NVIDIA GPU Compute

Benchmarks for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2208108-PTS-AMDGPUCO11
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
Show Result Confidence Charts

Limit displaying results to tests within:

CPU Massive 3 Tests
Creator Workloads 3 Tests
HPC - High Performance Computing 3 Tests
Machine Learning 2 Tests
Multi-Core 3 Tests
NVIDIA GPU Compute 15 Tests
OpenCL 8 Tests
Renderers 2 Tests
Vulkan Compute 3 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
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
RTX 3060
July 16 2022
  2 Hours, 44 Minutes
RTX 3060 Ti
July 16 2022
  2 Hours, 32 Minutes
RTX 3070
July 16 2022
  2 Hours, 34 Minutes
RTX 3070 Ti
July 17 2022
  2 Hours, 39 Minutes
RTX 3080
July 15 2022
  2 Hours, 28 Minutes
RTX 3080 Ti
July 16 2022
  2 Hours, 28 Minutes
RTX 3090
July 10 2022
  2 Hours, 35 Minutes
Invert Hiding All Results Option
  2 Hours, 34 Minutes

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


NVIDIA GPU ComputeOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 7 5800X3D 8-Core @ 3.40GHz (8 Cores / 16 Threads)ASUS ROG CROSSHAIR VIII HERO (4201 BIOS)AMD Starship/Matisse32GB1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB Samsung SSD 980 PRO 2TBeVGA NVIDIA GeForce RTX 3060 12GBNVIDIA GeForce RTX 3060 Ti 8GBNVIDIA GeForce RTX 3070 8GBNVIDIA GeForce RTX 3070 Ti 8GBNVIDIA GeForce RTX 3080 10GBNVIDIA GeForce RTX 3080 Ti 12GBNVIDIA GeForce RTX 3090 24GBNVIDIA GA106 HD AudioNVIDIA GA104 HD AudioNVIDIA GA102 HD AudioASUS MG28URealtek RTL8125 2.5GbE + Intel I211Ubuntu 22.045.18.0-051800-generic (x86_64)GNOME Shell 42.2X Server 1.21.1.3NVIDIA 515.49.064.6.0OpenCL 3.0 CUDA 11.7.991.2.204GCC 11.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudiosMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionNVIDIA GPU Compute 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-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/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: 0xa20120a- RTX 3060: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 94.06.14.40.46- RTX 3060 Ti: BAR1 / Visible vRAM Size: 8192 MiB - vBIOS Version: 94.04.25.00.2c- RTX 3070: BAR1 / Visible vRAM Size: 8192 MiB - vBIOS Version: 94.04.25.00.2b- RTX 3070 Ti: BAR1 / Visible vRAM Size: 8192 MiB - vBIOS Version: 94.04.5b.00.02- RTX 3080: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 94.02.20.00.07- RTX 3080 Ti: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 94.02.71.00.01- RTX 3090: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 94.02.27.00.02- RTX 3060: GPU Compute Cores: 3584- RTX 3060 Ti: GPU Compute Cores: 4864- RTX 3070: GPU Compute Cores: 5888- RTX 3070 Ti: GPU Compute Cores: 6144- RTX 3080: GPU Compute Cores: 8704- RTX 3080 Ti: GPU Compute Cores: 10240- RTX 3090: GPU Compute Cores: 10496- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

RTX 3060RTX 3060 TiRTX 3070RTX 3070 TiRTX 3080RTX 3080 TiRTX 3090Result OverviewPhoronix Test Suite100%146%192%238%284%HashcatSHOC Scalable HeterOgeneous ComputingRodiniaVkResampleLuxCoreRenderLeelaChessZeroIndigoBenchFinanceBenchMandelGPURealSR-NCNNcl-memViennaCLclpeakFAHBenchWaifu2x-NCNN VulkanDarktableJuliaGPU

RTX 3060RTX 3060 TiRTX 3070RTX 3070 TiRTX 3080RTX 3080 TiRTX 3090Per Watt Result OverviewPhoronix Test Suite100%126%153%179%205%JuliaGPUclpeakFAHBenchSHOC Scalable HeterOgeneous ComputingMandelGPUHashcatIndigoBenchLeelaChessZerocl-memLuxCoreRenderP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.M

NVIDIA GPU Computecl-mem: Copycl-mem: Readcl-mem: Writeviennacl: OpenCL BLAS - sCOPYviennacl: OpenCL BLAS - sAXPYviennacl: OpenCL BLAS - sDOTviennacl: OpenCL BLAS - dCOPYviennacl: OpenCL BLAS - dAXPYviennacl: OpenCL BLAS - dDOTclpeak: Global Memory Bandwidthclpeak: Transfer Bandwidth enqueueReadBuffershoc: OpenCL - FFT SPshoc: OpenCL - Max SP Flopsclpeak: Single-Precision Floatclpeak: Double-Precision Doubleshoc: OpenCL - S3Dshoc: OpenCL - GEMM SGEMM_Nviennacl: OpenCL BLAS - dGEMM-NNviennacl: OpenCL BLAS - dGEMM-NTviennacl: OpenCL BLAS - dGEMM-TNshoc: OpenCL - MD5 Hashclpeak: Integer Compute INThashcat: MD5hashcat: SHA1hashcat: 7-Ziphashcat: SHA-512hashcat: TrueCrypt RIPEMD160 + XTSindigobench: OpenCL GPU - Bedroomindigobench: OpenCL GPU - Supercarluxcorerender: Danish Mood - GPUluxcorerender: DLSC - GPUluxcorerender: Orange Juice - GPUluxcorerender: LuxCore Benchmark - GPUluxcorerender: Rainbow Colors and Prism - GPUlczero: OpenCLfahbench: juliagpu: GPUmandelgpu: GPUvkresample: 2x - Singlefinancebench: Monte-Carlo OpenCLfinancebench: Black-Scholes OpenCLrealsr-ncnn: 4x - Norealsr-ncnn: 4x - Yeswaifu2x-ncnn: 2x - 3 - Yesrodinia: OpenCL Particle Filterdarktable: Boat - OpenCLdarktable: Server Rack - OpenCLdarktable: Server Room - OpenCLclpeak: Kernel LatencyRTX 3060RTX 3060 TiRTX 3070RTX 3070 TiRTX 3080RTX 3080 TiRTX 3090270.1317.8302.7276306293315327329315.3913.29758.84413566.712581.21213.28172.6722768.2220420320415.10306368.802485206666777359000004113339932000002932578.52325.9472.974.304.913.7313.6428640186.0700305403296.1212133611.623.164619.04116816.22273410.77369.0335.0259.5321.9980.1410.9004.65296.9392.7383.6288359327351399397389.1013.32961.90519429.816000.79304.06211.7253435.0429229429121.52908369.373524415714310974150000573133141143333341630011.50534.0444.055.756.204.9518.2842098243.2202331465943.8285236027.417.680463.72216312.8788.62051.8194.3246.9521.6720.1410.8134.72294.8392.9379.7284359322368395398389.3713.301133.3523184.420075.82361.50218.0943796.8934134234025.294610228.604134693333312949050000664633166298333349167512.95237.3324.816.636.965.7320.3845516272.2660343766836.7324407884.817.575463.69733210.4368.08147.6274.1645.8861.5820.1360.7944.72337.1538.5513.9335436363464528519529.3213.651291.1823323.621511.25370.16285.2234711.3534634734526.199910922.684252823333313217233333703100169718333350618813.76838.9924.897.007.146.0521.1251302271.5871346928151.5329213346.413.578472.5978349.7597.33141.6683.8565.8481.4340.1330.7654.65354.7672.6642.9358474371554629602662.0013.331761.8934065.329623.78545.92338.1976270.9650150350037.522815428.956016518333318978266667963844242185000070891317.67946.6756.679.529.008.3726.6463379328.3813362268066.4420816923.111.265388.3474997.2806.26133.0283.4634.2691.3000.1320.7434.71355.0795.8736.9360492361594705647794.0413.382014.7837916.633708.85622.73420.2278056.3156556656242.053517388.0467455883333213397833331069067272323333379627520.25851.8377.9711.0010.069.7031.2767451339.6118366866427.6449383091.89.561323.9128376.5035.89330.0853.3943.7951.2340.1320.7274.76364.2817.7745.3366499371607723656812.3413.522101.4539615.235141.28656.12429.7588152.5560160459944.223318125.5271315400000225554333331123025287433333382017120.95653.3998.1211.4410.4310.1530.7868676351.7042368101296.7470569461.29.310321.8498386.1975.74828.8223.3353.6551.2060.1300.7194.75OpenBenchmarking.org

GPU Temperature Monitor

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30601530456075Min: 32 / Avg: 56.51 / Max: 69Min: 29 / Avg: 61.78 / Max: 77Min: 32 / Avg: 61.17 / Max: 76Min: 28 / Avg: 61.27 / Max: 80Min: 31 / Avg: 54.44 / Max: 73Min: 29 / Avg: 53.05 / Max: 71Min: 28 / Avg: 53.35 / Max: 67

GPU Power Consumption Monitor

OpenBenchmarking.orgWattsGPU Power Consumption MonitorPhoronix Test Suite System MonitoringRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 306060120180240300Min: 6.9 / Avg: 185.89 / Max: 349.02Min: 14.36 / Avg: 192.82 / Max: 350.38Min: 6.09 / Avg: 166.07 / Max: 321.26Min: 13.29 / Avg: 133.59 / Max: 289.89Min: 16.13 / Avg: 98.45 / Max: 220.01Min: 9.87 / Avg: 91.95 / Max: 199.9Min: 11.81 / Avg: 72.58 / Max: 170.09

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 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 306080160240320400SE +/- 0.06, N = 10SE +/- 0.08, N = 9SE +/- 0.15, N = 9SE +/- 0.15, N = 9SE +/- 0.11, N = 8SE +/- 0.25, N = 8SE +/- 0.09, N = 7364.2355.0354.7337.1294.8296.9270.11. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30602004006008001000SE +/- 0.15, N = 10SE +/- 0.13, N = 9SE +/- 0.12, N = 9SE +/- 0.07, N = 9SE +/- 0.12, N = 8SE +/- 0.15, N = 8SE +/- 0.05, N = 7817.7795.8672.6538.5392.9392.7317.81. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060160320480640800SE +/- 0.24, N = 10SE +/- 0.29, N = 9SE +/- 0.17, N = 9SE +/- 0.14, N = 9SE +/- 0.08, N = 8SE +/- 0.03, N = 8SE +/- 0.04, N = 7745.3736.9642.9513.9379.7383.6302.71. (CC) gcc options: -O2 -flto -lOpenCL

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: OpenCL BLAS - sCOPYRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 306080160240320400SE +/- 0.00, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 33663603583352842922761. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sAXPYRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060110220330440550SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34994924744363593593061. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sDOTRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 306080160240320400SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 33713623713633263272931. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPYRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060130260390520650SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 36075945544793733633151. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dAXPYRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060160320480640800SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 37237056295293953993271. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOTRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060140280420560700SE +/- 0.00, N = 3SE +/- 1.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.50, N = 2SE +/- 0.00, N = 36566476025234013993291. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

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 BandwidthRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30602004006008001000SE +/- 0.82, N = 14SE +/- 0.40, N = 13SE +/- 0.20, N = 15SE +/- 0.01, N = 13SE +/- 0.14, N = 15SE +/- 0.01, N = 13SE +/- 0.03, N = 15812.34794.04662.00529.32389.37389.10315.391. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueReadBufferRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 306048121620SE +/- 0.14, N = 15SE +/- 0.13, N = 6SE +/- 0.05, N = 4SE +/- 0.11, N = 15SE +/- 0.07, N = 6SE +/- 0.12, N = 7SE +/- 0.12, N = 413.5213.3813.3313.6513.3013.3213.291. (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.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30605001000150020002500SE +/- 0.14, N = 13SE +/- 0.11, N = 13SE +/- 0.11, N = 13SE +/- 0.04, N = 13SE +/- 0.83, N = 13SE +/- 0.04, N = 12SE +/- 0.18, N = 122101.452014.781761.891291.181133.35961.91758.841. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP FlopsRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30608K16K24K32K40KSE +/- 136.53, N = 3SE +/- 191.65, N = 3SE +/- 200.43, N = 3SE +/- 61.13, N = 3SE +/- 31.48, N = 3SE +/- 26.67, N = 3SE +/- 30.73, N = 339615.237916.634065.323323.623184.419429.813566.71. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -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 FloatRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30608K16K24K32K40KSE +/- 38.81, N = 14SE +/- 28.97, N = 14SE +/- 78.19, N = 13SE +/- 12.39, N = 15SE +/- 13.72, N = 15SE +/- 12.46, N = 14SE +/- 9.33, N = 1435141.2833708.8529623.7821511.2520075.8216000.7912581.211. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060140280420560700SE +/- 1.60, N = 3SE +/- 2.99, N = 3SE +/- 0.35, N = 3SE +/- 0.25, N = 3SE +/- 0.77, N = 3SE +/- 0.39, N = 3SE +/- 0.67, N = 3656.12622.73545.92370.16361.50304.06213.281. (CXX) g++ options: -O3 -rdynamic -lOpenCL

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3DRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30602468105.8535.4045.3774.9566.5326.1005.437

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3DRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 306090180270360450SE +/- 0.20, N = 12SE +/- 0.11, N = 13SE +/- 0.20, N = 13SE +/- 0.13, N = 13SE +/- 0.10, N = 13SE +/- 0.04, N = 13SE +/- 0.03, N = 13429.76420.23338.20285.22218.09211.73172.671. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30602K4K6K8K10KSE +/- 21.61, N = 12SE +/- 41.59, N = 12SE +/- 13.25, N = 11SE +/- 8.40, N = 10SE +/- 16.06, N = 10SE +/- 4.08, N = 10SE +/- 5.08, N = 98152.558056.316270.964711.353796.893435.042768.221. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

ViennaCL

OpenBenchmarking.orgGFLOPs/s Per Watt, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TNRTX 3080 TiRTX 3070 TiRTX 3070RTX 3060 TiRTX 30600.65841.31681.97522.63363.2922.5312.2382.9262.6522.267

OpenBenchmarking.orgGFLOPs/s Per Watt, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NTRTX 3070 TiRTX 30600.50921.01841.52762.03682.5462.2052.263

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NNRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060130260390520650SE +/- 1.67, N = 3SE +/- 1.53, N = 3SE +/- 1.33, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 36015655013463412922041. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NTRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060130260390520650SE +/- 1.33, N = 3SE +/- 1.53, N = 3SE +/- 1.53, N = 3SE +/- 0.00, N = 2SE +/- 1.00, N = 2SE +/- 0.50, N = 26045665033473422942031. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TNRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060130260390520650SE +/- 1.67, N = 3SE +/- 1.33, N = 3SE +/- 1.67, N = 3SE +/- 0.50, N = 2SE +/- 0.50, N = 2SE +/- 0.00, N = 2SE +/- 0.50, N = 25995625003453402912041. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgGHash/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30600.11090.22180.33270.44360.55450.4930.4370.4520.3410.4800.3920.300

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30601020304050SE +/- 0.05, N = 14SE +/- 0.04, N = 14SE +/- 0.03, N = 14SE +/- 0.01, N = 15SE +/- 0.01, N = 13SE +/- 0.01, N = 13SE +/- 0.01, N = 1244.2242.0537.5226.2025.2921.5315.101. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -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 INTRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30604K8K12K16K20KSE +/- 113.39, N = 12SE +/- 122.95, N = 12SE +/- 110.93, N = 15SE +/- 41.03, N = 13SE +/- 42.79, N = 13SE +/- 79.68, N = 15SE +/- 13.59, N = 1318125.5217388.0415428.9510922.6810228.608369.376368.801. (CXX) g++ options: -O3 -rdynamic -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 6.2.4Benchmark: MD5RTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 306015000M30000M45000M60000M75000MSE +/- 40483041.72, N = 6SE +/- 75640859.40, N = 6SE +/- 64657159.52, N = 6SE +/- 33659002.43, N = 6SE +/- 35442607.75, N = 6SE +/- 28489169.68, N = 7SE +/- 13467161.71, N = 671315400000674558833336016518333342528233333413469333333524415714324852066667

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.2.4Benchmark: SHA-512RTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30603M6M9M12M15M13874527.6312722045.4112742852.9710557672.6013463043.2712430572.2212255770.73

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.2.4Benchmark: TrueCrypt RIPEMD160 + XTSRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060120024003600480060005262.534901.785033.714286.215625.775077.014163.81

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA1RTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30605000M10000M15000M20000M25000MSE +/- 15969338.68, N = 6SE +/- 29607931.56, N = 6SE +/- 11254589.19, N = 6SE +/- 18212096.10, N = 6SE +/- 7193225.98, N = 6SE +/- 11825192.04, N = 6SE +/- 8981573.73, N = 62255543333321339783333189782666671321723333312949050000109741500007735900000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: 7-ZipRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060200K400K600K800K1000KSE +/- 480.98, N = 8SE +/- 463.08, N = 9SE +/- 2098.29, N = 9SE +/- 1169.52, N = 9SE +/- 294.39, N = 9SE +/- 923.46, N = 9SE +/- 486.77, N = 911230251069067963844703100664633573133411333

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA-512RTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060600M1200M1800M2400M3000MSE +/- 2053885.21, N = 6SE +/- 3496823.96, N = 6SE +/- 2677156.45, N = 6SE +/- 2413906.47, N = 6SE +/- 3141169.28, N = 6SE +/- 704114.89, N = 6SE +/- 493288.29, N = 6287433333327232333332421850000169718333316629833331411433333993200000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: TrueCrypt RIPEMD160 + XTSRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060200K400K600K800K1000KSE +/- 2556.01, N = 7SE +/- 2462.70, N = 8SE +/- 722.70, N = 8SE +/- 982.06, N = 8SE +/- 2213.90, N = 8SE +/- 1561.02, N = 8SE +/- 2490.54, N = 7820171796275708913506188491675416300293257

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 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060510152025SE +/- 0.033, N = 3SE +/- 0.042, N = 3SE +/- 0.019, N = 3SE +/- 0.009, N = 3SE +/- 0.027, N = 3SE +/- 0.014, N = 3SE +/- 0.010, N = 320.95620.25817.67913.76812.95211.5058.523

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: SupercarRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30601224364860SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 353.4051.8446.6838.9937.3334.0425.95

LuxCoreRender

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: GPURTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30600.01170.02340.03510.04680.05850.0520.0360.0360.0360.0430.0410.041

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Danish Mood - Acceleration: GPURTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060246810SE +/- 0.08, N = 6SE +/- 0.08, N = 3SE +/- 0.08, N = 4SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 48.127.976.674.894.814.052.97MIN: 1.69 / MAX: 10.34MIN: 1.8 / MAX: 10.01MIN: 1.29 / MAX: 8.52MIN: 1.07 / MAX: 6.21MIN: 1.12 / MAX: 6.01MIN: 1.18 / MAX: 5.06MIN: 0.94 / MAX: 3.68

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: GPURTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30600.01080.02160.03240.04320.0540.0360.0340.0360.0380.0450.0440.048

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: GPURTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30600.01190.02380.03570.04760.05950.0530.0360.0370.0360.0430.0400.040

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: GPURTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30600.03870.07740.11610.15480.19350.1440.1430.1430.1360.1720.1640.150

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: GPURTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30603691215SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 311.4411.009.527.006.635.754.30MIN: 9.35 / MAX: 11.78MIN: 10.28 / MAX: 11.23MIN: 9.11 / MAX: 9.69MIN: 6.86 / MAX: 7.14MIN: 6.25 / MAX: 6.91MIN: 5.62 / MAX: 5.95MIN: 4.18 / MAX: 4.53

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: GPURTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30603691215SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 310.4310.069.007.146.966.204.91MIN: 8.51 / MAX: 13.71MIN: 8.14 / MAX: 13.08MIN: 7.24 / MAX: 11.5MIN: 5.74 / MAX: 8.73MIN: 5.61 / MAX: 8.4MIN: 5.02 / MAX: 7.26MIN: 3.98 / MAX: 5.9

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: GPURTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30603691215SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 310.159.708.376.055.734.953.73MIN: 2.67 / MAX: 12.58MIN: 2.67 / MAX: 12.01MIN: 2.34 / MAX: 10.37MIN: 1.49 / MAX: 7.45MIN: 1.49 / MAX: 7.09MIN: 1.35 / MAX: 6.1MIN: 1.09 / MAX: 4.57

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: GPURTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060714212835SE +/- 0.16, N = 6SE +/- 0.18, N = 6SE +/- 0.14, N = 6SE +/- 0.08, N = 5SE +/- 0.20, N = 6SE +/- 0.05, N = 5SE +/- 0.08, N = 430.7831.2726.6421.1220.3818.2813.64MIN: 28.56 / MAX: 34.37MIN: 28.18 / MAX: 33.72MIN: 24.31 / MAX: 29.16MIN: 19.82 / MAX: 22.81MIN: 19.05 / MAX: 21.89MIN: 16.54 / MAX: 19.47MIN: 12 / MAX: 14.49

LeelaChessZero

OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterLeelaChessZero 0.28Backend: OpenCLRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 306050100150200250215.60202.15207.03189.58216.00219.43177.56

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: OpenCLRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 306015K30K45K60K75KSE +/- 461.39, N = 3SE +/- 567.42, N = 3SE +/- 173.33, N = 3SE +/- 245.06, N = 3SE +/- 346.36, N = 3SE +/- 504.73, N = 3SE +/- 134.62, N = 3686766745163379513024551642098286401. (CXX) g++ options: -flto -pthread

FAHBench

OpenBenchmarking.orgNs Per Day Per Watt, More Is BetterFAHBench 2.3.2RTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30600.51571.03141.54712.06282.57851.6741.5971.7461.7592.2922.2012.160

OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.2RTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 306080160240320400SE +/- 0.12, N = 3SE +/- 0.35, N = 3SE +/- 0.37, N = 3SE +/- 0.26, N = 3SE +/- 0.24, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3351.70339.61328.38271.59272.27243.22186.07

JuliaGPU

OpenBenchmarking.orgSamples/sec Per Watt, More Is BetterJuliaGPU 1.2pts1OpenCL Device: GPURTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30601.3M2.6M3.9M5.2M6.5M2948468.292903325.373336760.723761063.555540854.745296534.305955344.42

OpenBenchmarking.orgSamples/sec, More Is BetterJuliaGPU 1.2pts1OpenCL Device: GPURTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 306080M160M240M320M400MSE +/- 974048.68, N = 8SE +/- 1031833.35, N = 8SE +/- 1966974.36, N = 8SE +/- 1517808.00, N = 7SE +/- 948671.39, N = 7SE +/- 1475666.08, N = 7SE +/- 727588.65, N = 7368101296.7366866427.6362268066.4346928151.5343766836.7331465943.8305403296.11. (CC) gcc options: -O3 -march=native -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL -lm

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: GPURTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060100M200M300M400M500MSE +/- 1125013.79, N = 10SE +/- 735254.80, N = 10SE +/- 443784.10, N = 10SE +/- 303349.87, N = 9SE +/- 617743.30, N = 9SE +/- 409555.49, N = 8SE +/- 316579.92, N = 7470569461.2449383091.8420816923.1329213346.4324407884.8285236027.4212133611.61. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

RealSR-NCNN

MinAvgMaxRTX 309033.040.748.0RTX 3080 Ti35.044.653.0RTX 308035.045.054.0RTX 3070 Ti34.049.963.0RTX 307040.051.360.0RTX 3060 Ti34.047.057.0RTX 306035.051.460.0OpenBenchmarking.orgCelsius, Fewer Is BetterRealSR-NCNN 20200818GPU Temperature Monitor20406080100

MinAvgMaxRTX 309037.052.660.0RTX 3080 Ti43.061.170.0RTX 308043.062.471.0RTX 3070 Ti45.070.177.0RTX 307046.066.071.0RTX 3060 Ti41.064.271.0RTX 306042.063.267.0OpenBenchmarking.orgCelsius, Fewer Is BetterRealSR-NCNN 20200818GPU Temperature Monitor20406080100

Waifu2x-NCNN Vulkan

MinAvgMaxRTX 309049.051.856.0RTX 3080 Ti56.058.362.0RTX 308056.058.863.0RTX 3070 Ti55.060.867.0RTX 307052.056.262.0RTX 3060 Ti50.055.562.0RTX 306044.051.158.0OpenBenchmarking.orgCelsius, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818GPU Temperature Monitor20406080100

VkResample

MinAvgMaxRTX 309045.047.653.0RTX 3080 Ti49.052.359.0RTX 308049.052.359.0RTX 3070 Ti49.053.465.0RTX 307041.043.953.0RTX 3060 Ti39.042.453.0RTX 306043.048.459.0OpenBenchmarking.orgCelsius, Fewer Is BetterVkResample 1.0GPU Temperature Monitor20406080100

Rodinia

MinAvgMaxRTX 309050.053.656.0RTX 3080 Ti53.056.659.0RTX 308053.056.559.0RTX 3070 Ti51.057.962.0RTX 307046.050.653.0RTX 3060 Ti45.050.253.0RTX 306044.051.657.0OpenBenchmarking.orgCelsius, Fewer Is BetterRodinia 3.1GPU Temperature Monitor20406080100

FinanceBench

MinAvgMaxRTX 309048.051.356.0RTX 3080 Ti50.053.559.0RTX 308051.054.160.0RTX 3070 Ti49.052.858.0RTX 307045.049.056.0RTX 3060 Ti44.048.156.0RTX 306043.045.552.0OpenBenchmarking.orgCelsius, Fewer Is BetterFinanceBench 2016-07-25GPU Temperature Monitor1632486480

MinAvgMaxRTX 309044.045.948.0RTX 3080 Ti46.047.850.0RTX 308047.048.550.0RTX 3070 Ti45.047.651.0RTX 307041.042.445.0RTX 3060 Ti39.041.244.0RTX 306045.046.648.0OpenBenchmarking.orgCelsius, Fewer Is BetterFinanceBench 2016-07-25GPU Temperature Monitor1530456075

clpeak

MinAvgMaxRTX 309050.053.959.0RTX 3080 Ti52.056.864.0RTX 308053.056.763.0RTX 3070 Ti51.054.559.0RTX 307046.050.355.0RTX 3060 Ti45.049.154.0RTX 306043.045.048.0OpenBenchmarking.orgCelsius, Fewer Is BetterclpeakGPU Temperature Monitor20406080100

Darktable

MinAvgMaxRTX 309049.050.556.0RTX 3080 Ti54.056.961.0RTX 308053.055.560.0RTX 3070 Ti52.056.164.0RTX 307047.050.557.0RTX 3060 Ti45.049.456.0RTX 306043.049.960.0OpenBenchmarking.orgCelsius, Fewer Is BetterDarktable 3.8.1GPU Temperature Monitor20406080100

MinAvgMaxRTX 309042.043.645.0RTX 3080 Ti46.047.950.0RTX 308046.047.449.0RTX 3070 Ti45.047.751.0RTX 307039.040.742.0RTX 3060 Ti37.038.940.0RTX 306048.050.152.0OpenBenchmarking.orgCelsius, Fewer Is BetterDarktable 3.8.1GPU Temperature Monitor1530456075

MinAvgMaxRTX 309041.042.945.0RTX 3080 Ti45.046.849.0RTX 308044.046.349.0RTX 3070 Ti43.047.451.0RTX 307038.040.144.0RTX 3060 Ti36.038.242.0RTX 306049.052.559.0OpenBenchmarking.orgCelsius, Fewer Is BetterDarktable 3.8.1GPU Temperature Monitor1632486480

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: SingleRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060612182430SE +/- 0.012, N = 5SE +/- 0.007, N = 5SE +/- 0.007, N = 5SE +/- 0.005, N = 5SE +/- 0.004, N = 5SE +/- 0.011, N = 5SE +/- 0.011, N = 59.3109.56111.26513.57817.57517.68023.1641. (CXX) g++ options: -O3

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: Monte-Carlo OpenCLRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060130260390520650SE +/- 0.87, N = 6SE +/- 0.56, N = 6SE +/- 0.59, N = 6SE +/- 0.42, N = 6SE +/- 0.21, N = 6SE +/- 1.02, N = 6SE +/- 0.40, N = 6321.85323.91388.35472.60463.70463.72619.041. (CXX) g++ options: -O3 -march=native -fopenmp

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Black-Scholes OpenCLRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 306048121620SE +/- 0.006061, N = 14SE +/- 0.060047, N = 15SE +/- 0.008151, N = 14SE +/- 0.022159, N = 15SE +/- 0.038011, N = 14SE +/- 0.010411, N = 14SE +/- 0.020358, N = 156.1970006.5030007.2800009.75900010.43600012.87800016.2227341. (CXX) g++ options: -O3 -march=native -fopenmp

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 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30603691215SE +/- 0.006, N = 7SE +/- 0.007, N = 7SE +/- 0.005, N = 7SE +/- 0.017, N = 6SE +/- 0.008, N = 6SE +/- 0.009, N = 5SE +/- 0.017, N = 55.7485.8936.2617.3318.0818.62010.773

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30601530456075SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.11, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 328.8230.0933.0341.6747.6351.8269.03

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: YesRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30601.13062.26123.39184.52245.653SE +/- 0.003, N = 9SE +/- 0.003, N = 9SE +/- 0.004, N = 9SE +/- 0.004, N = 8SE +/- 0.003, N = 8SE +/- 0.003, N = 8SE +/- 0.007, N = 73.3353.3943.4633.8564.1644.3245.025

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 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30603691215SE +/- 0.019, N = 9SE +/- 0.003, N = 8SE +/- 0.006, N = 8SE +/- 0.008, N = 7SE +/- 0.007, N = 7SE +/- 0.011, N = 6SE +/- 0.020, N = 53.6553.7954.2695.8485.8866.9529.5321. (CXX) g++ options: -O2 -lOpenCL

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.8.1Test: Boat - Acceleration: OpenCLRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30600.44960.89921.34881.79842.248SE +/- 0.002, N = 10SE +/- 0.006, N = 11SE +/- 0.005, N = 11SE +/- 0.003, N = 11SE +/- 0.002, N = 10SE +/- 0.005, N = 10SE +/- 0.003, N = 101.2061.2341.3001.4341.5821.6721.998

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.8.1Test: Server Rack - Acceleration: OpenCLRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30600.03170.06340.09510.12680.1585SE +/- 0.000, N = 13SE +/- 0.000, N = 13SE +/- 0.000, N = 13SE +/- 0.000, N = 13SE +/- 0.000, N = 13SE +/- 0.001, N = 15SE +/- 0.000, N = 130.1300.1320.1320.1330.1360.1410.141

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.8.1Test: Server Room - Acceleration: OpenCLRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30600.20250.4050.60750.811.0125SE +/- 0.001, N = 11SE +/- 0.001, N = 11SE +/- 0.001, N = 11SE +/- 0.001, N = 11SE +/- 0.001, N = 11SE +/- 0.001, N = 11SE +/- 0.001, N = 110.7190.7270.7430.7650.7940.8130.900

clpeak

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

OpenBenchmarking.orgus, Fewer Is BetterclpeakOpenCL Test: Kernel LatencyRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 30601.0712.1423.2134.2845.355SE +/- 0.01, N = 14SE +/- 0.01, N = 15SE +/- 0.01, N = 15SE +/- 0.01, N = 15SE +/- 0.01, N = 15SE +/- 0.01, N = 15SE +/- 0.01, N = 154.754.764.714.654.724.724.651. (CXX) g++ options: -O3 -rdynamic -lOpenCL

75 Results Shown

GPU Temperature Monitor:
  Phoronix Test Suite System Monitoring:
    Celsius
    Watts
cl-mem:
  Copy
  Read
  Write
ViennaCL:
  OpenCL BLAS - sCOPY
  OpenCL BLAS - sAXPY
  OpenCL BLAS - sDOT
  OpenCL BLAS - dCOPY
  OpenCL BLAS - dAXPY
  OpenCL BLAS - dDOT
clpeak:
  Global Memory Bandwidth
  Transfer Bandwidth enqueueReadBuffer
SHOC Scalable HeterOgeneous Computing:
  OpenCL - FFT SP
  OpenCL - Max SP Flops
clpeak:
  Single-Precision Float
  Double-Precision Double
SHOC Scalable HeterOgeneous Computing
SHOC Scalable HeterOgeneous Computing:
  OpenCL - S3D
  OpenCL - GEMM SGEMM_N
ViennaCL:
  OpenCL BLAS - dGEMM-TN
  OpenCL BLAS - dGEMM-NT
ViennaCL:
  OpenCL BLAS - dGEMM-NN
  OpenCL BLAS - dGEMM-NT
  OpenCL BLAS - dGEMM-TN
SHOC Scalable HeterOgeneous Computing
SHOC Scalable HeterOgeneous Computing
clpeak
Hashcat
Hashcat:
  SHA-512
  TrueCrypt RIPEMD160 + XTS
Hashcat:
  SHA1
  7-Zip
  SHA-512
  TrueCrypt RIPEMD160 + XTS
IndigoBench:
  OpenCL GPU - Bedroom
  OpenCL GPU - Supercar
LuxCoreRender
LuxCoreRender
LuxCoreRender:
  Orange Juice - GPU
  LuxCore Benchmark - GPU
  Rainbow Colors and Prism - GPU
LuxCoreRender:
  DLSC - GPU
  Orange Juice - GPU
  LuxCore Benchmark - GPU
  Rainbow Colors and Prism - GPU
LeelaChessZero
LeelaChessZero
FAHBench
FAHBench
JuliaGPU
JuliaGPU
MandelGPU
RealSR-NCNN:
  GPU Temp Monitor:
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
VkResample
FinanceBench:
  Monte-Carlo OpenCL
  Black-Scholes OpenCL
RealSR-NCNN:
  4x - No
  4x - Yes
Waifu2x-NCNN Vulkan
Rodinia
Darktable:
  Boat - OpenCL
  Server Rack - OpenCL
  Server Room - OpenCL
clpeak