RTX 30 Compute September

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 2109061-TJ-RTX30COMP69
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 3 Tests
C++ Boost Tests 2 Tests
CPU Massive 4 Tests
Creator Workloads 4 Tests
Game Development 2 Tests
HPC - High Performance Computing 8 Tests
Machine Learning 5 Tests
Multi-Core 6 Tests
NVIDIA GPU Compute 27 Tests
OpenCL 4 Tests
OpenMPI Tests 2 Tests
Python Tests 2 Tests
Renderers 3 Tests
Scientific Computing 2 Tests
Server CPU Tests 2 Tests
Vulkan Compute 8 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 3070
September 06
  6 Hours, 15 Minutes
RTX 3090
September 06
  2 Hours, 7 Minutes
GeForce RTX 3090
September 06
  47 Minutes
Invert Hiding All Results Option
  3 Hours, 3 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):


RTX 30 Compute SeptemberOpenBenchmarking.orgPhoronix Test Suite 10.6.1AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads)ASUS ROG CROSSHAIR VIII HERO (3801 BIOS)AMD Starship/Matisse16GB1000GB Western Digital WDS100T1X0E-00AFY0 + 1000GB Western Digital WD_BLACK SN850 1TB + 2000GBNVIDIA GeForce RTX 3070 8GBNVIDIA GeForce RTX 3090 24GBNVIDIA GA104 HD AudioNVIDIA 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 11.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudiosMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionRTX 30 Compute September BenchmarksSystem Logs- Transparent Huge Pages: madvise- --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 - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016- RTX 3070: GPU Compute Cores: 5888- RTX 3090: GPU Compute Cores: 10496- GeForce RTX 3090: GPU Compute Cores: 10496- Python 3.9.6- 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 3070RTX 3090GeForce RTX 3090Result OverviewPhoronix Test Suite 10.6.1100%120%140%159%179%vkpeakHashcatSHOC Scalable HeterOgeneous ComputingRealSR-NCNNVkFFTWaifu2x-NCNN Vulkan

RTX 30 Compute Septembervkpeak: 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-TNncnn: 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 - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - googlenetindigobench: OpenCL GPU - Bedroomindigobench: OpenCL GPU - Supercarblender: BMW27 - CUDAblender: Classroom - CUDAblender: Fishy Cat - CUDAblender: Barbershop - CUDAblender: BMW27 - NVIDIA OptiXblender: Classroom - NVIDIA OptiXblender: Fishy Cat - NVIDIA OptiXviennacl: OpenCL BLAS - dGEMM-TTRTX 3070RTX 3090GeForce RTX 309011589.5915319.3111590.4822503.16363.75364.2911571.3511521.487644.3210106.837.85646.7904.1123155438925166667131948333336896671673633333503167219.19524.66711134.8225.4087326.5703732.8723102.926.283727.11352130.04296.8393.3382.00.12555216.40617.529415.199251226265.5078377905.9202.0896.685.066.996.2221.2710.45766.9100.815124.636.548.682.889.853.153.658.256.42913593223703963952223333413423374.311.912.141.712.013.170.985.431.681.903.746.574.432.424.1312.94137.31829.0076.0654.69507.3915.8245.7733.3421074.8927597.62095440868.96655.42655.3120836.3220743.813646.5616889.265.56628.4153.27643295667393000002285370000011546002884600000857500427.93525.52892349.1944.4267391.2118174.5440344.126.257127.07852228.01364.3826.67450.13155119.8249.254683.595999139344.0195536533.681.4811.538.6410.4210.9232.096.3576389.613622.634.843.277.683.852.45256.1543645013516077216632363766006025984.481.982.211.772.093.350.964.441.811.883.747.664.372.574.3820.96853.36418.3251.1834.65373.329.5228.6618.9760120871.3627390.0820714.1440423.41651.31651.220687.5520597.1913655.9716887.925.59528.4213.27544567665891000002279850000011611002881300000859400427.07825.44962348.0344.1942391.0918105.73OpenBenchmarking.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-scalarRTX 3070RTX 3090GeForce RTX 30905K10K15K20K25KSE +/- 35.78, N = 311589.5921074.8921146.01
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-scalarRTX 3070RTX 3090GeForce RTX 30904K8K12K16K20KMin: 11538.01 / Avg: 11589.59 / Max: 11658.33

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-vec4RTX 3070RTX 3090GeForce RTX 30906K12K18K24K30KSE +/- 35.81, N = 315319.3127597.6027807.75
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-vec4RTX 3070RTX 3090GeForce RTX 30905K10K15K20K25KMin: 15248.07 / Avg: 15319.31 / Max: 15361.33

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-scalarRTX 3070RTX 3090GeForce RTX 30904K8K12K16K20KSE +/- 26.04, N = 311590.4820954.0020953.65
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-scalarRTX 3070RTX 3090GeForce RTX 30904K8K12K16K20KMin: 11538.95 / Avg: 11590.48 / Max: 11622.79

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-vec4RTX 3070RTX 3090GeForce RTX 30909K18K27K36K45KSE +/- 71.70, N = 322503.1640868.9640869.19
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-vec4RTX 3070RTX 3090GeForce RTX 30907K14K21K28K35KMin: 22431.37 / Avg: 22503.16 / Max: 22646.57

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-scalarRTX 3070RTX 3090GeForce RTX 3090140280420560700SE +/- 0.36, N = 3363.75655.42658.56
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-scalarRTX 3070RTX 3090GeForce RTX 3090120240360480600Min: 363.39 / Avg: 363.75 / Max: 364.47

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-vec4RTX 3070RTX 3090GeForce RTX 3090140280420560700SE +/- 0.42, N = 3364.29655.31651.20
OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-vec4RTX 3070RTX 3090GeForce RTX 3090120240360480600Min: 363.85 / Avg: 364.29 / Max: 365.12

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-scalarRTX 3070RTX 3090GeForce RTX 30904K8K12K16K20KSE +/- 16.33, N = 311571.3520836.3220925.87
OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-scalarRTX 3070RTX 3090GeForce RTX 30904K8K12K16K20KMin: 11554.64 / Avg: 11571.35 / Max: 11604.01

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-vec4RTX 3070RTX 3090GeForce RTX 30904K8K12K16K20KSE +/- 18.17, N = 311521.4820743.8020746.67
OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-vec4RTX 3070RTX 3090GeForce RTX 30904K8K12K16K20KMin: 11499.32 / Avg: 11521.48 / Max: 11557.51

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-scalarRTX 3070RTX 3090GeForce RTX 30903K6K9K12K15KSE +/- 11.41, N = 37644.3213646.5613752.19
OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-scalarRTX 3070RTX 3090GeForce RTX 30902K4K6K8K10KMin: 7632.11 / Avg: 7644.32 / Max: 7667.11

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-vec4RTX 3070RTX 3090GeForce RTX 30904K8K12K16K20KSE +/- 20.90, N = 310106.8316889.2617006.61
OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-vec4RTX 3070RTX 3090GeForce RTX 30903K6K9K12K15KMin: 10085.76 / Avg: 10106.83 / Max: 10148.63

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: NoRTX 3070RTX 3090GeForce RTX 3090246810SE +/- 0.002, N = 37.8565.5665.595
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoRTX 3070RTX 3090GeForce RTX 30903691215Min: 7.85 / Avg: 7.86 / Max: 7.86

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesRTX 3070RTX 3090GeForce RTX 30901122334455SE +/- 0.04, N = 346.7928.4228.42
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesRTX 3070RTX 3090GeForce RTX 30901020304050Min: 46.72 / Avg: 46.79 / Max: 46.83

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.

Scale: 2x - Denoise: 3 - TAA: No

RTX 3070: Test failed to run.

RTX 3090: Test failed to run.

GeForce RTX 3090: Test failed to run.

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesRTX 3070RTX 3090GeForce RTX 30900.92521.85042.77563.70084.626SE +/- 0.006, N = 34.1123.2763.275
OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesRTX 3070RTX 3090GeForce RTX 3090246810Min: 4.11 / Avg: 4.11 / Max: 4.12

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 1.1.1RTX 3070RTX 3090GeForce RTX 309010K20K30K40K50KSE +/- 172.10, N = 33155443295445671. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.1.1RTX 3070RTX 3090GeForce RTX 30908K16K24K32K40KMin: 31217 / Avg: 31553.67 / Max: 317841. (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: MD5RTX 3070RTX 3090GeForce RTX 309014000M28000M42000M56000M70000MSE +/- 41756290.28, N = 3389251666676673930000066589100000
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: MD5RTX 3070RTX 3090GeForce RTX 309012000M24000M36000M48000M60000MMin: 38880300000 / Avg: 38925166666.67 / Max: 39008600000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA1RTX 3070RTX 3090GeForce RTX 30905000M10000M15000M20000M25000MSE +/- 7750340.49, N = 3131948333332285370000022798500000
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA1RTX 3070RTX 3090GeForce RTX 30904000M8000M12000M16000M20000MMin: 13183600000 / Avg: 13194833333.33 / Max: 13209700000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-ZipRTX 3070RTX 3090GeForce RTX 3090200K400K600K800K1000KSE +/- 1128.91, N = 368966711546001161100
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-ZipRTX 3070RTX 3090GeForce RTX 3090200K400K600K800K1000KMin: 687500 / Avg: 689666.67 / Max: 691300

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-512RTX 3070RTX 3090GeForce RTX 3090600M1200M1800M2400M3000MSE +/- 735602.55, N = 3167363333328846000002881300000
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-512RTX 3070RTX 3090GeForce RTX 3090500M1000M1500M2000M2500MMin: 1672800000 / Avg: 1673633333.33 / Max: 1675100000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTSRTX 3070RTX 3090GeForce RTX 3090200K400K600K800K1000KSE +/- 800.69, N = 3503167857500859400
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTSRTX 3070RTX 3090GeForce RTX 3090150K300K450K600K750KMin: 502000 / Avg: 503166.67 / Max: 504700

Mixbench

A benchmark suite for GPUs on mixed operational intensity kernels. Learn more via the OpenBenchmarking.org test page.

Backend: OpenCL - Benchmark: Integer

RTX 3070: ./mixbench: 3: ./mixbench-ocl-ro: not found

RTX 3090: ./mixbench: 3: ./mixbench-ocl-ro: not found

GeForce RTX 3090: ./mixbench: 3: ./mixbench-ocl-ro: not found

Backend: NVIDIA CUDA - Benchmark: Integer

RTX 3070: ./mixbench: 3: ./mixbench-cuda-ro: not found

RTX 3090: ./mixbench: 3: ./mixbench-cuda-ro: not found

GeForce RTX 3090: ./mixbench: 3: ./mixbench-cuda-ro: not found

Backend: OpenCL - Benchmark: Double Precision

RTX 3070: ./mixbench: 3: ./mixbench-ocl-ro: not found

RTX 3090: ./mixbench: 3: ./mixbench-ocl-ro: not found

GeForce RTX 3090: ./mixbench: 3: ./mixbench-ocl-ro: not found

Backend: OpenCL - Benchmark: Single Precision

RTX 3070: ./mixbench: 3: ./mixbench-ocl-ro: not found

RTX 3090: ./mixbench: 3: ./mixbench-ocl-ro: not found

GeForce RTX 3090: ./mixbench: 3: ./mixbench-ocl-ro: not found

Backend: NVIDIA CUDA - Benchmark: Half Precision

RTX 3070: ./mixbench: 3: ./mixbench-cuda-ro: not found

RTX 3090: ./mixbench: 3: ./mixbench-cuda-ro: not found

GeForce RTX 3090: ./mixbench: 3: ./mixbench-cuda-ro: not found

Backend: NVIDIA CUDA - Benchmark: Double Precision

RTX 3070: ./mixbench: 3: ./mixbench-cuda-ro: not found

RTX 3090: ./mixbench: 3: ./mixbench-cuda-ro: not found

GeForce RTX 3090: ./mixbench: 3: ./mixbench-cuda-ro: not found

Backend: NVIDIA CUDA - Benchmark: Single Precision

RTX 3070: ./mixbench: 3: ./mixbench-cuda-ro: not found

RTX 3090: ./mixbench: 3: ./mixbench-cuda-ro: not found

GeForce RTX 3090: ./mixbench: 3: ./mixbench-cuda-ro: not found

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: S3DRTX 3070RTX 3090GeForce RTX 309090180270360450SE +/- 0.17, N = 3219.20427.94427.081. (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: S3DRTX 3070RTX 3090GeForce RTX 309080160240320400Min: 218.98 / Avg: 219.19 / Max: 219.531. (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: TriadRTX 3070RTX 3090GeForce RTX 3090612182430SE +/- 0.01, N = 324.6725.5325.451. (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: TriadRTX 3070RTX 3090GeForce RTX 3090612182430Min: 24.66 / Avg: 24.67 / Max: 24.671. (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 SPRTX 3070RTX 3090GeForce RTX 30905001000150020002500SE +/- 0.78, N = 31134.822349.192348.031. (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 SPRTX 3070RTX 3090GeForce RTX 3090400800120016002000Min: 1133.3 / Avg: 1134.82 / Max: 1135.861. (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 HashRTX 3070RTX 3090GeForce RTX 30901020304050SE +/- 0.03, N = 325.4144.4344.191. (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 HashRTX 3070RTX 3090GeForce RTX 3090918273645Min: 25.37 / Avg: 25.41 / Max: 25.461. (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: ReductionRTX 3070RTX 3090GeForce RTX 309080160240320400SE +/- 0.70, N = 3326.57391.21391.091. (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: ReductionRTX 3070RTX 3090GeForce RTX 309070140210280350Min: 325.81 / Avg: 326.57 / Max: 327.971. (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_NRTX 3070RTX 3090GeForce RTX 30902K4K6K8K10KSE +/- 26.69, N = 33732.878174.548105.731. (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_NRTX 3070RTX 3090GeForce RTX 309014002800420056007000Min: 3680.6 / Avg: 3732.87 / Max: 3768.381. (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 FlopsRTX 3070RTX 30909K18K27K36K45KSE +/- 59.20, N = 323102.940344.11. (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 FlopsRTX 3070RTX 30907K14K21K28K35KMin: 22984.5 / Avg: 23102.9 / Max: 23162.11. (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 DownloadRTX 3070RTX 3090612182430SE +/- 0.02, N = 326.2826.261. (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 DownloadRTX 3070RTX 3090612182430Min: 26.25 / Avg: 26.28 / Max: 26.331. (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 ReadbackRTX 3070RTX 3090612182430SE +/- 0.01, N = 327.1127.081. (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 ReadbackRTX 3070RTX 3090612182430Min: 27.09 / Avg: 27.11 / Max: 27.131. (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 BandwidthRTX 3070RTX 30905001000150020002500SE +/- 6.58, N = 32130.042228.011. (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 BandwidthRTX 3070RTX 3090400800120016002000Min: 2117.78 / Avg: 2130.04 / Max: 2140.331. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

Libplacebo

Libplacebo is a multimedia rendering library based on the core rendering code of the MPV player. The libplacebo benchmark relies on the Vulkan API and tests various primitives. Learn more via the OpenBenchmarking.org test page.

RTX 3070: The test quit with a non-zero exit status.

RTX 3090: The test quit with a non-zero exit status.

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: CopyRTX 3070RTX 309080160240320400SE +/- 0.45, N = 3296.8364.31. (CC) gcc options: -O2 -flto -lOpenCL
OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyRTX 3070RTX 309070140210280350Min: 295.9 / Avg: 296.8 / Max: 297.31. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadRTX 3070RTX 30902004006008001000SE +/- 0.30, N = 3393.3826.61. (CC) gcc options: -O2 -flto -lOpenCL
OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadRTX 3070RTX 3090150300450600750Min: 392.7 / Avg: 393.27 / Max: 393.71. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteRTX 3070RTX 3090160320480640800SE +/- 0.09, N = 3382.0745.01. (CC) gcc options: -O2 -flto -lOpenCL
OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteRTX 3070RTX 3090130260390520650Min: 381.9 / Avg: 382.03 / Max: 382.21. (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 AtomsRTX 3070RTX 30900.02960.05920.08880.11840.148SE +/- 0.00049, N = 30.125550.13155
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD CUDA 2.14ATPase Simulation - 327,506 AtomsRTX 3070RTX 309012345Min: 0.12 / Avg: 0.13 / Max: 0.13

Betsy GPU Compressor

Betsy is an open-source GPU compressor of various GPU compression techniques. Betsy is written in GLSL for Vulkan/OpenGL (compute shader) support for GPU-based texture compression. Learn more via the OpenBenchmarking.org test page.

Codec: ETC1 - Quality: Highest

RTX 3070: ./betsy: 3: ./betsy: not found

RTX 3090: ./betsy: 3: ./betsy: not found

Codec: ETC2 RGB - Quality: Highest

RTX 3070: ./betsy: 3: ./betsy: not found

RTX 3090: ./betsy: 3: ./betsy: not found

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: DoubleRTX 3070RTX 309050100150200250SE +/- 0.03, N = 3216.41119.821. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: DoubleRTX 3070RTX 30904080120160200Min: 216.37 / Avg: 216.41 / Max: 216.471. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: SingleRTX 3070RTX 309048121620SE +/- 0.013, N = 317.5299.2541. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: SingleRTX 3070RTX 309048121620Min: 17.5 / Avg: 17.53 / Max: 17.541. (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 ScoreRTX 3070RTX 3090150300450600750415.20683.60

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 3.0RTX 3070RTX 309050100150200250SE +/- 0.33, N = 3226139
OpenBenchmarking.orgSeconds, Fewer Is BetterRedShift Demo 3.0RTX 3070RTX 30904080120160200Min: 226 / Avg: 226.33 / Max: 227

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 2.3.2RTX 3070RTX 309070140210280350SE +/- 0.05, N = 3265.51344.02
OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.2RTX 3070RTX 309060120180240300Min: 265.43 / Avg: 265.51 / Max: 265.58

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: OpenCLRTX 3070RTX 309011K22K33K44K55KSE +/- 178.94, N = 337790536531. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: OpenCLRTX 3070RTX 30909K18K27K36K45KMin: 37555 / Avg: 37789.67 / Max: 381411. (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 FilterRTX 3070RTX 30901.3322.6643.9965.3286.66SE +/- 0.007, N = 35.9203.6801. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenCL Particle FilterRTX 3070RTX 3090246810Min: 5.91 / Avg: 5.92 / Max: 5.931. (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 OpenCLRTX 3070RTX 30900.470.941.411.882.35SE +/- 0.001, N = 32.0891.4801. (CXX) g++ options: -rdynamic
OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient OpenCLRTX 3070RTX 3090246810Min: 2.09 / Avg: 2.09 / Max: 2.091. (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: GPURTX 3070RTX 30903691215SE +/- 0.00, N = 36.6811.53MIN: 6.25 / MAX: 6.94MIN: 11.29 / MAX: 11.68
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: GPURTX 3070RTX 30903691215Min: 6.68 / Avg: 6.68 / Max: 6.68

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Danish Mood - Acceleration: GPURTX 3070RTX 3090246810SE +/- 0.00, N = 35.068.64MIN: 1.5 / MAX: 6.12MIN: 2.95 / MAX: 10.48
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Danish Mood - Acceleration: GPURTX 3070RTX 30903691215Min: 5.06 / Avg: 5.06 / Max: 5.07

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: GPURTX 3070RTX 30903691215SE +/- 0.01, N = 36.9910.42MIN: 5.61 / MAX: 8.46MIN: 8.45 / MAX: 13.57
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: GPURTX 3070RTX 30903691215Min: 6.97 / Avg: 6.99 / Max: 7

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: GPURTX 3070RTX 30903691215SE +/- 0.01, N = 36.2210.92MIN: 2.05 / MAX: 7.38MIN: 3.29 / MAX: 13.01
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: GPURTX 3070RTX 30903691215Min: 6.2 / Avg: 6.22 / Max: 6.24

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Rainbow Colors and Prism - Acceleration: GPURTX 3070RTX 3090714212835SE +/- 0.03, N = 321.2732.09MIN: 20.13 / MAX: 22.99MIN: 28.96 / MAX: 34.45
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Rainbow Colors and Prism - Acceleration: GPURTX 3070RTX 3090714212835Min: 21.24 / Avg: 21.27 / Max: 21.33

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 OpenCLRTX 3070RTX 30903691215SE +/- 0.003, N = 310.4576.3571. (CXX) g++ options: -O3 -march=native -fopenmp
OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Black-Scholes OpenCLRTX 3070RTX 30903691215Min: 10.45 / Avg: 10.46 / Max: 10.461. (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 - sCOPYRTX 3070RTX 30901530456075SE +/- 0.58, N = 366.963.01. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sCOPYRTX 3070RTX 30901326395265Min: 65.9 / Avg: 66.9 / Max: 67.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPYRTX 3070RTX 309020406080100SE +/- 0.73, N = 3100.889.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPYRTX 3070RTX 309020406080100Min: 99.5 / Avg: 100.83 / Max: 1021. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOTRTX 3070RTX 3090306090120150SE +/- 0.88, N = 31511361. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOTRTX 3070RTX 3090306090120150Min: 150 / Avg: 151.33 / Max: 1531. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPYRTX 3070RTX 3090612182430SE +/- 0.03, N = 324.622.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPYRTX 3070RTX 3090612182430Min: 24.6 / Avg: 24.63 / Max: 24.71. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPYRTX 3070RTX 3090816243240SE +/- 0.32, N = 336.534.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPYRTX 3070RTX 3090816243240Min: 35.9 / Avg: 36.53 / Max: 36.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOTRTX 3070RTX 30901122334455SE +/- 0.50, N = 348.643.21. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOTRTX 3070RTX 30901020304050Min: 47.8 / Avg: 48.57 / Max: 49.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-NRTX 3070RTX 309020406080100SE +/- 0.09, N = 382.877.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-NRTX 3070RTX 30901632486480Min: 82.7 / Avg: 82.83 / Max: 831. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-TRTX 3070RTX 309020406080100SE +/- 0.10, N = 389.883.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-TRTX 3070RTX 309020406080100Min: 89.6 / Avg: 89.8 / Max: 89.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NNRTX 3070RTX 30901224364860SE +/- 0.26, N = 353.152.41. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NNRTX 3070RTX 30901122334455Min: 52.7 / Avg: 53.1 / Max: 53.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NTRTX 3070RTX 30901224364860SE +/- 0.12, N = 353.652.01. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NTRTX 3070RTX 30901122334455Min: 53.4 / Avg: 53.57 / Max: 53.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TNRTX 3070RTX 30901326395265SE +/- 0.00, N = 358.256.11. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TNRTX 3070RTX 30901224364860Min: 58.2 / Avg: 58.2 / Max: 58.21. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TTRTX 3070RTX 30901326395265SE +/- 0.09, N = 356.454.01. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TTRTX 3070RTX 30901122334455Min: 56.3 / Avg: 56.43 / Max: 56.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sCOPYRTX 3070RTX 309080160240320400SE +/- 0.58, N = 32913641. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sCOPYRTX 3070RTX 309070140210280350Min: 290 / Avg: 291 / Max: 2921. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sAXPYRTX 3070RTX 3090110220330440550SE +/- 0.33, N = 33595011. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sAXPYRTX 3070RTX 309090180270360450Min: 358 / Avg: 358.67 / Max: 3591. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sDOTRTX 3070RTX 309080160240320400SE +/- 0.67, N = 33223511. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sDOTRTX 3070RTX 309060120180240300Min: 321 / Avg: 322.33 / Max: 3231. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPYRTX 3070RTX 3090130260390520650SE +/- 0.33, N = 33706071. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPYRTX 3070RTX 3090110220330440550Min: 369 / Avg: 369.67 / Max: 3701. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dAXPYRTX 3070RTX 3090160320480640800SE +/- 0.00, N = 33967211. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dAXPYRTX 3070RTX 3090130260390520650Min: 396 / Avg: 396 / Max: 3961. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOTRTX 3070RTX 3090140280420560700SE +/- 0.00, N = 33956631. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOTRTX 3070RTX 3090120240360480600Min: 395 / Avg: 395 / Max: 3951. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-NRTX 3070RTX 309050100150200250SE +/- 0.58, N = 32222361. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-NRTX 3070RTX 30904080120160200Min: 221 / Avg: 222 / Max: 2231. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-TRTX 3070RTX 309080160240320400SE +/- 0.67, N = 33333761. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-TRTX 3070RTX 309070140210280350Min: 332 / Avg: 333.33 / Max: 3341. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NNRTX 3070RTX 3090130260390520650SE +/- 1.33, N = 33416001. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NNRTX 3070RTX 3090110220330440550Min: 338 / Avg: 340.67 / Max: 3421. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NTRTX 3070RTX 3090130260390520650SE +/- 1.33, N = 33426021. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NTRTX 3070RTX 3090110220330440550Min: 339 / Avg: 341.67 / Max: 3431. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TNRTX 3070RTX 30901302603905206503375981. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

Implementation: NVIDIA CUDA GPU - Input: water_GMX50_bare

RTX 3070: ./gromacs: 5: /cuda-build/run-gromacs: not found

RTX 3090: ./gromacs: 5: /cuda-build/run-gromacs: not found

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 100

RTX 3070: @ 0x7f685edc135f google::LogMessageFatal::~LogMessageFatal()

RTX 3090: @ 0x7f89c1f1c35f google::LogMessageFatal::~LogMessageFatal()

Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 200

RTX 3070: @ 0x7f54a717435f google::LogMessageFatal::~LogMessageFatal()

RTX 3090: @ 0x7ff7048f035f google::LogMessageFatal::~LogMessageFatal()

Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 1000

RTX 3070: @ 0x7fe4f22eb35f google::LogMessageFatal::~LogMessageFatal()

RTX 3090: @ 0x7fbdcb2cd35f google::LogMessageFatal::~LogMessageFatal()

Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 100

RTX 3070: @ 0x7f9ebe69635f google::LogMessageFatal::~LogMessageFatal()

RTX 3090: @ 0x7fa38655235f google::LogMessageFatal::~LogMessageFatal()

Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 200

RTX 3070: @ 0x7f2b3682d35f google::LogMessageFatal::~LogMessageFatal()

RTX 3090: @ 0x7f750274235f google::LogMessageFatal::~LogMessageFatal()

Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 1000

RTX 3070: @ 0x7fc850ea035f google::LogMessageFatal::~LogMessageFatal()

RTX 3090: @ 0x7f16f6b1035f google::LogMessageFatal::~LogMessageFatal()

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: mobilenetRTX 3070RTX 30901.0082.0163.0244.0325.04SE +/- 0.01, N = 34.314.47MIN: 4.25 / MAX: 5.94MIN: 4.1 / MAX: 24.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mobilenetRTX 3070RTX 3090246810Min: 4.3 / Avg: 4.31 / Max: 4.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2RTX 3070RTX 30900.44550.8911.33651.7822.2275SE +/- 0.01, N = 31.911.98MIN: 1.88 / MAX: 3.42MIN: 1.84 / MAX: 7.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2RTX 3070RTX 3090246810Min: 1.9 / Avg: 1.91 / Max: 1.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3RTX 3070RTX 30900.51981.03961.55942.07922.599SE +/- 0.01, N = 32.142.31MIN: 2.11 / MAX: 3.93MIN: 2.09 / MAX: 11.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3RTX 3070RTX 3090246810Min: 2.13 / Avg: 2.14 / Max: 2.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: shufflenet-v2RTX 3070RTX 30900.39830.79661.19491.59321.9915SE +/- 0.01, N = 31.711.77MIN: 1.68 / MAX: 3.55MIN: 1.67 / MAX: 9.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: shufflenet-v2RTX 3070RTX 3090246810Min: 1.7 / Avg: 1.71 / Max: 1.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mnasnetRTX 3070RTX 30900.48150.9631.44451.9262.4075SE +/- 0.01, N = 32.012.14MIN: 1.98 / MAX: 4.82MIN: 1.94 / MAX: 8.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mnasnetRTX 3070RTX 3090246810Min: 2 / Avg: 2.01 / Max: 2.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: efficientnet-b0RTX 3070RTX 30900.75381.50762.26143.01523.769SE +/- 0.01, N = 33.173.34MIN: 3.14 / MAX: 5.06MIN: 3.09 / MAX: 9.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: efficientnet-b0RTX 3070RTX 3090246810Min: 3.15 / Avg: 3.17 / Max: 3.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: blazefaceRTX 3070RTX 30900.24080.48160.72240.96321.204SE +/- 0.00, N = 30.981.07MIN: 0.95 / MAX: 2.27MIN: 0.89 / MAX: 21.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: blazefaceRTX 3070RTX 3090246810Min: 0.97 / Avg: 0.98 / Max: 0.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: vgg16RTX 3070RTX 30901.22182.44363.66544.88726.109SE +/- 0.01, N = 35.434.35MIN: 5.38 / MAX: 9.58MIN: 4.02 / MAX: 18.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: vgg16RTX 3070RTX 3090246810Min: 5.41 / Avg: 5.43 / Max: 5.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet18RTX 3070RTX 30900.40730.81461.22191.62922.0365SE +/- 0.01, N = 31.681.66MIN: 1.66 / MAX: 1.97MIN: 1.53 / MAX: 9.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet18RTX 3070RTX 3090246810Min: 1.67 / Avg: 1.68 / Max: 1.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: alexnetRTX 3070RTX 30900.43880.87761.31641.75522.194SE +/- 0.01, N = 31.901.95MIN: 1.86 / MAX: 5.12MIN: 1.76 / MAX: 18.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: alexnetRTX 3070RTX 3090246810Min: 1.89 / Avg: 1.9 / Max: 1.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet50RTX 3070RTX 30900.84151.6832.52453.3664.2075SE +/- 0.01, N = 33.743.68MIN: 3.71 / MAX: 4.06MIN: 3.44 / MAX: 13.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet50RTX 3070RTX 3090246810Min: 3.73 / Avg: 3.74 / Max: 3.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: yolov4-tinyRTX 3070RTX 3090246810SE +/- 0.01, N = 36.577.20MIN: 6.33 / MAX: 6.98MIN: 6.44 / MAX: 31.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: yolov4-tinyRTX 3070RTX 30903691215Min: 6.56 / Avg: 6.57 / Max: 6.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: squeezenet_ssdRTX 3070RTX 30900.99681.99362.99043.98724.984SE +/- 0.13, N = 34.434.37MIN: 4.1 / MAX: 7.62MIN: 3.93 / MAX: 23.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: squeezenet_ssdRTX 3070RTX 3090246810Min: 4.18 / Avg: 4.43 / Max: 4.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: regnety_400mRTX 3070RTX 30900.57831.15661.73492.31322.8915SE +/- 0.01, N = 32.422.52MIN: 2.4 / MAX: 3.84MIN: 2.38 / MAX: 10.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: regnety_400mRTX 3070RTX 3090246810Min: 2.41 / Avg: 2.42 / Max: 2.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: googlenetRTX 3070RTX 30900.99231.98462.97693.96924.9615SE +/- 0.13, N = 24.134.41MIN: 3.77 / MAX: 13.51MIN: 3.6 / MAX: 14.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: googlenetRTX 3070RTX 3090246810Min: 4 / Avg: 4.13 / Max: 4.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

FP16: No - Mode: Training - Network: Mobilenet - Device: OpenCL

RTX 3070: Test failed to run.

RTX 3090: Test failed to run.

FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL

RTX 3070: Test failed to run.

RTX 3090: Test failed to run.

FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL

RTX 3070: Test failed to run.

RTX 3090: Test failed to run.

FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL

RTX 3070: Test failed to run.

RTX 3090: Test failed to run.

FP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL

RTX 3070: Test failed to run.

RTX 3090: Test failed to run.

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: BedroomRTX 3070RTX 3090510152025SE +/- 0.02, N = 312.9420.97
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: BedroomRTX 3070RTX 3090510152025Min: 12.9 / Avg: 12.94 / Max: 12.98

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: SupercarRTX 3070RTX 30901224364860SE +/- 0.04, N = 337.3253.36
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: SupercarRTX 3070RTX 30901122334455Min: 37.25 / Avg: 37.32 / Max: 37.36

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: CUDARTX 3070RTX 3090714212835SE +/- 0.04, N = 329.0018.32
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CUDARTX 3070RTX 3090612182430Min: 28.93 / Avg: 29 / Max: 29.08

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CUDARTX 3070RTX 309020406080100SE +/- 0.01, N = 376.0651.18
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CUDARTX 3070RTX 30901530456075Min: 76.03 / Avg: 76.06 / Max: 76.07

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CUDARTX 3070RTX 30901224364860SE +/- 0.04, N = 354.6934.65
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CUDARTX 3070RTX 30901122334455Min: 54.62 / Avg: 54.69 / Max: 54.75

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CUDARTX 3070RTX 3090110220330440550SE +/- 0.17, N = 3507.39373.32
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CUDARTX 3070RTX 309090180270360450Min: 507.06 / Avg: 507.39 / Max: 507.65

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: NVIDIA OptiXRTX 3070RTX 309048121620SE +/- 0.01, N = 315.829.52
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: NVIDIA OptiXRTX 3070RTX 309048121620Min: 15.79 / Avg: 15.82 / Max: 15.83

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: NVIDIA OptiXRTX 3070RTX 30901020304050SE +/- 0.02, N = 345.7728.66
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: NVIDIA OptiXRTX 3070RTX 3090918273645Min: 45.74 / Avg: 45.77 / Max: 45.8

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 3070RTX 3090816243240SE +/- 0.01, N = 333.3418.97
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 3070RTX 3090714212835Min: 33.33 / Avg: 33.34 / Max: 33.35

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.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TTRTX 30901302603905206506011. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL