RTX 3090 Compute

AMD Ryzen 9 5900X 12-Core testing with a ASUS ROG CROSSHAIR VIII HERO (3801 BIOS) and NVIDIA GeForce RTX 3090 24GB on Ubuntu 21.10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2108296-TJ-RTX3090CO87
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
CPU Massive 4 Tests
Creator Workloads 4 Tests
HPC - High Performance Computing 5 Tests
Machine Learning 3 Tests
Multi-Core 6 Tests
NVIDIA GPU Compute 24 Tests
OpenCL 6 Tests
Renderers 4 Tests
Server CPU Tests 2 Tests
Vulkan Compute 6 Tests
Common Workstation Benchmarks 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
RTX 3090
August 28 2021
  6 Hours, 53 Minutes
2
August 29 2021
  2 Hours, 17 Minutes
3
August 29 2021
  2 Hours, 17 Minutes
Invert Hiding All Results Option
  3 Hours, 49 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

RTX 3090

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016
OpenCL Notes: GPU Compute Cores: 10496
Python Notes: Python 3.9.6
Security Notes: 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

2

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016
OpenCL Notes: GPU Compute Cores: 10496
Security Notes: 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

3

Processor: AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (3801 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB + 2000GB, Graphics: NVIDIA GeForce RTX 3090 24GB, Audio: NVIDIA GA102 HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel I211

OS: Ubuntu 21.10, Kernel: 5.13.0-14-generic (x86_64), Desktop: GNOME Shell 40.2, Display Server: X Server 1.20.11, Display Driver: NVIDIA 470.63.01, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 11.4.112, Vulkan: 1.2.175, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160

RTX 3090 ComputeProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionRTX 309023AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads)ASUS ROG CROSSHAIR VIII HERO (3801 BIOS)AMD Starship/Matisse16GB1000GB Western Digital WD_BLACK SN850 1TB + 2000GBNVIDIA GeForce RTX 3090 24GBNVIDIA GA102 HD AudioASUS VP28URealtek RTL8125 2.5GbE + Intel I211Ubuntu 21.105.13.0-14-generic (x86_64)GNOME Shell 40.2X Server 1.20.11NVIDIA 470.63.014.6.0OpenCL 3.0 CUDA 11.4.1121.2.175GCC 11.2.0ext43840x2160OpenBenchmarking.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-M6DaQn/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016 OpenCL Details- GPU Compute Cores: 10496Python Details- RTX 3090: Python 3.9.6Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

RTX 309023Result OverviewPhoronix Test Suite100%101%102%103%104%BlenderVkFFTRodiniavkpeakRealSR-NCNNNCNNWaifu2x-NCNN VulkanRedShift DemoArrayFireLuxCoreRenderLeelaChessZeroclpeakMandelGPUFAHBenchNAMD CUDAHashcatSHOC Scalable HeterOgeneous ComputingChaos Group V-RAYIndigoBenchViennaCLOctaneBenchVkResampleFinanceBenchcl-mem

RTX 3090 Computevkpeak: fp32-scalarvkpeak: fp32-vec4vkpeak: fp16-scalarvkpeak: fp16-vec4vkpeak: fp64-scalarvkpeak: fp64-vec4vkpeak: int32-scalarvkpeak: int32-vec4vkpeak: int16-scalarvkpeak: int16-vec4realsr-ncnn: 4x - Norealsr-ncnn: 4x - Yeswaifu2x-ncnn: 2x - 3 - Yesvkfft: hashcat: MD5hashcat: SHA1hashcat: 7-Ziphashcat: SHA-512hashcat: TrueCrypt RIPEMD160 + XTSshoc: OpenCL - S3Dshoc: OpenCL - Triadshoc: OpenCL - FFT SPshoc: OpenCL - MD5 Hashshoc: OpenCL - Reductionshoc: OpenCL - GEMM SGEMM_Nshoc: OpenCL - Max SP Flopsshoc: OpenCL - Bus Speed Downloadshoc: OpenCL - Bus Speed Readbackshoc: OpenCL - Texture Read Bandwidthcl-mem: Copycl-mem: Readcl-mem: Writenamd-cuda: ATPase Simulation - 327,506 Atomsvkresample: 2x - Doublevkresample: 2x - Singleoctanebench: Total Scoreredshift: fahbench: lczero: OpenCLrodinia: OpenCL Particle Filterarrayfire: Conjugate Gradient OpenCLluxcorerender: DLSC - GPUluxcorerender: Danish Mood - GPUluxcorerender: Orange Juice - GPUluxcorerender: LuxCore Benchmark - GPUluxcorerender: Rainbow Colors and Prism - GPUfinancebench: Black-Scholes OpenCLviennacl: CPU BLAS - sCOPYviennacl: CPU BLAS - sAXPYviennacl: CPU BLAS - sDOTviennacl: CPU BLAS - dCOPYviennacl: CPU BLAS - dAXPYviennacl: CPU BLAS - dDOTviennacl: CPU BLAS - dGEMV-Nviennacl: CPU BLAS - dGEMV-Tviennacl: CPU BLAS - dGEMM-NNviennacl: CPU BLAS - dGEMM-NTviennacl: CPU BLAS - dGEMM-TNviennacl: CPU BLAS - dGEMM-TTviennacl: OpenCL BLAS - sCOPYviennacl: OpenCL BLAS - sAXPYviennacl: OpenCL BLAS - sDOTviennacl: OpenCL BLAS - dCOPYviennacl: OpenCL BLAS - dAXPYviennacl: OpenCL BLAS - dDOTviennacl: OpenCL BLAS - dGEMV-Nviennacl: OpenCL BLAS - dGEMV-Tviennacl: OpenCL BLAS - dGEMM-NNviennacl: OpenCL BLAS - dGEMM-NTviennacl: OpenCL BLAS - dGEMM-TNviennacl: OpenCL BLAS - dGEMM-TTncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400mindigobench: OpenCL GPU - Bedroomindigobench: OpenCL GPU - Supercarblender: BMW27 - CUDAblender: Classroom - CUDAblender: Fishy Cat - CUDAblender: Barbershop - CUDAblender: BMW27 - NVIDIA OptiXblender: Classroom - NVIDIA OptiXblender: Fishy Cat - NVIDIA OptiXblender: Barbershop - NVIDIA OptiXblender: Pabellon Barcelona - CUDAblender: Pabellon Barcelona - NVIDIA OptiXmandelgpu: GPUclpeak: Integer Compute INTclpeak: Single-Precision Floatclpeak: Double-Precision Doubleclpeak: Global Memory Bandwidthv-ray: NVIDIA RTX GPUv-ray: NVIDIA CUDA GPURTX 30902320910.2927572.3420776.3540572.58653.53653.5020763.6520652.4713670.4416931.705.59228.5083.30643351667266333332283970000011531332879033333854867430.30125.46642349.2044.5445391.5468329.8640181.126.315527.09982236.38363.8827.3740.10.12056119.6489.272681.17956138345.3526539553.7301.47211.508.9310.3811.0132.616.27167.910215524.336.347.582.189.153.253.758.456.63634993725937216582403776026056006034.181.862.101.691.963.110.914.214.061.561.783.446.754.162.4120.93553.16818.3151.3134.53373.9612.2028.6021.66315.25120.3343.45483619873.618162.9135211.37657.71810.352941211521142.2127739.8120950.5240867.15658.57658.5520924.8120673.0513709.917004.325.52328.2453.27743413669143000002286060000011601002884800000860700430.15625.4781235244.2953390.9148432.9640013.326.33827.12482237.75363.7827.37390.12076119.3949.271682.731009139343.5447539503.6721.48311.58.6610.3610.9332.816.27169.410515624.736.947.881.789.853.353.858.256.73634993705927206582393766006025976014.161.842.11.681.953.130.923.94.041.551.813.446.7742.4120.98753.3918.3351.0734.44372.819.528.5818.94314.61120.5443.5148316470918313.835226656.4813.512939211620946.9627428.3720725.4540257.04648.73648.7220614.0520517.6113608.2616875.095.57328.2993.28742399667067000002282100000011575002882500000855400429.42325.47072348.0344.1942390.2938278.6739723.326.298227.08762241.48363.6827.7737.60.12115119.1079.286682.901259138344.8072535983.6751.47311.58.8610.4210.9732.876.26367.210115224.636.847.582.289.854.653.858.456.63674983716077246602403776056076024.131.852.11.691.963.120.913.854.11.551.83.436.683.992.4120.97653.41418.3651.1334.5373.19.5128.9718.99317.94120.4843.55485737287.818533.0935183.92658.23813.5429592116OpenBenchmarking.org

vkpeak

Vkpeak is a Vulkan compute benchmark inspired by OpenCL's clpeak. Vkpeak provides Vulkan compute performance measurements for FP16 / FP32 / FP64 / INT16 / INT32 scalar and vec4 performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-scalar23RTX 30905K10K15K20K25KSE +/- 144.67, N = 321142.2120946.9620910.29
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-scalar23RTX 30904K8K12K16K20KMin: 20725.18 / Avg: 20910.29 / Max: 21195.43

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-vec423RTX 30906K12K18K24K30KSE +/- 183.95, N = 327739.8127428.3727572.34
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-vec423RTX 30905K10K15K20K25KMin: 27388.38 / Avg: 27572.34 / Max: 27940.24

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-scalar23RTX 30904K8K12K16K20KSE +/- 67.18, N = 320950.5220725.4520776.35
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-scalar23RTX 30904K8K12K16K20KMin: 20707.27 / Avg: 20776.35 / Max: 20910.68

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-vec423RTX 30909K18K27K36K45KSE +/- 147.11, N = 340867.1540257.0440572.58
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-vec423RTX 30907K14K21K28K35KMin: 40418.35 / Avg: 40572.58 / Max: 40866.69

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-scalar23RTX 3090140280420560700SE +/- 2.50, N = 3658.57648.73653.53
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-scalar23RTX 3090120240360480600Min: 651 / Avg: 653.53 / Max: 658.54

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-vec423RTX 3090140280420560700SE +/- 2.55, N = 3658.55648.72653.50
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-vec423RTX 3090120240360480600Min: 650.95 / Avg: 653.5 / Max: 658.6

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-scalar23RTX 30904K8K12K16K20KSE +/- 81.20, N = 320924.8120614.0520763.65
OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-scalar23RTX 30904K8K12K16K20KMin: 20681.84 / Avg: 20763.65 / Max: 20926.06

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-vec423RTX 30904K8K12K16K20KSE +/- 55.18, N = 320673.0520517.6120652.47
OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-vec423RTX 30904K8K12K16K20KMin: 20595.36 / Avg: 20652.47 / Max: 20762.8

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-scalar23RTX 30903K6K9K12K15KSE +/- 20.28, N = 313709.9013608.2613670.44
OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-scalar23RTX 30902K4K6K8K10KMin: 13648.64 / Avg: 13670.44 / Max: 13710.95

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-vec423RTX 30904K8K12K16K20KSE +/- 41.21, N = 317004.3216875.0916931.70
OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-vec423RTX 30903K6K9K12K15KMin: 16881.67 / Avg: 16931.7 / Max: 17013.43

RealSR-NCNN

RealSR-NCNN is an NCNN neural network implementation of the RealSR project and accelerated using the Vulkan API. RealSR is the Real-World Super Resolution via Kernel Estimation and Noise Injection. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image by a scale of 4x with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: No23RTX 30901.25822.51643.77465.03286.291SE +/- 0.008, N = 35.5235.5735.592
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: No23RTX 3090246810Min: 5.58 / Avg: 5.59 / Max: 5.61

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: Yes23RTX 3090714212835SE +/- 0.04, N = 328.2528.3028.51
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: Yes23RTX 3090612182430Min: 28.44 / Avg: 28.51 / Max: 28.57

Waifu2x-NCNN Vulkan

Waifu2x-NCNN is an NCNN neural network implementation of the Waifu2x converter project and accelerated using the Vulkan API. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: Yes23RTX 30900.74391.48782.23172.97563.7195SE +/- 0.016, N = 33.2773.2873.306
OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: Yes23RTX 3090246810Min: 3.29 / Avg: 3.31 / Max: 3.34

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.1.123RTX 30909K18K27K36K45KSE +/- 375.64, N = 34341342399433511. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.1.123RTX 30908K16K24K32K40KMin: 42724 / Avg: 43351.33 / Max: 440231. (CXX) g++ options: -O3 -pthread

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: MD523RTX 309014000M28000M42000M56000M70000MSE +/- 4511220.58, N = 3669143000006670670000066726633333
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: MD523RTX 309012000M24000M36000M48000M60000MMin: 66719700000 / Avg: 66726633333.33 / Max: 66735100000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA123RTX 30905000M10000M15000M20000M25000MSE +/- 24017979.38, N = 3228606000002282100000022839700000
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA123RTX 30904000M8000M12000M16000M20000MMin: 22798200000 / Avg: 22839700000 / Max: 22881400000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-Zip23RTX 3090200K400K600K800K1000KSE +/- 1017.08, N = 3116010011575001153133
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-Zip23RTX 3090200K400K600K800K1000KMin: 1151700 / Avg: 1153133.33 / Max: 1155100

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-51223RTX 3090600M1200M1800M2400M3000MSE +/- 3299158.14, N = 3288480000028825000002879033333
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-51223RTX 3090500M1000M1500M2000M2500MMin: 2873100000 / Avg: 2879033333.33 / Max: 2884500000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTS23RTX 3090200K400K600K800K1000KSE +/- 1741.97, N = 3860700855400854867
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTS23RTX 3090150K300K450K600K750KMin: 851400 / Avg: 854866.67 / Max: 856900

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3D23RTX 309090180270360450SE +/- 0.25, N = 3430.16429.42430.301. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3D23RTX 309080160240320400Min: 429.8 / Avg: 430.3 / Max: 430.621. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Triad23RTX 3090612182430SE +/- 0.02, N = 325.4825.4725.471. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Triad23RTX 3090612182430Min: 25.44 / Avg: 25.47 / Max: 25.491. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SP23RTX 30905001000150020002500SE +/- 1.26, N = 32352.002348.032349.201. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SP23RTX 3090400800120016002000Min: 2347.21 / Avg: 2349.2 / Max: 2351.541. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 Hash23RTX 30901020304050SE +/- 0.00, N = 344.3044.1944.541. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 Hash23RTX 3090918273645Min: 44.54 / Avg: 44.54 / Max: 44.551. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Reduction23RTX 309080160240320400SE +/- 0.20, N = 3390.91390.29391.551. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Reduction23RTX 309070140210280350Min: 391.21 / Avg: 391.55 / Max: 391.91. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_N23RTX 30902K4K6K8K10KSE +/- 56.22, N = 38432.968278.678329.861. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_N23RTX 309015003000450060007500Min: 8238.96 / Avg: 8329.86 / Max: 8432.631. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP Flops23RTX 30909K18K27K36K45KSE +/- 475.87, N = 340013.339723.340181.11. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP Flops23RTX 30907K14K21K28K35KMin: 39402.2 / Avg: 40181.1 / Max: 41044.21. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed Download23RTX 3090612182430SE +/- 0.03, N = 326.3426.3026.321. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed Download23RTX 3090612182430Min: 26.26 / Avg: 26.32 / Max: 26.351. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed Readback23RTX 3090612182430SE +/- 0.01, N = 327.1227.0927.101. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed Readback23RTX 3090612182430Min: 27.09 / Avg: 27.1 / Max: 27.121. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read Bandwidth23RTX 30905001000150020002500SE +/- 5.62, N = 32237.752241.482236.381. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read Bandwidth23RTX 3090400800120016002000Min: 2225.7 / Avg: 2236.38 / Max: 2244.761. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

cl-mem

A basic OpenCL memory benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Copy23RTX 309080160240320400SE +/- 0.15, N = 3363.7363.6363.81. (CC) gcc options: -O2 -flto -lOpenCL
OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Copy23RTX 309060120180240300Min: 363.6 / Avg: 363.8 / Max: 364.11. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Read23RTX 30902004006008001000SE +/- 0.42, N = 3827.3827.7827.31. (CC) gcc options: -O2 -flto -lOpenCL
OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Read23RTX 3090150300450600750Min: 826.8 / Avg: 827.27 / Max: 828.11. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Write23RTX 3090160320480640800SE +/- 0.23, N = 3739.0737.6740.11. (CC) gcc options: -O2 -flto -lOpenCL
OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Write23RTX 3090130260390520650Min: 739.6 / Avg: 740.07 / Max: 740.31. (CC) gcc options: -O2 -flto -lOpenCL

NAMD CUDA

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. This version of the NAMD test profile uses CUDA GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD CUDA 2.14ATPase Simulation - 327,506 Atoms23RTX 30900.02730.05460.08190.10920.1365SE +/- 0.00027, N = 30.120760.121150.12056
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD CUDA 2.14ATPase Simulation - 327,506 Atoms23RTX 309012345Min: 0.12 / Avg: 0.12 / Max: 0.12

VkResample

VkResample is a Vulkan-based image upscaling library based on VkFFT. The sample input file is upscaling a 4K image to 8K using Vulkan-based GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: Double23RTX 3090306090120150SE +/- 0.14, N = 3119.39119.11119.651. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: Double23RTX 309020406080100Min: 119.38 / Avg: 119.65 / Max: 119.831. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: Single23RTX 30903691215SE +/- 0.015, N = 39.2719.2869.2721. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: Single23RTX 30903691215Min: 9.24 / Avg: 9.27 / Max: 9.291. (CXX) g++ options: -O3 -pthread

OctaneBench

OctaneBench is a test of the OctaneRender on the GPU and requires the use of NVIDIA CUDA. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterOctaneBench 2020.1Total Score23RTX 3090150300450600750682.73682.90681.18

RedShift Demo

This is a test of MAXON's RedShift demo build that currently requires NVIDIA GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRedShift Demo 3.023RTX 3090306090120150SE +/- 0.33, N = 3139138138
OpenBenchmarking.orgSeconds, Fewer Is BetterRedShift Demo 3.023RTX 3090306090120150Min: 138 / Avg: 138.33 / Max: 139

FAHBench

FAHBench is a Folding@Home benchmark on the GPU. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.223RTX 309080160240320400SE +/- 0.17, N = 3343.54344.81345.35
OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.223RTX 309060120180240300Min: 345.02 / Avg: 345.35 / Max: 345.57

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: OpenCL23RTX 309012K24K36K48K60KSE +/- 24.25, N = 35395053598539551. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: OpenCL23RTX 30909K18K27K36K45KMin: 53907 / Avg: 53955.33 / Max: 539831. (CXX) g++ options: -flto -pthread

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenCL Particle Filter23RTX 30900.83931.67862.51793.35724.1965SE +/- 0.044, N = 43.6723.6753.7301. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenCL Particle Filter23RTX 3090246810Min: 3.67 / Avg: 3.73 / Max: 3.861. (CXX) g++ options: -O2 -lOpenCL

ArrayFire

ArrayFire is an GPU and CPU numeric processing library, this test uses the built-in CPU and OpenCL ArrayFire benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient OpenCL23RTX 30900.33370.66741.00111.33481.6685SE +/- 0.001, N = 31.4831.4731.4721. (CXX) g++ options: -rdynamic
OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient OpenCL23RTX 3090246810Min: 1.47 / Avg: 1.47 / Max: 1.471. (CXX) g++ options: -rdynamic

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: GPU23RTX 30903691215SE +/- 0.01, N = 311.5011.5011.50MIN: 11.34 / MAX: 11.68MIN: 11.35 / MAX: 11.71MIN: 11.31 / MAX: 11.72
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: GPU23RTX 30903691215Min: 11.49 / Avg: 11.5 / Max: 11.51

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Danish Mood - Acceleration: GPU23RTX 3090246810SE +/- 0.13, N = 38.668.868.93MIN: 2.96 / MAX: 10.52MIN: 3.16 / MAX: 10.65MIN: 2.97 / MAX: 10.79
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Danish Mood - Acceleration: GPU23RTX 30903691215Min: 8.67 / Avg: 8.93 / Max: 9.06

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: GPU23RTX 30903691215SE +/- 0.03, N = 310.3610.4210.38MIN: 8.48 / MAX: 13.54MIN: 8.51 / MAX: 13.74MIN: 8.42 / MAX: 13.74
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: GPU23RTX 30903691215Min: 10.33 / Avg: 10.38 / Max: 10.44

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: GPU23RTX 30903691215SE +/- 0.03, N = 310.9310.9711.01MIN: 3.29 / MAX: 12.95MIN: 3.33 / MAX: 13.02MIN: 3.31 / MAX: 13.09
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: GPU23RTX 30903691215Min: 10.96 / Avg: 11.01 / Max: 11.07

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Rainbow Colors and Prism - Acceleration: GPU23RTX 3090816243240SE +/- 0.18, N = 332.8132.8732.61MIN: 30.72 / MAX: 35.61MIN: 30.74 / MAX: 35.64MIN: 29.7 / MAX: 35.64
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Rainbow Colors and Prism - Acceleration: GPU23RTX 3090714212835Min: 32.25 / Avg: 32.61 / Max: 32.84

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Black-Scholes OpenCL23RTX 3090246810SE +/- 0.001, N = 36.2716.2636.2711. (CXX) g++ options: -O3 -march=native -fopenmp
OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Black-Scholes OpenCL23RTX 30903691215Min: 6.27 / Avg: 6.27 / Max: 6.271. (CXX) g++ options: -O3 -march=native -fopenmp

ViennaCL

ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile makes use of ViennaCL's built-in benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sCOPY23RTX 30901530456075SE +/- 0.06, N = 369.467.267.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sCOPY23RTX 30901326395265Min: 67.8 / Avg: 67.9 / Max: 681. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPY23RTX 309020406080100SE +/- 0.33, N = 31051011021. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPY23RTX 309020406080100Min: 102 / Avg: 102.33 / Max: 1031. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOT23RTX 3090306090120150SE +/- 0.67, N = 31561521551. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOT23RTX 3090306090120150Min: 154 / Avg: 154.67 / Max: 1561. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPY23RTX 3090612182430SE +/- 0.09, N = 324.724.624.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPY23RTX 3090612182430Min: 24.2 / Avg: 24.33 / Max: 24.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPY23RTX 3090816243240SE +/- 0.25, N = 336.936.836.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPY23RTX 3090816243240Min: 35.8 / Avg: 36.3 / Max: 36.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOT23RTX 30901122334455SE +/- 0.23, N = 347.847.547.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOT23RTX 30901020304050Min: 47.3 / Avg: 47.53 / Max: 481. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-N23RTX 309020406080100SE +/- 0.10, N = 381.782.282.11. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-N23RTX 30901632486480Min: 82 / Avg: 82.1 / Max: 82.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-T23RTX 309020406080100SE +/- 0.03, N = 389.889.889.11. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-T23RTX 309020406080100Min: 89.1 / Avg: 89.13 / Max: 89.21. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NN23RTX 30901224364860SE +/- 0.52, N = 353.354.653.21. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NN23RTX 30901122334455Min: 52.2 / Avg: 53.23 / Max: 53.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NT23RTX 30901224364860SE +/- 0.07, N = 353.853.853.71. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NT23RTX 30901122334455Min: 53.6 / Avg: 53.67 / Max: 53.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TN23RTX 30901326395265SE +/- 0.09, N = 358.258.458.41. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TN23RTX 30901224364860Min: 58.3 / Avg: 58.43 / Max: 58.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TT23RTX 30901326395265SE +/- 0.09, N = 356.756.656.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TT23RTX 30901122334455Min: 56.5 / Avg: 56.63 / Max: 56.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sCOPY23RTX 309080160240320400SE +/- 0.58, N = 33633643631. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sCOPY23RTX 309070140210280350Min: 362 / Avg: 363 / Max: 3641. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sAXPY23RTX 3090110220330440550SE +/- 0.33, N = 34994984991. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sAXPY23RTX 309090180270360450Min: 499 / Avg: 499.33 / Max: 5001. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sDOT23RTX 309080160240320400SE +/- 0.33, N = 33703713721. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sDOT23RTX 309070140210280350Min: 371 / Avg: 371.67 / Max: 3721. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPY23RTX 3090130260390520650SE +/- 0.33, N = 35926075931. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPY23RTX 3090110220330440550Min: 592 / Avg: 592.67 / Max: 5931. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dAXPY23RTX 3090160320480640800SE +/- 0.33, N = 37207247211. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dAXPY23RTX 3090130260390520650Min: 720 / Avg: 720.67 / Max: 7211. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOT23RTX 3090140280420560700SE +/- 0.67, N = 36586606581. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOT23RTX 3090120240360480600Min: 657 / Avg: 658.33 / Max: 6591. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-N23RTX 309050100150200250SE +/- 0.33, N = 32392402401. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-N23RTX 30904080120160200Min: 239 / Avg: 239.67 / Max: 2401. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-T23RTX 309080160240320400SE +/- 0.33, N = 33763773771. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-T23RTX 309070140210280350Min: 376 / Avg: 376.67 / Max: 3771. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NN23RTX 3090130260390520650SE +/- 1.67, N = 36006056021. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NN23RTX 3090110220330440550Min: 599 / Avg: 602.33 / Max: 6041. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NT23RTX 3090130260390520650SE +/- 1.33, N = 36026076051. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NT23RTX 3090110220330440550Min: 602 / Avg: 604.67 / Max: 6061. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TN23RTX 3090130260390520650SE +/- 1.53, N = 35976026001. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TN23RTX 3090110220330440550Min: 597 / Avg: 600 / Max: 6021. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TT2RTX 3090130260390520650SE +/- 1.67, N = 36016031. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TT2RTX 3090110220330440550Min: 600 / Avg: 603.33 / Max: 6051. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mobilenet23RTX 30900.94051.8812.82153.7624.7025SE +/- 0.00, N = 34.164.134.18MIN: 4.11 / MAX: 4.52MIN: 4.09 / MAX: 4.58MIN: 4.11 / MAX: 4.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mobilenet23RTX 3090246810Min: 4.17 / Avg: 4.18 / Max: 4.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v2-v2 - Model: mobilenet-v223RTX 30900.41850.8371.25551.6742.0925SE +/- 0.00, N = 31.841.851.86MIN: 1.82 / MAX: 2.57MIN: 1.83 / MAX: 3.41MIN: 1.82 / MAX: 5.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v2-v2 - Model: mobilenet-v223RTX 3090246810Min: 1.86 / Avg: 1.86 / Max: 1.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v3-v3 - Model: mobilenet-v323RTX 30900.47250.9451.41751.892.3625SE +/- 0.01, N = 32.102.102.10MIN: 2.08 / MAX: 3.15MIN: 2.08 / MAX: 2.65MIN: 2.07 / MAX: 3.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v3-v3 - Model: mobilenet-v323RTX 3090246810Min: 2.09 / Avg: 2.1 / Max: 2.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: shufflenet-v223RTX 30900.38030.76061.14091.52121.9015SE +/- 0.01, N = 31.681.691.69MIN: 1.67 / MAX: 2.34MIN: 1.67 / MAX: 2.42MIN: 1.67 / MAX: 3.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: shufflenet-v223RTX 3090246810Min: 1.68 / Avg: 1.69 / Max: 1.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mnasnet23RTX 30900.4410.8821.3231.7642.205SE +/- 0.01, N = 31.951.961.96MIN: 1.94 / MAX: 2.45MIN: 1.94 / MAX: 2.95MIN: 1.94 / MAX: 3.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mnasnet23RTX 3090246810Min: 1.95 / Avg: 1.96 / Max: 1.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: efficientnet-b023RTX 30900.70431.40862.11292.81723.5215SE +/- 0.01, N = 33.113.123.11MIN: 3.1 / MAX: 3.23MIN: 3.1 / MAX: 4.74MIN: 3.09 / MAX: 4.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: efficientnet-b023RTX 3090246810Min: 3.1 / Avg: 3.11 / Max: 3.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: blazeface23RTX 30900.2070.4140.6210.8281.035SE +/- 0.01, N = 30.910.910.91MIN: 0.89 / MAX: 1.76MIN: 0.9 / MAX: 2.07MIN: 0.89 / MAX: 1.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: blazeface23RTX 3090246810Min: 0.9 / Avg: 0.91 / Max: 0.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: googlenet23RTX 30900.94731.89462.84193.78924.7365SE +/- 0.06, N = 33.873.854.21MIN: 3.62 / MAX: 14.75MIN: 3.62 / MAX: 14.78MIN: 3.58 / MAX: 15.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: googlenet23RTX 3090246810Min: 4.09 / Avg: 4.21 / Max: 4.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: vgg1623RTX 30900.92251.8452.76753.694.6125SE +/- 0.01, N = 34.044.104.06MIN: 4.02 / MAX: 4.12MIN: 4.01 / MAX: 14.21MIN: 4.01 / MAX: 10.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: vgg1623RTX 3090246810Min: 4.05 / Avg: 4.06 / Max: 4.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet1823RTX 30900.3510.7021.0531.4041.755SE +/- 0.02, N = 31.551.551.56MIN: 1.52 / MAX: 1.82MIN: 1.54 / MAX: 1.85MIN: 1.52 / MAX: 10.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet1823RTX 3090246810Min: 1.54 / Avg: 1.56 / Max: 1.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: alexnet23RTX 30900.40730.81461.22191.62922.0365SE +/- 0.01, N = 31.781.801.78MIN: 1.76 / MAX: 1.96MIN: 1.77 / MAX: 1.97MIN: 1.75 / MAX: 2.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: alexnet23RTX 3090246810Min: 1.77 / Avg: 1.78 / Max: 1.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet5023RTX 30900.77631.55262.32893.10523.8815SE +/- 0.01, N = 33.443.433.44MIN: 3.43 / MAX: 3.55MIN: 3.42 / MAX: 3.7MIN: 3.42 / MAX: 3.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet5023RTX 3090246810Min: 3.43 / Avg: 3.44 / Max: 3.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: yolov4-tiny23RTX 3090246810SE +/- 0.03, N = 36.776.686.75MIN: 6.42 / MAX: 8.75MIN: 6.33 / MAX: 7.23MIN: 6.39 / MAX: 7.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: yolov4-tiny23RTX 30903691215Min: 6.7 / Avg: 6.75 / Max: 6.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: squeezenet_ssd23RTX 30900.9361.8722.8083.7444.68SE +/- 0.12, N = 24.003.994.16MIN: 3.92 / MAX: 4.17MIN: 3.91 / MAX: 4.27MIN: 3.94 / MAX: 5.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: squeezenet_ssd23RTX 3090246810Min: 4.04 / Avg: 4.16 / Max: 4.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: regnety_400m23RTX 30900.54231.08461.62692.16922.7115SE +/- 0.01, N = 32.402.412.41MIN: 2.39 / MAX: 2.53MIN: 2.39 / MAX: 3.92MIN: 2.37 / MAX: 3.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: regnety_400m23RTX 3090246810Min: 2.39 / Avg: 2.41 / Max: 2.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: Bedroom23RTX 3090510152025SE +/- 0.05, N = 320.9920.9820.94
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: Bedroom23RTX 3090510152025Min: 20.86 / Avg: 20.94 / Max: 21.03

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: Supercar23RTX 30901224364860SE +/- 0.06, N = 353.3953.4153.17
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: Supercar23RTX 30901122334455Min: 53.06 / Avg: 53.17 / Max: 53.23

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CUDA23RTX 3090510152025SE +/- 0.01, N = 318.3318.3618.31
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CUDA23RTX 3090510152025Min: 18.28 / Avg: 18.31 / Max: 18.32

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CUDA23RTX 30901224364860SE +/- 0.05, N = 351.0751.1351.31
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CUDA23RTX 30901020304050Min: 51.23 / Avg: 51.31 / Max: 51.39

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CUDA23RTX 3090816243240SE +/- 0.01, N = 334.4434.5034.53
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CUDA23RTX 3090714212835Min: 34.51 / Avg: 34.53 / Max: 34.54

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CUDA23RTX 309080160240320400SE +/- 0.27, N = 3372.81373.10373.96
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CUDA23RTX 309070140210280350Min: 373.44 / Avg: 373.96 / Max: 374.37

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: NVIDIA OptiX23RTX 30903691215SE +/- 2.70, N = 159.509.5112.20
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: NVIDIA OptiX23RTX 309048121620Min: 9.48 / Avg: 12.2 / Max: 50.01

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: NVIDIA OptiX23RTX 3090714212835SE +/- 0.04, N = 328.5828.9728.60
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: NVIDIA OptiX23RTX 3090612182430Min: 28.54 / Avg: 28.6 / Max: 28.68

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: NVIDIA OptiX23RTX 3090510152025SE +/- 2.66, N = 1518.9418.9921.66
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: NVIDIA OptiX23RTX 3090510152025Min: 18.98 / Avg: 21.66 / Max: 58.84

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: NVIDIA OptiX23RTX 309070140210280350SE +/- 0.18, N = 3314.61317.94315.25
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: NVIDIA OptiX23RTX 309060120180240300Min: 314.88 / Avg: 315.25 / Max: 315.44

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CUDA23RTX 3090306090120150SE +/- 0.05, N = 3120.54120.48120.33
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CUDA23RTX 309020406080100Min: 120.23 / Avg: 120.33 / Max: 120.39

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX23RTX 30901020304050SE +/- 0.09, N = 343.5143.5543.45
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX23RTX 3090918273645Min: 43.28 / Avg: 43.45 / Max: 43.58

MandelGPU

MandelGPU is an OpenCL benchmark and this test runs with the OpenCL rendering float4 kernel with a maximum of 4096 iterations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSamples/sec, More Is BetterMandelGPU 1.3pts1OpenCL Device: GPU23RTX 3090100M200M300M400M500MSE +/- 222116.26, N = 3483164709.0485737287.8483619873.61. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL
OpenBenchmarking.orgSamples/sec, More Is BetterMandelGPU 1.3pts1OpenCL Device: GPU23RTX 309080M160M240M320M400MMin: 483272850.4 / Avg: 483619873.57 / Max: 484033568.61. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INT23RTX 30904K8K12K16K20KSE +/- 148.97, N = 918313.8018533.0918162.911. (CXX) g++ options: -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INT23RTX 30903K6K9K12K15KMin: 17642.85 / Avg: 18162.91 / Max: 18887.371. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision Float23RTX 30908K16K24K32K40KSE +/- 13.13, N = 335226.0035183.9235211.371. (CXX) g++ options: -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision Float23RTX 30906K12K18K24K30KMin: 35185.12 / Avg: 35211.37 / Max: 35224.51. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision Double23RTX 3090140280420560700SE +/- 0.02, N = 3656.40658.23657.711. (CXX) g++ options: -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision Double23RTX 3090120240360480600Min: 657.67 / Avg: 657.71 / Max: 657.751. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory Bandwidth23RTX 30902004006008001000SE +/- 3.03, N = 3813.51813.54810.351. (CXX) g++ options: -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory Bandwidth23RTX 3090140280420560700Min: 804.28 / Avg: 810.35 / Max: 813.391. (CXX) g++ options: -O3 -rdynamic -lOpenCL

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgvrays, More Is BetterChaos Group V-RAY 5Mode: NVIDIA RTX GPU23RTX 30906001200180024003000SE +/- 11.15, N = 3293929592941
OpenBenchmarking.orgvrays, More Is BetterChaos Group V-RAY 5Mode: NVIDIA RTX GPU23RTX 30905001000150020002500Min: 2920 / Avg: 2941 / Max: 2958

OpenBenchmarking.orgvpaths, More Is BetterChaos Group V-RAY 5Mode: NVIDIA CUDA GPU23RTX 30905001000150020002500SE +/- 0.88, N = 3211621162115
OpenBenchmarking.orgvpaths, More Is BetterChaos Group V-RAY 5Mode: NVIDIA CUDA GPU23RTX 3090400800120016002000Min: 2113 / Avg: 2114.67 / Max: 2116

105 Results Shown

vkpeak:
  fp32-scalar
  fp32-vec4
  fp16-scalar
  fp16-vec4
  fp64-scalar
  fp64-vec4
  int32-scalar
  int32-vec4
  int16-scalar
  int16-vec4
RealSR-NCNN:
  4x - No
  4x - Yes
Waifu2x-NCNN Vulkan
VkFFT
Hashcat:
  MD5
  SHA1
  7-Zip
  SHA-512
  TrueCrypt RIPEMD160 + XTS
SHOC Scalable HeterOgeneous Computing:
  OpenCL - S3D
  OpenCL - Triad
  OpenCL - FFT SP
  OpenCL - MD5 Hash
  OpenCL - Reduction
  OpenCL - GEMM SGEMM_N
  OpenCL - Max SP Flops
  OpenCL - Bus Speed Download
  OpenCL - Bus Speed Readback
  OpenCL - Texture Read Bandwidth
cl-mem:
  Copy
  Read
  Write
NAMD CUDA
VkResample:
  2x - Double
  2x - Single
OctaneBench
RedShift Demo
FAHBench
LeelaChessZero
Rodinia
ArrayFire
LuxCoreRender:
  DLSC - GPU
  Danish Mood - GPU
  Orange Juice - GPU
  LuxCore Benchmark - GPU
  Rainbow Colors and Prism - GPU
FinanceBench
ViennaCL:
  CPU BLAS - sCOPY
  CPU BLAS - sAXPY
  CPU BLAS - sDOT
  CPU BLAS - dCOPY
  CPU BLAS - dAXPY
  CPU BLAS - dDOT
  CPU BLAS - dGEMV-N
  CPU BLAS - dGEMV-T
  CPU BLAS - dGEMM-NN
  CPU BLAS - dGEMM-NT
  CPU BLAS - dGEMM-TN
  CPU BLAS - dGEMM-TT
  OpenCL BLAS - sCOPY
  OpenCL BLAS - sAXPY
  OpenCL BLAS - sDOT
  OpenCL BLAS - dCOPY
  OpenCL BLAS - dAXPY
  OpenCL BLAS - dDOT
  OpenCL BLAS - dGEMV-N
  OpenCL BLAS - dGEMV-T
  OpenCL BLAS - dGEMM-NN
  OpenCL BLAS - dGEMM-NT
  OpenCL BLAS - dGEMM-TN
  OpenCL BLAS - dGEMM-TT
NCNN:
  Vulkan GPU - mobilenet
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU - shufflenet-v2
  Vulkan GPU - mnasnet
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - blazeface
  Vulkan GPU - googlenet
  Vulkan GPU - vgg16
  Vulkan GPU - resnet18
  Vulkan GPU - alexnet
  Vulkan GPU - resnet50
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - squeezenet_ssd
  Vulkan GPU - regnety_400m
IndigoBench:
  OpenCL GPU - Bedroom
  OpenCL GPU - Supercar
Blender:
  BMW27 - CUDA
  Classroom - CUDA
  Fishy Cat - CUDA
  Barbershop - CUDA
  BMW27 - NVIDIA OptiX
  Classroom - NVIDIA OptiX
  Fishy Cat - NVIDIA OptiX
  Barbershop - NVIDIA OptiX
  Pabellon Barcelona - CUDA
  Pabellon Barcelona - NVIDIA OptiX
MandelGPU
clpeak:
  Integer Compute INT
  Single-Precision Float
  Double-Precision Double
  Global Memory Bandwidth
Chaos Group V-RAY:
  NVIDIA RTX GPU
  NVIDIA CUDA GPU

RTX 3090

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016
OpenCL Notes: GPU Compute Cores: 10496
Python Notes: Python 3.9.6
Security Notes: 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

Testing initiated at 28 August 2021 20:57 by user phoronix.

2

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016
OpenCL Notes: GPU Compute Cores: 10496
Security Notes: 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

Testing initiated at 29 August 2021 05:15 by user phoronix.

3

Processor: AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (3801 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB + 2000GB, Graphics: NVIDIA GeForce RTX 3090 24GB, Audio: NVIDIA GA102 HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel I211

OS: Ubuntu 21.10, Kernel: 5.13.0-14-generic (x86_64), Desktop: GNOME Shell 40.2, Display Server: X Server 1.20.11, Display Driver: NVIDIA 470.63.01, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 11.4.112, Vulkan: 1.2.175, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016
OpenCL Notes: GPU Compute Cores: 10496
Security Notes: 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

Testing initiated at 29 August 2021 06:54 by user phoronix.