RTX Ada Linux Kernel Driver Benchmarks NVIDIA RTX A2000 and A4000 with the MIT GPL versus Proprietary kernel driver options with the NVIDIA R555 (555.58.02) Linux driver. Benchmarks by Michael Larabel for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2407084-PTS-RTXADAKE17 Proprietary: RTX A2000 Processor: AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (2007 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 16GB DRAM-6000MT/s G Skill F5-6000J3038F16G, Disk: Western Digital WD_BLACK SN850X 2000GB + 64GB Flash Drive, Graphics: NVIDIA RTX 2000 Ada Generation 16GB, Audio: NVIDIA Device 22be, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411
OS: Ubuntu 22.04, Kernel: 6.5.0-41-generic (x86_64), Desktop: GNOME Shell 42.9, Display Server: X Server 1.21.1.4, Display Driver: NVIDIA 555.58.02, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.5.85, Vulkan: 1.3.278, Compiler: GCC 12.3.0, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: nouveau.modeset=0 - Transparent Huge Pages: madviseCompiler Notes: --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 -vProcessor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601206Graphics Notes: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.07.47.00.05OpenCL Notes: GPU Compute Cores: 2816Python Notes: Python 3.10.12Security Notes: 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
Proprietary: RTX A4000 Changed Graphics to NVIDIA RTX 4000 Ada Generation 20GB .
Graphics Change: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.04.5c.00.0dOpenCL Change: GPU Compute Cores: 6144
MIT GPL: RTX A2000 Changed Graphics to NVIDIA RTX 2000 Ada Generation 16GB .
MIT GPL: RTX A4000 Changed Graphics to NVIDIA RTX 4000 Ada Generation 20GB .
Graphics Change: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.04.5c.00.0dOpenCL Change: GPU Compute Cores: 6144
RTX Ada Linux Kernel Driver Benchmarks OpenBenchmarking.org Phoronix Test Suite AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads) ASUS ROG STRIX X670E-E GAMING WIFI (2007 BIOS) AMD Device 14d8 2 x 16GB DRAM-6000MT/s G Skill F5-6000J3038F16G Western Digital WD_BLACK SN850X 2000GB + 64GB Flash Drive NVIDIA RTX 2000 Ada Generation 16GB NVIDIA RTX 4000 Ada Generation 20GB NVIDIA Device 22be NVIDIA Device 22bc DELL U2723QE Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 Ubuntu 22.04 6.5.0-41-generic (x86_64) GNOME Shell 42.9 X Server 1.21.1.4 NVIDIA 555.58.02 4.6.0 OpenCL 3.0 CUDA 12.5.85 1.3.278 GCC 12.3.0 ext4 3840x2160 Processor Motherboard Chipset Memory Disk Graphics Audios Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Vulkan Compiler File-System Screen Resolution RTX Ada Linux Kernel Driver Benchmarks Performance System Logs - nouveau.modeset=0 - Transparent Huge Pages: madvise - --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 - Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601206 - Proprietary: RTX A2000: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.07.47.00.05 - Proprietary: RTX A4000: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.04.5c.00.0d - MIT GPL: RTX A2000: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.07.47.00.05 - MIT GPL: RTX A4000: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.04.5c.00.0d - Proprietary: RTX A2000: GPU Compute Cores: 2816 - Proprietary: RTX A4000: GPU Compute Cores: 6144 - MIT GPL: RTX A2000: GPU Compute Cores: 2816 - MIT GPL: RTX A4000: GPU Compute Cores: 6144 - Python 3.10.12 - 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
v-ray: NVIDIA CUDA GPU v-ray: NVIDIA RTX GPU octanebench: Total Score indigobench: OpenCL GPU - Supercar indigobench: OpenCL GPU - Bedroom blender: BMW27 - NVIDIA CUDA blender: BMW27 - NVIDIA OptiX blender: Classroom - NVIDIA CUDA blender: Classroom - NVIDIA OptiX blender: Fishy Cat - NVIDIA CUDA blender: Fishy Cat - NVIDIA OptiX blender: Pabellon Barcelona - NVIDIA CUDA blender: Pabellon Barcelona - NVIDIA OptiX blender: Barbershop - NVIDIA CUDA blender: Barbershop - NVIDIA OptiX blender: Junkshop - NVIDIA CUDA blender: Junkshop - NVIDIA OptiX luxmark: GPU - Luxball HDR luxmark: GPU - Microphone luxmark: GPU - Hotel fluidx3d: FP32-FP32 fluidx3d: FP32-FP16S fluidx3d: FP32-FP16C specviewperf2020: 1920 x 1080 - CATIA-06 specviewperf2020: 1920 x 1080 - CREO-03 specviewperf2020: 1920 x 1080 - ENERGY-03 specviewperf2020: 1920 x 1080 - MAYA-06 specviewperf2020: 1920 x 1080 - MEDICAL-O3 specviewperf2020: 1920 x 1080 - SNX-04 specviewperf2020: 1920 x 1080 - SOLIDWORKS-07 specviewperf2020: 2560 x 1440 - CATIA-06 specviewperf2020: 2560 x 1440 - CREO-03 specviewperf2020: 2560 x 1440 - ENERGY-03 specviewperf2020: 2560 x 1440 - MAYA-06 specviewperf2020: 2560 x 1440 - MEDICAL-O3 specviewperf2020: 2560 x 1440 - SNX-04 specviewperf2020: 2560 x 1440 - SOLIDWORKS-07 unigine-super: 1920 x 1080 - Fullscreen - Low - OpenGL unigine-super: 1920 x 1080 - Fullscreen - Medium - OpenGL unigine-super: 1920 x 1080 - Fullscreen - High - OpenGL unigine-super: 1920 x 1080 - Fullscreen - Ultra - OpenGL unigine-super: 2560 x 1440 - Fullscreen - Low - OpenGL unigine-super: 2560 x 1440 - Fullscreen - Medium - OpenGL unigine-super: 2560 x 1440 - Fullscreen - High - OpenGL unigine-super: 2560 x 1440 - Fullscreen - Ultra - OpenGL breaking-limit: 1920 x 1080 - On breaking-limit: 1920 x 1080 - Off breaking-limit: 2560 x 1440 - On breaking-limit: 2560 x 1440 - Off paraview: Many Spheres - 1920 x 1080 paraview: Many Spheres - 1920 x 1080 paraview: Many Spheres - 2560 x 1440 paraview: Many Spheres - 2560 x 1440 paraview: Wavelet Contour - 1920 x 1080 paraview: Wavelet Contour - 1920 x 1080 paraview: Wavelet Contour - 2560 x 1440 paraview: Wavelet Contour - 2560 x 1440 paraview: Wavelet Volume - 1920 x 1080 paraview: Wavelet Volume - 1920 x 1080 paraview: Wavelet Volume - 2560 x 1440 paraview: Wavelet Volume - 2560 x 1440 Proprietary MIT GPL RTX A2000 RTX A4000 RTX A2000 RTX A4000 1653 2037 284.830693 24.802 8.333 22.57 10.41 44.94 27.79 47.06 22.78 108.43 30.39 186.23 111.31 37.77 21.59 32886 25323 7181 1371 2488 2556 83.40 136.64 51.31 371.37 103.52 334.05 200.59 83.43 111.02 31.75 273.51 65.69 286.27 183.88 208.3 105.2 75 30.9 142.8 65.7 44.2 17.9 33.09 102.86 20.74 70.22 49.86 4998.433 48.77 4889.876 253.24 2639.025 203.83 2124.142 448.44 7175.023 301.50 4823.934 2340 2832 495.030899 38.125 13.322 13.30 7.13 25.98 17.22 26.12 12.80 58.81 18.86 105.87 69.88 22.54 14.04 53209 39074 12065 2159 4006 4280 144.18 192.14 98.42 540.09 142.54 495.75 336.92 144.40 160.57 62.60 416.35 97.00 421.61 304.80 323.3 178.9 128.5 51.2 242.0 114.6 77.4 29.6 61.98 181.40 39.19 125.55 101.92 10217.673 98.36 9861.257 448.72 4676.206 370.36 3859.581 701.98 11231.590 513.10 8209.650 1642 2020 280.903124 24.396 8.181 22.76 10.57 45.24 27.86 47.28 22.64 108.86 30.66 187.86 112.84 38.22 22.02 32501 25078 7183 1330 2416 2495 83.67 136.80 51.51 375.02 103.80 334.87 200.81 83.56 111.11 31.80 273.74 65.84 287.19 184.18 208.9 105.5 75.2 31.1 143.2 66.0 44.4 17.9 33.23 103.55 20.85 70.63 49.87 4999.660 48.81 4893.831 253.15 2638.139 204.16 2127.565 448.76 7180.140 301.44 4823.032 2340 2927 482.879547 36.981 12.882 13.50 7.39 26.34 17.61 26.30 12.96 59.25 19.33 107.41 71.75 23.08 14.50 51531 38207 11595 2049 3814 4065 143.45 192.12 98.09 539.31 142.75 496.61 340.81 144.74 160.53 62.47 414.44 97.22 423.50 308.53 324.6 179.1 128.6 51.1 242.0 114.6 77.4 29.6 61.89 181.16 39.17 125.39 101.88 10214.160 98.41 9865.540 448.11 4669.861 368.43 3839.488 701.45 11223.158 503.14 8050.292 OpenBenchmarking.org
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.
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.
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.
Unigine Superposition This test calculates the average frame-rate within the Superposition demo for the Unigine engine, released in 2017. This engine is extremely demanding on the system's graphics card. Learn more via the OpenBenchmarking.org test page.
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.
Result
Proprietary MIT GPL OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.10.1 Test: Many Spheres - Resolution: 1920 x 1080 RTX A2000 RTX A4000 20 40 60 80 100 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 49.86 101.92 49.87 101.88
MiPolys / Sec
Proprietary MIT GPL OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.10.1 Test: Many Spheres - Resolution: 1920 x 1080 RTX A2000 RTX A4000 2K 4K 6K 8K 10K SE +/- 2.90, N = 3 SE +/- 2.93, N = 3 SE +/- 0.83, N = 3 SE +/- 2.02, N = 3 4998.43 10217.67 4999.66 10214.16
MiPolys / Sec Per Watt
Proprietary MIT GPL OpenBenchmarking.org MiPolys / Sec Per Watt, More Is Better ParaView 5.10.1 Test: Many Spheres - Resolution: 1920 x 1080 RTX A2000 RTX A4000 50 100 150 200 250 150.60 220.57 152.65 219.73
GPU Power Consumption
Proprietary MIT GPL OpenBenchmarking.org Watts, Fewer Is Better ParaView 5.10.1 GPU Power Consumption Monitor RTX A2000 RTX A4000 20 40 60 80 100 Min: 7.21 / Avg: 33.19 / Max: 67.5 Min: 14.12 / Avg: 46.32 / Max: 124.16 Min: 6.89 / Avg: 32.75 / Max: 67.38 Min: 14.13 / Avg: 46.49 / Max: 124.43
GPU Temp
Proprietary MIT GPL OpenBenchmarking.org Celsius, Fewer Is Better ParaView 5.10.1 GPU Temperature Monitor RTX A2000 RTX A4000 13 26 39 52 65 Min: 55 / Avg: 60.78 / Max: 69 Min: 51 / Avg: 54.89 / Max: 62 Min: 54 / Avg: 60.13 / Max: 68 Min: 52 / Avg: 55.48 / Max: 63
Result
Proprietary MIT GPL OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.10.1 Test: Many Spheres - Resolution: 2560 x 1440 RTX A2000 RTX A4000 20 40 60 80 100 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 48.77 98.36 48.81 98.41
MiPolys / Sec
Proprietary MIT GPL OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.10.1 Test: Many Spheres - Resolution: 2560 x 1440 RTX A2000 RTX A4000 2K 4K 6K 8K 10K SE +/- 2.13, N = 3 SE +/- 8.11, N = 3 SE +/- 1.06, N = 3 SE +/- 2.84, N = 3 4889.88 9861.26 4893.83 9865.54
MiPolys / Sec Per Watt
Proprietary MIT GPL OpenBenchmarking.org MiPolys / Sec Per Watt, More Is Better ParaView 5.10.1 Test: Many Spheres - Resolution: 2560 x 1440 RTX A2000 RTX A4000 50 100 150 200 250 144.75 208.85 145.26 205.12
GPU Power Consumption
Proprietary MIT GPL OpenBenchmarking.org Watts, Fewer Is Better ParaView 5.10.1 GPU Power Consumption Monitor RTX A2000 RTX A4000 20 40 60 80 100 Min: 7.01 / Avg: 33.78 / Max: 69 Min: 13.55 / Avg: 47.22 / Max: 126.07 Min: 6.79 / Avg: 33.69 / Max: 69.02 Min: 13.99 / Avg: 48.1 / Max: 126.69
GPU Temp
Proprietary MIT GPL OpenBenchmarking.org Celsius, Fewer Is Better ParaView 5.10.1 GPU Temperature Monitor RTX A2000 RTX A4000 13 26 39 52 65 Min: 52 / Avg: 58.8 / Max: 68 Min: 48 / Avg: 52.67 / Max: 61 Min: 52 / Avg: 58.42 / Max: 67 Min: 49 / Avg: 53.74 / Max: 62
Result
Proprietary MIT GPL OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.10.1 Test: Wavelet Contour - Resolution: 1920 x 1080 RTX A2000 RTX A4000 100 200 300 400 500 SE +/- 0.28, N = 5 SE +/- 1.31, N = 6 SE +/- 0.33, N = 5 SE +/- 0.58, N = 6 253.24 448.72 253.15 448.11
MiPolys / Sec
Proprietary MIT GPL OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.10.1 Test: Wavelet Contour - Resolution: 1920 x 1080 RTX A2000 RTX A4000 1000 2000 3000 4000 5000 SE +/- 2.93, N = 5 SE +/- 13.61, N = 6 SE +/- 3.45, N = 5 SE +/- 6.02, N = 6 2639.03 4676.21 2638.14 4669.86
MiPolys / Sec Per Watt
Proprietary MIT GPL OpenBenchmarking.org MiPolys / Sec Per Watt, More Is Better ParaView 5.10.1 Test: Wavelet Contour - Resolution: 1920 x 1080 RTX A2000 RTX A4000 30 60 90 120 150 112.33 128.73 113.61 126.45
GPU Power Consumption
Proprietary MIT GPL OpenBenchmarking.org Watts, Fewer Is Better ParaView 5.10.1 GPU Power Consumption Monitor RTX A2000 RTX A4000 20 40 60 80 100 Min: 7.17 / Avg: 23.49 / Max: 69.95 Min: 13.6 / Avg: 36.32 / Max: 125.2 Min: 6.71 / Avg: 23.22 / Max: 69.89 Min: 14.01 / Avg: 36.93 / Max: 124.95
GPU Temp
Proprietary MIT GPL OpenBenchmarking.org Celsius, Fewer Is Better ParaView 5.10.1 GPU Temperature Monitor RTX A2000 RTX A4000 13 26 39 52 65 Min: 51 / Avg: 54.81 / Max: 64 Min: 47 / Avg: 49.4 / Max: 58 Min: 51 / Avg: 54.62 / Max: 64 Min: 48 / Avg: 50.59 / Max: 58
Result
Proprietary MIT GPL OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.10.1 Test: Wavelet Contour - Resolution: 2560 x 1440 RTX A2000 RTX A4000 80 160 240 320 400 SE +/- 0.11, N = 5 SE +/- 0.44, N = 5 SE +/- 0.10, N = 5 SE +/- 0.22, N = 5 203.83 370.36 204.16 368.43
MiPolys / Sec
Proprietary MIT GPL OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.10.1 Test: Wavelet Contour - Resolution: 2560 x 1440 RTX A2000 RTX A4000 800 1600 2400 3200 4000 SE +/- 1.11, N = 5 SE +/- 4.63, N = 5 SE +/- 1.04, N = 5 SE +/- 2.33, N = 5 2124.14 3859.58 2127.57 3839.49
MiPolys / Sec Per Watt
Proprietary MIT GPL OpenBenchmarking.org MiPolys / Sec Per Watt, More Is Better ParaView 5.10.1 Test: Wavelet Contour - Resolution: 2560 x 1440 RTX A2000 RTX A4000 20 40 60 80 100 83.85 100.85 85.86 101.19
GPU Power Consumption
Proprietary MIT GPL OpenBenchmarking.org Watts, Fewer Is Better ParaView 5.10.1 GPU Power Consumption Monitor RTX A2000 RTX A4000 20 40 60 80 100 Min: 6.87 / Avg: 25.33 / Max: 69.71 Min: 13.38 / Avg: 38.27 / Max: 124.72 Min: 6.52 / Avg: 24.78 / Max: 69.43 Min: 13.77 / Avg: 37.94 / Max: 123.93
GPU Temp
Proprietary MIT GPL OpenBenchmarking.org Celsius, Fewer Is Better ParaView 5.10.1 GPU Temperature Monitor RTX A2000 RTX A4000 12 24 36 48 60 Min: 49 / Avg: 53.72 / Max: 63 Min: 45 / Avg: 47.54 / Max: 56 Min: 49 / Avg: 53 / Max: 62 Min: 46 / Avg: 48.7 / Max: 56