nv-test-run

nvidia test run

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2107240-IB-NVTESTRUN71
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
nvidia test run
July 23 2021
  6 Hours, 55 Minutes
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):


nv-test-runOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 5900 12-Core @ 3.00GHz (12 Cores / 24 Threads)Alienware 0TYR0X (2.1.2 BIOS)AMD Starship/Matisse32GBKioxia KXG70PNV2T04 NVMe 2048GBNVIDIA GeForce RTX 3080 10GBNVIDIA Device 1aefLEN L24q-30Realtek Device 2600 + Intel Wi-Fi 6 AX200Ubuntu 20.045.8.0-63-generic (x86_64)GNOME Shell 3.36.9X Server 1.20.9NVIDIA 470.57.02OpenCL 3.0 CUDA 11.4.941.2.175GCC 9.3.0ext42560x1440ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenCLVulkanCompilerFile-SystemScreen ResolutionNv-test-run BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --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-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 ondemand (Boost: Enabled) - CPU Microcode: 0xa201009 - GPU Compute Cores: 8704- Python 3.8.10- 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

nv-test-runshoc: OpenCL - Max SP Flopsvkfft: blender: Barbershop - CUDAblender: Barbershop - NVIDIA OptiXluxcorerender: Danish Mood - GPUvkpeak: int16-vec4vkpeak: int16-scalarvkpeak: int32-vec4vkpeak: int32-scalarvkpeak: fp64-vec4vkpeak: fp64-scalarvkpeak: fp16-vec4vkpeak: fp16-scalarvkpeak: fp32-vec4vkpeak: fp32-scalarblender: Pabellon Barcelona - CUDAoctanebench: Total Scoreblender: Fishy Cat - NVIDIA OptiXluxcorerender: LuxCore Benchmark - GPUluxcorerender: DLSC - GPUfahbench: namd-cuda: ATPase Simulation - 327,506 Atomsblender: BMW27 - NVIDIA OptiXindigobench: OpenCL GPU - Bedroomluxcorerender: Orange Juice - GPUindigobench: OpenCL GPU - Supercarblender: Classroom - CUDAncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetblender: Pabellon Barcelona - NVIDIA OptiXblender: Fishy Cat - CUDAclpeak: Double-Precision Doubleblender: Classroom - NVIDIA OptiXrealsr-ncnn: 4x - Yesvkresample: 2x - Doubleviennacl: CPU BLAS - dGEMM-NTviennacl: CPU BLAS - dGEMM-TTviennacl: CPU BLAS - dGEMM-TNviennacl: CPU BLAS - dGEMM-NNviennacl: CPU BLAS - dGEMV-Tviennacl: CPU BLAS - dGEMV-Nviennacl: CPU BLAS - dDOTviennacl: CPU BLAS - dAXPYviennacl: CPU BLAS - dCOPYviennacl: CPU BLAS - sDOTviennacl: CPU BLAS - sAXPYviennacl: CPU BLAS - sCOPYblender: BMW27 - CUDAviennacl: OpenCL BLAS - dGEMM-TNviennacl: OpenCL BLAS - dGEMM-NTviennacl: OpenCL BLAS - dGEMM-NNviennacl: OpenCL BLAS - dGEMV-Tviennacl: OpenCL BLAS - dGEMV-Nviennacl: OpenCL BLAS - dDOTviennacl: OpenCL BLAS - dAXPYviennacl: OpenCL BLAS - dCOPYviennacl: OpenCL BLAS - sDOTviennacl: OpenCL BLAS - sAXPYviennacl: OpenCL BLAS - sCOPYshoc: OpenCL - Texture Read Bandwidthvkresample: 2x - Singleluxcorerender: Rainbow Colors and Prism - GPUhashcat: SHA-512realsr-ncnn: 4x - Nohashcat: SHA1hashcat: MD5rodinia: OpenCL Particle Filterhashcat: TrueCrypt RIPEMD160 + XTSbetsy: ETC2 RGB - Highestarrayfire: Conjugate Gradient OpenCLwaifu2x-ncnn: 2x - 3 - Yesbetsy: ETC1 - Highestcl-mem: Copycl-mem: Readcl-mem: Writeshoc: OpenCL - S3Dmandelgpu: GPUshoc: OpenCL - Bus Speed Readbackhashcat: 7-Zipshoc: OpenCL - GEMM SGEMM_Nclpeak: Integer Compute INTshoc: OpenCL - Triadshoc: OpenCL - FFT SPclpeak: Global Memory Bandwidthshoc: OpenCL - Bus Speed Downloadshoc: OpenCL - Reductionclpeak: Single-Precision Floatneatbench: GPUfinancebench: Black-Scholes OpenCLshoc: OpenCL - MD5 Hashnvidia test run33021.041236448.21375.956.4013785.1711203.8716945.4017022.36533.37532.8633156.8817093.1422559.7617147.74146.68566.50484825.898.259.49315.48640.1420114.3717.5089.0846.15061.4611.7416.9525.3825.3812.2915.5257.5915.351.946.024.254.674.614.6814.2852.4942.34538.3034.3633.781144.99140.042.042.840.383.676.344.934.322.914693.862.522.394964994983742405966285553714703532184.0011.27126.7323547666676.36318624600000545316666674.3567029334.5891.5763.5193.409354.4672.5648.7338.629413842119.713.52919551676265.6315263.5713.13791918.08662.2813.4448385.29029406.1930807.34636.7918OpenBenchmarking.org

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: Max SP Flopsnvidia test run7K14K21K28K35KSE +/- 280.66, N = 333021.01. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

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 1.1.1nvidia test run9K18K27K36K45KSE +/- 372.44, N = 9412361. (CXX) g++ options: -O3 -pthread

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: Barbershop - Compute: CUDAnvidia test run100200300400500SE +/- 0.12, N = 3448.21

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: NVIDIA OptiXnvidia test run80160240320400SE +/- 0.80, N = 3375.95

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: Danish Mood - Acceleration: GPUnvidia test run246810SE +/- 0.05, N = 156.40MIN: 1.46 / MAX: 8.47

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.orgGIOPS, More Is Bettervkpeak 20210424int16-vec4nvidia test run3K6K9K12K15KSE +/- 2.91, N = 313785.17

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-scalarnvidia test run2K4K6K8K10KSE +/- 3.20, N = 311203.87

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-vec4nvidia test run4K8K12K16K20KSE +/- 30.65, N = 316945.40

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-scalarnvidia test run4K8K12K16K20KSE +/- 33.97, N = 317022.36

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-vec4nvidia test run120240360480600SE +/- 1.30, N = 3533.37

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-scalarnvidia test run120240360480600SE +/- 0.56, N = 3532.86

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-vec4nvidia test run7K14K21K28K35KSE +/- 146.61, N = 333156.88

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-scalarnvidia test run4K8K12K16K20KSE +/- 45.31, N = 317093.14

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-vec4nvidia test run5K10K15K20K25KSE +/- 172.93, N = 322559.76

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-scalarnvidia test run4K8K12K16K20KSE +/- 118.61, N = 317147.74

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: Pabellon Barcelona - Compute: CUDAnvidia test run306090120150SE +/- 0.04, N = 3146.68

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 Scorenvidia test run120240360480600566.50

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: Fishy Cat - Compute: NVIDIA OptiXnvidia test run612182430SE +/- 2.94, N = 1525.89

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: LuxCore Benchmark - Acceleration: GPUnvidia test run246810SE +/- 0.04, N = 38.25MIN: 1.92 / MAX: 10.39

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: GPUnvidia test run3691215SE +/- 0.02, N = 39.49MIN: 9.15 / MAX: 9.75

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 2.3.2nvidia test run70140210280350SE +/- 0.17, N = 3315.49

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 Atomsnvidia test run0.0320.0640.0960.1280.16SE +/- 0.00134, N = 60.14201

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: NVIDIA OptiXnvidia test run48121620SE +/- 2.96, N = 1514.37

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: Bedroomnvidia test run48121620SE +/- 0.01, N = 317.51

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: Orange Juice - Acceleration: GPUnvidia test run3691215SE +/- 0.05, N = 39.08MIN: 7.22 / MAX: 11.54

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: Supercarnvidia test run1020304050SE +/- 0.02, N = 346.15

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: Classroom - Compute: CUDAnvidia test run1428425670SE +/- 0.05, N = 361.46

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 20210525Target: Vulkan GPU - Model: regnety_400mnvidia test run3691215SE +/- 0.13, N = 311.74MIN: 11.16 / MAX: 22.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: squeezenet_ssdnvidia test run48121620SE +/- 0.10, N = 316.95MIN: 16.23 / MAX: 18.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: yolov4-tinynvidia test run612182430SE +/- 0.80, N = 325.38MIN: 23.07 / MAX: 36.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: resnet50nvidia test run612182430SE +/- 0.55, N = 325.38MIN: 23.77 / MAX: 36.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: alexnetnvidia test run3691215SE +/- 0.05, N = 312.29MIN: 11.92 / MAX: 12.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: resnet18nvidia test run48121620SE +/- 0.10, N = 315.52MIN: 14.96 / MAX: 22.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: vgg16nvidia test run1326395265SE +/- 0.20, N = 357.59MIN: 56.31 / MAX: 72.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: googlenetnvidia test run48121620SE +/- 0.25, N = 315.35MIN: 13.64 / MAX: 33.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: blazefacenvidia test run0.43650.8731.30951.7462.1825SE +/- 0.03, N = 31.94MIN: 1.83 / MAX: 2.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: efficientnet-b0nvidia test run246810SE +/- 0.03, N = 36.02MIN: 5.85 / MAX: 21.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: mnasnetnvidia test run0.95631.91262.86893.82524.7815SE +/- 0.01, N = 34.25MIN: 4.14 / MAX: 5.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: shufflenet-v2nvidia test run1.05082.10163.15244.20325.254SE +/- 0.02, N = 34.67MIN: 4.51 / MAX: 5.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3nvidia test run1.03732.07463.11194.14925.1865SE +/- 0.04, N = 34.61MIN: 4.45 / MAX: 14.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2nvidia test run1.0532.1063.1594.2125.265SE +/- 0.02, N = 34.68MIN: 4.55 / MAX: 6.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: mobilenetnvidia test run48121620SE +/- 0.14, N = 314.28MIN: 13.73 / MAX: 32.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

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: Pabellon Barcelona - Compute: NVIDIA OptiXnvidia test run1224364860SE +/- 0.04, N = 352.49

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CUDAnvidia test run1020304050SE +/- 0.01, N = 342.34

clpeak

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

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision Doublenvidia test run120240360480600SE +/- 1.33, N = 3538.301. (CXX) g++ options: -O3 -rdynamic -lOpenCL

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: Classroom - Compute: NVIDIA OptiXnvidia test run816243240SE +/- 0.03, N = 334.36

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: Yesnvidia test run816243240SE +/- 0.05, N = 333.78

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: Doublenvidia test run306090120150SE +/- 0.03, N = 3144.991. (CXX) g++ options: -O3 -pthread

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: CPU BLAS - dGEMM-NTnvidia test run918273645SE +/- 0.10, N = 240.01. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TTnvidia test run1020304050SE +/- 0.10, N = 342.01. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TNnvidia test run1020304050SE +/- 0.12, N = 342.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NNnvidia test run918273645SE +/- 0.25, N = 340.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-Tnvidia test run20406080100SE +/- 0.20, N = 383.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-Nnvidia test run20406080100SE +/- 1.03, N = 376.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOTnvidia test run1020304050SE +/- 0.62, N = 344.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPYnvidia test run816243240SE +/- 0.03, N = 334.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPYnvidia test run510152025SE +/- 0.03, N = 322.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOTnvidia test run3060901201501461. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPYnvidia test run20406080100SE +/- 0.33, N = 393.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sCOPYnvidia test run1428425670SE +/- 0.25, N = 362.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

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: CUDAnvidia test run510152025SE +/- 0.00, N = 322.39

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-TNnvidia test run110220330440550SE +/- 1.33, N = 34961. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NTnvidia test run110220330440550SE +/- 1.33, N = 34991. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NNnvidia test run110220330440550SE +/- 1.33, N = 34981. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-Tnvidia test run801602403204003741. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-Nnvidia test run501001502002502401. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOTnvidia test run130260390520650SE +/- 1.15, N = 35961. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dAXPYnvidia test run1402804205607006281. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPYnvidia test run120240360480600SE +/- 0.33, N = 35551. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sDOTnvidia test run80160240320400SE +/- 0.58, N = 33711. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sAXPYnvidia test run100200300400500SE +/- 0.58, N = 34701. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sCOPYnvidia test run80160240320400SE +/- 0.67, N = 33531. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

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.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read Bandwidthnvidia test run5001000150020002500SE +/- 1.12, N = 32184.001. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

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: Singlenvidia test run3691215SE +/- 0.02, N = 311.271. (CXX) g++ options: -O3 -pthread

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: Rainbow Colors and Prism - Acceleration: GPUnvidia test run612182430SE +/- 0.37, N = 326.73MIN: 24.94 / MAX: 28.91

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: SHA-512nvidia test run500M1000M1500M2000M2500MSE +/- 3777712.42, N = 32354766667

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: Nonvidia test run246810SE +/- 0.024, N = 36.363

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: SHA1nvidia test run4000M8000M12000M16000M20000MSE +/- 14437566.74, N = 318624600000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: MD5nvidia test run12000M24000M36000M48000M60000MSE +/- 85507199.18, N = 354531666667

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 Filternvidia test run0.98011.96022.94033.92044.9005SE +/- 0.053, N = 44.3561. (CXX) g++ options: -O2 -lOpenCL

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: TrueCrypt RIPEMD160 + XTSnvidia test run150K300K450K600K750KSE +/- 1089.85, N = 3702933

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC2 RGB - Quality: Highestnvidia test run1.03252.0653.09754.135.1625SE +/- 0.026, N = 34.5891. (CXX) g++ options: -O3 -O2 -lpthread -ldl

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 OpenCLnvidia test run0.35460.70921.06381.41841.773SE +/- 0.004, N = 31.5761. (CXX) g++ options: -rdynamic

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: Yesnvidia test run0.79181.58362.37543.16723.959SE +/- 0.003, N = 33.519

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC1 - Quality: Highestnvidia test run0.7671.5342.3013.0683.835SE +/- 0.007, N = 33.4091. (CXX) g++ options: -O3 -O2 -lpthread -ldl

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: Copynvidia test run80160240320400SE +/- 0.12, N = 3354.41. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Readnvidia test run150300450600750SE +/- 0.58, N = 3672.51. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Writenvidia test run140280420560700SE +/- 0.54, N = 3648.71. (CC) gcc options: -O2 -flto -lOpenCL

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: S3Dnvidia test run70140210280350SE +/- 0.09, N = 3338.631. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

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: GPUnvidia test run90M180M270M360M450MSE +/- 2312617.08, N = 3413842119.71. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

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.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed Readbacknvidia test run3691215SE +/- 0.00, N = 313.531. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

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: 7-Zipnvidia test run200K400K600K800K1000KSE +/- 240.37, N = 3955167

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: GEMM SGEMM_Nnvidia test run13002600390052006500SE +/- 21.28, N = 36265.631. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

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 INTnvidia test run3K6K9K12K15KSE +/- 95.64, N = 315263.571. (CXX) g++ options: -O3 -rdynamic -lOpenCL

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.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Triadnvidia test run3691215SE +/- 0.00, N = 313.141. (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 SPnvidia test run400800120016002000SE +/- 1.16, N = 31918.081. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

clpeak

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

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory Bandwidthnvidia test run140280420560700SE +/- 0.09, N = 3662.281. (CXX) g++ options: -O3 -rdynamic -lOpenCL

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.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed Downloadnvidia test run3691215SE +/- 0.00, N = 313.441. (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: Reductionnvidia test run80160240320400SE +/- 0.12, N = 3385.291. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

clpeak

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

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision Floatnvidia test run6K12K18K24K30KSE +/- 64.01, N = 329406.191. (CXX) g++ options: -O3 -rdynamic -lOpenCL

NeatBench

NeatBench is a benchmark of the cross-platform Neat Video software on the CPU and optional GPU (OpenCL / CUDA) support. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: GPUnvidia test run70014002100280035003080

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 OpenCLnvidia test run246810SE +/- 0.028, N = 37.3461. (CXX) g++ options: -O3 -march=native -fopenmp

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.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 Hashnvidia test run816243240SE +/- 0.09, N = 336.791. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

103 Results Shown

SHOC Scalable HeterOgeneous Computing
VkFFT
Blender:
  Barbershop - CUDA
  Barbershop - NVIDIA OptiX
LuxCoreRender
vkpeak:
  int16-vec4
  int16-scalar
  int32-vec4
  int32-scalar
  fp64-vec4
  fp64-scalar
  fp16-vec4
  fp16-scalar
  fp32-vec4
  fp32-scalar
Blender
OctaneBench
Blender
LuxCoreRender:
  LuxCore Benchmark - GPU
  DLSC - GPU
FAHBench
NAMD CUDA
Blender
IndigoBench
LuxCoreRender
IndigoBench
Blender
NCNN:
  Vulkan GPU - regnety_400m
  Vulkan GPU - squeezenet_ssd
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - resnet50
  Vulkan GPU - alexnet
  Vulkan GPU - resnet18
  Vulkan GPU - vgg16
  Vulkan GPU - googlenet
  Vulkan GPU - blazeface
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - mnasnet
  Vulkan GPU - shufflenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU - mobilenet
Blender:
  Pabellon Barcelona - NVIDIA OptiX
  Fishy Cat - CUDA
clpeak
Blender
RealSR-NCNN
VkResample
ViennaCL:
  CPU BLAS - dGEMM-NT
  CPU BLAS - dGEMM-TT
  CPU BLAS - dGEMM-TN
  CPU BLAS - dGEMM-NN
  CPU BLAS - dGEMV-T
  CPU BLAS - dGEMV-N
  CPU BLAS - dDOT
  CPU BLAS - dAXPY
  CPU BLAS - dCOPY
  CPU BLAS - sDOT
  CPU BLAS - sAXPY
  CPU BLAS - sCOPY
Blender
ViennaCL:
  OpenCL BLAS - dGEMM-TN
  OpenCL BLAS - dGEMM-NT
  OpenCL BLAS - dGEMM-NN
  OpenCL BLAS - dGEMV-T
  OpenCL BLAS - dGEMV-N
  OpenCL BLAS - dDOT
  OpenCL BLAS - dAXPY
  OpenCL BLAS - dCOPY
  OpenCL BLAS - sDOT
  OpenCL BLAS - sAXPY
  OpenCL BLAS - sCOPY
SHOC Scalable HeterOgeneous Computing
VkResample
LuxCoreRender
Hashcat
RealSR-NCNN
Hashcat:
  SHA1
  MD5
Rodinia
Hashcat
Betsy GPU Compressor
ArrayFire
Waifu2x-NCNN Vulkan
Betsy GPU Compressor
cl-mem:
  Copy
  Read
  Write
SHOC Scalable HeterOgeneous Computing
MandelGPU
SHOC Scalable HeterOgeneous Computing
Hashcat
SHOC Scalable HeterOgeneous Computing
clpeak
SHOC Scalable HeterOgeneous Computing:
  OpenCL - Triad
  OpenCL - FFT SP
clpeak
SHOC Scalable HeterOgeneous Computing:
  OpenCL - Bus Speed Download
  OpenCL - Reduction
clpeak
NeatBench
FinanceBench
SHOC Scalable HeterOgeneous Computing