3 9.272 9.292 9.291 7.760 1. (CXX) g++ options: -O3
ParaView Test: Wavelet Contour - Resolution: 3840 x 2160 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.9 Test: Wavelet Contour - Resolution: 3840 x 2160 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 2K 4K 6K 8K 10K SE +/- 31.15, N = 3 SE +/- 17.54, N = 3 4134.49 4070.88 4081.30 8296.77
ParaView Test: Wavelet Contour - Resolution: 3840 x 2160 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Wavelet Contour - Resolution: 3840 x 2160 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 2.99, N = 3 SE +/- 1.68, N = 3 396.74 390.64 391.63 796.14
Hashcat Benchmark: SHA-512 OpenBenchmarking.org H/s, More Is Better Hashcat 6.2.4 Benchmark: SHA-512 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 1300M 2600M 3900M 5200M 6500M SE +/- 2179704.36, N = 3 SE +/- 1942792.95, N = 3 2887000000 2884666667 2892900000 6300233333
ParaView Test: Wavelet Volume - Resolution: 3840 x 2160 OpenBenchmarking.org MiVoxels / Sec, More Is Better ParaView 5.9 Test: Wavelet Volume - Resolution: 3840 x 2160 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 4K 8K 12K 16K 20K SE +/- 65.03, N = 5 SE +/- 157.61, N = 3 6157.36 6028.37 6107.07 18202.54
ParaView Test: Wavelet Volume - Resolution: 3840 x 2160 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Wavelet Volume - Resolution: 3840 x 2160 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 4.06, N = 5 SE +/- 9.85, N = 3 384.84 376.77 381.69 1137.66
ParaView Test: Wavelet Contour - Resolution: 2560 x 1440 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.9 Test: Wavelet Contour - Resolution: 2560 x 1440 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 2K 4K 6K 8K 10K SE +/- 16.63, N = 3 SE +/- 11.72, N = 3 5366.18 5374.98 5430.39 8282.33
ParaView Test: Wavelet Contour - Resolution: 2560 x 1440 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Wavelet Contour - Resolution: 2560 x 1440 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 1.60, N = 3 SE +/- 1.13, N = 3 514.93 515.78 521.09 794.76
ParaView Test: Wavelet Contour - Resolution: 1920 x 1200 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.9 Test: Wavelet Contour - Resolution: 1920 x 1200 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 2K 4K 6K 8K 10K SE +/- 54.66, N = 3 SE +/- 3.68, N = 3 5849.68 5867.72 5836.22 8344.58
ParaView Test: Wavelet Contour - Resolution: 1920 x 1200 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Wavelet Contour - Resolution: 1920 x 1200 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 5.24, N = 3 SE +/- 0.35, N = 3 561.32 563.05 560.03 800.73
ParaView Test: Wavelet Contour - Resolution: 1920 x 1080 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.9 Test: Wavelet Contour - Resolution: 1920 x 1080 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 2K 4K 6K 8K 10K SE +/- 54.90, N = 3 SE +/- 16.65, N = 3 6274.52 6206.04 6247.74 8320.03
ParaView Test: Wavelet Contour - Resolution: 1920 x 1080 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Wavelet Contour - Resolution: 1920 x 1080 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 5.27, N = 3 SE +/- 1.60, N = 3 602.09 595.52 599.52 798.37
Hashcat Benchmark: SHA1 OpenBenchmarking.org H/s, More Is Better Hashcat 6.2.4 Benchmark: SHA1 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 11000M 22000M 33000M 44000M 55000M SE +/- 32122473.96, N = 3 SE +/- 15117135.24, N = 3 22599300000 22678500000 22813100000 49722966667
Hashcat Benchmark: MD5 OpenBenchmarking.org H/s, More Is Better Hashcat 6.2.4 Benchmark: MD5 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 30000M 60000M 90000M 120000M 150000M SE +/- 78065236.25, N = 3 SE +/- 166666666.67, N = 3 71446900000 71411366667 71436200000 151433333333
Hashcat Benchmark: TrueCrypt RIPEMD160 + XTS OpenBenchmarking.org H/s, More Is Better Hashcat 6.2.4 Benchmark: TrueCrypt RIPEMD160 + XTS RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 400K 800K 1200K 1600K 2000K SE +/- 4520.08, N = 3 SE +/- 16650.59, N = 7 846100 825633 816300 1827614
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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 8 16 24 32 40 SE +/- 0.21, N = 3 SE +/- 0.22, N = 3 32.33 32.60 32.25 35.74 MIN: 30.03 / MAX: 34.38 MIN: 30.12 / MAX: 34.6 MIN: 29.03 / MAX: 34.55 MIN: 34.18 / MAX: 37.28
ParaView Test: Wavelet Volume - Resolution: 2560 x 1440 OpenBenchmarking.org MiVoxels / Sec, More Is Better ParaView 5.9 Test: Wavelet Volume - Resolution: 2560 x 1440 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 4K 8K 12K 16K 20K SE +/- 49.80, N = 3 SE +/- 106.54, N = 3 8944.75 8719.75 9049.54 18033.64
ParaView Test: Wavelet Volume - Resolution: 2560 x 1440 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Wavelet Volume - Resolution: 2560 x 1440 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 3.11, N = 3 SE +/- 6.66, N = 3 559.05 544.98 565.60 1127.10
ParaView Test: Wavelet Volume - Resolution: 1920 x 1200 OpenBenchmarking.org MiVoxels / Sec, More Is Better ParaView 5.9 Test: Wavelet Volume - Resolution: 1920 x 1200 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 4K 8K 12K 16K 20K SE +/- 74.83, N = 3 SE +/- 64.74, N = 3 10151.48 10300.04 10497.89 17621.06
ParaView Test: Wavelet Volume - Resolution: 1920 x 1200 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Wavelet Volume - Resolution: 1920 x 1200 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 4.68, N = 3 SE +/- 4.05, N = 3 634.47 643.75 656.12 1101.32
ParaView Test: Wavelet Volume - Resolution: 1920 x 1080 OpenBenchmarking.org MiVoxels / Sec, More Is Better ParaView 5.9 Test: Wavelet Volume - Resolution: 1920 x 1080 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 4K 8K 12K 16K 20K SE +/- 88.00, N = 3 SE +/- 42.71, N = 3 10874.71 11036.99 11143.49 17786.53
ParaView Test: Wavelet Volume - Resolution: 1920 x 1080 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Wavelet Volume - Resolution: 1920 x 1080 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 5.50, N = 3 SE +/- 2.67, N = 3 679.67 689.81 696.47 1111.66
RealSR-NCNN Scale: 4x - TAA: No OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: No RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 1.2859 2.5718 3.8577 5.1436 6.4295 SE +/- 0.022, N = 3 SE +/- 0.005, N = 3 5.621 5.715 5.673 4.166
Rodinia Test: OpenCL Particle Filter OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenCL Particle Filter RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.8647 1.7294 2.5941 3.4588 4.3235 SE +/- 0.013, N = 3 SE +/- 0.050, N = 3 3.843 3.694 3.627 2.055 1. (CXX) g++ options: -O2 -lOpenCL
Hashcat Benchmark: 7-Zip OpenBenchmarking.org H/s, More Is Better Hashcat 6.2.4 Benchmark: 7-Zip RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 500K 1000K 1500K 2000K 2500K SE +/- 4014.97, N = 3 SE +/- 4152.51, N = 3 1138500 1140100 1141500 2547700
ArrayFire Test: Conjugate Gradient OpenCL OpenBenchmarking.org ms, Fewer Is Better ArrayFire 3.7 Test: Conjugate Gradient OpenCL RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.3341 0.6682 1.0023 1.3364 1.6705 SE +/- 0.0055, N = 3 SE +/- 0.0019, N = 3 1.4700 1.4700 1.4850 0.9347 1. (CXX) g++ options: -rdynamic
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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 6 12 18 24 30 SE +/- 0.0002, N = 3 SE +/- 0.0000, N = 3 27.1252 27.1252 27.0904 3.3579 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 0.7565 1.513 2.2695 3.026 3.7825 SE +/- 0.004, N = 3 SE +/- 0.006, N = 3 3.313 3.362 3.318 2.506
cl-mem Benchmark: Copy OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Copy RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 90 180 270 360 450 SE +/- 0.19, N = 3 SE +/- 0.17, N = 3 364.1 364.2 362.8 411.7 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 0.84, N = 3 SE +/- 0.09, N = 3 794.6 794.3 795.2 887.9 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 0.33, N = 3 SE +/- 0.43, N = 3 743.1 744.7 742.8 804.3 1. (CC) gcc options: -O2 -flto -lOpenCL
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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 6K 12K 18K 24K 30K SE +/- 67.62, N = 3 SE +/- 2.47, N = 3 8102.38 8336.71 8098.46 27192.40 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
MandelGPU OpenCL Device: GPU OpenBenchmarking.org Samples/sec, More Is Better MandelGPU 1.3pts1 OpenCL Device: GPU RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 130M 260M 390M 520M 650M SE +/- 1595019.30, N = 3 SE +/- 430679.16, N = 3 481322759.6 475794831.7 472928214.8 587587462.0 1. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL
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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 140 280 420 560 700 SE +/- 0.21, N = 3 SE +/- 0.34, N = 3 429.08 430.35 430.28 646.06 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 6 12 18 24 30 SE +/- 0.0129, N = 3 SE +/- 0.0000, N = 3 26.3342 26.3282 26.3202 3.3878 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 6 12 18 24 30 SE +/- 0.0039, N = 3 SE +/- 0.0005, N = 3 25.4781 25.4840 25.4505 3.3663 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
clpeak OpenCL Test: Integer Compute INT OpenBenchmarking.org GIOPS, More Is Better clpeak OpenCL Test: Integer Compute INT RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 9K 18K 27K 36K 45K SE +/- 115.05, N = 3 SE +/- 370.89, N = 3 17725.14 18044.25 18742.70 41856.42 1. (CXX) g++ options: -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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 600 1200 1800 2400 3000 SE +/- 0.42, N = 3 SE +/- 1.73, N = 3 2100.51 2101.08 2101.82 2787.07 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 0.19, N = 3 SE +/- 0.25, N = 3 391.21 391.57 392.03 953.25 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 1.03, N = 15 44.19 44.55 44.54 94.62 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
clpeak OpenCL Test: Single-Precision Float OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Single-Precision Float RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 20K 40K 60K 80K 100K SE +/- 88.80, N = 3 SE +/- 435.51, N = 3 35227.21 35136.60 35225.40 81211.79 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 RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 200 400 600 800 1000 SE +/- 0.02, N = 3 SE +/- 0.19, N = 3 813.42 813.45 813.47 870.62 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
FinanceBench Benchmark: Black-Scholes OpenCL OpenBenchmarking.org ms, Fewer Is Better FinanceBench 2016-07-25 Benchmark: Black-Scholes OpenCL RTX 3090 NVIDIA RTX 3090 NVIDIA 3090 RTX 4090 2 4 6 8 10 SE +/- 0.004, N = 3 SE +/- 0.024, N = 3 6.259 6.258 6.256 2.953 1. (CXX) g++ options: -O3 -march=native -fopenmp
NeatBench Acceleration: GPU OpenBenchmarking.org FPS, More Is Better NeatBench 5 Acceleration: GPU RTX 4090 900 1800 2700 3600 4500 4090
Phoronix Test Suite v10.8.5