NVIDIA GeForce RTX 5090 Compute Linux Benchmarks

NVIDIA GeForce RTX 5090 Linux GPU compute (OpenCL / CUDA / OptiX) benchmarks by Michael Larabel for a future article on Phoronix looking at initial RTX 5090 compute performance on Ubuntu Linux.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2501248-PTS-NVIDIACO39
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
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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

Sensor Monitoring

Show Accumulated Sensor Monitoring Data For Displayed Results
Generate Power Efficiency / Performance Per Watt Results

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
RTX 2070
January 21
  4 Hours, 24 Minutes
RTX 2070 SUPER
January 20
  4 Hours, 2 Minutes
RTX 2080
January 20
  4 Hours, 25 Minutes
RTX 2080 SUPER
January 19
  4 Hours, 6 Minutes
RTX 2080 Ti
January 19
  3 Hours, 28 Minutes
TITAN RTX
January 19
  3 Hours, 27 Minutes
RTX 3070
January 18
  4 Hours, 37 Minutes
RTX 3070 Ti
January 18
  4 Hours, 38 Minutes
RTX 3080
January 17
  4 Hours, 2 Minutes
RTX 3090
January 17
  3 Hours, 46 Minutes
RTX 4070
January 16
  4 Hours, 1 Minute
RTX 4070 SUPER
January 16
  3 Hours, 52 Minutes
RTX 4070 Ti SUPER
January 16
  4 Hours, 6 Minutes
RTX 4080
January 15
  3 Hours, 49 Minutes
RTX 4080 SUPER
January 17
  3 Hours, 46 Minutes
RTX 4090
January 17
  3 Hours, 35 Minutes
RTX 5090
January 23
  3 Hours, 4 Minutes
Invert Behavior (Only Show Selected Data)
  3 Hours, 57 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 GeForce RTX 5090 Compute Linux BenchmarksOpenBenchmarking.orgPhoronix Test SuiteIntel Core Ultra 9 285K @ 5.10GHz (24 Cores)ASUS ROG MAXIMUS Z890 HERO (1203 BIOS)Intel Device ae7f2 x 16GB DDR5-6400MT/s Micron CP16G64C38U5B.M8D14001GB Western Digital WD_BLACK SN850X 4000GB + 1000GB Western Digital WDS100T1X0E-00AFY0ASUS NVIDIA GeForce RTX 2070 8GBASUS NVIDIA GeForce RTX 2070 SUPER 8GBASUS NVIDIA GeForce RTX 2080 8GBASUS NVIDIA GeForce RTX 2080 SUPER 8GBASUS NVIDIA GeForce RTX 2080 Ti 11GBASUS NVIDIA TITAN RTX 24GBASUS NVIDIA GeForce RTX 3070 8GBASUS NVIDIA GeForce RTX 3070 Ti 8GBASUS NVIDIA GeForce RTX 3080 10GBASUS NVIDIA GeForce RTX 3090 24GBASUS NVIDIA GeForce RTX 4070 12GBASUS NVIDIA GeForce RTX 4070 SUPER 12GBASUS NVIDIA GeForce RTX 4070 Ti SUPER 16GBASUS NVIDIA GeForce RTX 4080 16GBASUS NVIDIA GeForce RTX 4080 SUPER 16GBASUS NVIDIA GeForce RTX 4090 24GBASUS NVIDIA GeForce RTX 5090 32GBIntel Device 7f50ASUS VP28URealtek Device 8126 + Intel I226-V + Intel Wi-Fi 7Ubuntu 24.106.11.0-13-generic (x86_64)GNOME Shell 47.0X Server 1.21.1.13NVIDIA 565.77NVIDIA 570.86.104.6.0OpenCL 3.0 CUDA 12.7.33 + OpenCL 3.0OpenCL 3.0 CUDA 12.8.51 + OpenCL 3.0GCC 14.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriversOpenGLOpenCLsCompilerFile-SystemScreen ResolutionNVIDIA GeForce RTX 5090 Compute Linux Benchmarks PerformanceSystem Logs- nouveau.modeset=0 - 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,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/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: intel_pstate performance (EPP: default) - CPU Microcode: 0x114 - Thermald 2.5.8- RTX 2070: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 90.06.0b.40.83- RTX 2070 SUPER: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 90.04.76.00.01- RTX 2080: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 90.04.0d.00.1e- RTX 2080 SUPER: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 90.04.79.00.01- RTX 2080 Ti: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 90.02.0b.00.0e- TITAN RTX: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 90.02.23.00.01- 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: 256 MiB - vBIOS Version: 94.02.20.00.07- RTX 3090: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 94.02.27.00.02- RTX 4070: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.04.49.00.03- RTX 4070 SUPER: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.04.69.00.01- RTX 4070 Ti SUPER: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.45.00.9c- RTX 4080: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.0e.00.04- RTX 4080 SUPER: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.44.00.01- RTX 4090: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.02.20.00.01- RTX 5090: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 98.02.2e.00.03- RTX 2070: GPU Compute Cores: 2304- RTX 2070 SUPER: GPU Compute Cores: 2560- RTX 2080: GPU Compute Cores: 2944- RTX 2080 SUPER: GPU Compute Cores: 3072- RTX 2080 Ti: GPU Compute Cores: 4352- TITAN RTX: GPU Compute Cores: 4608- RTX 3070: GPU Compute Cores: 5888- RTX 3070 Ti: GPU Compute Cores: 6144- RTX 3080: GPU Compute Cores: 8704- RTX 3090: GPU Compute Cores: 10496- RTX 4070: GPU Compute Cores: 5888- RTX 4070 SUPER: GPU Compute Cores: 7168- RTX 4070 Ti SUPER: GPU Compute Cores: 8448- RTX 4080: GPU Compute Cores: 9728- RTX 4080 SUPER: GPU Compute Cores: 10240- RTX 4090: GPU Compute Cores: 16384- RTX 5090: GPU Compute Cores: 21760- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

RTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3070RTX 3070 TiRTX 3080RTX 3090RTX 4070RTX 4070 SUPERRTX 4070 Ti SUPERRTX 4080RTX 4080 SUPERRTX 4090RTX 5090Result OverviewPhoronix Test Suite100%327%553%780%1007%FinanceBenchclpeakSHOC Scalable HeterOgeneous ComputingvkpeakProjectPhysX OpenCL-BenchmarkHashcatGpuOwlBlenderIndigoBenchVkFFTcl-memFluidX3DChaos Group V-RAY

NVIDIA GeForce RTX 5090 Compute Linux Benchmarksvkpeak: fp32-vec4clpeak: Integer Computeclpeak: Integer 24-bit Computeshoc: OpenCL - MD5 Hashopencl-benchmark: INT16 Computeopencl-benchmark: INT8 Computeblender: Pabellon Barcelona - NVIDIA CUDAvkpeak: fp16-vec4opencl-benchmark: INT32 Computevkpeak: fp32-scalarvkpeak: fp16-scalarvkpeak: fp64-scalarvkpeak: fp64-vec4vkpeak: int32-vec4vkpeak: int32-scalarvkpeak: int16-scalarhashcat: TrueCrypt RIPEMD160 + XTSopencl-benchmark: FP64 Computeclpeak: Double-Precision Computefinancebench: Black-Scholes OpenCLvkpeak: int16-vec4opencl-benchmark: FP16 Computegpuowl: 332220523hashcat: SHA-512blender: Classroom - NVIDIA CUDAgpuowl: 77936867hashcat: 7-Ziphashcat: SHA1gpuowl: 57885161blender: Barbershop - NVIDIA CUDAblender: Fishy Cat - NVIDIA OptiXblender: Pabellon Barcelona - NVIDIA OptiXblender: Classroom - NVIDIA OptiXblender: Barbershop - NVIDIA OptiXshoc: OpenCL - S3Dvkfft: FFT + iFFT R2C / C2Rindigobench: OpenCL GPU - Bedroomblender: Fishy Cat - NVIDIA CUDAvkfft: FFT + iFFT C2C multidimensional in single precisionvkfft: FFT + iFFT C2C 1D batched in double precisioncl-mem: Writeblender: BMW27 - NVIDIA OptiXvkfft: FFT + iFFT C2C Bluestein benchmark in double precisionblender: Junkshop - NVIDIA CUDAblender: Junkshop - NVIDIA OptiXopencl-benchmark: Memory Bandwidth Coalesced Writefluidx3d: FP32-FP16Cclpeak: Global Memory Bandwidthshoc: OpenCL - FFT SPfluidx3d: FP32-FP32opencl-benchmark: Memory Bandwidth Coalesced Readindigobench: OpenCL GPU - Supercarfluidx3d: FP32-FP16Svkfft: FFT + iFFT C2C 1D batched in single precisionvkfft: FFT + iFFT C2C 1D batched in single precision, no reshufflingcl-mem: Readclpeak: Single-Precision Computeshoc: OpenCL - Max SP Flopsfinancebench: Monte-Carlo OpenCLopencl-benchmark: FP32 Computeshoc: OpenCL - GEMM SGEMM_Nv-ray: NVIDIA RTX GPURTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3070RTX 3070 TiRTX 3080RTX 3090RTX 4070RTX 4070 SUPERRTX 4070 Ti SUPERRTX 4080RTX 4080 SUPERRTX 4090RTX 50908405.516524.206528.2817.01776.6565.210136.099266.628.0308351.788353.51263.48263.398334.508381.395399.083744000.263267.8615.1513856004.5916.81657.93123585000056.10273.5049228010526400000369.37226.9628.6243.9737.41149.17194.451290647.58649.922822712806326.913.56215940.1724.99419.094387368.531040.162444388.4723.17750175979963674395.17461.618528.22789.7138278.5063043.1411849775.778341.038280.8621.79428.4986.564121.5211226.009.7309782.309755.16303.11303.839724.069748.376351.944647800.302310.3212.0677136.5619.49466.99154960000051.11315.5659975012987075000425.36203.8225.2942.0135.43135.41199.610317358.04843.763089414491311.512.84240137.5024.09386.714964368.581074.872296390.1524.72649605989863469395.58869.369869.46822.5944939.7843306.48165310889.068996.628850.3723.95279.2987.195117.1612468.6510.84810846.7810866.07338.94340.2910624.1010753.256866.475038400.338344.1011.3307632.6521.76573.64167470000050.56345.7065086713992775000465.12201.5224.1542.3036.12136.58196.697321948.03341.723107115800316.712.92260537.1624.52397.104977368.511086.002318388.2425.00649636017763738393.89536.1610952.8841.83516410.9263329.94154811884.7410214.6310130.3326.517410.4437.949110.8313645.0211.78411868.7811860.76369.92369.9011793.8311852.807703.395514630.368375.259.8298619.5823.62680.83183570000048.29378.9373190015316350000513.52195.0422.8141.1634.85132.50213.695344978.28438.993353117208329.012.64283135.7223.77434.575390401.511187.762427426.9625.75153896592069782432.910954.7112015.3861.46133411.8903683.48157216399.9811917.7711881.3235.066113.40210.48379.8418364.6516.10516334.6016324.55509.11510.3815382.2915574.929968.397088600.513522.368.91410958.4532.750110.96235622500036.22508.8285477319593675000691.40144.9817.4031.0926.73101.81271.7824084911.45429.313762823193443.09.99354526.7118.37516.866780501.231477.493080534.9433.37765628105685833541.214149.2516527.7658.64615916.5204807.98214617226.6312534.5813113.8336.552813.99811.02674.9519237.0917.09017156.2917105.62534.78534.7616098.3016298.3110425.887505800.535542.518.54611451.7034.214116.24245070000034.29535.1490245020460700000718.74136.8516.8228.7125.3595.68288.9654354112.03528.094081324553486.09.49366525.5817.48587.037153526.751558.523320557.2935.16870879008495315563.314889.4817332.8570.90511117.2655189.67219615298.5810123.1010133.0425.154410.0518.44486.0512617.8811.49111560.8011503.81360.84362.4911551.3711563.217525.965414400.359361.359.8688409.3522.98678.98177042500036.91371.2072517514829100000499.50142.0318.2829.0326.1791.56218.2433912113.18533.383789317072374.810.24283027.5117.17421.885023388.991132.312592414.2936.93851596808969260392.219751.0723101.9479.49950222.3023812.56258615516.3110504.6410835.7026.223310.1478.74281.7512765.4211.67311705.8011637.99368.00367.9411702.0711780.927681.715548600.365363.569.3908774.2723.33479.69180305000034.59374.7777642515067300000506.93134.3617.4826.8324.1386.21284.5884343413.90832.214248918048501.99.46283525.6915.75577.385926521.981508.303490562.6838.21068079017392498535.020654.0623312.3490.79199222.6644647.78273322671.3014696.9214896.0737.389314.68112.22059.2918616.3817.07317123.1416977.64533.50534.8016810.2116861.7610920.877632000.531539.776.95412126.6034.136116.20254002500025.95533.90101721721015250000726.5799.9913.0121.4418.8566.96335.6395355217.77623.675040825751625.07.67374020.0112.80721.667887659.561914.214291702.5845.9948064113353115705665.729052.4833883.3403.70928532.8716121.92342527485.1717745.6017706.4844.062417.37014.30948.4522634.5620.69720819.0920712.13648.34648.1919997.7720027.9113005.178748600.647650.205.92514318.4941.442140.91298602500021.67661.52119310024271300000886.5383.4210.9917.8615.8956.29431.8756200221.12019.965882931005734.96.51432517.4110.97885.269517805.992346.985317863.8052.7049859139138142087821.334446.6839944.7333.81333139.6407919.72406421796.1914405.3814439.0336.290914.19012.27051.4118862.6516.33216454.3016391.26516.38516.2916390.6816419.8210830.097515200.512516.487.04612214.1932.692112.63246537500023.10530.69102165020154675000714.9793.6411.5616.9815.5862.10285.9775578518.08322.856023622945388.36.40402419.9512.45456.605362435.841331.142859464.9448.09746257651177775444.728122.1832743.0134.46471531.6889662.14355126255.7617504.9917523.9343.699916.94214.39843.2722733.7019.75019849.9219758.01621.48621.6319761.8819768.0612828.308936400.617618.685.87414339.1739.448135.34293372500019.55636.67123477523925450000858.1380.0510.0414.8513.3954.37295.0496586519.60719.487011025662399.35.71457117.1610.89455.305554435.551282.092751465.2552.11151497277773976444.734198.5339320.0123.81328638.22511454.6432130995.9121577.5321557.8551.305520.18517.17537.5626811.3023.20323427.2423374.68735.69735.9223336.2423388.9615276.7010419200.729730.714.83417120.7746.500159.16343207500017.01742.57147655027748050000999.66699966769.558.7813.0211.8347.27384.8077383924.06917.027885731760536.85.15509515.409.77606.857271578.661811.933842619.7260.2296440102178103763593.342259.9046711.7101.48157145.01714093.0513435588.2224073.6624110.2859.411923.09620.12132.2030834.6526.63726906.1426849.69846.10845.9226854.2026859.6217739.8812003600.835838.174.45320277.9053.291183.88394025000014.49868.811669275317174750001146.7961.367.7911.1610.0541.58424.7289249525.80115.009084735151570.04.51573613.488.44610.327660611.731823.363790651.6565.5497073103628105069624.747020.0153756.194.43100051.57317291.1597336981.7325832.5125861.8061.622524.00620.86631.6132039.8127.64527937.4727901.24877.02876.8227866.1627873.3518424.2312402200.868871.364.17421036.9355.338190.30408530000014.42898.741725050328409750001191.8951132360.347.5711.1010.1541.31444.7549099426.36014.848985536256592.04.56581713.468.40631.018026637.951909.783980680.0765.2277510106209107672651.450431.7155618.992.16657053.62317850.8594158187.0139218.4339014.0890.928638.42733.27521.8250245.1744.37444025.4743982.721383.961388.3243917.5143905.0928947.3518985001.3951344.422.97332637.8388.835294.26626620000010.721384.402580925504541500001864.5145.755.669.138.0933.10641.44711201734.62010.8511190054760771.83.77818410.987.23905.6511318834.402776.165595927.7877.5969614151153153088862.976614.8186101.378.83557085.72627552.9846383116.5662214.1961979.76142.44353.52641.52317.3372700.5561.65062849.5962479.991967.621966.4562007.9862182.8240041.9727688601.9451973.532.06143825.03122.630417.0788784500008.361834.863269400688963250002415.4635.154.536.996.1324.551121.8716452242.7928.90143709637851551.42.9299308.975.631690.14191531565.854403.7395171607.7393.017184002339942431531309.0121683.0512438762.144714117.80235979.911918OpenBenchmarking.org

vkpeak

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp32-vec4RTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 3080RTX 4070TITAN RTXRTX 2080 TiRTX 3070 TiRTX 3070RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 207020K40K60K80K100KSE +/- 74.83, N = 3SE +/- 197.02, N = 3SE +/- 29.94, N = 3SE +/- 55.62, N = 3SE +/- 22.54, N = 3SE +/- 104.22, N = 3SE +/- 16.50, N = 3SE +/- 68.11, N = 3SE +/- 39.72, N = 3SE +/- 92.69, N = 3SE +/- 86.63, N = 3SE +/- 37.54, N = 3SE +/- 18.05, N = 3SE +/- 53.54, N = 3SE +/- 29.37, N = 3SE +/- 25.39, N = 3SE +/- 4.03, N = 383116.5658187.0136981.7335588.2230995.9127485.1726255.7622671.3021796.1917226.6316399.9815516.3115298.5811884.7410889.069775.778405.51

clpeak

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

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer ComputeRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 3080RTX 4070TITAN RTXRTX 2080 TiRTX 3070 TiRTX 2080 SUPERRTX 3070RTX 2080RTX 2070 SUPERRTX 207013K26K39K52K65KSE +/- 5.22, N = 13SE +/- 41.24, N = 13SE +/- 8.05, N = 15SE +/- 15.44, N = 15SE +/- 103.56, N = 13SE +/- 90.22, N = 13SE +/- 10.99, N = 13SE +/- 123.87, N = 15SE +/- 9.52, N = 13SE +/- 155.28, N = 15SE +/- 157.16, N = 15SE +/- 116.95, N = 15SE +/- 56.41, N = 13SE +/- 34.10, N = 13SE +/- 71.00, N = 15SE +/- 61.06, N = 15SE +/- 57.45, N = 1562214.1939218.4325832.5124073.6621577.5317745.6017504.9914696.9214405.3812534.5811917.7710504.6410214.6310123.108996.628341.036524.201. (CXX) g++ options: -O3

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer 24-bit ComputeRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 3080RTX 4070TITAN RTXRTX 2080 TiRTX 3070 TiRTX 3070RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 207013K26K39K52K65KSE +/- 5.50, N = 13SE +/- 137.43, N = 13SE +/- 16.98, N = 15SE +/- 13.72, N = 13SE +/- 133.04, N = 13SE +/- 66.63, N = 13SE +/- 13.94, N = 13SE +/- 67.72, N = 13SE +/- 9.07, N = 13SE +/- 157.77, N = 15SE +/- 150.95, N = 15SE +/- 28.80, N = 13SE +/- 31.16, N = 13SE +/- 101.56, N = 15SE +/- 41.57, N = 13SE +/- 40.89, N = 13SE +/- 44.65, N = 1561979.7639014.0825861.8024110.2821557.8517706.4817523.9314896.0714439.0313113.8311881.3210835.7010133.0410130.338850.378280.866528.281. (CXX) g++ options: -O3

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 HashRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 3080TITAN RTXRTX 4070RTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 2070306090120150SE +/- 0.02, N = 13SE +/- 1.13, N = 15SE +/- 0.02, N = 13SE +/- 0.01, N = 13SE +/- 0.16, N = 13SE +/- 0.04, N = 13SE +/- 0.03, N = 13SE +/- 0.22, N = 13SE +/- 0.23, N = 15SE +/- 0.01, N = 13SE +/- 0.04, N = 13SE +/- 0.01, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.01, N = 12SE +/- 0.00, N = 15SE +/- 0.03, N = 12142.4490.9361.6259.4151.3144.0643.7037.3936.5536.2935.0726.5226.2225.1523.9521.7917.021. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

ProjectPhysX OpenCL-Benchmark

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: INT16 ComputeRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 3080RTX 4070TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 20701224364860SE +/- 0.071, N = 6SE +/- 0.010, N = 5SE +/- 0.012, N = 4SE +/- 0.005, N = 4SE +/- 0.003, N = 4SE +/- 0.020, N = 4SE +/- 0.008, N = 4SE +/- 0.001, N = 4SE +/- 0.006, N = 4SE +/- 0.081, N = 3SE +/- 0.077, N = 3SE +/- 0.042, N = 3SE +/- 0.001, N = 3SE +/- 0.011, N = 3SE +/- 0.038, N = 3SE +/- 0.046, N = 3SE +/- 0.057, N = 353.52638.42724.00623.09620.18517.37016.94214.68114.19013.99813.40210.44310.14710.0519.2988.4986.6561. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: INT8 ComputeRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 4070RTX 3080TITAN RTXRTX 2080 TiRTX 3070 TiRTX 3070RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070918273645SE +/- 0.058, N = 6SE +/- 0.031, N = 5SE +/- 0.006, N = 4SE +/- 0.006, N = 4SE +/- 0.026, N = 4SE +/- 0.021, N = 4SE +/- 0.001, N = 4SE +/- 0.016, N = 4SE +/- 0.048, N = 4SE +/- 0.067, N = 3SE +/- 0.058, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.020, N = 3SE +/- 0.016, N = 3SE +/- 0.016, N = 3SE +/- 0.011, N = 341.52333.27520.86620.12117.17514.39814.30912.27012.22011.02610.4838.7428.4447.9497.1956.5645.2101. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: NVIDIA CUDARTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 4070RTX 3080TITAN RTXRTX 2080 TiRTX 3070 TiRTX 3070RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070306090120150SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.25, N = 3SE +/- 0.14, N = 3SE +/- 0.17, N = 317.3321.8231.6132.2037.5643.2748.4551.4159.2974.9579.8481.7586.05110.83117.16121.52136.09

vkpeak

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp16-vec4RTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090TITAN RTXRTX 4070RTX 3080RTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 207016K32K48K64K80KSE +/- 68.93, N = 3SE +/- 49.12, N = 3SE +/- 25.90, N = 3SE +/- 46.26, N = 3SE +/- 20.68, N = 3SE +/- 0.25, N = 3SE +/- 16.77, N = 3SE +/- 80.89, N = 3SE +/- 15.96, N = 3SE +/- 17.19, N = 3SE +/- 63.29, N = 3SE +/- 34.40, N = 3SE +/- 0.47, N = 3SE +/- 15.92, N = 3SE +/- 33.93, N = 3SE +/- 51.15, N = 3SE +/- 36.37, N = 372700.5550245.1732039.8130834.6526811.3022733.7022634.5619237.0918862.6518616.3818364.6513645.0212765.4212617.8812468.6511226.009266.62

ProjectPhysX OpenCL-Benchmark

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: INT32 ComputeRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERTITAN RTXRTX 3080RTX 4070RTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 20701428425670SE +/- 0.039, N = 6SE +/- 0.025, N = 5SE +/- 0.009, N = 4SE +/- 0.001, N = 4SE +/- 0.015, N = 4SE +/- 0.001, N = 4SE +/- 0.002, N = 4SE +/- 0.033, N = 3SE +/- 0.032, N = 4SE +/- 0.012, N = 4SE +/- 0.049, N = 3SE +/- 0.015, N = 3SE +/- 0.000, N = 3SE +/- 0.013, N = 3SE +/- 0.027, N = 3SE +/- 0.024, N = 3SE +/- 0.040, N = 361.65044.37427.64526.63723.20320.69719.75017.09017.07316.33216.10511.78411.67311.49110.8489.7308.0301. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

vkpeak

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp32-scalarRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERTITAN RTXRTX 3080RTX 4070RTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 207013K26K39K52K65KSE +/- 119.36, N = 3SE +/- 78.27, N = 3SE +/- 14.72, N = 3SE +/- 44.22, N = 3SE +/- 24.56, N = 3SE +/- 102.38, N = 3SE +/- 24.55, N = 3SE +/- 94.15, N = 3SE +/- 94.45, N = 3SE +/- 40.14, N = 3SE +/- 87.09, N = 3SE +/- 80.71, N = 3SE +/- 29.04, N = 3SE +/- 34.17, N = 3SE +/- 29.35, N = 3SE +/- 41.97, N = 3SE +/- 17.58, N = 362849.5944025.4727937.4726906.1423427.2420819.0919849.9217156.2917123.1416454.3016334.6011868.7811705.8011560.8010846.789782.308351.78

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp16-scalarRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERTITAN RTXRTX 3080RTX 4070RTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 207013K26K39K52K65KSE +/- 62.98, N = 3SE +/- 11.15, N = 3SE +/- 23.88, N = 3SE +/- 43.02, N = 3SE +/- 0.37, N = 3SE +/- 52.22, N = 3SE +/- 32.76, N = 3SE +/- 66.50, N = 3SE +/- 13.04, N = 3SE +/- 29.10, N = 3SE +/- 43.46, N = 3SE +/- 52.79, N = 3SE +/- 0.11, N = 3SE +/- 14.53, N = 3SE +/- 29.23, N = 3SE +/- 24.92, N = 3SE +/- 31.04, N = 362479.9943982.7227901.2426849.6923374.6820712.1319758.0117105.6216977.6416391.2616324.5511860.7611637.9911503.8110866.079755.168353.51

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp64-scalarRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERTITAN RTXRTX 3080RTX 4070RTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 2070400800120016002000SE +/- 0.05, N = 3SE +/- 1.89, N = 3SE +/- 0.46, N = 3SE +/- 0.02, N = 3SE +/- 0.15, N = 3SE +/- 0.02, N = 3SE +/- 0.81, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.52, N = 3SE +/- 0.01, N = 3SE +/- 0.93, N = 3SE +/- 0.02, N = 3SE +/- 0.28, N = 3SE +/- 0.01, N = 3SE +/- 0.80, N = 3SE +/- 0.72, N = 31967.621383.96877.02846.10735.69648.34621.48534.78533.50516.38509.11369.92368.00360.84338.94303.11263.48

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp64-vec4RTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 3080TITAN RTXRTX 4070RTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 2070400800120016002000SE +/- 0.40, N = 3SE +/- 1.18, N = 3SE +/- 0.49, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 1.12, N = 3SE +/- 0.62, N = 3SE +/- 0.03, N = 3SE +/- 0.56, N = 3SE +/- 1.33, N = 3SE +/- 0.95, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 1.38, N = 2SE +/- 0.01, N = 3SE +/- 0.72, N = 31966.451388.32876.82845.92735.92648.19621.63534.80534.76516.29510.38369.90367.94362.49340.29303.83263.39

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int32-vec4RTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 3080RTX 4070TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 207013K26K39K52K65KSE +/- 104.05, N = 3SE +/- 45.51, N = 3SE +/- 23.13, N = 3SE +/- 16.61, N = 3SE +/- 19.38, N = 3SE +/- 14.43, N = 3SE +/- 1.56, N = 3SE +/- 1.89, N = 3SE +/- 1.05, N = 3SE +/- 18.18, N = 3SE +/- 15.93, N = 3SE +/- 0.37, N = 3SE +/- 0.55, N = 3SE +/- 0.17, N = 3SE +/- 5.36, N = 3SE +/- 25.85, N = 3SE +/- 5.37, N = 362007.9843917.5127866.1626854.2023336.2419997.7719761.8816810.2116390.6816098.3015382.2911793.8311702.0711551.3710624.109724.068334.50

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int32-scalarRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 3080RTX 4070TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 207013K26K39K52K65KSE +/- 16.80, N = 3SE +/- 21.31, N = 3SE +/- 21.56, N = 3SE +/- 17.94, N = 3SE +/- 4.70, N = 3SE +/- 23.15, N = 3SE +/- 4.54, N = 3SE +/- 6.45, N = 3SE +/- 14.55, N = 3SE +/- 42.73, N = 3SE +/- 35.79, N = 3SE +/- 30.41, N = 3SE +/- 0.72, N = 3SE +/- 10.31, N = 3SE +/- 24.86, N = 3SE +/- 0.25, N = 3SE +/- 23.10, N = 362182.8243905.0927873.3526859.6223388.9620027.9119768.0616861.7616419.8216298.3115574.9211852.8011780.9211563.2110753.259748.378381.39

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int16-scalarRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 3080RTX 4070TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 20709K18K27K36K45KSE +/- 92.26, N = 3SE +/- 25.04, N = 3SE +/- 8.69, N = 3SE +/- 18.02, N = 3SE +/- 3.81, N = 3SE +/- 11.27, N = 3SE +/- 13.57, N = 3SE +/- 13.89, N = 3SE +/- 8.31, N = 3SE +/- 17.82, N = 3SE +/- 13.41, N = 3SE +/- 11.20, N = 3SE +/- 0.44, N = 3SE +/- 0.13, N = 3SE +/- 2.63, N = 3SE +/- 17.31, N = 3SE +/- 10.23, N = 340041.9728947.3518424.2317739.8815276.7013005.1712828.3010920.8710830.0910425.889968.397703.397681.717525.966866.476351.945399.08

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: TrueCrypt RIPEMD160 + XTSRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 3080RTX 4070TITAN RTXRTX 2080 TiRTX 3070 TiRTX 2080 SUPERRTX 3070RTX 2080RTX 2070 SUPERRTX 2070600K1200K1800K2400K3000KSE +/- 5285.13, N = 5SE +/- 11519.85, N = 5SE +/- 265.33, N = 5SE +/- 995.29, N = 5SE +/- 3158.23, N = 5SE +/- 498.60, N = 5SE +/- 8206.50, N = 5SE +/- 3936.24, N = 5SE +/- 295.63, N = 5SE +/- 1982.02, N = 5SE +/- 1648.51, N = 5SE +/- 2665.45, N = 5SE +/- 4543.12, N = 8SE +/- 2007.64, N = 5SE +/- 3865.18, N = 5SE +/- 1115.97, N = 5SE +/- 1026.16, N = 527688601898500124022012003601041920893640874860763200751520750580708860554860551463541440503840464780374400

ProjectPhysX OpenCL-Benchmark

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: FP64 ComputeRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERTITAN RTXRTX 3080RTX 2080 TiRTX 4070RTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 20700.43760.87521.31281.75042.188SE +/- 0.000, N = 6SE +/- 0.001, N = 5SE +/- 0.000, N = 4SE +/- 0.000, N = 4SE +/- 0.000, N = 4SE +/- 0.001, N = 4SE +/- 0.001, N = 4SE +/- 0.001, N = 3SE +/- 0.001, N = 4SE +/- 0.001, N = 3SE +/- 0.001, N = 4SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 31.9451.3950.8680.8350.7290.6470.6170.5350.5310.5130.5120.3680.3650.3590.3380.3020.2631. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

clpeak

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

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Double-Precision ComputeRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERTITAN RTXRTX 3080RTX 2080 TiRTX 4070RTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 2070400800120016002000SE +/- 0.35, N = 6SE +/- 3.05, N = 5SE +/- 1.34, N = 6SE +/- 1.44, N = 6SE +/- 2.04, N = 6SE +/- 3.27, N = 5SE +/- 1.23, N = 6SE +/- 3.00, N = 4SE +/- 0.81, N = 5SE +/- 1.02, N = 4SE +/- 0.60, N = 6SE +/- 1.19, N = 5SE +/- 1.23, N = 4SE +/- 1.47, N = 5SE +/- 1.50, N = 4SE +/- 0.51, N = 4SE +/- 0.69, N = 41973.531344.42871.36838.17730.71650.20618.68542.51539.77522.36516.48375.25363.56361.35344.10310.32267.861. (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: Black-Scholes OpenCLRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 3080RTX 4070TITAN RTXRTX 2080 TiRTX 3070 TiRTX 2080 SUPERRTX 3070RTX 2080RTX 2070 SUPERRTX 207048121620SE +/- 0.002542, N = 13SE +/- 0.031800, N = 15SE +/- 0.019792, N = 15SE +/- 0.020898, N = 15SE +/- 0.007498, N = 14SE +/- 0.020372, N = 15SE +/- 0.046383, N = 15SE +/- 0.049640, N = 15SE +/- 0.048189, N = 15SE +/- 0.166780, N = 15SE +/- 0.106855, N = 15SE +/- 0.142777, N = 15SE +/- 0.001893, N = 13SE +/- 0.073765, N = 15SE +/- 0.099396, N = 15SE +/- 0.065111, N = 15SE +/- 0.085925, N = 132.0610002.9730004.1740004.4530004.8340005.8740005.9250006.9540007.0460008.5460008.9140009.3900009.8290009.86800011.33000012.06700015.1513851. (CXX) g++ options: -O3 -march=native -fopenmp

vkpeak

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int16-vec4RTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 4070RTX 3080TITAN RTXRTX 2080 TiRTX 3070 TiRTX 2080 SUPERRTX 3070RTX 2080RTX 2070 SUPERRTX 20709K18K27K36K45KSE +/- 74.96, N = 3SE +/- 13.78, N = 3SE +/- 21.68, N = 3SE +/- 4.58, N = 3SE +/- 9.02, N = 3SE +/- 10.35, N = 3SE +/- 12.13, N = 3SE +/- 8.64, N = 3SE +/- 15.52, N = 3SE +/- 25.37, N = 3SE +/- 6.33, N = 3SE +/- 4.02, N = 3SE +/- 8.31, N = 3SE +/- 2.36, N = 3SE +/- 1.41, N = 3SE +/- 12.73, N = 3SE +/- 1.72, N = 343825.0332637.8321036.9320277.9017120.7714339.1714318.4912214.1912126.6011451.7010958.458774.278619.588409.357632.657136.566004.59

ProjectPhysX OpenCL-Benchmark

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: FP16 ComputeRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERTITAN RTXRTX 3080RTX 2080 TiRTX 4070RTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 2070306090120150SE +/- 0.01, N = 6SE +/- 0.04, N = 5SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.02, N = 4SE +/- 0.08, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 3SE +/- 0.06, N = 4SE +/- 0.09, N = 3SE +/- 0.02, N = 4SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3122.6388.8455.3453.2946.5041.4439.4534.2134.1432.7532.6923.6323.3322.9921.7719.4916.821. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

GpuOwl

GpuOwl is a Mersenne primality tester leveraging OpenCL for cross-vendor GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 332220523RTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERTITAN RTXRTX 3080RTX 4070RTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 207090180270360450SE +/- 0.06, N = 3SE +/- 0.13, N = 3SE +/- 0.25, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3417.07294.26190.30183.88159.16140.91135.34116.24116.20112.63110.9680.8379.6978.9873.6466.9957.931. (CXX) g++ options: -O3 -lgmp -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: SHA-512RTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 3080RTX 4070TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 20702000M4000M6000M8000M10000MSE +/- 3733072.91, N = 4SE +/- 30735891.07, N = 4SE +/- 385140.67, N = 4SE +/- 655108.13, N = 4SE +/- 4375380.94, N = 4SE +/- 5377170.10, N = 4SE +/- 1037926.62, N = 4SE +/- 6222589.89, N = 4SE +/- 404917.69, N = 4SE +/- 5585546.82, N = 4SE +/- 666301.98, N = 4SE +/- 8285831.28, N = 4SE +/- 6399153.59, N = 4SE +/- 3218274.64, N = 4SE +/- 5775955.91, N = 4SE +/- 1882817.04, N = 4SE +/- 2151937.11, N = 488784500006266200000408530000039402500003432075000298602500029337250002540025000246537500024507000002356225000183570000018030500001770425000167470000015496000001235850000

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: NVIDIA CUDARTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 4070RTX 3080TITAN RTXRTX 3070 TiRTX 2080 TiRTX 3070RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 20701326395265SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 4SE +/- 0.01, N = 4SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 38.3610.7214.4214.4917.0119.5521.6723.1025.9534.2934.5936.2236.9148.2950.5651.1156.10

GpuOwl

GpuOwl is a Mersenne primality tester leveraging OpenCL for cross-vendor GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 77936867RTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERTITAN RTXRTX 3080RTX 4070RTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 2070400800120016002000SE +/- 0.00, N = 3SE +/- 1.28, N = 3SE +/- 0.27, N = 3SE +/- 0.00, N = 3SE +/- 0.37, N = 3SE +/- 0.53, N = 3SE +/- 0.14, N = 3SE +/- 0.53, N = 3SE +/- 0.57, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.17, N = 3SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 31834.861384.40898.74868.81742.57661.52636.67535.14533.90530.69508.82378.93374.77371.20345.70315.56273.501. (CXX) g++ options: -O3 -lgmp -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: 7-ZipRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 4070RTX 3080TITAN RTXRTX 2080 TiRTX 3070 TiRTX 2080 SUPERRTX 3070RTX 2080RTX 2070 SUPERRTX 2070700K1400K2100K2800K3500KSE +/- 4312.96, N = 4SE +/- 9326.97, N = 4SE +/- 8850.66, N = 4SE +/- 14128.19, N = 4SE +/- 14282.30, N = 4SE +/- 3043.13, N = 4SE +/- 8273.25, N = 4SE +/- 2058.11, N = 4SE +/- 9432.34, N = 6SE +/- 13330.27, N = 12SE +/- 6815.59, N = 15SE +/- 7174.77, N = 4SE +/- 5626.87, N = 4SE +/- 2088.21, N = 4SE +/- 6989.52, N = 15SE +/- 3101.21, N = 4SE +/- 5476.08, N = 5326940025809251725050166927514765501234775119310010216501017217902450854773776425731900725175650867599750492280

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA1RTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 3080TITAN RTXRTX 4070RTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 207015000M30000M45000M60000M75000MSE +/- 72445857.66, N = 4SE +/- 63352459.83, N = 4SE +/- 8255742.95, N = 4SE +/- 7553296.74, N = 4SE +/- 20033035.22, N = 4SE +/- 31237770.94, N = 4SE +/- 13413457.17, N = 4SE +/- 30678887.96, N = 4SE +/- 57395658.95, N = 4SE +/- 10041030.41, N = 4SE +/- 23647705.14, N = 4SE +/- 25827682.18, N = 4SE +/- 33784069.22, N = 4SE +/- 12319970.24, N = 4SE +/- 18485867.35, N = 4SE +/- 11443875.73, N = 4SE +/- 42617602.00, N = 46889632500050454150000328409750003171747500027748050000242713000002392545000021015250000204607000002015467500019593675000153163500001506730000014829100000139927750001298707500010526400000

GpuOwl

GpuOwl is a Mersenne primality tester leveraging OpenCL for cross-vendor GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 57885161RTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 3080TITAN RTXRTX 4070RTX 2080 TiRTX 2080 SUPERRTX 3070 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 20705001000150020002500SE +/- 0.00, N = 3SE +/- 1.16, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.45, N = 3SE +/- 1.23, N = 3SE +/- 0.63, N = 3SE +/- 0.69, N = 3SE +/- 0.34, N = 3SE +/- 0.16, N = 3SE +/- 0.18, N = 3SE +/- 0.17, N = 3SE +/- 0.00, N = 3SE +/- 0.12, N = 3SE +/- 1.08, N = 3SE +/- 0.18, N = 32415.461864.511191.901146.79999.67886.53858.13726.57718.74714.97691.40513.52506.93499.50465.12425.36369.371. (CXX) g++ options: -O3 -lgmp -lOpenCL

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: NVIDIA CUDARTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 4070RTX 3080RTX 3070 TiTITAN RTXRTX 3070RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 207050100150200250SE +/- 0.07, N = 3SE +/- 0.19, N = 3SE +/- 0.36, N = 3SE +/- 0.49, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.26, N = 3SE +/- 0.25, N = 3SE +/- 0.29, N = 3SE +/- 0.32, N = 3SE +/- 0.11, N = 3SE +/- 0.32, N = 3SE +/- 0.14, N = 3SE +/- 0.26, N = 335.1545.7560.3461.3669.5580.0583.4293.6499.99134.36136.85142.03144.98195.04201.52203.82226.96

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 4070RTX 3080TITAN RTXRTX 2080 TiRTX 3070 TiRTX 3070RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070714212835SE +/- 0.04, N = 15SE +/- 0.03, N = 15SE +/- 0.01, N = 6SE +/- 0.07, N = 6SE +/- 0.01, N = 5SE +/- 0.09, N = 5SE +/- 0.01, N = 4SE +/- 0.01, N = 4SE +/- 0.13, N = 4SE +/- 0.16, N = 3SE +/- 0.01, N = 3SE +/- 0.16, N = 3SE +/- 0.00, N = 3SE +/- 0.15, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.13, N = 34.535.667.577.798.7810.0410.9911.5613.0116.8217.4017.4818.2822.8124.1525.2928.62

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 3090RTX 3080RTX 3070 TiTITAN RTXRTX 3070RTX 2080 TiRTX 2080 SUPERRTX 2070 SUPERRTX 2080RTX 20701020304050SE +/- 0.01, N = 6SE +/- 0.00, N = 5SE +/- 0.01, N = 4SE +/- 0.01, N = 4SE +/- 0.01, N = 4SE +/- 0.02, N = 4SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 36.999.1311.1011.1613.0214.8516.9817.8621.4426.8328.7129.0331.0941.1642.0142.3043.97

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: NVIDIA OptiXRTX 5090RTX 4090RTX 4080RTX 4080 SUPERRTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 3090RTX 3080RTX 3070 TiTITAN RTXRTX 3070RTX 2080 TiRTX 2080 SUPERRTX 2070 SUPERRTX 2080RTX 2070918273645SE +/- 0.01, N = 6SE +/- 0.01, N = 6SE +/- 0.02, N = 5SE +/- 0.03, N = 5SE +/- 0.01, N = 4SE +/- 0.04, N = 4SE +/- 0.01, N = 4SE +/- 0.01, N = 4SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 36.138.0910.0510.1511.8313.3915.5815.8918.8524.1325.3526.1726.7334.8535.4336.1237.41

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: NVIDIA OptiXRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 4070RTX 3080RTX 3070 TiRTX 3070TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 2070 SUPERRTX 2080RTX 2070306090120150SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 3SE +/- 0.09, N = 3SE +/- 0.19, N = 3SE +/- 0.24, N = 3SE +/- 0.13, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 324.5533.1041.3141.5847.2754.3756.2962.1066.9686.2191.5695.68101.81132.50135.41136.58149.17

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 5090RTX 4090RTX 4080 SUPERRTX 3090RTX 4080RTX 4070 Ti SUPERRTX 3080RTX 4070 SUPERTITAN RTXRTX 4070RTX 3070 TiRTX 2080 TiRTX 3070RTX 2080 SUPERRTX 2070 SUPERRTX 2080RTX 20702004006008001000SE +/- 0.66, N = 12SE +/- 0.25, N = 13SE +/- 0.30, N = 13SE +/- 0.26, N = 12SE +/- 0.25, N = 12SE +/- 0.05, N = 13SE +/- 0.18, N = 12SE +/- 0.06, N = 13SE +/- 0.14, N = 12SE +/- 0.23, N = 13SE +/- 0.21, N = 13SE +/- 0.12, N = 12SE +/- 0.16, N = 13SE +/- 0.09, N = 12SE +/- 0.07, N = 12SE +/- 0.06, N = 12SE +/- 0.08, N = 121121.87641.45444.75431.88424.73384.81335.64295.05288.97285.98284.59271.78218.24213.70199.61196.70194.451. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -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 1.3.4Test: FFT + iFFT R2C / C2RRTX 5090RTX 4090RTX 4080RTX 4080 SUPERRTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 4070RTX 3080TITAN RTXRTX 3070 TiRTX 2080 TiRTX 3070RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 207040K80K120K160K200KSE +/- 660.95, N = 6SE +/- 547.25, N = 6SE +/- 200.05, N = 6SE +/- 64.83, N = 6SE +/- 138.14, N = 5SE +/- 104.18, N = 5SE +/- 39.00, N = 5SE +/- 32.10, N = 5SE +/- 76.26, N = 5SE +/- 57.18, N = 5SE +/- 130.04, N = 5SE +/- 47.01, N = 4SE +/- 3.77, N = 4SE +/- 42.51, N = 4SE +/- 123.34, N = 4SE +/- 7.96, N = 4SE +/- 30.60, N = 41645221120179249590994738396586562002557855355243541434344084939121344973219431735290641. (CXX) g++ options: -O3

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 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 4070RTX 3080RTX 3070 TiRTX 3070TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 2070 SUPERRTX 2080RTX 20701020304050SE +/- 0.098, N = 3SE +/- 0.047, N = 3SE +/- 0.004, N = 3SE +/- 0.009, N = 3SE +/- 0.009, N = 3SE +/- 0.011, N = 3SE +/- 0.002, N = 3SE +/- 0.004, N = 3SE +/- 0.011, N = 3SE +/- 0.014, N = 3SE +/- 0.005, N = 3SE +/- 0.033, N = 3SE +/- 0.014, N = 3SE +/- 0.009, N = 3SE +/- 0.001, N = 3SE +/- 0.006, N = 3SE +/- 0.008, N = 342.79234.62026.36025.80124.06921.12019.60718.08317.77613.90813.18512.03511.4548.2848.0488.0337.586

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: NVIDIA CUDARTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 4070RTX 3080TITAN RTXRTX 2080 TiRTX 3070 TiRTX 3070RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 20701122334455SE +/- 0.01, N = 5SE +/- 0.06, N = 5SE +/- 0.05, N = 4SE +/- 0.02, N = 4SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 38.9010.8514.8415.0017.0219.4819.9622.8523.6728.0929.3132.2133.3838.9941.7243.7649.92

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 1.3.4Test: FFT + iFFT C2C multidimensional in single precisionRTX 5090RTX 4090RTX 4080RTX 4080 SUPERRTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 3090RTX 3080RTX 3070 TiTITAN RTXRTX 3070RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 207030K60K90K120K150KSE +/- 509.43, N = 4SE +/- 1226.08, N = 5SE +/- 856.16, N = 6SE +/- 392.27, N = 4SE +/- 324.88, N = 4SE +/- 334.24, N = 3SE +/- 455.88, N = 3SE +/- 91.90, N = 3SE +/- 145.37, N = 3SE +/- 110.27, N = 3SE +/- 114.64, N = 3SE +/- 28.00, N = 3SE +/- 64.36, N = 3SE +/- 56.70, N = 3SE +/- 21.73, N = 3SE +/- 15.89, N = 3SE +/- 37.68, N = 31437091119009084789855788577011060236588295040842489408133789337628335313107130894282271. (CXX) g++ options: -O3

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in double precisionRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 3080RTX 4070 SUPERTITAN RTXRTX 2080 TiRTX 4070RTX 3070 TiRTX 2080 SUPERRTX 3070RTX 2080RTX 2070 SUPERRTX 207014K28K42K56K70KSE +/- 487.66, N = 3SE +/- 121.47, N = 3SE +/- 114.30, N = 3SE +/- 62.53, N = 3SE +/- 43.21, N = 3SE +/- 30.01, N = 3SE +/- 66.61, N = 3SE +/- 36.88, N = 3SE +/- 55.12, N = 3SE +/- 61.53, N = 3SE +/- 52.27, N = 3SE +/- 15.32, N = 3SE +/- 7.84, N = 3SE +/- 38.21, N = 3SE +/- 27.06, N = 3SE +/- 31.67, N = 3SE +/- 28.48, N = 363785547603625635151317603100525751256622455323193229451804817208170721580014491128061. (CXX) g++ options: -O3

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: WriteRTX 5090RTX 4090RTX 3090RTX 3080RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3070 TiTITAN RTXRTX 2080 TiRTX 4070 SUPERRTX 4070RTX 3070RTX 2080 SUPERRTX 2070RTX 2080RTX 2070 SUPER30060090012001500SE +/- 1.81, N = 10SE +/- 1.03, N = 10SE +/- 2.06, N = 9SE +/- 2.29, N = 9SE +/- 0.41, N = 9SE +/- 0.77, N = 9SE +/- 0.24, N = 9SE +/- 2.51, N = 8SE +/- 2.88, N = 8SE +/- 0.98, N = 8SE +/- 0.46, N = 8SE +/- 0.20, N = 8SE +/- 0.09, N = 8SE +/- 1.95, N = 8SE +/- 1.54, N = 7SE +/- 1.96, N = 7SE +/- 0.50, N = 71551.4771.8734.9625.0592.0570.0536.8501.9486.0443.0399.3388.3374.8329.0326.9316.7311.51. (CC) gcc options: -O2 -flto -lOpenCL

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: NVIDIA OptiXRTX 5090RTX 4090RTX 4080RTX 4080 SUPERRTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 3090RTX 3080RTX 3070 TiTITAN RTXRTX 2080 TiRTX 3070RTX 2080 SUPERRTX 2070 SUPERRTX 2080RTX 20703691215SE +/- 0.04, N = 15SE +/- 0.03, N = 15SE +/- 0.03, N = 15SE +/- 0.01, N = 7SE +/- 0.01, N = 7SE +/- 0.03, N = 15SE +/- 0.01, N = 6SE +/- 0.02, N = 6SE +/- 0.07, N = 7SE +/- 0.10, N = 5SE +/- 0.09, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.12, N = 4SE +/- 0.01, N = 4SE +/- 0.01, N = 4SE +/- 0.10, N = 42.923.774.514.565.155.716.406.517.679.469.499.9910.2412.6412.8412.9213.56

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 1.3.4Test: FFT + iFFT C2C Bluestein benchmark in double precisionRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 4070RTX 3080TITAN RTXRTX 2080 TiRTX 3070 TiRTX 2080 SUPERRTX 3070RTX 2080RTX 2070 SUPERRTX 20702K4K6K8K10KSE +/- 3.33, N = 3SE +/- 4.70, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 7.55, N = 3SE +/- 0.58, N = 3SE +/- 8.50, N = 3SE +/- 2.40, N = 3SE +/- 10.93, N = 3SE +/- 2.60, N = 3SE +/- 1.33, N = 3SE +/- 6.43, N = 3SE +/- 8.17, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3993081845817573650954571432540243740366535452835283128302605240121591. (CXX) g++ options: -O3

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: NVIDIA CUDARTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 4070RTX 3080TITAN RTXRTX 3070 TiRTX 2080 TiRTX 3070RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070918273645SE +/- 0.02, N = 5SE +/- 0.01, N = 5SE +/- 0.03, N = 4SE +/- 0.01, N = 4SE +/- 0.02, N = 4SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 38.9710.9813.4613.4815.4017.1617.4119.9520.0125.5825.6926.7127.5135.7237.1637.5040.17

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: NVIDIA OptiXRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 4070RTX 3080RTX 3070 TiRTX 3070TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 2070 SUPERRTX 2080RTX 2070612182430SE +/- 0.01, N = 7SE +/- 0.00, N = 6SE +/- 0.01, N = 5SE +/- 0.02, N = 5SE +/- 0.01, N = 5SE +/- 0.02, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 4SE +/- 0.02, N = 4SE +/- 0.02, N = 4SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 35.637.238.408.449.7710.8910.9712.4512.8015.7517.1717.4818.3723.7724.0924.5224.99

ProjectPhysX OpenCL-Benchmark

OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: Memory Bandwidth Coalesced WriteRTX 5090RTX 4090RTX 3090RTX 3080RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERTITAN RTXRTX 3070 TiRTX 2080 TiRTX 4070RTX 4070 SUPERRTX 2080 SUPERRTX 3070RTX 2070RTX 2080RTX 2070 SUPER400800120016002000SE +/- 1.93, N = 6SE +/- 0.25, N = 5SE +/- 0.08, N = 4SE +/- 0.02, N = 4SE +/- 0.41, N = 4SE +/- 0.65, N = 4SE +/- 0.23, N = 4SE +/- 1.22, N = 3SE +/- 0.01, N = 3SE +/- 0.62, N = 3SE +/- 0.27, N = 4SE +/- 0.05, N = 4SE +/- 0.22, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.37, N = 3SE +/- 1.15, N = 31690.14905.65885.26721.66631.01610.32606.85587.03577.38516.86456.60455.30434.57421.88419.09397.10386.711. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

FluidX3D

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 3.0Test: FP32-FP16CRTX 5090RTX 4090RTX 3090RTX 4080 SUPERRTX 3080RTX 4080RTX 4070 Ti SUPERTITAN RTXRTX 2080 TiRTX 3070 TiRTX 4070 SUPERRTX 2080 SUPERRTX 4070RTX 3070RTX 2080RTX 2070 SUPERRTX 20704K8K12K16K20KSE +/- 8.41, N = 5SE +/- 0.63, N = 4SE +/- 7.17, N = 3SE +/- 3.93, N = 3SE +/- 3.53, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 1.45, N = 3SE +/- 2.40, N = 3SE +/- 11.33, N = 3SE +/- 0.58, N = 3SE +/- 2.52, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 1.67, N = 3SE +/- 0.33, N = 3SE +/- 56.46, N = 151915311318951780267887766072717153678059265554539053625023497749644387

clpeak

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

OpenBenchmarking.orgGBPS, More Is Betterclpeak 1.1.2OpenCL Test: Global Memory BandwidthRTX 5090RTX 4090RTX 3090RTX 3080RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERTITAN RTXRTX 3070 TiRTX 2080 TiRTX 4070RTX 4070 SUPERRTX 2080 SUPERRTX 3070RTX 2070 SUPERRTX 2070RTX 208030060090012001500SE +/- 1.10, N = 11SE +/- 0.52, N = 10SE +/- 5.51, N = 10SE +/- 1.97, N = 15SE +/- 0.02, N = 10SE +/- 0.01, N = 10SE +/- 2.57, N = 9SE +/- 0.16, N = 9SE +/- 4.73, N = 15SE +/- 2.82, N = 10SE +/- 0.06, N = 10SE +/- 0.10, N = 10SE +/- 2.79, N = 15SE +/- 0.01, N = 11SE +/- 0.08, N = 10SE +/- 0.19, N = 11SE +/- 0.03, N = 101565.85834.40805.99659.56637.95611.73578.66526.75521.98501.23435.84435.55401.51388.99368.58368.53368.511. (CXX) g++ options: -O3

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 5090RTX 4090RTX 3090RTX 3080RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERTITAN RTXRTX 3070 TiRTX 2080 TiRTX 4070RTX 4070 SUPERRTX 2080 SUPERRTX 3070RTX 2080RTX 2070 SUPERRTX 20709001800270036004500SE +/- 8.96, N = 15SE +/- 1.52, N = 11SE +/- 0.99, N = 11SE +/- 0.73, N = 11SE +/- 1.30, N = 11SE +/- 1.67, N = 11SE +/- 0.44, N = 11SE +/- 5.71, N = 10SE +/- 0.70, N = 15SE +/- 2.00, N = 11SE +/- 0.83, N = 11SE +/- 0.62, N = 11SE +/- 2.66, N = 10SE +/- 0.47, N = 11SE +/- 2.37, N = 10SE +/- 3.07, N = 10SE +/- 10.60, N = 154403.732776.162346.981914.211909.781823.361811.931558.521508.301477.491331.141282.091187.761132.311086.001074.871040.161. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

FluidX3D

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 3.0Test: FP32-FP32RTX 5090RTX 4090RTX 3090RTX 3080RTX 4080 SUPERRTX 4070 Ti SUPERRTX 4080RTX 3070 TiTITAN RTXRTX 2080 TiRTX 4070RTX 4070 SUPERRTX 3070RTX 2070RTX 2080 SUPERRTX 2080RTX 2070 SUPER2K4K6K8K10KSE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 2.08, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 395175595531742913980384237903490332030802859275125922444242723182296

ProjectPhysX OpenCL-Benchmark

OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: Memory Bandwidth Coalesced ReadRTX 5090RTX 4090RTX 3090RTX 3080RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3070 TiTITAN RTXRTX 2080 TiRTX 4070 SUPERRTX 4070RTX 2080 SUPERRTX 3070RTX 2070 SUPERRTX 2070RTX 208030060090012001500SE +/- 2.56, N = 6SE +/- 0.08, N = 5SE +/- 0.10, N = 4SE +/- 0.02, N = 4SE +/- 0.02, N = 4SE +/- 0.05, N = 4SE +/- 0.00, N = 4SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.19, N = 3SE +/- 0.01, N = 4SE +/- 0.02, N = 4SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 31607.73927.78863.80702.58680.07651.65619.72562.68557.29534.94465.25464.94426.96414.29390.15388.47388.241. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

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: SupercarRTX 5090RTX 4090RTX 4080RTX 4080 SUPERRTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 4070RTX 3080RTX 3070 TiRTX 3070TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 207020406080100SE +/- 0.06, N = 3SE +/- 0.15, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.19, N = 3SE +/- 0.20, N = 3SE +/- 0.01, N = 3SE +/- 0.18, N = 3SE +/- 0.10, N = 3SE +/- 0.11, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 393.0277.6065.5565.2360.2352.7052.1148.1045.9938.2136.9435.1733.3825.7525.0124.7323.18

FluidX3D

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 3.0Test: FP32-FP16SRTX 5090RTX 3090RTX 4090RTX 3080RTX 4080 SUPERTITAN RTXRTX 4080RTX 3070 TiRTX 2080 TiRTX 4070 Ti SUPERRTX 2080 SUPERRTX 3070RTX 4070 SUPERRTX 2070RTX 2080RTX 2070 SUPERRTX 40704K8K12K16K20KSE +/- 1.14, N = 5SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 1.86, N = 3SE +/- 0.67, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 2.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 1.33, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3184009859961480647510708770736807656264405389515951495017496349604625

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 1.3.4Test: FFT + iFFT C2C 1D batched in single precisionRTX 5090RTX 4090RTX 3090RTX 3080RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3070 TiTITAN RTXRTX 2080 TiRTX 4070RTX 4070 SUPERRTX 3070RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 207050K100K150K200K250KSE +/- 2849.67, N = 4SE +/- 58.55, N = 3SE +/- 49.38, N = 3SE +/- 48.46, N = 3SE +/- 9.74, N = 3SE +/- 13.87, N = 3SE +/- 51.21, N = 3SE +/- 66.79, N = 3SE +/- 290.72, N = 3SE +/- 104.11, N = 3SE +/- 11.68, N = 3SE +/- 11.72, N = 3SE +/- 4.00, N = 3SE +/- 52.29, N = 3SE +/- 15.39, N = 3SE +/- 17.90, N = 3SE +/- 11.85, N = 3233994151153139138113353106209103628102178901739008481056765117277768089659206017759898597991. (CXX) g++ options: -O3

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in single precision, no reshufflingRTX 5090RTX 4090RTX 3090RTX 3080RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERTITAN RTXRTX 3070 TiRTX 2080 TiRTX 4070RTX 4070 SUPERRTX 2080 SUPERRTX 3070RTX 2080RTX 2070RTX 2070 SUPER50K100K150K200K250KSE +/- 1769.18, N = 3SE +/- 5.36, N = 3SE +/- 55.76, N = 3SE +/- 81.77, N = 3SE +/- 29.02, N = 3SE +/- 30.83, N = 3SE +/- 9.96, N = 3SE +/- 266.54, N = 3SE +/- 53.54, N = 3SE +/- 94.56, N = 3SE +/- 11.02, N = 3SE +/- 30.37, N = 3SE +/- 34.68, N = 3SE +/- 19.19, N = 3SE +/- 177.67, N = 3SE +/- 23.95, N = 3SE +/- 16.00, N = 3243153153088142087115705107672105069103763953159249885833777757397669782692606373863674634691. (CXX) g++ options: -O3

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: ReadRTX 5090RTX 4090RTX 3090RTX 3080RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERTITAN RTXRTX 2080 TiRTX 3070 TiRTX 4070 SUPERRTX 4070RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080RTX 307030060090012001500SE +/- 0.69, N = 10SE +/- 2.27, N = 10SE +/- 3.15, N = 9SE +/- 2.78, N = 9SE +/- 0.06, N = 9SE +/- 0.08, N = 9SE +/- 0.08, N = 9SE +/- 1.89, N = 8SE +/- 2.00, N = 8SE +/- 2.60, N = 8SE +/- 0.10, N = 8SE +/- 0.11, N = 8SE +/- 2.39, N = 8SE +/- 0.13, N = 7SE +/- 0.46, N = 7SE +/- 1.74, N = 7SE +/- 0.20, N = 81309.0862.9821.3665.7651.4624.7593.3563.3541.2535.0444.7444.7432.9395.5395.1393.8392.21. (CC) gcc options: -O2 -flto -lOpenCL

clpeak

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

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Single-Precision ComputeRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 3080RTX 4070RTX 3070 TiRTX 3070TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 207030K60K90K120K150KSE +/- 4.12, N = 13SE +/- 83.12, N = 13SE +/- 8.39, N = 15SE +/- 30.64, N = 13SE +/- 193.76, N = 13SE +/- 104.83, N = 12SE +/- 23.26, N = 13SE +/- 114.80, N = 13SE +/- 22.86, N = 15SE +/- 189.25, N = 15SE +/- 64.21, N = 13SE +/- 211.70, N = 15SE +/- 130.13, N = 15SE +/- 96.10, N = 15SE +/- 67.41, N = 11SE +/- 69.56, N = 15SE +/- 75.40, N = 15121683.0576614.8150431.7147020.0142259.9034446.6834198.5329052.4828122.1820654.0619751.0714889.4814149.2510954.719536.168869.367461.611. (CXX) g++ options: -O3

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 FlopsRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 3080RTX 4070RTX 3070 TiRTX 3070TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 207030K60K90K120K150KSE +/- 20.95, N = 3SE +/- 51.45, N = 3SE +/- 15.38, N = 3SE +/- 46.42, N = 3SE +/- 82.80, N = 3SE +/- 72.32, N = 3SE +/- 36.45, N = 3SE +/- 87.54, N = 3SE +/- 77.85, N = 3SE +/- 45.55, N = 3SE +/- 64.35, N = 3SE +/- 46.00, N = 3SE +/- 43.57, N = 3SE +/- 30.90, N = 3SE +/- 29.37, N = 3SE +/- 25.56, N = 3SE +/- 22.91, N = 3124387.0086101.3055618.9053756.1046711.7039944.7039320.0033883.3032743.0023312.3023101.9017332.8016527.7012015.3010952.809869.468528.221. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

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 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 3090RTX 3080RTX 3070RTX 3070 TiTITAN RTXRTX 2080 TiRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPER2004006008001000SE +/- 0.10, N = 7SE +/- 0.12, N = 7SE +/- 0.03, N = 7SE +/- 0.12, N = 7SE +/- 0.04, N = 7SE +/- 0.09, N = 7SE +/- 0.08, N = 7SE +/- 2.75, N = 9SE +/- 2.43, N = 7SE +/- 0.55, N = 6SE +/- 1.85, N = 6SE +/- 4.50, N = 9SE +/- 2.43, N = 6SE +/- 1.00, N = 6SE +/- 0.18, N = 6SE +/- 7.78, N = 6SE +/- 6.81, N = 662.1478.8492.1794.43101.48123.81134.46333.81403.71479.50490.79570.91658.65789.71822.59841.84861.461. (CXX) g++ options: -O3 -march=native -fopenmp

ProjectPhysX OpenCL-Benchmark

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: FP32 ComputeRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 3090RTX 4070 SUPERRTX 3080RTX 4070RTX 3070 TiRTX 3070TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070306090120150SE +/- 0.063, N = 6SE +/- 0.057, N = 5SE +/- 0.013, N = 4SE +/- 0.033, N = 4SE +/- 0.026, N = 4SE +/- 0.068, N = 4SE +/- 0.042, N = 4SE +/- 0.062, N = 4SE +/- 0.009, N = 4SE +/- 0.000, N = 3SE +/- 0.017, N = 3SE +/- 0.046, N = 3SE +/- 0.042, N = 3SE +/- 0.030, N = 3SE +/- 0.029, N = 3SE +/- 0.000, N = 3SE +/- 0.023, N = 3117.80285.72653.62351.57345.01739.64038.22532.87131.68822.66422.30217.26516.52011.89010.9269.7848.5061. (CXX) g++ options: -std=c++17 -pthread -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: GEMM SGEMM_NRTX 5090RTX 4090RTX 4080 SUPERRTX 4080RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 3090RTX 3080TITAN RTXRTX 2080 TiRTX 3070 TiRTX 3070RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 20708K16K24K32K40KSE +/- 15.77, N = 12SE +/- 190.91, N = 11SE +/- 5.53, N = 11SE +/- 6.99, N = 11SE +/- 5.74, N = 11SE +/- 12.00, N = 11SE +/- 28.62, N = 10SE +/- 11.71, N = 10SE +/- 11.00, N = 10SE +/- 34.74, N = 13SE +/- 13.65, N = 9SE +/- 6.89, N = 10SE +/- 23.09, N = 9SE +/- 1.56, N = 8SE +/- 1.06, N = 8SE +/- 0.50, N = 8SE +/- 13.50, N = 835979.9027552.9017850.8017291.1014093.0011454.609662.147919.726121.925189.674807.984647.783812.563683.483329.943306.483043.141. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

Chaos Group V-RAY

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

OpenBenchmarking.orgvpaths, More Is BetterChaos Group V-RAY 6.0Mode: NVIDIA RTX GPURTX 5090RTX 4090RTX 4080RTX 4080 SUPERRTX 4070 Ti SUPERRTX 4070 SUPERRTX 3090RTX 4070RTX 3080RTX 3070 TiRTX 3070TITAN RTXRTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERRTX 2080RTX 20703K6K9K12K15KSE +/- 5.33, N = 3SE +/- 18.91, N = 3SE +/- 5.33, N = 3SE +/- 5.00, N = 3SE +/- 0.00, N = 3SE +/- 5.33, N = 3SE +/- 8.95, N = 3SE +/- 0.00, N = 3SE +/- 9.24, N = 3SE +/- 8.95, N = 3SE +/- 5.33, N = 3SE +/- 2.33, N = 3SE +/- 3.33, N = 3SE +/- 3.33, N = 3SE +/- 6.06, N = 3SE +/- 3.33, N = 3SE +/- 6.06, N = 3119188463597359415134432140643551342527332586219621461653157215481184