NVIDIA GeForce RTX 3090

AMD Ryzen 9 5950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (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/2112069-PTS-NVIDIAGE39&rdt&grs.

NVIDIA GeForce RTX 3090ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionRTX 3090NVIDIA RTX 3090NVIDIA 3090AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3801 BIOS)AMD Starship/Matisse32GB1000GB Sabrent Rocket 4.0 PlusNVIDIA GeForce RTX 3090 24GBNVIDIA GA102 HD AudioASUS MG28URealtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 21.105.13.0-22-generic (x86_64)GNOME Shell 40.5X Server 1.20.13NVIDIA 495.444.6.0OpenCL 3.0 CUDA 11.5.1001.2.186GCC 11.2.0 + Clang 13.0.0-2ext43840x2160OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler 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-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 Processor Details- Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201016 Graphics Details- BAR1 / Visible vRAM Size: 32768 MiBOpenCL Details- GPU Compute Cores: 10496Python Details- Python 3.9.7Security 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

NVIDIA GeForce RTX 3090ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - yolov4-tinyunvanquished: 1920 x 1080 - Highncnn: Vulkan GPU - shufflenet-v2rodinia: OpenCL Particle Filterclpeak: Integer Compute INTncnn: Vulkan GPU - efficientnet-b0viennacl: CPU BLAS - dGEMM-NTvkfft: paraview: Wavelet Volume - 2560 x 1440paraview: Wavelet Volume - 2560 x 1440hashcat: TrueCrypt RIPEMD160 + XTSviennacl: OpenCL BLAS - dDOTparaview: Wavelet Volume - 1920 x 1200paraview: Wavelet Volume - 1920 x 1200blender: Classroom - NVIDIA OptiXunvanquished: 1920 x 1200 - Mediumshoc: OpenCL - GEMM SGEMM_Nncnn: Vulkan GPU - blazefaceunvanquished: 1920 x 1200 - Highunvanquished: 3840 x 2160 - Ultraparaview: Wavelet Volume - 1920 x 1080paraview: Wavelet Volume - 1920 x 1080unvanquished: 2560 x 1440 - Mediumparaview: Many Spheres - 1920 x 1200paraview: Many Spheres - 1920 x 1200viennacl: CPU BLAS - sDOTxonotic: 3840 x 2160 - Lowparaview: Wavelet Volume - 3840 x 2160paraview: Wavelet Volume - 3840 x 2160etlegacy: 1920 x 1200luxcorerender: Danish Mood - GPUwarsow: 3840 x 2160etlegacy: 3840 x 2160unvanquished: 3840 x 2160 - Highxonotic: 3840 x 2160 - Ultimatexonotic: 3840 x 2160 - Highviennacl: CPU BLAS - dDOTxonotic: 3840 x 2160 - Ultraunvanquished: 1920 x 1080 - Mediumncnn: Vulkan GPU - resnet18mandelgpu: GPUunvanquished: 1920 x 1200 - Ultraviennacl: CPU BLAS - dAXPYunvanquished: 2560 x 1440 - Highrealsr-ncnn: 4x - Noparaview: Wavelet Contour - 3840 x 2160paraview: Wavelet Contour - 3840 x 2160viennacl: CPU BLAS - dGEMV-Nwaifu2x-ncnn: 2x - 3 - Yesunvanquished: 3840 x 2160 - Mediumviennacl: CPU BLAS - sAXPYncnn: Vulkan GPU - mobilenetviennacl: CPU BLAS - dGEMM-TNlczero: OpenCLvkpeak: fp16-vec4vkpeak: fp64-scalarviennacl: CPU BLAS - dGEMM-NNviennacl: CPU BLAS - dGEMM-TTshoc: OpenCL - Max SP Flopsvkpeak: fp32-vec4viennacl: OpenCL BLAS - dGEMV-Nviennacl: CPU BLAS - sCOPYparaview: Wavelet Contour - 2560 x 1440paraview: Wavelet Contour - 2560 x 1440etlegacy: 2560 x 1440etlegacy: 1920 x 1080vkpeak: fp16-scalarvkpeak: int32-scalarvkpeak: fp64-vec4paraview: Wavelet Contour - 1920 x 1080paraview: Wavelet Contour - 1920 x 1080viennacl: OpenCL BLAS - sCOPYluxcorerender: Rainbow Colors and Prism - GPUviennacl: OpenCL BLAS - sDOTvkresample: 2x - Doubleunvanquished: 1920 x 1080 - Ultrancnn: Vulkan GPU - alexnetnamd-cuda: ATPase Simulation - 327,506 Atomsblender: Barbershop - CUDAarrayfire: Conjugate Gradient OpenCLv-ray: NVIDIA RTX GPUwarsow: 1920 x 1080hashcat: SHA1viennacl: CPU BLAS - dGEMV-Tblender: Fishy Cat - NVIDIA OptiXshoc: OpenCL - MD5 Hashvkpeak: int16-vec4octanebench: Total Scoreviennacl: OpenCL BLAS - dGEMM-NNviennacl: OpenCL BLAS - dGEMM-TTvkpeak: fp32-scalarblender: BMW27 - CUDAparaview: Many Spheres - 3840 x 2160paraview: Many Spheres - 3840 x 2160viennacl: OpenCL BLAS - sAXPYrealsr-ncnn: 4x - Yesparaview: Wavelet Contour - 1920 x 1200paraview: Wavelet Contour - 1920 x 1200blender: Classroom - CUDAncnn: Vulkan GPU-v2-v2 - mobilenet-v2viennacl: OpenCL BLAS - dGEMM-TNviennacl: OpenCL BLAS - dCOPYwarsow: 1920 x 1200blender: BMW27 - NVIDIA OptiXviennacl: CPU BLAS - dCOPYparaview: Many Spheres - 2560 x 1440paraview: Many Spheres - 2560 x 1440ncnn: Vulkan GPU - regnety_400mblender: Fishy Cat - CUDAcl-mem: Copyluxcorerender: Orange Juice - GPUvkpeak: int16-scalarvkpeak: int32-vec4luxcorerender: DLSC - GPUv-ray: NVIDIA CUDA GPUviennacl: OpenCL BLAS - dGEMM-NTfahbench: indigobench: OpenCL GPU - Supercarshoc: OpenCL - S3Dparaview: Many Spheres - 1920 x 1080hashcat: SHA-512blender: Barbershop - NVIDIA OptiXncnn: Vulkan GPU - resnet50paraview: Many Spheres - 1920 x 1080shoc: OpenCL - Texture Read Bandwidthhashcat: 7-Zipclpeak: Single-Precision Floatcl-mem: Writencnn: Vulkan GPU - vgg16blender: Pabellon Barcelona - NVIDIA OptiXvkresample: 2x - Singleshoc: OpenCL - Reductionblender: Pabellon Barcelona - CUDAluxcorerender: LuxCore Benchmark - GPUviennacl: OpenCL BLAS - dAXPYshoc: OpenCL - Triadshoc: OpenCL - Bus Speed Readbackcl-mem: Readwarsow: 2560 x 1440indigobench: OpenCL GPU - Bedroomclpeak: Double-Precision Doubleshoc: OpenCL - FFT SPshoc: OpenCL - Bus Speed Downloadhashcat: MD5financebench: Black-Scholes OpenCLclpeak: Global Memory Bandwidthncnn: Vulkan GPU - mnasnetviennacl: OpenCL BLAS - dGEMV-Tncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - googlenetunvanquished: 2560 x 1440 - Ultrawaifu2x-ncnn: 2x - 3 - NoRTX 3090NVIDIA RTX 3090NVIDIA 30903.177.024821.943.84317725.143.2688.445831559.058944.74684610066010151.478634.4717.4473.68102.381.06464.9456.8679.6710874.708492.593.919414.686140655.142588384.846157.361645.39.18960.8648.4463.6374.4286255556.929700142.4499.2632615496.11.67481322759.646334.94695.6214134.488396.7468.13.313490.199.64.2893.82273941184.89653.6181.591.940753.927806.7423966.15366.18514.93640.2652.320949.6420769.276274.519602.0936832.33375117.817470.81.910.1279291.131.472856984.32259930000076.111.2244.193216885.79686.23125860160220927.9911.049169.63691.4650328.9495849.675561.3222.761.98599606984.86.9423.39343.81793.22.5422.86364.110.4513708.5820672.192119604353.891553.438429.0829419.399288700000056.193.5593.952246.17113850035227.21743.14.1717.969.272391.20948.1172225.478127.1252794.6984.720.961658.162100.5126.3342714469000006.259813.422.0837715.965.85461.72.246.72479.01.83.69418044.253.2584.444252544.988719.75082563365710300.044643.7517.43488.58336.711.03478.3461.2689.8111036.994488.594.289451.903137659.9059394376.776028.366659.19.20980.7638.7471.0369.9242194567.721430041.6492.4660277487.31.67475794831.7469.834.7467.65.7154070.881390.6467.13.362485.698.24.2292.52271140926.17649.5381.990.740238.827457.9024065.55374.983515.78647.6654.520717.3120689.72651.176206.035595.5236432.60371118.517469.51.920.1291291.291.4702856975.52267850000075.511.3244.545316880.01685.10965660060120826.6611.029217.22891.9450129.0645867.721563.0522.691.97601605980.36.9123.29356.71093.332.5322.87364.210.4113657.3620594.7811.572112605353.327253.500430.3479429.536288466666756.353.5594.052240.09114010035136.60744.74.1818.009.292391.57348.1811.2072225.484027.1252794.3985.720.951657.712101.0826.3282714113666676.258813.452.0837717.316.07452.52.247.434401.83.62718742.73.4286.844147565.69049.54381630063710497.894656.1217.984848098.461.05474.6469.7696.4711143.486481.292.139236.629137645.8515908381.696107.065657.89.01978.6635.5472.9367.1052632566.122869342.2490.2778714491.91.7472928214.8471.134.3475.75.6734081.298391.6367.53.31848398.34.2392.82302941496.68658.582.690.840566.227806.5523765.35430.386521.09643.7659.820953.7220924.98658.516247.735599.5236432.25371119.073474.51.90.1277990.361.4852829984.82281310000075.411.2244.535817012.23681.12610860460520960.2511.099226.85492.0350028.8915836.216560.0322.641.97602608984.96.9223.29380.93293.572.5322.78362.810.4313709.4120672.2111.612115606354.462353.6430.2799402.63289290000056.343.5693.792245.23114150035225.4742.84.1717.969.291392.0348.0911.2272325.450527.0904795.2985.520.943658.162101.8226.3202714362000006.256813.472.0837719.735.75466.6OpenBenchmarking.org

NCNN

Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3RTX 3090NVIDIA RTX 3090NVIDIA 30900.71331.42662.13992.85323.5665SE +/- 0.00, N = 33.172.242.24MIN: 2.21 / MAX: 20.43MIN: 2.21 / MAX: 3.37MIN: 2.21 / MAX: 4.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: yolov4-tinyRTX 3090NVIDIA RTX 3090NVIDIA 3090246810SE +/- 0.04, N = 37.026.727.43MIN: 6.34 / MAX: 30.81MIN: 6.3 / MAX: 19.53MIN: 6.36 / MAX: 36.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Unvanquished

Resolution: 1920 x 1080 - Effects Quality: High

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1080 - Effects Quality: HighRTX 3090NVIDIA RTX 3090NVIDIA 3090100200300400500SE +/- 2.19, N = 3482.0479.0440.0

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: shufflenet-v2RTX 3090NVIDIA RTX 3090NVIDIA 30900.43650.8731.30951.7462.1825SE +/- 0.00, N = 31.941.801.80MIN: 1.78 / MAX: 2.28MIN: 1.76 / MAX: 3MIN: 1.77 / MAX: 2.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Rodinia

Test: OpenCL Particle Filter

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenCL Particle FilterRTX 3090NVIDIA RTX 3090NVIDIA 30900.86471.72942.59413.45884.3235SE +/- 0.013, N = 33.8433.6943.6271. (CXX) g++ options: -O2 -lOpenCL

clpeak

OpenCL Test: Integer Compute INT

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTRTX 3090NVIDIA RTX 3090NVIDIA 30904K8K12K16K20KSE +/- 115.05, N = 317725.1418044.2518742.701. (CXX) g++ options: -O3 -rdynamic -lOpenCL

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: efficientnet-b0RTX 3090NVIDIA RTX 3090NVIDIA 30900.76951.5392.30853.0783.8475SE +/- 0.00, N = 33.263.253.42MIN: 3.23 / MAX: 3.42MIN: 3.22 / MAX: 4.42MIN: 3.24 / MAX: 4.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

ViennaCL

Test: CPU BLAS - dGEMM-NT

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NTRTX 3090NVIDIA RTX 3090NVIDIA 309020406080100SE +/- 0.12, N = 388.484.486.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

VkFFT

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.1.1RTX 3090NVIDIA RTX 3090NVIDIA 309010K20K30K40K50KSE +/- 384.18, N = 94583144252441471. (CXX) g++ options: -O3

ParaView

Test: Wavelet Volume - Resolution: 2560 x 1440

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Wavelet Volume - Resolution: 2560 x 1440RTX 3090NVIDIA RTX 3090NVIDIA 3090120240360480600SE +/- 3.11, N = 3559.05544.98565.60

ParaView

Test: Wavelet Volume - Resolution: 2560 x 1440

OpenBenchmarking.orgMiVoxels / Sec, More Is BetterParaView 5.9Test: Wavelet Volume - Resolution: 2560 x 1440RTX 3090NVIDIA RTX 3090NVIDIA 30902K4K6K8K10KSE +/- 49.80, N = 38944.758719.759049.54

Hashcat

Benchmark: TrueCrypt RIPEMD160 + XTS

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: TrueCrypt RIPEMD160 + XTSRTX 3090NVIDIA RTX 3090NVIDIA 3090200K400K600K800K1000KSE +/- 4520.08, N = 3846100825633816300

ViennaCL

Test: OpenCL BLAS - dDOT

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOTRTX 3090NVIDIA RTX 3090NVIDIA 3090140280420560700SE +/- 0.58, N = 36606576371. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ParaView

Test: Wavelet Volume - Resolution: 1920 x 1200

OpenBenchmarking.orgMiVoxels / Sec, More Is BetterParaView 5.9Test: Wavelet Volume - Resolution: 1920 x 1200RTX 3090NVIDIA RTX 3090NVIDIA 30902K4K6K8K10KSE +/- 74.83, N = 310151.4810300.0410497.89

ParaView

Test: Wavelet Volume - Resolution: 1920 x 1200

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Wavelet Volume - Resolution: 1920 x 1200RTX 3090NVIDIA RTX 3090NVIDIA 3090140280420560700SE +/- 4.68, N = 3634.47643.75656.12

Blender

Blend File: Classroom - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: Classroom - Compute: NVIDIA OptiXRTX 3090NVIDIA RTX 3090NVIDIA 309048121620SE +/- 0.02, N = 317.4017.4317.98

Unvanquished

Resolution: 1920 x 1200 - Effects Quality: Medium

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1200 - Effects Quality: MediumRTX 3090NVIDIA RTX 3090NVIDIA 3090110220330440550SE +/- 1.98, N = 3473.6488.5484.0

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: GEMM SGEMM_N

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NRTX 3090NVIDIA RTX 3090NVIDIA 30902K4K6K8K10KSE +/- 67.62, N = 38102.388336.718098.461. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: blazefaceRTX 3090NVIDIA RTX 3090NVIDIA 30900.23850.4770.71550.9541.1925SE +/- 0.00, N = 31.061.031.05MIN: 1.02 / MAX: 2.12MIN: 1 / MAX: 2.07MIN: 1.01 / MAX: 2.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Unvanquished

Resolution: 1920 x 1200 - Effects Quality: High

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1200 - Effects Quality: HighRTX 3090NVIDIA RTX 3090NVIDIA 3090100200300400500SE +/- 4.62, N = 3464.9478.3474.6

Unvanquished

Resolution: 3840 x 2160 - Effects Quality: Ultra

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 3840 x 2160 - Effects Quality: UltraRTX 3090NVIDIA RTX 3090NVIDIA 3090100200300400500SE +/- 4.41, N = 3456.8461.2469.7

ParaView

Test: Wavelet Volume - Resolution: 1920 x 1080

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Wavelet Volume - Resolution: 1920 x 1080RTX 3090NVIDIA RTX 3090NVIDIA 3090150300450600750SE +/- 5.50, N = 3679.67689.81696.47

ParaView

Test: Wavelet Volume - Resolution: 1920 x 1080

OpenBenchmarking.orgMiVoxels / Sec, More Is BetterParaView 5.9Test: Wavelet Volume - Resolution: 1920 x 1080RTX 3090NVIDIA RTX 3090NVIDIA 30902K4K6K8K10KSE +/- 88.00, N = 310874.7111036.9911143.49

Unvanquished

Resolution: 2560 x 1440 - Effects Quality: Medium

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 2560 x 1440 - Effects Quality: MediumRTX 3090NVIDIA RTX 3090NVIDIA 3090110220330440550SE +/- 3.75, N = 3492.5488.5481.2

ParaView

Test: Many Spheres - Resolution: 1920 x 1200

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Many Spheres - Resolution: 1920 x 1200RTX 3090NVIDIA RTX 3090NVIDIA 309020406080100SE +/- 0.06, N = 393.9194.2892.13

ParaView

Test: Many Spheres - Resolution: 1920 x 1200

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.9Test: Many Spheres - Resolution: 1920 x 1200RTX 3090NVIDIA RTX 3090NVIDIA 30902K4K6K8K10KSE +/- 5.73, N = 39414.699451.909236.63

ViennaCL

Test: CPU BLAS - sDOT

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOTRTX 3090NVIDIA RTX 3090NVIDIA 3090306090120150SE +/- 0.67, N = 31401371371. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Xonotic

Resolution: 3840 x 2160 - Effects Quality: Low

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: LowRTX 3090NVIDIA RTX 3090NVIDIA 3090140280420560700SE +/- 0.55, N = 3655.14659.91645.85MIN: 103 / MAX: 1300MIN: 109 / MAX: 1303MIN: 117 / MAX: 1283

ParaView

Test: Wavelet Volume - Resolution: 3840 x 2160

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Wavelet Volume - Resolution: 3840 x 2160RTX 3090NVIDIA RTX 3090NVIDIA 309080160240320400SE +/- 4.06, N = 5384.84376.77381.69

ParaView

Test: Wavelet Volume - Resolution: 3840 x 2160

OpenBenchmarking.orgMiVoxels / Sec, More Is BetterParaView 5.9Test: Wavelet Volume - Resolution: 3840 x 2160RTX 3090NVIDIA RTX 3090NVIDIA 309013002600390052006500SE +/- 65.03, N = 56157.366028.376107.07

ET: Legacy

Resolution: 1920 x 1200

OpenBenchmarking.orgFrames Per Second, More Is BetterET: Legacy 2.78Resolution: 1920 x 1200RTX 3090NVIDIA RTX 3090NVIDIA 3090140280420560700SE +/- 2.46, N = 3645.3659.1657.8

LuxCoreRender

Scene: Danish Mood - Acceleration: GPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Danish Mood - Acceleration: GPURTX 3090NVIDIA RTX 3090NVIDIA 30903691215SE +/- 0.08, N = 39.189.209.01MIN: 3.53 / MAX: 10.86MIN: 3.03 / MAX: 10.91MIN: 3.3 / MAX: 10.77

Warsow

Resolution: 3840 x 2160

OpenBenchmarking.orgFrames Per Second, More Is BetterWarsow 2.5 BetaResolution: 3840 x 2160RTX 3090NVIDIA RTX 3090NVIDIA 30902004006008001000SE +/- 0.78, N = 3960.8980.7978.6

ET: Legacy

Resolution: 3840 x 2160

OpenBenchmarking.orgFrames Per Second, More Is BetterET: Legacy 2.78Resolution: 3840 x 2160RTX 3090NVIDIA RTX 3090NVIDIA 3090140280420560700SE +/- 6.04, N = 3648.4638.7635.5

Unvanquished

Resolution: 3840 x 2160 - Effects Quality: High

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 3840 x 2160 - Effects Quality: HighRTX 3090NVIDIA RTX 3090NVIDIA 3090100200300400500SE +/- 3.53, N = 3463.6471.0472.9

Xonotic

Resolution: 3840 x 2160 - Effects Quality: Ultimate

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: UltimateRTX 3090NVIDIA RTX 3090NVIDIA 309080160240320400SE +/- 1.53, N = 3374.43369.92367.11MIN: 65 / MAX: 751MIN: 58 / MAX: 764MIN: 65 / MAX: 749

Xonotic

Resolution: 3840 x 2160 - Effects Quality: High

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: HighRTX 3090NVIDIA RTX 3090NVIDIA 3090120240360480600SE +/- 1.97, N = 3556.93567.72566.12MIN: 114 / MAX: 1122MIN: 91 / MAX: 1163MIN: 113 / MAX: 1151

ViennaCL

Test: CPU BLAS - dDOT

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOTRTX 3090NVIDIA RTX 3090NVIDIA 30901020304050SE +/- 0.42, N = 342.441.642.21. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Xonotic

Resolution: 3840 x 2160 - Effects Quality: Ultra

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: UltraRTX 3090NVIDIA RTX 3090NVIDIA 3090110220330440550SE +/- 1.15, N = 3499.26492.47490.28MIN: 117 / MAX: 913MIN: 93 / MAX: 902MIN: 122 / MAX: 891

Unvanquished

Resolution: 1920 x 1080 - Effects Quality: Medium

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1080 - Effects Quality: MediumRTX 3090NVIDIA RTX 3090NVIDIA 3090110220330440550SE +/- 3.91, N = 3496.1487.3491.9

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet18RTX 3090NVIDIA RTX 3090NVIDIA 30900.38250.7651.14751.531.9125SE +/- 0.00, N = 31.671.671.70MIN: 1.64 / MAX: 1.9MIN: 1.64 / MAX: 4.75MIN: 1.65 / MAX: 9.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

MandelGPU

OpenCL Device: GPU

OpenBenchmarking.orgSamples/sec, More Is BetterMandelGPU 1.3pts1OpenCL Device: GPURTX 3090NVIDIA RTX 3090NVIDIA 3090100M200M300M400M500MSE +/- 1595019.30, N = 3481322759.6475794831.7472928214.81. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

Unvanquished

Resolution: 1920 x 1200 - Effects Quality: Ultra

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1200 - Effects Quality: UltraRTX 3090NVIDIA RTX 3090NVIDIA 3090100200300400500SE +/- 5.55, N = 3463.0469.8471.1

ViennaCL

Test: CPU BLAS - dAXPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPYRTX 3090NVIDIA RTX 3090NVIDIA 3090816243240SE +/- 0.00, N = 334.934.734.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Unvanquished

Resolution: 2560 x 1440 - Effects Quality: High

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 2560 x 1440 - Effects Quality: HighRTX 3090NVIDIA RTX 3090NVIDIA 3090100200300400500SE +/- 2.97, N = 3469.0467.6475.7

RealSR-NCNN

Scale: 4x - TAA: No

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoRTX 3090NVIDIA RTX 3090NVIDIA 30901.28592.57183.85775.14366.4295SE +/- 0.022, N = 35.6215.7155.673

ParaView

Test: Wavelet Contour - Resolution: 3840 x 2160

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.9Test: Wavelet Contour - Resolution: 3840 x 2160RTX 3090NVIDIA RTX 3090NVIDIA 30909001800270036004500SE +/- 31.15, N = 34134.494070.884081.30

ParaView

Test: Wavelet Contour - Resolution: 3840 x 2160

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Wavelet Contour - Resolution: 3840 x 2160RTX 3090NVIDIA RTX 3090NVIDIA 309090180270360450SE +/- 2.99, N = 3396.74390.64391.63

ViennaCL

Test: CPU BLAS - dGEMV-N

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-NRTX 3090NVIDIA RTX 3090NVIDIA 30901530456075SE +/- 0.17, N = 368.167.167.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Waifu2x-NCNN Vulkan

Scale: 2x - Denoise: 3 - TAA: Yes

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesRTX 3090NVIDIA RTX 3090NVIDIA 30900.75651.5132.26953.0263.7825SE +/- 0.004, N = 33.3133.3623.318

Unvanquished

Resolution: 3840 x 2160 - Effects Quality: Medium

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 3840 x 2160 - Effects Quality: MediumRTX 3090NVIDIA RTX 3090NVIDIA 3090110220330440550SE +/- 2.17, N = 3490.1485.6483.0

ViennaCL

Test: CPU BLAS - sAXPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPYRTX 3090NVIDIA RTX 3090NVIDIA 309020406080100SE +/- 0.68, N = 399.698.298.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mobilenetRTX 3090NVIDIA RTX 3090NVIDIA 30900.9631.9262.8893.8524.815SE +/- 0.01, N = 34.284.224.23MIN: 4.15 / MAX: 15.44MIN: 4.13 / MAX: 4.48MIN: 4.16 / MAX: 4.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

ViennaCL

Test: CPU BLAS - dGEMM-TN

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TNRTX 3090NVIDIA RTX 3090NVIDIA 309020406080100SE +/- 0.32, N = 393.892.592.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

LeelaChessZero

Backend: OpenCL

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: OpenCLRTX 3090NVIDIA RTX 3090NVIDIA 30905K10K15K20K25KSE +/- 98.83, N = 32273922711230291. (CXX) g++ options: -flto -pthread

vkpeak

fp16-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-vec4RTX 3090NVIDIA RTX 3090NVIDIA 30909K18K27K36K45KSE +/- 52.39, N = 341184.8940926.1741496.68

vkpeak

fp64-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-scalarRTX 3090NVIDIA RTX 3090NVIDIA 3090140280420560700SE +/- 0.83, N = 3653.61649.53658.50

ViennaCL

Test: CPU BLAS - dGEMM-NN

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NNRTX 3090NVIDIA RTX 3090NVIDIA 309020406080100SE +/- 0.18, N = 381.581.982.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - dGEMM-TT

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TTRTX 3090NVIDIA RTX 3090NVIDIA 309020406080100SE +/- 0.26, N = 391.990.790.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Max SP Flops

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP FlopsRTX 3090NVIDIA RTX 3090NVIDIA 30909K18K27K36K45KSE +/- 297.72, N = 340753.940238.840566.21. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

vkpeak

fp32-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-vec4RTX 3090NVIDIA RTX 3090NVIDIA 30906K12K18K24K30KSE +/- 69.31, N = 327806.7427457.9027806.55

ViennaCL

Test: OpenCL BLAS - dGEMV-N

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-NRTX 3090NVIDIA RTX 3090NVIDIA 309050100150200250SE +/- 0.33, N = 32392402371. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - sCOPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sCOPYRTX 3090NVIDIA RTX 3090NVIDIA 30901530456075SE +/- 0.09, N = 366.165.565.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ParaView

Test: Wavelet Contour - Resolution: 2560 x 1440

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.9Test: Wavelet Contour - Resolution: 2560 x 1440RTX 3090NVIDIA RTX 3090NVIDIA 309012002400360048006000SE +/- 16.63, N = 35366.185374.985430.39

ParaView

Test: Wavelet Contour - Resolution: 2560 x 1440

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Wavelet Contour - Resolution: 2560 x 1440RTX 3090NVIDIA RTX 3090NVIDIA 3090110220330440550SE +/- 1.60, N = 3514.93515.78521.09

ET: Legacy

Resolution: 2560 x 1440

OpenBenchmarking.orgFrames Per Second, More Is BetterET: Legacy 2.78Resolution: 2560 x 1440RTX 3090NVIDIA RTX 3090NVIDIA 3090140280420560700SE +/- 7.88, N = 4640.2647.6643.7

ET: Legacy

Resolution: 1920 x 1080

OpenBenchmarking.orgFrames Per Second, More Is BetterET: Legacy 2.78Resolution: 1920 x 1080RTX 3090NVIDIA RTX 3090NVIDIA 3090140280420560700SE +/- 3.73, N = 3652.3654.5659.8

vkpeak

fp16-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-scalarRTX 3090NVIDIA RTX 3090NVIDIA 30904K8K12K16K20KSE +/- 45.34, N = 320949.6420717.3120953.72

vkpeak

int32-scalar

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-scalarRTX 3090NVIDIA RTX 3090NVIDIA 30904K8K12K16K20KSE +/- 44.97, N = 320769.2720689.7220924.98

vkpeak

fp64-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-vec4NVIDIA RTX 3090NVIDIA 3090140280420560700SE +/- 1.42, N = 3651.17658.51

ParaView

Test: Wavelet Contour - Resolution: 1920 x 1080

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.9Test: Wavelet Contour - Resolution: 1920 x 1080RTX 3090NVIDIA RTX 3090NVIDIA 309013002600390052006500SE +/- 54.90, N = 36274.526206.046247.74

ParaView

Test: Wavelet Contour - Resolution: 1920 x 1080

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Wavelet Contour - Resolution: 1920 x 1080RTX 3090NVIDIA RTX 3090NVIDIA 3090130260390520650SE +/- 5.27, N = 3602.09595.52599.52

ViennaCL

Test: OpenCL BLAS - sCOPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sCOPYRTX 3090NVIDIA RTX 3090NVIDIA 309080160240320400SE +/- 0.88, N = 33683643641. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

LuxCoreRender

Scene: Rainbow Colors and Prism - Acceleration: GPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Rainbow Colors and Prism - Acceleration: GPURTX 3090NVIDIA RTX 3090NVIDIA 3090816243240SE +/- 0.21, N = 332.3332.6032.25MIN: 30.03 / MAX: 34.38MIN: 30.12 / MAX: 34.6MIN: 29.03 / MAX: 34.55

ViennaCL

Test: OpenCL BLAS - sDOT

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sDOTRTX 3090NVIDIA RTX 3090NVIDIA 309080160240320400SE +/- 0.58, N = 33753713711. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

VkResample

Upscale: 2x - Precision: Double

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: DoubleRTX 3090NVIDIA RTX 3090NVIDIA 3090306090120150SE +/- 0.08, N = 3117.82118.52119.071. (CXX) g++ options: -O3

Unvanquished

Resolution: 1920 x 1080 - Effects Quality: Ultra

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1080 - Effects Quality: UltraRTX 3090NVIDIA RTX 3090NVIDIA 3090100200300400500SE +/- 1.10, N = 3470.8469.5474.5

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: alexnetRTX 3090NVIDIA RTX 3090NVIDIA 30900.4320.8641.2961.7282.16SE +/- 0.01, N = 31.911.921.90MIN: 1.86 / MAX: 9.04MIN: 1.87 / MAX: 7.42MIN: 1.87 / MAX: 2.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NAMD CUDA

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD CUDA 2.14ATPase Simulation - 327,506 AtomsRTX 3090NVIDIA RTX 3090NVIDIA 30900.02910.05820.08730.11640.1455SE +/- 0.00047, N = 30.127920.129120.12779

Blender

Blend File: Barbershop - Compute: CUDA

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: Barbershop - Compute: CUDARTX 3090NVIDIA RTX 3090NVIDIA 309020406080100SE +/- 0.17, N = 391.1391.2990.36

ArrayFire

Test: Conjugate Gradient OpenCL

OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient OpenCLRTX 3090NVIDIA RTX 3090NVIDIA 30900.33410.66821.00231.33641.6705SE +/- 0.006, N = 31.4701.4701.4851. (CXX) g++ options: -rdynamic

Chaos Group V-RAY

Mode: NVIDIA RTX GPU

OpenBenchmarking.orgvrays, More Is BetterChaos Group V-RAY 5Mode: NVIDIA RTX GPURTX 3090NVIDIA RTX 3090NVIDIA 30906001200180024003000SE +/- 11.72, N = 3285628562829

Warsow

Resolution: 1920 x 1080

OpenBenchmarking.orgFrames Per Second, More Is BetterWarsow 2.5 BetaResolution: 1920 x 1080RTX 3090NVIDIA RTX 3090NVIDIA 30902004006008001000SE +/- 5.54, N = 3984.3975.5984.8

Hashcat

Benchmark: SHA1

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA1RTX 3090NVIDIA RTX 3090NVIDIA 30905000M10000M15000M20000M25000MSE +/- 32122473.96, N = 3225993000002267850000022813100000

ViennaCL

Test: CPU BLAS - dGEMV-T

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-TRTX 3090NVIDIA RTX 3090NVIDIA 309020406080100SE +/- 0.36, N = 376.175.575.41. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Blender

Blend File: Fishy Cat - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 3090NVIDIA RTX 3090NVIDIA 30903691215SE +/- 0.09, N = 311.2211.3211.22

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: MD5 Hash

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashRTX 3090NVIDIA RTX 3090NVIDIA 30901020304050SE +/- 0.00, N = 344.1944.5544.541. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

vkpeak

int16-vec4

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-vec4RTX 3090NVIDIA RTX 3090NVIDIA 30904K8K12K16K20KSE +/- 2.98, N = 316885.7916880.0117012.23

OctaneBench

Total Score

OpenBenchmarking.orgScore, More Is BetterOctaneBench 2020.1Total ScoreRTX 3090NVIDIA RTX 3090NVIDIA 3090150300450600750686.23685.11681.13

ViennaCL

Test: OpenCL BLAS - dGEMM-NN

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NNRTX 3090NVIDIA RTX 3090NVIDIA 30901302603905206506016006041. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: OpenCL BLAS - dGEMM-TT

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TTRTX 3090NVIDIA RTX 3090NVIDIA 30901302603905206506026016051. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

vkpeak

fp32-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-scalarRTX 3090NVIDIA RTX 3090NVIDIA 30904K8K12K16K20KSE +/- 65.72, N = 320927.9920826.6620960.25

Blender

Blend File: BMW27 - Compute: CUDA

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: BMW27 - Compute: CUDARTX 3090NVIDIA RTX 3090NVIDIA 30903691215SE +/- 0.01, N = 311.0411.0211.09

ParaView

Test: Many Spheres - Resolution: 3840 x 2160

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.9Test: Many Spheres - Resolution: 3840 x 2160RTX 3090NVIDIA RTX 3090NVIDIA 30902K4K6K8K10KSE +/- 6.01, N = 39169.649217.239226.85

ParaView

Test: Many Spheres - Resolution: 3840 x 2160

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Many Spheres - Resolution: 3840 x 2160RTX 3090NVIDIA RTX 3090NVIDIA 309020406080100SE +/- 0.06, N = 391.4691.9492.03

ViennaCL

Test: OpenCL BLAS - sAXPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sAXPYRTX 3090NVIDIA RTX 3090NVIDIA 3090110220330440550SE +/- 0.33, N = 35035015001. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

RealSR-NCNN

Scale: 4x - TAA: Yes

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesRTX 3090NVIDIA RTX 3090NVIDIA 3090714212835SE +/- 0.06, N = 328.9529.0628.89

ParaView

Test: Wavelet Contour - Resolution: 1920 x 1200

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.9Test: Wavelet Contour - Resolution: 1920 x 1200RTX 3090NVIDIA RTX 3090NVIDIA 309013002600390052006500SE +/- 54.66, N = 35849.685867.725836.22

ParaView

Test: Wavelet Contour - Resolution: 1920 x 1200

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Wavelet Contour - Resolution: 1920 x 1200RTX 3090NVIDIA RTX 3090NVIDIA 3090120240360480600SE +/- 5.24, N = 3561.32563.05560.03

Blender

Blend File: Classroom - Compute: CUDA

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: Classroom - Compute: CUDARTX 3090NVIDIA RTX 3090NVIDIA 3090510152025SE +/- 0.03, N = 322.7622.6922.64

NCNN

Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2RTX 3090NVIDIA RTX 3090NVIDIA 30900.44550.8911.33651.7822.2275SE +/- 0.00, N = 31.981.971.97MIN: 1.94 / MAX: 6.06MIN: 1.94 / MAX: 3.15MIN: 1.94 / MAX: 2.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

ViennaCL

Test: OpenCL BLAS - dGEMM-TN

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TNRTX 3090NVIDIA RTX 3090NVIDIA 3090130260390520650SE +/- 1.33, N = 35996016021. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: OpenCL BLAS - dCOPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPYRTX 3090NVIDIA RTX 3090NVIDIA 3090130260390520650SE +/- 0.33, N = 36066056081. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Warsow

Resolution: 1920 x 1200

OpenBenchmarking.orgFrames Per Second, More Is BetterWarsow 2.5 BetaResolution: 1920 x 1200RTX 3090NVIDIA RTX 3090NVIDIA 30902004006008001000SE +/- 5.60, N = 3984.8980.3984.9

Blender

Blend File: BMW27 - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: BMW27 - Compute: NVIDIA OptiXRTX 3090NVIDIA RTX 3090NVIDIA 3090246810SE +/- 0.01, N = 36.946.916.92

ViennaCL

Test: CPU BLAS - dCOPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPYRTX 3090NVIDIA RTX 3090NVIDIA 3090612182430SE +/- 0.00, N = 323.323.223.21. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ParaView

Test: Many Spheres - Resolution: 2560 x 1440

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.9Test: Many Spheres - Resolution: 2560 x 1440RTX 3090NVIDIA RTX 3090NVIDIA 30902K4K6K8K10KSE +/- 7.77, N = 39343.829356.719380.93

ParaView

Test: Many Spheres - Resolution: 2560 x 1440

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Many Spheres - Resolution: 2560 x 1440RTX 3090NVIDIA RTX 3090NVIDIA 309020406080100SE +/- 0.08, N = 393.2093.3393.57

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: regnety_400mRTX 3090NVIDIA RTX 3090NVIDIA 30900.57151.1431.71452.2862.8575SE +/- 0.01, N = 32.542.532.53MIN: 2.5 / MAX: 3.7MIN: 2.49 / MAX: 3.64MIN: 2.51 / MAX: 2.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Blender

Blend File: Fishy Cat - Compute: CUDA

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: Fishy Cat - Compute: CUDARTX 3090NVIDIA RTX 3090NVIDIA 3090510152025SE +/- 0.04, N = 322.8622.8722.78

cl-mem

Benchmark: Copy

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyRTX 3090NVIDIA RTX 3090NVIDIA 309080160240320400SE +/- 0.19, N = 3364.1364.2362.81. (CC) gcc options: -O2 -flto -lOpenCL

LuxCoreRender

Scene: Orange Juice - Acceleration: GPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: GPURTX 3090NVIDIA RTX 3090NVIDIA 30903691215SE +/- 0.10, N = 310.4510.4110.43MIN: 8.53 / MAX: 13.8MIN: 8.47 / MAX: 13.76MIN: 8.54 / MAX: 13.75

vkpeak

int16-scalar

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-scalarRTX 3090NVIDIA RTX 3090NVIDIA 30903K6K9K12K15KSE +/- 29.87, N = 313708.5813657.3613709.41

vkpeak

int32-vec4

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-vec4RTX 3090NVIDIA RTX 3090NVIDIA 30904K8K12K16K20KSE +/- 44.80, N = 320672.1920594.7820672.21

LuxCoreRender

Scene: DLSC - Acceleration: GPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: GPUNVIDIA RTX 3090NVIDIA 30903691215SE +/- 0.03, N = 311.5711.61MIN: 11.39 / MAX: 11.73MIN: 11.41 / MAX: 11.72

Chaos Group V-RAY

Mode: NVIDIA CUDA GPU

OpenBenchmarking.orgvpaths, More Is BetterChaos Group V-RAY 5Mode: NVIDIA CUDA GPURTX 3090NVIDIA RTX 3090NVIDIA 30905001000150020002500SE +/- 0.33, N = 3211921122115

ViennaCL

Test: OpenCL BLAS - dGEMM-NT

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NTRTX 3090NVIDIA RTX 3090NVIDIA 3090130260390520650SE +/- 1.67, N = 36046056061. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

FAHBench

OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.2RTX 3090NVIDIA RTX 3090NVIDIA 309080160240320400SE +/- 0.32, N = 3353.89353.33354.46

IndigoBench

Acceleration: OpenCL GPU - Scene: Supercar

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: SupercarRTX 3090NVIDIA RTX 3090NVIDIA 30901224364860SE +/- 0.03, N = 353.4453.5053.60

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: S3D

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3DRTX 3090NVIDIA RTX 3090NVIDIA 309090180270360450SE +/- 0.21, N = 3429.08430.35430.281. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

ParaView

Test: Many Spheres - Resolution: 1920 x 1080

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.9Test: Many Spheres - Resolution: 1920 x 1080RTX 3090NVIDIA RTX 3090NVIDIA 30902K4K6K8K10KSE +/- 4.72, N = 39419.409429.549402.63

Hashcat

Benchmark: SHA-512

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA-512RTX 3090NVIDIA RTX 3090NVIDIA 3090600M1200M1800M2400M3000MSE +/- 2179704.36, N = 3288700000028846666672892900000

Blender

Blend File: Barbershop - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: Barbershop - Compute: NVIDIA OptiXRTX 3090NVIDIA RTX 3090NVIDIA 30901326395265SE +/- 0.06, N = 356.1956.3556.34

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet50RTX 3090NVIDIA RTX 3090NVIDIA 30900.8011.6022.4033.2044.005SE +/- 0.00, N = 33.553.553.56MIN: 3.52 / MAX: 3.69MIN: 3.52 / MAX: 3.75MIN: 3.53 / MAX: 3.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

ParaView

Test: Many Spheres - Resolution: 1920 x 1080

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Many Spheres - Resolution: 1920 x 1080RTX 3090NVIDIA RTX 3090NVIDIA 309020406080100SE +/- 0.05, N = 393.9594.0593.79

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Texture Read Bandwidth

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read BandwidthRTX 3090NVIDIA RTX 3090NVIDIA 30905001000150020002500SE +/- 3.07, N = 32246.172240.092245.231. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

Hashcat

Benchmark: 7-Zip

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: 7-ZipRTX 3090NVIDIA RTX 3090NVIDIA 3090200K400K600K800K1000KSE +/- 4014.97, N = 3113850011401001141500

clpeak

OpenCL Test: Single-Precision Float

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatRTX 3090NVIDIA RTX 3090NVIDIA 30908K16K24K32K40KSE +/- 88.80, N = 335227.2135136.6035225.401. (CXX) g++ options: -O3 -rdynamic -lOpenCL

cl-mem

Benchmark: Write

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteRTX 3090NVIDIA RTX 3090NVIDIA 3090160320480640800SE +/- 0.33, N = 3743.1744.7742.81. (CC) gcc options: -O2 -flto -lOpenCL

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: vgg16RTX 3090NVIDIA RTX 3090NVIDIA 30900.94051.8812.82153.7624.7025SE +/- 0.02, N = 34.174.184.17MIN: 4.12 / MAX: 4.86MIN: 4.12 / MAX: 11.44MIN: 4.13 / MAX: 4.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Blender

Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXRTX 3090NVIDIA RTX 3090NVIDIA 309048121620SE +/- 0.02, N = 317.9618.0017.96

VkResample

Upscale: 2x - Precision: Single

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: SingleRTX 3090NVIDIA RTX 3090NVIDIA 30903691215SE +/- 0.003, N = 39.2729.2929.2911. (CXX) g++ options: -O3

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Reduction

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: ReductionRTX 3090NVIDIA RTX 3090NVIDIA 309090180270360450SE +/- 0.19, N = 3391.21391.57392.031. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

Blender

Blend File: Pabellon Barcelona - Compute: CUDA

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: Pabellon Barcelona - Compute: CUDARTX 3090NVIDIA RTX 3090NVIDIA 30901122334455SE +/- 0.01, N = 348.1148.1848.09

LuxCoreRender

Scene: LuxCore Benchmark - Acceleration: GPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: GPUNVIDIA RTX 3090NVIDIA 30903691215SE +/- 0.01, N = 311.2011.22MIN: 3.54 / MAX: 13.16MIN: 3.57 / MAX: 13.17

ViennaCL

Test: OpenCL BLAS - dAXPY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dAXPYRTX 3090NVIDIA RTX 3090NVIDIA 3090160320480640800SE +/- 0.00, N = 37227227231. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Triad

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: TriadRTX 3090NVIDIA RTX 3090NVIDIA 3090612182430SE +/- 0.00, N = 325.4825.4825.451. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Readback

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed ReadbackRTX 3090NVIDIA RTX 3090NVIDIA 3090612182430SE +/- 0.00, N = 327.1327.1327.091. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

cl-mem

Benchmark: Read

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadRTX 3090NVIDIA RTX 3090NVIDIA 30902004006008001000SE +/- 0.84, N = 3794.6794.3795.21. (CC) gcc options: -O2 -flto -lOpenCL

Warsow

Resolution: 2560 x 1440

OpenBenchmarking.orgFrames Per Second, More Is BetterWarsow 2.5 BetaResolution: 2560 x 1440RTX 3090NVIDIA RTX 3090NVIDIA 30902004006008001000SE +/- 0.35, N = 3984.7985.7985.5

IndigoBench

Acceleration: OpenCL GPU - Scene: Bedroom

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: BedroomRTX 3090NVIDIA RTX 3090NVIDIA 3090510152025SE +/- 0.01, N = 320.9620.9520.94

clpeak

OpenCL Test: Double-Precision Double

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleRTX 3090NVIDIA RTX 3090NVIDIA 3090140280420560700SE +/- 0.03, N = 3658.16657.71658.161. (CXX) g++ options: -O3 -rdynamic -lOpenCL

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: FFT SP

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPRTX 3090NVIDIA RTX 3090NVIDIA 30905001000150020002500SE +/- 0.42, N = 32100.512101.082101.821. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Download

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed DownloadRTX 3090NVIDIA RTX 3090NVIDIA 3090612182430SE +/- 0.01, N = 326.3326.3326.321. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

Hashcat

Benchmark: MD5

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: MD5RTX 3090NVIDIA RTX 3090NVIDIA 309015000M30000M45000M60000M75000MSE +/- 78065236.25, N = 3714469000007141136666771436200000

FinanceBench

Benchmark: Black-Scholes OpenCL

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Black-Scholes OpenCLRTX 3090NVIDIA RTX 3090NVIDIA 3090246810SE +/- 0.004, N = 36.2596.2586.2561. (CXX) g++ options: -O3 -march=native -fopenmp

clpeak

OpenCL Test: Global Memory Bandwidth

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthRTX 3090NVIDIA RTX 3090NVIDIA 30902004006008001000SE +/- 0.02, N = 3813.42813.45813.471. (CXX) g++ options: -O3 -rdynamic -lOpenCL

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mnasnetRTX 3090NVIDIA RTX 3090NVIDIA 30900.4680.9361.4041.8722.34SE +/- 0.01, N = 32.082.082.08MIN: 2.06 / MAX: 2.29MIN: 2.05 / MAX: 3.23MIN: 2.06 / MAX: 2.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

ViennaCL

Test: OpenCL BLAS - dGEMV-T

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-TRTX 3090NVIDIA RTX 3090NVIDIA 309080160240320400SE +/- 0.33, N = 33773773771. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: squeezenet_ssdRTX 3090NVIDIA RTX 3090NVIDIA 3090510152025SE +/- 1.24, N = 315.9617.3119.73MIN: 5.77 / MAX: 36.07MIN: 5.63 / MAX: 36.32MIN: 7.36 / MAX: 35.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: googlenetRTX 3090NVIDIA RTX 3090NVIDIA 3090246810SE +/- 0.26, N = 35.856.075.75MIN: 3.71 / MAX: 29.49MIN: 3.71 / MAX: 31.52MIN: 3.72 / MAX: 311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Unvanquished

Resolution: 2560 x 1440 - Effects Quality: Ultra

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 2560 x 1440 - Effects Quality: UltraRTX 3090NVIDIA RTX 3090NVIDIA 3090100200300400500SE +/- 14.16, N = 12461.7452.5466.6


Phoronix Test Suite v10.8.5