NVIDIA RTX 2000 / 4000 / 6000 Ada Generation

Benchmarks for a future article by Michael Larabel of NVIDIA RTX 6000 Ada Generation and other cards against Radeon PRO W7000 series on Linux.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2409147-PTS-NVIDIART65
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 4 Tests
Multi-Core 5 Tests
NVIDIA GPU Compute 9 Tests
OpenCL 3 Tests
Renderers 4 Tests
Server CPU Tests 2 Tests
Common Workstation Benchmarks 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 2000 Ada Generation
September 13
  6 Hours, 12 Minutes
RTX 4000 Ada Generation
September 13
  5 Hours, 1 Minute
RTX 6000 Ada Generation
September 11
  4 Hours, 22 Minutes
Radeon PRO W7500
September 14
  9 Hours, 55 Minutes
Radeon PRO W7600
September 14
  6 Hours, 2 Minutes
Radeon PRO W7700
September 13
  5 Hours, 2 Minutes
Radeon PRO W7900
September 14
  5 Hours, 37 Minutes
Invert Hiding All Results Option
  6 Hours, 2 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 RTX 2000 / 4000 / 6000 Ada GenerationProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen ResolutionRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W7900AMD Ryzen 9 9950X 16-Core @ 8.18GHz (16 Cores / 32 Threads)ASUS ROG STRIX X670E-E GAMING WIFI (2308 BIOS)AMD Device 14d82 x 32GB DDR5-6400MT/s Corsair CMK64GX5M2B6400C32Western Digital WD_BLACK SN850X 2000GBNVIDIA RTX 6000 Ada Generation 48GBNVIDIA AD102 HD AudioDELL U2723QEIntel I225-V + Intel Wi-Fi 6EUbuntu 24.046.8.0-41-generic (x86_64)GNOME Shell 46.0X Server 1.21.1.11NVIDIA 560.35.034.6.0OpenCL 3.0 CUDA 12.6.65GCC 13.2.0ext43840x2160NVIDIA RTX 2000 Ada Generation 16GBNVIDIA Device 22beNVIDIA RTX 4000 Ada Generation 20GBNVIDIA Device 22bcAMD Radeon PRO W7700 15GBAMD Navi 31 HDMI/DPX Server 1.21.1.11 + Wayland4.6 Mesa 24.2.0-devel (LLVM 18.1.7 DRM 3.58)OpenCL 2.1 AMD-APP (3625.0)AMD Radeon PRO W7500 8GBAMD Radeon PRO W7600 8GBAMD Radeon PRO W7900 45GBOpenBenchmarking.orgKernel Details- RTX 6000 Ada Generation: nouveau.modeset=0 - Transparent Huge Pages: madvise- RTX 2000 Ada Generation: nouveau.modeset=0 - Transparent Huge Pages: madvise- RTX 4000 Ada Generation: nouveau.modeset=0 - Transparent Huge Pages: madvise- Radeon PRO W7700: Transparent Huge Pages: madvise- Radeon PRO W7500: Transparent Huge Pages: madvise- Radeon PRO W7600: Transparent Huge Pages: madvise- Radeon PRO W7900: Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/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-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb40401cGraphics Details- RTX 6000 Ada Generation: BAR1 / Visible vRAM Size: 65536 MiB - vBIOS Version: 95.02.3a.00.01- RTX 2000 Ada Generation: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.07.47.00.05- RTX 4000 Ada Generation: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.04.5c.00.0d- Radeon PRO W7700: BAR1 / Visible vRAM Size: 15344 MB- Radeon PRO W7500: BAR1 / Visible vRAM Size: 8176 MB- Radeon PRO W7600: BAR1 / Visible vRAM Size: 8176 MB- Radeon PRO W7900: BAR1 / Visible vRAM Size: 46064 MBOpenCL Details- RTX 6000 Ada Generation: GPU Compute Cores: 18176- RTX 2000 Ada Generation: GPU Compute Cores: 2816- RTX 4000 Ada Generation: GPU Compute Cores: 6144Python Details- Python 3.12.3Security Details- 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; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W7900Result OverviewPhoronix Test Suite100%299%499%698%897%LuxCoreRendervkpeakclpeakProjectPhysX OpenCL-BenchmarkGpuOwlFluidX3DSPECViewPerf 2020IndigoBenchFinanceBenchParaView

RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W7900Per Watt Result OverviewPhoronix Test Suite100%150%200%249%299%ParaViewLuxCoreRenderProjectPhysX OpenCL-BenchmarkFluidX3DGpuOwlSPECViewPerf 2020vkpeakIndigoBenchclpeakP.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 RTX 2000 / 4000 / 6000 Ada Generationvkpeak: fp32-scalarluxcorerender: Danish Mood - GPUvkpeak: fp16-scalaropencl-benchmark: INT8 Computevkpeak: int16-vec4clpeak: Integer 24-bit Computeclpeak: Double-Precision Computevkpeak: fp64-scalaropencl-benchmark: FP64 Computevkpeak: fp64-vec4gpuowl: 332220523vkpeak: int16-scalaropencl-benchmark: INT16 Computegpuowl: 57885161gpuowl: 77936867fluidx3d: FP32-FP16Cfluidx3d: FP32-FP16Sfluidx3d: FP32-FP32financebench: Black-Scholes OpenCLopencl-benchmark: Memory Bandwidth Coalesced Readclpeak: Global Memory Bandwidthopencl-benchmark: Memory Bandwidth Coalesced Writeluxcorerender: Rainbow Colors and Prism - GPUblender: Pabellon Barcelona - NVIDIA CUDAspecviewperf2020: 2560 x 1440 - SNX-04indigobench: OpenCL GPU - Bedroomblender: Fishy Cat - NVIDIA CUDArodinia: OpenCL Particle Filterblender: Classroom - NVIDIA CUDAparaview: Wavelet Contour - 3000 - 3840 x 2160paraview: Wavelet Volume - 3000 - 3840 x 2160v-ray: NVIDIA CUDA GPUparaview: Wavelet Contour - 3000 - 2560 x 1440blender: Fishy Cat - NVIDIA OptiXblender: Barbershop - NVIDIA CUDAblender: BMW27 - NVIDIA CUDAv-ray: NVIDIA RTX GPUopencl-benchmark: INT64 Computeindigobench: OpenCL GPU - Supercarblender: Pabellon Barcelona - Radeon HIPblender: Barbershop - Radeon HIPblender: Classroom - Radeon HIPblender: Fishy Cat - Radeon HIPparaview: Many Spheres - 3000 - 3840 x 2160blender: Classroom - NVIDIA OptiXspecviewperf2020: 2560 x 1440 - SOLIDWORKS-07paraview: Many Spheres - 3000 - 2560 x 1440specviewperf2020: 2560 x 1440 - MAYA-06blender: Pabellon Barcelona - NVIDIA OptiXspecviewperf2020: 2560 x 1440 - CATIA-06blender: Barbershop - NVIDIA OptiXblender: Junkshop - NVIDIA CUDAblender: Junkshop - Radeon HIPblender: BMW27 - Radeon HIPfinancebench: Monte-Carlo OpenCLblender: Junkshop - NVIDIA OptiXparaview: Wavelet Volume - 3000 - 2560 x 1440blender: BMW27 - NVIDIA OptiXspecviewperf2020: 2560 x 1440 - CREO-03fahbench: luxcorerender: Orange Juice - GPUvkpeak: fp32-vec4opencl-benchmark: FP32 Computeclpeak: Single-Precision Computespecviewperf2020: 2560 x 1440 - MEDICAL-O3vkpeak: fp16-vec4specviewperf2020: 2560 x 1440 - ENERGY-03luxcorerender: LuxCore Benchmark - GPUluxcorerender: DLSC - GPUparaview: Wavelet Volume - 3000 - 3840 x 2160paraview: Wavelet Volume - 3000 - 2560 x 1440paraview: Wavelet Contour - 3000 - 3840 x 2160paraview: Wavelet Contour - 3000 - 2560 x 1440paraview: Many Spheres - 3000 - 3840 x 2160paraview: Many Spheres - 3000 - 2560 x 1440RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790048174.3317.7246258.4321.79238953.7140310.581534.701538.941.511533.64322.4231027.6632.2972043.601490.31105851020852522.710865.57815.91850.0435.6521.301026.5629.28210.672.09110.44625.76639.675984811.195.4845.655.5781743.77473.905158.477.92578.10167.61813.188.86236.9632.9111.0899.2392877.34853.683.61256.46462.313115.8662508.5490.80583188.79211.9893562.47156.1717.7818.9510234.76213658.9056521.1528453.56715887.66716804.1386944.944.096968.174.7876167.155965.80217.61218.820.215218.8247.854634.075.947308.39226.6425312434133116.228143207.71195.00211.8111.92108.95285.228.16147.269.20645.87145.70150.831419194.0122.74188.7622.5320231.73524.39943.2928.55184.7347.27276.4431.0783.69114.4538.40266.03514322.30285.7310.45113.82207.85005.219186.8113.43911596.8265.6013745.3031.734.634.612413.3354571.6351518.3562021.8214339.6574739.46613990.276.9213985.479.69212381.1113209.06439.32440.870.433440.0195.309328.0111.483612.37449.514039377020477.693326.85307.54333.7817.6259.20423.6612.87826.134.99126.56267.98269.031960346.7712.90107.8513.2629272.82436.91589.0417.86308.7296.58430.1019.40142.9572.3622.96199.92686014.62466.707.19170.61281.64647.7018498.6426.96125785.6897.3527650.7062.748.037.964304.5147467.0902792.6543613.7118926.8069682.32112385.234.1612392.956.11525011.6911408.66462.25484.510.469484.53102.1012377.1410.693735.11545.262865291116326.779403.72391.21308.9314.98360.2312.033320.57340.94400.302.36436.45290.92164.7340.4539.9496.28336.76109.72501.38137.5631.3622.45152.220712564.16208.572.3110997.0714.35312304.2433.2625066.8536.674.904.095455.0819026.5703340.7254171.5749652.08210999.5404887.921.905005.482.7278451.355462.75238.56235.120.237229.9249.084897.024.855315.99226.911682163085612.201146.92139.39149.236.92209.926.370160.57151.97218.561.04718.503181.37348.2684.3979.1249.08162.1755.01229.6567.8463.3845.14327.081569291.53113.671.054345.636.4806072.1616.028701.8714.532.191.922431.5364664.4031673.2592277.7054920.5485514.7727784.732.557839.683.82015006.126985.95332.83332.940.324329.5266.187740.886.731467.65345.112317219411779.724237.72220.39213.469.27263.698.740212.95229.33274.721.46325.080135.28258.0663.0158.4568.77216.5275.07316.2587.8747.9734.40261.737998398.03151.461.296876.758.9197710.9525.2715112.5323.033.012.543669.2946368.4912219.2022862.8776894.4587526.37225619.416.6225838.0812.56648689.6822802.741096.591118.441.0571117.47206.3025473.8922.4591460.581088.535503465027963.382590.24496.42459.2220.69582.3019.348582.89589.04734.054.22654.96947.2191.4422.2821.42147.76530.89168.48770.35203.2218.6713.52100.719712653.03276.102.9322828.3731.03125936.6553.7149210.0967.467.696.289424.65110448.3916074.4267649.73914813.52516890.756OpenBenchmarking.org

vkpeak

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

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp32-scalarRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790010K20K30K40K50KSE +/- 370.02, N = 3SE +/- 12.68, N = 3SE +/- 16.39, N = 3SE +/- 10.33, N = 3SE +/- 42.52, N = 8SE +/- 53.71, N = 3SE +/- 289.96, N = 448174.336944.9413990.2712385.234887.927784.7325619.41

LuxCoreRender

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

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Danish Mood - Acceleration: GPURTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790048121620SE +/- 0.17, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 317.724.096.924.161.902.556.62MIN: 6.81 / MAX: 20.39MIN: 1.83 / MAX: 4.63MIN: 3.18 / MAX: 7.9MIN: 1.91 / MAX: 4.68MIN: 0.73 / MAX: 2.13MIN: 1.07 / MAX: 2.84MIN: 2.89 / MAX: 7.51

vkpeak

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

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp16-scalarRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790010K20K30K40K50KSE +/- 153.56, N = 3SE +/- 14.03, N = 3SE +/- 9.85, N = 3SE +/- 3.75, N = 3SE +/- 32.58, N = 8SE +/- 11.58, N = 3SE +/- 158.36, N = 446258.436968.1713985.4712392.955005.487839.6825838.08

ProjectPhysX OpenCL-Benchmark

ProjectPhysX OpenCL-Benchmark provides various OpenCL compute and memory bandwidth micro-benchmarks Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT8 ComputeRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W7900510152025SE +/- 0.068, N = 6SE +/- 0.011, N = 3SE +/- 0.017, N = 4SE +/- 0.012, N = 3SE +/- 0.035, N = 3SE +/- 0.070, N = 3SE +/- 0.050, N = 521.7924.7879.6926.1152.7273.82012.5661. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

vkpeak

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

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20230730int16-vec4RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790010K20K30K40K50KSE +/- 89.71, N = 3SE +/- 0.02, N = 3SE +/- 0.51, N = 3SE +/- 5.00, N = 3SE +/- 28.67, N = 8SE +/- 2.93, N = 3SE +/- 18.90, N = 438953.716167.1512381.1125011.698451.3515006.1248689.68

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 24-bit ComputeRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79009K18K27K36K45KSE +/- 289.03, N = 15SE +/- 17.53, N = 13SE +/- 6.66, N = 13SE +/- 27.65, N = 13SE +/- 25.04, N = 12SE +/- 31.15, N = 13SE +/- 99.46, N = 1340310.585965.8013209.0611408.665462.756985.9522802.741. (CXX) g++ options: -O3

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Double-Precision ComputeRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790030060090012001500SE +/- 2.12, N = 6SE +/- 0.22, N = 5SE +/- 0.36, N = 5SE +/- 1.47, N = 7SE +/- 0.17, N = 7SE +/- 0.86, N = 7SE +/- 0.78, N = 81534.70217.61439.32462.25238.56332.831096.591. (CXX) g++ options: -O3

vkpeak

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

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp64-scalarRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790030060090012001500SE +/- 0.14, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.12, N = 3SE +/- 0.81, N = 8SE +/- 0.01, N = 3SE +/- 0.27, N = 41538.94218.82440.87484.51235.12332.941118.44

ProjectPhysX OpenCL-Benchmark

ProjectPhysX OpenCL-Benchmark provides various OpenCL compute and memory bandwidth micro-benchmarks Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: FP64 ComputeRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79000.33980.67961.01941.35921.699SE +/- 0.000, N = 6SE +/- 0.000, N = 3SE +/- 0.000, N = 4SE +/- 0.002, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 51.5100.2150.4330.4690.2370.3241.0571. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

vkpeak

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

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp64-vec4RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790030060090012001500SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.73, N = 8SE +/- 0.04, N = 3SE +/- 0.18, N = 41533.64218.82440.01484.53229.92329.521117.47

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 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790070140210280350SE +/- 1.45, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 3322.4247.8595.30102.1049.0866.18206.301. (CXX) g++ options: -O3 -lgmp -lOpenCL

vkpeak

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

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20230730int16-scalarRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79007K14K21K28K35KSE +/- 5.73, N = 3SE +/- 8.93, N = 3SE +/- 11.44, N = 3SE +/- 0.51, N = 3SE +/- 15.50, N = 8SE +/- 0.62, N = 3SE +/- 13.76, N = 431027.664634.079328.0112377.144897.027740.8825473.89

ProjectPhysX OpenCL-Benchmark

ProjectPhysX OpenCL-Benchmark provides various OpenCL compute and memory bandwidth micro-benchmarks Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT16 ComputeRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W7900816243240SE +/- 0.127, N = 6SE +/- 0.011, N = 3SE +/- 0.004, N = 4SE +/- 0.062, N = 3SE +/- 0.078, N = 3SE +/- 0.221, N = 3SE +/- 0.144, N = 532.2975.94711.48310.6934.8556.73122.4591. (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: 57885161RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W7900400800120016002000SE +/- 1.39, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.18, N = 3SE +/- 0.23, N = 3SE +/- 0.07, N = 3SE +/- 2.85, N = 32043.60308.39612.37735.11315.99467.651460.581. (CXX) g++ options: -O3 -lgmp -lOpenCL

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 77936867RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790030060090012001500SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.60, N = 3SE +/- 0.22, N = 3SE +/- 1.00, N = 3SE +/- 0.40, N = 31490.31226.64449.51545.26226.91345.111088.531. (CXX) g++ options: -O3 -lgmp -lOpenCL

FluidX3D

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.17Test: FP32-FP16CRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79002K4K6K8K10KSE +/- 3.50, N = 4SE +/- 1.67, N = 3SE +/- 2.03, N = 3SE +/- 2.73, N = 3SE +/- 0.00, N = 3SE +/- 3.84, N = 3SE +/- 73.37, N = 310585253140392865168223175503

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.17Test: FP32-FP16SRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79002K4K6K8K10KSE +/- 2.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 1.45, N = 3SE +/- 2.31, N = 3SE +/- 0.88, N = 3SE +/- 12.73, N = 310208243437702911163021944650

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.17Test: FP32-FP32RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790011002200330044005500SE +/- 16.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 1.15, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 7.22, N = 3525213312047163285611772796

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 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790048121620SE +/- 0.003806, N = 15SE +/- 0.001644, N = 14SE +/- 0.041867, N = 15SE +/- 0.015787, N = 15SE +/- 0.061748, N = 14SE +/- 0.061700, N = 15SE +/- 0.017790, N = 152.71000016.2281437.6930006.77900012.2010009.7240003.3820001. (CXX) g++ options: -O3 -march=native -fopenmp

ProjectPhysX OpenCL-Benchmark

ProjectPhysX OpenCL-Benchmark provides various OpenCL compute and memory bandwidth micro-benchmarks Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: Memory Bandwidth Coalesced ReadRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79002004006008001000SE +/- 0.06, N = 6SE +/- 0.00, N = 3SE +/- 0.00, N = 4SE +/- 10.49, N = 3SE +/- 0.32, N = 3SE +/- 2.74, N = 3SE +/- 2.98, N = 5865.57207.71326.85403.72146.92237.72590.241. (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.orgGBPS, More Is Betterclpeak 1.1.2OpenCL Test: Global Memory BandwidthRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79002004006008001000SE +/- 0.03, N = 11SE +/- 0.06, N = 7SE +/- 0.05, N = 8SE +/- 0.98, N = 8SE +/- 0.08, N = 5SE +/- 0.18, N = 7SE +/- 1.00, N = 9815.91195.00307.54391.21139.39220.39496.421. (CXX) g++ options: -O3

ProjectPhysX OpenCL-Benchmark

ProjectPhysX OpenCL-Benchmark provides various OpenCL compute and memory bandwidth micro-benchmarks Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: Memory Bandwidth Coalesced WriteRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79002004006008001000SE +/- 0.26, N = 6SE +/- 0.01, N = 3SE +/- 0.02, N = 4SE +/- 3.49, N = 3SE +/- 1.37, N = 3SE +/- 2.65, N = 3SE +/- 1.25, N = 5850.04211.81333.78308.93149.23213.46459.221. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

LuxCoreRender

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

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: GPURTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W7900816243240SE +/- 0.09, N = 7SE +/- 0.02, N = 4SE +/- 0.04, N = 5SE +/- 0.01, N = 5SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 535.6511.9217.6214.986.929.2720.69MIN: 31.82 / MAX: 39.14MIN: 10.89 / MAX: 12.56MIN: 16.21 / MAX: 18.4MIN: 13.88 / MAX: 15.48MIN: 6.36 / MAX: 7.09MIN: 8.58 / MAX: 9.52MIN: 19.26 / MAX: 21.65

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Pabellon Barcelona - Compute: NVIDIA CUDARTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation20406080100SE +/- 0.09, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 321.30108.9559.20

SPECViewPerf 2020

This test runs SPECViewPerf 2020 if available on your system. SPECViewPerf is made up of real-world OpenGL workstation tests such as CATIA and SolidWorks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 2560 x 1440 - Viewset: SNX-04RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79002004006008001000SE +/- 5.90, N = 3SE +/- 0.62, N = 3SE +/- 0.27, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.42, N = 31026.56285.22423.66360.23209.92263.69582.30

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 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W7900714212835SE +/- 0.029, N = 3SE +/- 0.002, N = 3SE +/- 0.009, N = 3SE +/- 0.004, N = 3SE +/- 0.003, N = 3SE +/- 0.002, N = 3SE +/- 0.007, N = 329.2828.16112.87812.0336.3708.74019.348

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Fishy Cat - Compute: NVIDIA CUDARTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation1122334455SE +/- 0.01, N = 5SE +/- 0.01, N = 3SE +/- 0.02, N = 310.6747.2626.13

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 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation3691215SE +/- 0.004, N = 11SE +/- 0.009, N = 5SE +/- 0.005, N = 72.0919.2064.9911. (CXX) g++ options: -O2 -lOpenCL

Test: OpenCL Particle Filter

Radeon PRO W7700: The test run did not produce a result. E: ERROR: clEnqueueNDRangeKernel(kernel_likelihood)=>-54 failed

Radeon PRO W7500: The test run did not produce a result. E: ERROR: clEnqueueNDRangeKernel(kernel_likelihood)=>-54 failed

Radeon PRO W7600: The test run did not produce a result. E: ERROR: clEnqueueNDRangeKernel(kernel_likelihood)=>-54 failed

Radeon PRO W7900: The test run did not produce a result. E: ERROR: clEnqueueNDRangeKernel(kernel_likelihood)=>-54 failed

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Classroom - Compute: NVIDIA CUDARTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation1020304050SE +/- 0.02, N = 5SE +/- 0.01, N = 3SE +/- 0.01, N = 310.4445.8726.56

ParaView

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.13Test: Wavelet Contour - Frames: 3000 - Resolution: 3840 x 2160RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W7900140280420560700SE +/- 0.45, N = 3SE +/- 0.11, N = 3SE +/- 0.16, N = 3SE +/- 0.57, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.90, N = 3625.76145.70267.98320.57160.57212.95582.89

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.13Test: Wavelet Volume - Frames: 3000 - Resolution: 3840 x 2160RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W7900140280420560700SE +/- 6.56, N = 3SE +/- 0.22, N = 3SE +/- 0.11, N = 3SE +/- 0.42, N = 3SE +/- 0.19, N = 3SE +/- 0.07, N = 3SE +/- 2.09, N = 3639.67150.83269.03340.94151.97229.33589.04

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 CUDA GPURTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation13002600390052006500SE +/- 24.01, N = 3SE +/- 3.67, N = 3SE +/- 0.00, N = 3598414191960

ParaView

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.13Test: Wavelet Contour - Frames: 3000 - Resolution: 2560 x 1440RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79002004006008001000SE +/- 0.63, N = 3SE +/- 0.41, N = 3SE +/- 0.38, N = 3SE +/- 0.87, N = 3SE +/- 0.14, N = 3SE +/- 0.38, N = 3SE +/- 1.91, N = 3811.19194.01346.77400.30218.56274.72734.05

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation510152025SE +/- 0.05, N = 15SE +/- 0.01, N = 3SE +/- 0.01, N = 45.4822.7412.90

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Barbershop - Compute: NVIDIA CUDARTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation4080120160200SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 345.65188.76107.85

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: BMW27 - Compute: NVIDIA CUDARTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation510152025SE +/- 0.01, N = 7SE +/- 0.02, N = 3SE +/- 0.02, N = 45.5722.5313.26

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 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation2K4K6K8K10KSE +/- 8.95, N = 3SE +/- 0.00, N = 3SE +/- 13.86, N = 3817420232927

ProjectPhysX OpenCL-Benchmark

ProjectPhysX OpenCL-Benchmark provides various OpenCL compute and memory bandwidth micro-benchmarks Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT64 ComputeRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79000.95091.90182.85273.80364.7545SE +/- 0.021, N = 6SE +/- 0.009, N = 3SE +/- 0.060, N = 4SE +/- 0.006, N = 3SE +/- 0.005, N = 3SE +/- 0.004, N = 3SE +/- 0.016, N = 53.7741.7352.8242.3641.0471.4634.2261. (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 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79001632486480SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.10, N = 373.9124.4036.9236.4518.5025.0854.97

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Pabellon Barcelona - Compute: Radeon HIPRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79004080120160200SE +/- 0.04, N = 3SE +/- 0.25, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 390.92181.37135.2847.21

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Barbershop - Compute: Radeon HIPRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790080160240320400SE +/- 0.16, N = 3SE +/- 0.08, N = 3SE +/- 0.71, N = 3SE +/- 0.06, N = 3164.73348.26258.0691.44

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Classroom - Compute: Radeon HIPRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790020406080100SE +/- 0.02, N = 3SE +/- 0.16, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 340.4584.3963.0122.28

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Fishy Cat - Compute: Radeon HIPRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790020406080100SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 339.9479.1258.4521.42

ParaView

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.13Test: Many Spheres - Frames: 3000 - Resolution: 3840 x 2160RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79004080120160200SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.11, N = 3158.4743.2989.0496.2849.0868.77147.76

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Classroom - Compute: NVIDIA OptiXRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation714212835SE +/- 0.01, N = 6SE +/- 0.06, N = 3SE +/- 0.03, N = 37.9228.5517.86

SPECViewPerf 2020

This test runs SPECViewPerf 2020 if available on your system. SPECViewPerf is made up of real-world OpenGL workstation tests such as CATIA and SolidWorks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 2560 x 1440 - Viewset: SOLIDWORKS-07RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W7900120240360480600SE +/- 0.20, N = 3SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.28, N = 3SE +/- 0.25, N = 3SE +/- 0.09, N = 3SE +/- 0.42, N = 3578.10184.73308.72336.76162.17216.52530.89

ParaView

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.13Test: Many Spheres - Frames: 3000 - Resolution: 2560 x 1440RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79004080120160200SE +/- 0.74, N = 3SE +/- 0.12, N = 3SE +/- 0.05, N = 3SE +/- 0.18, N = 3SE +/- 0.05, N = 3SE +/- 0.25, N = 3SE +/- 0.41, N = 3167.6147.2796.58109.7255.0175.07168.48

SPECViewPerf 2020

This test runs SPECViewPerf 2020 if available on your system. SPECViewPerf is made up of real-world OpenGL workstation tests such as CATIA and SolidWorks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 2560 x 1440 - Viewset: MAYA-06RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79002004006008001000SE +/- 0.66, N = 3SE +/- 0.26, N = 3SE +/- 0.09, N = 3SE +/- 1.26, N = 3SE +/- 0.58, N = 3SE +/- 0.09, N = 3SE +/- 4.21, N = 3813.18276.44430.10501.38229.65316.25770.35

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation714212835SE +/- 0.01, N = 5SE +/- 0.04, N = 3SE +/- 0.01, N = 38.8631.0719.40

SPECViewPerf 2020

This test runs SPECViewPerf 2020 if available on your system. SPECViewPerf is made up of real-world OpenGL workstation tests such as CATIA and SolidWorks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 2560 x 1440 - Viewset: CATIA-06RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790050100150200250SE +/- 1.01, N = 3SE +/- 0.26, N = 3SE +/- 0.05, N = 3SE +/- 0.33, N = 3SE +/- 0.57, N = 3SE +/- 0.37, N = 3SE +/- 1.26, N = 3236.9683.69142.95137.5667.8487.87203.22

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Barbershop - Compute: NVIDIA OptiXRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation306090120150SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 332.91114.4572.36

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Junkshop - Compute: NVIDIA CUDARTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation918273645SE +/- 0.01, N = 4SE +/- 0.04, N = 3SE +/- 0.03, N = 311.0838.4022.96

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Junkshop - Compute: Radeon HIPRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79001428425670SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 331.3663.3847.9718.67

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: BMW27 - Compute: Radeon HIPRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79001020304050SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 422.4545.1434.4013.52

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 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790070140210280350SE +/- 0.04, N = 7SE +/- 0.11, N = 7SE +/- 0.04, N = 7SE +/- 0.22, N = 7SE +/- 0.35, N = 7SE +/- 0.99, N = 7SE +/- 0.25, N = 799.24266.04199.93152.22327.08261.74100.721. (CXX) g++ options: -O3 -march=native -fopenmp

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Junkshop - Compute: NVIDIA OptiXRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation510152025SE +/- 0.01, N = 6SE +/- 0.04, N = 3SE +/- 0.02, N = 47.3422.3014.62

ParaView

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.13Test: Wavelet Volume - Frames: 3000 - Resolution: 2560 x 1440RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79002004006008001000SE +/- 2.56, N = 3SE +/- 0.37, N = 3SE +/- 0.99, N = 3SE +/- 1.43, N = 3SE +/- 0.21, N = 3SE +/- 1.21, N = 3SE +/- 2.07, N = 3853.68285.73466.70564.16291.53398.03653.03

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: BMW27 - Compute: NVIDIA OptiXRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation3691215SE +/- 0.00, N = 8SE +/- 0.01, N = 5SE +/- 0.01, N = 63.6110.457.19

SPECViewPerf 2020

This test runs SPECViewPerf 2020 if available on your system. SPECViewPerf is made up of real-world OpenGL workstation tests such as CATIA and SolidWorks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 2560 x 1440 - Viewset: CREO-03RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790060120180240300SE +/- 0.47, N = 3SE +/- 0.07, N = 3SE +/- 0.17, N = 3SE +/- 0.14, N = 3SE +/- 0.13, N = 3SE +/- 0.08, N = 3SE +/- 0.53, N = 3256.46113.82170.61208.57113.67151.46276.10

FAHBench

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

OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.2RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada Generation100200300400500SE +/- 0.94, N = 3SE +/- 0.16, N = 3SE +/- 0.14, N = 3462.31207.85281.65

Radeon PRO W7700: The test run did not produce a result.

Radeon PRO W7500: The test run did not produce a result.

Radeon PRO W7600: The test run did not produce a result.

Radeon PRO W7900: The test run did not produce a result.

LuxCoreRender

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

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: GPURTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790048121620SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 315.865.217.702.311.051.292.93MIN: 13.68 / MAX: 21.62MIN: 4.19 / MAX: 6.51MIN: 6.01 / MAX: 9.92MIN: 2.09 / MAX: 3.15MIN: 2.69 / MAX: 3.71

vkpeak

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

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp32-vec4RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790013K26K39K52K65KSE +/- 485.03, N = 3SE +/- 18.50, N = 3SE +/- 31.57, N = 3SE +/- 6.54, N = 3SE +/- 32.25, N = 8SE +/- 16.67, N = 3SE +/- 342.60, N = 462508.549186.8118498.6410997.074345.636876.7522828.37

ProjectPhysX OpenCL-Benchmark

ProjectPhysX OpenCL-Benchmark provides various OpenCL compute and memory bandwidth micro-benchmarks Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: FP32 ComputeRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790020406080100SE +/- 0.081, N = 6SE +/- 0.000, N = 3SE +/- 0.002, N = 4SE +/- 0.040, N = 3SE +/- 0.102, N = 3SE +/- 0.135, N = 3SE +/- 0.188, N = 590.80513.43926.96114.3536.4808.91931.0311. (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: Single-Precision ComputeRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790020K40K60K80K100KSE +/- 359.84, N = 13SE +/- 14.33, N = 15SE +/- 26.99, N = 13SE +/- 27.07, N = 12SE +/- 9.29, N = 12SE +/- 14.09, N = 12SE +/- 73.46, N = 1283188.7911596.8225785.6812304.246072.167710.9525936.651. (CXX) g++ options: -O3

SPECViewPerf 2020

This test runs SPECViewPerf 2020 if available on your system. SPECViewPerf is made up of real-world OpenGL workstation tests such as CATIA and SolidWorks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 2560 x 1440 - Viewset: MEDICAL-O3RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790050100150200250SE +/- 0.21, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3211.9865.6097.3533.2616.0225.2753.71

vkpeak

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

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp16-vec4RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790020K40K60K80K100KSE +/- 692.18, N = 3SE +/- 27.78, N = 3SE +/- 16.63, N = 3SE +/- 8.54, N = 3SE +/- 53.19, N = 8SE +/- 2.46, N = 3SE +/- 135.83, N = 493562.4713745.3027650.7025066.858701.8715112.5349210.09

SPECViewPerf 2020

This test runs SPECViewPerf 2020 if available on your system. SPECViewPerf is made up of real-world OpenGL workstation tests such as CATIA and SolidWorks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 2560 x 1440 - Viewset: ENERGY-03RTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W7900306090120150SE +/- 0.57, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3156.1731.7362.7436.6714.5323.0367.46

GPU Temperature Monitor

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79001632486480Min: 41 / Avg: 72.97 / Max: 87Min: 36 / Avg: 66.43 / Max: 79Min: 29 / Avg: 63.59 / Max: 80Min: 31 / Avg: 68.93 / Max: 83Min: 30 / Avg: 74.13 / Max: 83Min: 27 / Avg: 76.2 / Max: 86Min: 27 / Avg: 70.28 / Max: 80

GPU Power Consumption Monitor

OpenBenchmarking.orgWattsGPU Power Consumption MonitorPhoronix Test Suite System MonitoringRTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790050100150200250Min: 21.72 / Avg: 191 / Max: 303.57Min: 7.09 / Avg: 47.88 / Max: 70Min: 6.46 / Avg: 78.35 / Max: 130.8Min: 5 / Avg: 111.28 / Max: 154Min: 1 / Avg: 43.46 / Max: 54Min: 1 / Avg: 79.44 / Max: 101Min: 8 / Avg: 189.77 / Max: 249

LuxCoreRender

MinAvgMaxRTX 6000 Ada Generation53.068.183.0RTX 2000 Ada Generation56.069.173.0RTX 4000 Ada Generation53.067.372.0Radeon PRO W770064.077.483.0Radeon PRO W750060.075.279.0Radeon PRO W760064.080.183.0Radeon PRO W790053.073.077.0OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.6GPU Temperature Monitor20406080100

MinAvgMaxRTX 6000 Ada Generation27.1169.0299.9RTX 2000 Ada Generation7.754.862.5RTX 4000 Ada Generation14.393.3105.9Radeon PRO W77008.0130.9154.0Radeon PRO W75001.045.653.0Radeon PRO W76001.084.7100.0Radeon PRO W790012.0209.3245.0OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6GPU Power Consumption Monitor80160240320400

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: GPURTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79000.02360.04720.07080.09440.1180.1050.0840.0860.0370.0480.0360.037

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: GPURTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W790048121620SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.12, N = 12SE +/- 0.05, N = 12SE +/- 0.07, N = 12SE +/- 0.18, N = 1217.784.638.034.902.193.017.69MIN: 7.98 / MAX: 20.82MIN: 1.89 / MAX: 5.26MIN: 3.12 / MAX: 9.08MIN: 0.86 / MAX: 5.64MIN: 0.35 / MAX: 2.52MIN: 0.48 / MAX: 3.47MIN: 1.31 / MAX: 8.88

MinAvgMaxRTX 6000 Ada Generation63.081.485.0RTX 2000 Ada Generation56.071.776.0RTX 4000 Ada Generation54.070.174.0Radeon PRO W770045.074.881.0Radeon PRO W750042.074.680.0Radeon PRO W760040.078.984.0Radeon PRO W790046.074.077.0OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.6GPU Temperature Monitor20406080100

MinAvgMaxRTX 6000 Ada Generation32.7279.1300.3RTX 2000 Ada Generation7.760.765.8RTX 4000 Ada Generation14.6102.3111.7Radeon PRO W77007.0138.0154.0Radeon PRO W75001.048.654.0Radeon PRO W76001.090.7100.0Radeon PRO W790014.0222.0249.0OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6GPU Power Consumption Monitor80160240320400

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: GPURTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W79000.01760.03520.05280.07040.0880.0680.0760.0780.0300.0390.0280.028

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: GPURTX 6000 Ada GenerationRTX 2000 Ada GenerationRTX 4000 Ada GenerationRadeon PRO W7700Radeon PRO W7500Radeon PRO W7600Radeon PRO W7900510152025SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 12SE +/- 0.05, N = 12SE +/- 0.07, N = 12SE +/- 0.17, N = 1218.954.617.964.091.922.546.28MIN: 18.15 / MAX: 19.18MIN: 4.41 / MAX: 4.76MIN: 7.71 / MAX: 8.17MIN: 0.84 / MAX: 4.42MIN: 0.52 / MAX: 2.75MIN: 1.27 / MAX: 6.75

77 Results Shown

vkpeak
LuxCoreRender
vkpeak
ProjectPhysX OpenCL-Benchmark
vkpeak
clpeak:
  Integer 24-bit Compute
  Double-Precision Compute
vkpeak
ProjectPhysX OpenCL-Benchmark
vkpeak
GpuOwl
vkpeak
ProjectPhysX OpenCL-Benchmark
GpuOwl:
  57885161
  77936867
FluidX3D:
  FP32-FP16C
  FP32-FP16S
  FP32-FP32
FinanceBench
ProjectPhysX OpenCL-Benchmark
clpeak
ProjectPhysX OpenCL-Benchmark
LuxCoreRender
Blender
SPECViewPerf 2020
IndigoBench
Blender
Rodinia
Blender
ParaView:
  Wavelet Contour - 3000 - 3840 x 2160
  Wavelet Volume - 3000 - 3840 x 2160
Chaos Group V-RAY
ParaView
Blender:
  Fishy Cat - NVIDIA OptiX
  Barbershop - NVIDIA CUDA
  BMW27 - NVIDIA CUDA
Chaos Group V-RAY
ProjectPhysX OpenCL-Benchmark
IndigoBench
Blender:
  Pabellon Barcelona - Radeon HIP
  Barbershop - Radeon HIP
  Classroom - Radeon HIP
  Fishy Cat - Radeon HIP
ParaView
Blender
SPECViewPerf 2020
ParaView
SPECViewPerf 2020
Blender
SPECViewPerf 2020
Blender:
  Barbershop - NVIDIA OptiX
  Junkshop - NVIDIA CUDA
  Junkshop - Radeon HIP
  BMW27 - Radeon HIP
FinanceBench
Blender
ParaView
Blender
SPECViewPerf 2020
FAHBench
LuxCoreRender
vkpeak
ProjectPhysX OpenCL-Benchmark
clpeak
SPECViewPerf 2020
vkpeak
SPECViewPerf 2020
GPU Temperature Monitor:
  Phoronix Test Suite System Monitoring:
    Celsius
    Watts
  GPU Temp Monitor:
    Celsius
  GPU Power Consumption Monitor:
    Watts
  LuxCore Benchmark - GPU:
    M samples/sec Per Watt
LuxCoreRender
LuxCoreRender:
  GPU Temp Monitor
  GPU Power Consumption Monitor
  DLSC - GPU
LuxCoreRender