NVIDIA RTX A2000 And RTX A4000 Linux Benchmarks Against AMD Radeon PRO

NVIDIA RTX A2000 / RTX A4000 benchmarks by Michael Larabel for a future article on Phoronix.com

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2407082-PTS-RTXADAPR74
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:

Creator Workloads 2 Tests
Multi-Core 2 Tests
NVIDIA GPU Compute 2 Tests
OpenCL 2 Tests
Renderers 2 Tests
Common Workstation Benchmarks 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs
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
NVIDIA RTX 2000 Ada
July 06
  3 Hours, 47 Minutes
NVIDIA RTX 4000 Ada
July 05
  3 Hours, 19 Minutes
AMD PRO W7500
July 07
  4 Hours, 52 Minutes
AMD PRO W7600
July 08
  4 Hours, 2 Minutes
AMD PRO W7700
July 07
  3 Hours, 26 Minutes
Invert Hiding All Results Option
  3 Hours, 53 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 A2000 And RTX A4000 Linux Benchmarks Against AMD Radeon PROProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionNVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W7700AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads)ASUS ROG STRIX X670E-E GAMING WIFI (2007 BIOS)AMD Device 14d82 x 16GB DRAM-6000MT/s G Skill F5-6000J3038F16GWestern Digital WD_BLACK SN850X 2000GB + 64GB Flash DriveNVIDIA RTX 2000 Ada Generation 16GBNVIDIA Device 22beDELL U2723QEIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 22.046.5.0-41-generic (x86_64)GNOME Shell 42.9X Server 1.21.1.4NVIDIA 555.58.024.6.0OpenCL 3.0 CUDA 12.5.851.3.278GCC 12.3.0ext43840x2160NVIDIA RTX 4000 Ada Generation 20GBNVIDIA Device 22bcAMD Radeon PRO W7500 8GB (810/674MHz)AMD Device ab30X Server 1.21.1.4 + Wayland4.6 Mesa 24.1.0-devel (LLVM 17.0.6 DRM 3.57)OpenCL 2.1 AMD-APP (3614.0)1.3.255AMD Radeon PRO W7600 8GB (1940/1124MHz)AMD Radeon PRO W7700 15GB (1617/1124MHz)OpenBenchmarking.orgKernel Details- NVIDIA RTX 2000 Ada: nouveau.modeset=0 - Transparent Huge Pages: madvise- NVIDIA RTX 4000 Ada: nouveau.modeset=0 - Transparent Huge Pages: madvise- AMD PRO W7500: Transparent Huge Pages: madvise- AMD PRO W7600: Transparent Huge Pages: madvise- AMD PRO W7700: 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-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-12-ALHxjy/gcc-12-12.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-ALHxjy/gcc-12-12.3.0/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 powersave (EPP: balance_performance) - CPU Microcode: 0xa601206Graphics Details- NVIDIA RTX 2000 Ada: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.07.47.00.05- NVIDIA RTX 4000 Ada: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.04.5c.00.0d- AMD PRO W7500: BAR1 / Visible vRAM Size: 8176 MB - vBIOS Version: 113-D7491100-102- AMD PRO W7600: BAR1 / Visible vRAM Size: 8176 MB - vBIOS Version: 113-D7490100-102- AMD PRO W7700: BAR1 / Visible vRAM Size: 15344 MB - vBIOS Version: 113-D7170100-000OpenCL Details- NVIDIA RTX 2000 Ada: GPU Compute Cores: 2816- NVIDIA RTX 4000 Ada: GPU Compute Cores: 6144Python Details- Python 3.10.12Security Details- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + 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

NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W7700Result OverviewPhoronix Test Suite100%167%235%302%369%LuxMarkSPECViewPerf 2020FluidX3DParaViewIndigoBench

NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W7700Per Watt Result OverviewPhoronix Test Suite100%128%156%184%212%LuxMarkFluidX3DParaViewSPECViewPerf 2020IndigoBenchP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.M

NVIDIA RTX A2000 And RTX A4000 Linux Benchmarks Against AMD Radeon PROblender: Barbershop - Radeon HIPspecviewperf2020: 2560 x 1440 - CREO-03specviewperf2020: 1920 x 1080 - CREO-03specviewperf2020: 2560 x 1440 - MAYA-06specviewperf2020: 2560 x 1440 - MEDICAL-O3specviewperf2020: 1920 x 1080 - MAYA-06specviewperf2020: 1920 x 1080 - MEDICAL-O3specviewperf2020: 2560 x 1440 - SOLIDWORKS-07specviewperf2020: 1920 x 1080 - SOLIDWORKS-07specviewperf2020: 2560 x 1440 - SNX-04specviewperf2020: 1920 x 1080 - SNX-04specviewperf2020: 1920 x 1080 - CATIA-06specviewperf2020: 2560 x 1440 - CATIA-06blender: Barbershop - NVIDIA CUDAblender: Pabellon Barcelona - Radeon HIPspecviewperf2020: 2560 x 1440 - ENERGY-03specviewperf2020: 1920 x 1080 - ENERGY-03fluidx3d: FP32-FP32luxmark: GPU - Microphoneluxmark: GPU - Hotelluxmark: GPU - Luxball HDRblender: Barbershop - NVIDIA OptiXblender: Pabellon Barcelona - NVIDIA CUDAfluidx3d: FP32-FP16Sblender: Classroom - Radeon HIPfluidx3d: FP32-FP16Cindigobench: OpenCL GPU - Bedroomindigobench: OpenCL GPU - Supercarblender: Fishy Cat - Radeon HIPblender: Junkshop - Radeon HIPblender: Fishy Cat - NVIDIA CUDAblender: BMW27 - Radeon HIPblender: Classroom - NVIDIA CUDAblender: BMW27 - NVIDIA OptiXblender: Junkshop - NVIDIA CUDAblender: Pabellon Barcelona - NVIDIA OptiXblender: Classroom - NVIDIA OptiXparaview: Many Spheres - 2560 x 1440paraview: Many Spheres - 2560 x 1440paraview: Many Spheres - 1920 x 1080paraview: Many Spheres - 1920 x 1080blender: Junkshop - NVIDIA OptiXblender: BMW27 - NVIDIA CUDAblender: Fishy Cat - NVIDIA OptiXparaview: Wavelet Contour - 1920 x 1080paraview: Wavelet Contour - 1920 x 1080paraview: Wavelet Contour - 2560 x 1440paraview: Wavelet Contour - 2560 x 1440paraview: Wavelet Volume - 2560 x 1440paraview: Wavelet Volume - 2560 x 1440paraview: Wavelet Volume - 1920 x 1080paraview: Wavelet Volume - 1920 x 1080NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W7700111.02136.64273.5165.69371.37103.52183.88200.59286.27334.0583.4083.43186.2331.7551.31137125323718132886111.31108.43248825568.33324.80247.0644.9410.4137.7730.3927.794889.87648.774998.43349.8621.5922.5722.782639.025253.242124.142203.834823.934301.507175.023448.44160.57192.14416.3597.00540.09142.54304.80336.92421.61495.75144.18144.40105.8762.6098.42215939074120655320969.8858.814006428013.32238.12526.1225.987.1322.5418.8617.229861.25798.3610217.673101.9214.0413.3012.804676.206448.723859.581370.368209.650513.1011231.590701.98106.62131.19211.8216.15316.8625.07145.80153.15193.25223.2262.4862.50203.1114.0820.1185713183223016935167095.3216916.10317.89184.1269.3348.125038.28350.265248.39752.352337.916224.341953.486187.454291.377268.216286.081392.88146.11174.67309.2925.43452.5837.92211.96222.21263.19299.9688.5688.59137.5223.5931.98117620542351025425228166.3522868.74125.30159.2150.2935.547425.03574.067723.94577.043257.106312.552825.466271.126176.550386.0310059.840628.74171.14194.62224.75485.9833.60654.2847.24335.66350.02362.79400.04137.99137.9592.7437.1352.97154532610545642836293442.48289912.00536.32940.6233.6123.5411164.365111.3611636.901116.074763.387457.094144.519397.709868.789616.8013113.811819.61OpenBenchmarking.org

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Barbershop - Compute: Radeon HIPAMD PRO W77004080120160200SE +/- 0.24, N = 3171.14

Blend File: Barbershop - Compute: Radeon HIP

AMD PRO W7500: The test quit with a non-zero exit status.

AMD PRO W7600: The test quit with a non-zero exit status.

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-03NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W77004080120160200SE +/- 0.09, N = 3SE +/- 0.16, N = 3SE +/- 0.67, N = 3SE +/- 0.31, N = 3SE +/- 0.17, N = 3111.02160.57106.62146.11194.62

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 1920 x 1080 - Viewset: CREO-03NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W770050100150200250SE +/- 0.16, N = 3SE +/- 0.15, N = 3SE +/- 0.18, N = 3SE +/- 1.07, N = 3SE +/- 0.39, N = 3136.64192.14131.19174.67224.75

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 2560 x 1440 - Viewset: MAYA-06NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W7700110220330440550SE +/- 0.58, N = 3SE +/- 1.59, N = 3SE +/- 0.66, N = 3SE +/- 0.50, N = 3SE +/- 1.59, N = 3273.51416.35211.82309.29485.98

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 2560 x 1440 - Viewset: MEDICAL-O3NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W770020406080100SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 365.6997.0016.1525.4333.60

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 1920 x 1080 - Viewset: MAYA-06NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W7700140280420560700SE +/- 2.79, N = 3SE +/- 2.35, N = 3SE +/- 0.53, N = 3SE +/- 0.16, N = 3SE +/- 1.60, N = 3371.37540.09316.86452.58654.28

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 1920 x 1080 - Viewset: MEDICAL-O3NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W7700306090120150SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3103.52142.5425.0737.9247.24

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 2560 x 1440 - Viewset: SOLIDWORKS-07NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W770070140210280350SE +/- 0.09, N = 3SE +/- 0.20, N = 3SE +/- 0.37, N = 3SE +/- 0.10, N = 3SE +/- 0.30, N = 3183.88304.80145.80211.96335.66

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 1920 x 1080 - Viewset: SOLIDWORKS-07NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W770080160240320400SE +/- 0.17, N = 3SE +/- 0.57, N = 3SE +/- 0.65, N = 3SE +/- 0.04, N = 3SE +/- 0.15, N = 3200.59336.92153.15222.21350.02

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 2560 x 1440 - Viewset: SNX-04NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W770090180270360450SE +/- 0.06, N = 3SE +/- 1.18, N = 3SE +/- 0.34, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3286.27421.61193.25263.19362.79

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 1920 x 1080 - Viewset: SNX-04NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W7700110220330440550SE +/- 0.16, N = 3SE +/- 0.37, N = 3SE +/- 0.21, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3334.05495.75223.22299.96400.04

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 1920 x 1080 - Viewset: CATIA-06NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W7700306090120150SE +/- 0.14, N = 3SE +/- 0.45, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 383.40144.1862.4888.56137.99

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 2560 x 1440 - Viewset: CATIA-06NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W7700306090120150SE +/- 0.09, N = 3SE +/- 0.26, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 383.43144.4062.5088.59137.95

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Barbershop - Compute: NVIDIA CUDANVIDIA RTX 2000 AdaNVIDIA RTX 4000 Ada4080120160200SE +/- 0.30, N = 3SE +/- 0.08, N = 3186.23105.87

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Pabellon Barcelona - Compute: Radeon HIPAMD PRO W7500AMD PRO W7600AMD PRO W77004080120160200SE +/- 0.93, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3203.11137.5292.74

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-03NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W77001428425670SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 331.7562.6014.0823.5937.13

OpenBenchmarking.orgComposite Score, More Is BetterSPECViewPerf 2020 3.0Resolution: 1920 x 1080 - Viewset: ENERGY-03NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W770020406080100SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 351.3198.4220.1131.9852.97

FluidX3D

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.17Test: FP32-FP32NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W77005001000150020002500SE +/- 0.00, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 1.53, N = 3SE +/- 1.86, N = 31371215985711761545

LuxMark

LuxMark is a multi-platform OpenGL benchmark using LuxRender. LuxMark supports targeting different OpenCL devices and has multiple scenes available for rendering. LuxMark is a fully open-source OpenCL program with real-world rendering examples. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: MicrophoneNVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W77008K16K24K32K40KSE +/- 9.61, N = 3SE +/- 16.65, N = 3SE +/- 62.43, N = 3SE +/- 24.54, N = 3SE +/- 27.51, N = 32532339074131832054232610

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: HotelNVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W77003K6K9K12K15KSE +/- 1.45, N = 3SE +/- 9.21, N = 3SE +/- 7.37, N = 3SE +/- 0.00, N = 3SE +/- 1.00, N = 3718112065223035105456

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: Luxball HDRNVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W770011K22K33K44K55KSE +/- 92.15, N = 3SE +/- 303.83, N = 3SE +/- 120.83, N = 3SE +/- 100.35, N = 3SE +/- 95.17, N = 33288653209169352542542836

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Barbershop - Compute: NVIDIA OptiXNVIDIA RTX 2000 AdaNVIDIA RTX 4000 Ada20406080100SE +/- 0.07, N = 3SE +/- 0.09, N = 3111.3169.88

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Pabellon Barcelona - Compute: NVIDIA CUDANVIDIA RTX 2000 AdaNVIDIA RTX 4000 Ada20406080100SE +/- 0.04, N = 3SE +/- 0.02, N = 3108.4358.81

FluidX3D

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.17Test: FP32-FP16SNVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W77009001800270036004500SE +/- 0.00, N = 3SE +/- 1.15, N = 3SE +/- 1.45, N = 3SE +/- 1.15, N = 3SE +/- 1.33, N = 324884006167022812934

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Classroom - Compute: Radeon HIPAMD PRO W7500AMD PRO W7600AMD PRO W770020406080100SE +/- 1.01, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 395.3266.3542.48

FluidX3D

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.17Test: FP32-FP16CNVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W77009001800270036004500SE +/- 2.52, N = 3SE +/- 0.88, N = 3SE +/- 2.08, N = 3SE +/- 0.33, N = 3SE +/- 3.38, N = 325564280169122862899

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: BedroomNVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W77003691215SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.012, N = 3SE +/- 0.008, N = 3SE +/- 0.008, N = 38.33313.3226.1038.74112.005

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: SupercarNVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W7700918273645SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 324.8038.1317.8925.3036.33

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Fishy Cat - Compute: Radeon HIPAMD PRO W7500AMD PRO W7600AMD PRO W770020406080100SE +/- 0.21, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 384.1259.2140.62

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Junkshop - Compute: Radeon HIPAMD PRO W7500AMD PRO W7600AMD PRO W77001530456075SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 369.3350.2933.61

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Fishy Cat - Compute: NVIDIA CUDANVIDIA RTX 2000 AdaNVIDIA RTX 4000 Ada1122334455SE +/- 0.04, N = 3SE +/- 0.01, N = 347.0626.12

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: BMW27 - Compute: Radeon HIPAMD PRO W7500AMD PRO W7600AMD PRO W77001122334455SE +/- 0.13, N = 3SE +/- 0.17, N = 3SE +/- 0.04, N = 348.1235.5423.54

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Classroom - Compute: NVIDIA CUDANVIDIA RTX 2000 AdaNVIDIA RTX 4000 Ada1020304050SE +/- 0.01, N = 3SE +/- 0.03, N = 344.9425.98

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: BMW27 - Compute: NVIDIA OptiXNVIDIA RTX 2000 AdaNVIDIA RTX 4000 Ada3691215SE +/- 0.06, N = 15SE +/- 0.01, N = 610.417.13

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Junkshop - Compute: NVIDIA CUDANVIDIA RTX 2000 AdaNVIDIA RTX 4000 Ada918273645SE +/- 0.03, N = 3SE +/- 0.02, N = 337.7722.54

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXNVIDIA RTX 2000 AdaNVIDIA RTX 4000 Ada714212835SE +/- 0.05, N = 3SE +/- 0.00, N = 330.3918.86

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Classroom - Compute: NVIDIA OptiXNVIDIA RTX 2000 AdaNVIDIA RTX 4000 Ada714212835SE +/- 0.06, N = 3SE +/- 0.03, N = 327.7917.22

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Paraview describes itself as "an open-source, multi-platform data analysis and visualization application. ParaView users can quickly build visualizations to analyze their data using qualitative and quantitative techniques." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.10.1Test: Many Spheres - Resolution: 2560 x 1440NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W77002K4K6K8K10KSE +/- 2.13, N = 3SE +/- 8.11, N = 3SE +/- 2.49, N = 3SE +/- 5.39, N = 3SE +/- 3.90, N = 34889.889861.265038.287425.0411164.37

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.10.1Test: Many Spheres - Resolution: 2560 x 1440NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W770020406080100SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 348.7798.3650.2674.06111.36

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.10.1Test: Many Spheres - Resolution: 1920 x 1080NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W77002K4K6K8K10KSE +/- 2.90, N = 3SE +/- 2.93, N = 3SE +/- 9.19, N = 3SE +/- 9.18, N = 3SE +/- 33.23, N = 34998.4310217.675248.407723.9511636.90

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.10.1Test: Many Spheres - Resolution: 1920 x 1080NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W7700306090120150SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.33, N = 349.86101.9252.3577.04116.07

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Junkshop - Compute: NVIDIA OptiXNVIDIA RTX 2000 AdaNVIDIA RTX 4000 Ada510152025SE +/- 0.04, N = 3SE +/- 0.03, N = 421.5914.04

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: BMW27 - Compute: NVIDIA CUDANVIDIA RTX 2000 AdaNVIDIA RTX 4000 Ada510152025SE +/- 0.01, N = 3SE +/- 0.02, N = 422.5713.30

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Fishy Cat - Compute: NVIDIA OptiXNVIDIA RTX 2000 AdaNVIDIA RTX 4000 Ada510152025SE +/- 0.28, N = 3SE +/- 0.02, N = 422.7812.80

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Paraview describes itself as "an open-source, multi-platform data analysis and visualization application. ParaView users can quickly build visualizations to analyze their data using qualitative and quantitative techniques." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.10.1Test: Wavelet Contour - Resolution: 1920 x 1080NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W770010002000300040005000SE +/- 2.93, N = 5SE +/- 13.61, N = 6SE +/- 6.55, N = 5SE +/- 5.47, N = 6SE +/- 15.58, N = 62639.034676.212337.923257.114763.39

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.10.1Test: Wavelet Contour - Resolution: 1920 x 1080NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W7700100200300400500SE +/- 0.28, N = 5SE +/- 1.31, N = 6SE +/- 0.63, N = 5SE +/- 0.52, N = 6SE +/- 1.50, N = 6253.24448.72224.34312.55457.09

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.10.1Test: Wavelet Contour - Resolution: 2560 x 1440NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W77009001800270036004500SE +/- 1.11, N = 5SE +/- 4.63, N = 5SE +/- 3.70, N = 5SE +/- 1.99, N = 5SE +/- 7.55, N = 62124.143859.581953.492825.474144.52

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.10.1Test: Wavelet Contour - Resolution: 2560 x 1440NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W770090180270360450SE +/- 0.11, N = 5SE +/- 0.44, N = 5SE +/- 0.36, N = 5SE +/- 0.19, N = 5SE +/- 0.72, N = 6203.83370.36187.45271.12397.70

OpenBenchmarking.orgMiVoxels / Sec, More Is BetterParaView 5.10.1Test: Wavelet Volume - Resolution: 2560 x 1440NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W77002K4K6K8K10KSE +/- 9.42, N = 6SE +/- 16.02, N = 7SE +/- 16.06, N = 6SE +/- 12.22, N = 7SE +/- 38.59, N = 74823.938209.654291.386176.559868.79

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.10.1Test: Wavelet Volume - Resolution: 2560 x 1440NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W7700130260390520650SE +/- 0.59, N = 6SE +/- 1.00, N = 7SE +/- 1.00, N = 6SE +/- 0.76, N = 7SE +/- 2.41, N = 7301.50513.10268.21386.03616.80

OpenBenchmarking.orgMiVoxels / Sec, More Is BetterParaView 5.10.1Test: Wavelet Volume - Resolution: 1920 x 1080NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W77003K6K9K12K15KSE +/- 46.50, N = 7SE +/- 81.78, N = 7SE +/- 23.07, N = 7SE +/- 44.07, N = 7SE +/- 90.12, N = 77175.0211231.596286.0810059.8413113.81

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.10.1Test: Wavelet Volume - Resolution: 1920 x 1080NVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W77002004006008001000SE +/- 2.91, N = 7SE +/- 5.11, N = 7SE +/- 1.44, N = 7SE +/- 2.75, N = 7SE +/- 5.63, N = 7448.44701.98392.88628.74819.61

GPU Temperature Monitor

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringNVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W77001632486480Min: 32 / Avg: 72.27 / Max: 81Min: 31 / Avg: 68.43 / Max: 80Min: 30 / Avg: 76.21 / Max: 84Min: 28 / Avg: 79.71 / Max: 87Min: 29 / Avg: 71.94 / Max: 81

GPU Power Consumption Monitor

OpenBenchmarking.orgWattsGPU Power Consumption MonitorPhoronix Test Suite System MonitoringNVIDIA RTX 2000 AdaNVIDIA RTX 4000 AdaAMD PRO W7500AMD PRO W7600AMD PRO W7700306090120150Min: 4.55 / Avg: 56.48 / Max: 70.06Min: 6.67 / Avg: 92.95 / Max: 130.53Min: 2 / Avg: 47.42 / Max: 56Min: 2 / Avg: 87.37 / Max: 102Min: 5 / Avg: 120.06 / Max: 154

54 Results Shown

Blender
SPECViewPerf 2020:
  2560 x 1440 - CREO-03
  1920 x 1080 - CREO-03
  2560 x 1440 - MAYA-06
  2560 x 1440 - MEDICAL-O3
  1920 x 1080 - MAYA-06
  1920 x 1080 - MEDICAL-O3
  2560 x 1440 - SOLIDWORKS-07
  1920 x 1080 - SOLIDWORKS-07
  2560 x 1440 - SNX-04
  1920 x 1080 - SNX-04
  1920 x 1080 - CATIA-06
  2560 x 1440 - CATIA-06
Blender:
  Barbershop - NVIDIA CUDA
  Pabellon Barcelona - Radeon HIP
SPECViewPerf 2020:
  2560 x 1440 - ENERGY-03
  1920 x 1080 - ENERGY-03
FluidX3D
LuxMark:
  GPU - Microphone
  GPU - Hotel
  GPU - Luxball HDR
Blender:
  Barbershop - NVIDIA OptiX
  Pabellon Barcelona - NVIDIA CUDA
FluidX3D
Blender
FluidX3D
IndigoBench:
  OpenCL GPU - Bedroom
  OpenCL GPU - Supercar
Blender:
  Fishy Cat - Radeon HIP
  Junkshop - Radeon HIP
  Fishy Cat - NVIDIA CUDA
  BMW27 - Radeon HIP
  Classroom - NVIDIA CUDA
  BMW27 - NVIDIA OptiX
  Junkshop - NVIDIA CUDA
  Pabellon Barcelona - NVIDIA OptiX
  Classroom - NVIDIA OptiX
ParaView:
  Many Spheres - 2560 x 1440:
    MiPolys / Sec
    Frames / Sec
  Many Spheres - 1920 x 1080:
    MiPolys / Sec
    Frames / Sec
Blender:
  Junkshop - NVIDIA OptiX
  BMW27 - NVIDIA CUDA
  Fishy Cat - NVIDIA OptiX
ParaView:
  Wavelet Contour - 1920 x 1080:
    MiPolys / Sec
    Frames / Sec
  Wavelet Contour - 2560 x 1440:
    MiPolys / Sec
    Frames / Sec
  Wavelet Volume - 2560 x 1440:
    MiVoxels / Sec
    Frames / Sec
  Wavelet Volume - 1920 x 1080:
    MiVoxels / Sec
    Frames / Sec
GPU Temperature Monitor:
  Phoronix Test Suite System Monitoring:
    Celsius
    Watts