NVIDIA Kernel Drivers

AMD Ryzen 9 7950X 16-Core testing with a ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS) and NVIDIA GeForce RTX 4080 16GB on Ubuntu 23.10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2403037-PTS-NVIDIAKE39
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

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

Table

Show Detailed System Result Table

Run Management

Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Smoke
March 02
  7 Hours, 38 Minutes
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 Kernel DriversOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads)ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS)AMD Device 14d82 x 16GB DRAM-6000MT/s G Skill F5-6000J3038F16G2000GB Samsung SSD 980 PRO 2TB + 4001GB Western Digital WD_BLACK SN850X 4000GBNVIDIA GeForce RTX 4080 16GBNVIDIA Device 22bbDELL U2723QEIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 23.106.7.0-060700-generic (x86_64)GNOME Shell 45.2X Server 1.21.1.7NVIDIA 550.54.144.6.0OpenCL 3.0 CUDA 12.4.89GCC 13.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen ResolutionNVIDIA Kernel Drivers PerformanceSystem Logs- Transparent Huge Pages: madvise- Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203- GLAMOR - BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.0e.00.04- 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: Vulnerable: Safe RET no microcode + 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 + srbds: Not affected + tsx_async_abort: Not affected

NVIDIA Kernel Driversvkfft: FFT + iFFT C2C 1D batched in double precisionhitman3: 3840 x 2160 - Ultrafurmark: 3840 x 2160 - Furmark Knot Vulkan - 8shadowofthetombraider: 1920 x 1080 - Highest - Offshadowofthetombraider: 3840 x 2160 - Highest - Offdirt-rally2: 2560 x 1080 - Ultradirt-rally2: 2880 x 1620 - Ultradirt-rally2: 3840 x 1600 - Ultraunigine-super: 3840 x 2160 - Fullscreen - Ultra - OpenGLunigine-super: 1920 x 1080 - Fullscreen - Ultra - OpenGLunigine-super: 2560 x 1440 - Fullscreen - Ultra - OpenGLcs2: 1920 x 1080f122: 3840 x 2160 - Ultra Highf122: 1920 x 1080 - Ultra Highoctanebench: Total Scorevkfft: FFT + iFFT C2C multidimensional in single precisionhitman3: 1920 x 1080 - Ultravkmark: 3840 x 2160 - Immediatevkmark: 2560 x 1440 - Immediatevkmark: 1920 x 1080 - Immediatehitman3: 2560 x 1440 - Ultraglmark2: 3840 x 2160vkfft: FFT + iFFT C2C Bluestein benchmark in double precisionluxcorerender: DLSC - GPUv-ray: NVIDIA CUDA GPUluxcorerender: LuxCore Benchmark - GPUv-ray: NVIDIA RTX GPUcs2: 3840 x 2160vkfft: FFT + iFFT R2C / C2Rfurmark: 3840 x 2160 - FurMark Vulkan - 8furmark: 3840 x 2160 - Furmark Knot Vulkan - Offindigobench: OpenCL GPU - Bedroomfurmark: 3840 x 2160 - FurMark Vulkan - Offfurmark: 2560 x 1440 - Furmark Knot Vulkan - 8furmark: 1920 x 1080 - FurMark Vulkan - 8furmark: 2560 x 1440 - FurMark Vulkan - 8furmark: 3840 x 2160 - FurMark Knot OpenGL - 8furmark: 1920 x 1080 - Furmark Knot Vulkan - 8furmark: 3840 x 2160 - FurMark Knot OpenGL - Offfurmark: 1920 x 1080 - Furmark Knot Vulkan - Offfurmark: 2560 x 1440 - FurMark Vulkan - Offfurmark: 2560 x 1440 - Furmark Knot Vulkan - Offfurmark: 1920 x 1080 - FurMark Vulkan - Offfurmark: 3840 x 2160 - FurMark OpenGL - Offfurmark: 3840 x 2160 - FurMark OpenGL - 8indigobench: OpenCL GPU - Supercarfurmark: 2560 x 1440 - FurMark Knot OpenGL - 8furmark: 2560 x 1440 - FurMark Knot OpenGL - Offfurmark: 1920 x 1080 - FurMark Knot OpenGL - Offfurmark: 1920 x 1080 - FurMark Knot OpenGL - 8furmark: 2560 x 1440 - FurMark OpenGL - Offfurmark: 1920 x 1080 - FurMark OpenGL - 8furmark: 2560 x 1440 - FurMark OpenGL - 8furmark: 1920 x 1080 - FurMark OpenGL - Offluxcorerender: Orange Juice - GPUvkfft: FFT + iFFT C2C 1D batched in single precisionluxcorerender: Danish Mood - GPUblender: Barbershop - NVIDIA CUDAvkfft: FFT + iFFT C2C 1D batched in single precision, no reshufflingvkfft: FFT + iFFT C2C Bluestein in single precisioncs2: 2560 x 1440fluidx3d: FP32-FP32blender: Barbershop - NVIDIA OptiXblender: Fishy Cat - NVIDIA OptiXvkfft: FFT + iFFT C2C 1D batched in half precisionblender: Pabellon Barcelona - NVIDIA CUDAblender: BMW27 - NVIDIA OptiXfluidx3d: FP32-FP16Sfluidx3d: FP32-FP16Cquake2rtx: 3840 x 2160 - High - On - VK_KHR_ray_tracing_pipelinequake2rtx: 3840 x 2160 - High - On - VK_NV_ray_tracingquake2rtx: 3840 x 2160 - High - On - VK_KHR_ray_queryquake2rtx: 3840 x 2160 - Off - On - VK_KHR_ray_tracing_pipelinequake2rtx: 3840 x 2160 - High - Off - VK_KHR_ray_tracing_pipelinequake2rtx: 3840 x 2160 - Off - Off - VK_KHR_ray_queryblender: Fishy Cat - NVIDIA CUDAquake2rtx: 3840 x 2160 - Off - Off - VK_KHR_ray_tracing_pipelinequake2rtx: 3840 x 2160 - Off - On - VK_KHR_ray_queryquake2rtx: 3840 x 2160 - Off - On - VK_NV_ray_tracingquake2rtx: 3840 x 2160 - High - Off - VK_KHR_ray_queryquake2rtx: 3840 x 2160 - High - Off - VK_NV_ray_tracingblender: Classroom - NVIDIA CUDAquake2rtx: 3840 x 2160 - Off - Off - VK_NV_ray_tracingblender: Pabellon Barcelona - NVIDIA OptiXopencl-benchmark: Memory Bandwidth Coalesced Writeopencl-benchmark: Memory Bandwidth Coalesced Readopencl-benchmark: INT8 Computeopencl-benchmark: INT16 Computeopencl-benchmark: INT32 Computeopencl-benchmark: INT64 Computeopencl-benchmark: FP32 Computeopencl-benchmark: FP64 Computeblender: Classroom - NVIDIA OptiXblender: BMW27 - NVIDIA CUDAluxcorerender: Rainbow Colors and Prism - GPUSmoke31468160.8620.054316298.1136.1294.525401234.136637200.68003831.7111.669.6405.072178965.18097472319364.08166740456728286.073767564415.59483514.766056164.96696223.83613464.06698125.748157.31063346.907614101.86417954.27799241.66842984.74859641.610461164.012573271.605814131.839518360.839905174.756871175.19015065.55987.90101987.988973127.258174127.529210310.201569416.238353309.998179416.17142712.6810381612.9460.7810520716924308.7384440.867.7713668732.294.607707785855.10605758.94340959.19117174.86132376.211070132.80125815.75113.42719084.37753583.86122485.20679586.10108414.56134.89773611.13614.66652.3220.15323.15826.6594.53251.6810.83210.037.8333.81OpenBenchmarking.org

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in double precisionSmoke7K14K21K28K35KSE +/- 376.32, N = 12314681. (CXX) g++ options: -O3

HITMAN 3

OpenBenchmarking.orgMilliseconds, Fewer Is BetterHITMAN 3Resolution: 3840 x 2160 - Quality Level: Ultra - Total Frame TimeSmoke3691215Min: 3.17 / Avg: 6.17 / Max: 10.72

OpenBenchmarking.orgFrames Per Second, More Is BetterHITMAN 3Resolution: 3840 x 2160 - Quality Level: UltraSmoke4080120160200SE +/- 1.28, N = 9160.86MIN: 150.66 / MAX: 162.9

FurMark

FurMark 2 is a cross-platform GPU stress test that can exercise both OpenGL and Vulkan drivers/GPUs. FurMark 2 is the successor to the original FurMark benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 3840 x 2160 - Demo: Furmark Knot Vulkan - MSAA: 8Smoke510152025SE +/- 0.20, N = 1520.05MIN: 18 / MAX: 25

Shadow of the Tomb Raider

Shadow of the Tomb Raider on Steam. The test profile assumes you have a Steam account, have Steam installed for the system, and that you own a copy of this game. This automates the process of executing the game and using its built-in benchmark mode. Backs up old preferences (in ~/.local/share/feral-interactive/) for the run. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterShadow of the Tomb RaiderResolution: 1920 x 1080 - Graphics Preset: Highest - Anti Aliasing: OffSmoke60120180240300SE +/- 0.18, N = 3298.1MAX: 521.6

OpenBenchmarking.orgFrames Per Second, More Is BetterShadow of the Tomb RaiderResolution: 3840 x 2160 - Graphics Preset: Highest - Anti Aliasing: OffSmoke306090120150SE +/- 0.10, N = 3136.1MAX: 203.4

DiRT Rally 2.0

This is a benchmark of DiRT Rally 2.0 running under Steam Play (Proton) on Linux. The test profile assumes you have a Steam account, have Steam installed for the system, and that the game is already purchased/installed. This automates the process of executing the game and using a standardized scene. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterDiRT Rally 2.0Resolution: 2560 x 1080 - Graphics Preset: UltraSmoke60120180240300SE +/- 0.72, N = 3294.53MIN: 217.81 / MAX: 373.07

OpenBenchmarking.orgFrames Per Second, More Is BetterDiRT Rally 2.0Resolution: 2880 x 1620 - Graphics Preset: UltraSmoke50100150200250SE +/- 0.18, N = 3234.14MIN: 182.07 / MAX: 288.16

OpenBenchmarking.orgFrames Per Second, More Is BetterDiRT Rally 2.0Resolution: 3840 x 1600 - Graphics Preset: UltraSmoke4080120160200SE +/- 0.22, N = 3200.68MIN: 159.56 / MAX: 244.78

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.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 3840 x 2160 - Mode: Fullscreen - Quality: Ultra - Renderer: OpenGLSmoke714212835SE +/- 0.00, N = 331.7MAX: 34.9

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: Ultra - Renderer: OpenGLSmoke20406080100SE +/- 0.12, N = 3111.6MAX: 139.3

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 2560 x 1440 - Mode: Fullscreen - Quality: Ultra - Renderer: OpenGLSmoke1530456075SE +/- 0.03, N = 369.6MAX: 79

Counter-Strike 2

This is a benchmark of Valve's Counter-Strike 2 game. The test profile assumes you have a Steam account, have Steam installed for the system, and that Counter-Strike 2 is already installed. This automates the process of executing the game and using a standardized time demo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterCounter-Strike 2Resolution: 1920 x 1080Smoke90180270360450SE +/- 5.80, N = 12405.0MIN: 342.5 / MAX: 417.8

F1 22

OpenBenchmarking.orgMilliseconds, Fewer Is BetterF1 22Resolution: 3840 x 2160 - Graphics Preset: Ultra High - Total Frame TimeSmoke48121620Min: 10.63 / Avg: 13.82 / Max: 17.3

OpenBenchmarking.orgFrames Per Second, More Is BetterF1 22Resolution: 3840 x 2160 - Graphics Preset: Ultra HighSmoke1632486480SE +/- 0.33, N = 372MIN: 61 / MAX: 84

OpenBenchmarking.orgMilliseconds, Fewer Is BetterF1 22Resolution: 1920 x 1080 - Graphics Preset: Ultra High - Total Frame TimeSmoke3691215Min: 3.54 / Avg: 5.5 / Max: 10.98

OpenBenchmarking.orgFrames Per Second, More Is BetterF1 22Resolution: 1920 x 1080 - Graphics Preset: Ultra HighSmoke4080120160200SE +/- 2.19, N = 3178MIN: 112 / MAX: 208

OctaneBench

OctaneBench is a test of the OctaneRender on the GPU and requires the use of NVIDIA CUDA. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterOctaneBench 2020.1Total ScoreSmoke2004006008001000965.18

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C multidimensional in single precisionSmoke15K30K45K60K75KSE +/- 889.16, N = 15723191. (CXX) g++ options: -O3

HITMAN 3

OpenBenchmarking.orgMilliseconds, Fewer Is BetterHITMAN 3Resolution: 1920 x 1080 - Quality Level: Ultra - Total Frame TimeSmoke48121620Min: 1.04 / Avg: 2.75 / Max: 15.82

OpenBenchmarking.orgFrames Per Second, More Is BetterHITMAN 3Resolution: 1920 x 1080 - Quality Level: UltraSmoke80160240320400SE +/- 0.64, N = 3364.08MIN: 363.03 / MAX: 365.24

VKMark

VKMark is a collection of open-source Vulkan tests / rendering benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVKMark Score, More Is BetterVKMark 2022-05-16Resolution: 3840 x 2160 - Present Mode: ImmediateSmoke400800120016002000SE +/- 1.33, N = 316671. (CXX) g++ options: -pthread -ldl -std=c++14 -O0 -MD -MQ -MF

OpenBenchmarking.orgVKMark Score, More Is BetterVKMark 2022-05-16Resolution: 2560 x 1440 - Present Mode: ImmediateSmoke9001800270036004500SE +/- 1.67, N = 340451. (CXX) g++ options: -pthread -ldl -std=c++14 -O0 -MD -MQ -MF

OpenBenchmarking.orgVKMark Score, More Is BetterVKMark 2022-05-16Resolution: 1920 x 1080 - Present Mode: ImmediateSmoke14002800420056007000SE +/- 2.60, N = 367281. (CXX) g++ options: -pthread -ldl -std=c++14 -O0 -MD -MQ -MF

HITMAN 3

OpenBenchmarking.orgMilliseconds, Fewer Is BetterHITMAN 3Resolution: 2560 x 1440 - Quality Level: Ultra - Total Frame TimeSmoke48121620Min: 1.58 / Avg: 3.49 / Max: 13.31

OpenBenchmarking.orgFrames Per Second, More Is BetterHITMAN 3Resolution: 2560 x 1440 - Quality Level: UltraSmoke60120180240300SE +/- 0.45, N = 3286.07MIN: 285.17 / MAX: 286.63

GLmark2

This is a test of GLmark2, a basic OpenGL and OpenGL ES 2.0 benchmark supporting various windowing/display back-ends. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterGLmark2 2023.01Resolution: 3840 x 2160Smoke80016002400320040003767

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C Bluestein benchmark in double precisionSmoke12002400360048006000SE +/- 7.45, N = 356441. (CXX) g++ options: -O3

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: DLSC - Acceleration: GPUSmoke48121620SE +/- 0.02, N = 315.59MIN: 15.39 / MAX: 15.76

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 GPUSmoke10002000300040005000SE +/- 15.67, N = 34835

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: LuxCore Benchmark - Acceleration: GPUSmoke48121620SE +/- 0.02, N = 314.76MIN: 5.77 / MAX: 17.18

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 GPUSmoke13002600390052006500SE +/- 8.95, N = 36056

Counter-Strike 2

This is a benchmark of Valve's Counter-Strike 2 game. The test profile assumes you have a Steam account, have Steam installed for the system, and that Counter-Strike 2 is already installed. This automates the process of executing the game and using a standardized time demo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterCounter-Strike 2Resolution: 3840 x 2160Smoke4080120160200SE +/- 0.10, N = 3164.9MIN: 164.7 / MAX: 165

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT R2C / C2RSmoke14K28K42K56K70KSE +/- 833.94, N = 15669621. (CXX) g++ options: -O3

FurMark

FurMark 2 is a cross-platform GPU stress test that can exercise both OpenGL and Vulkan drivers/GPUs. FurMark 2 is the successor to the original FurMark benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 3840 x 2160 - Demo: FurMark Vulkan - MSAA: 8Smoke612182430SE +/- 0.00, N = 323.84MAX: 27

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 3840 x 2160 - Demo: Furmark Knot Vulkan - MSAA: OffSmoke1428425670SE +/- 0.18, N = 364.07MIN: 63 / MAX: 67

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: BedroomSmoke612182430SE +/- 0.01, N = 325.75

FurMark

FurMark 2 is a cross-platform GPU stress test that can exercise both OpenGL and Vulkan drivers/GPUs. FurMark 2 is the successor to the original FurMark benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 3840 x 2160 - Demo: FurMark Vulkan - MSAA: OffSmoke306090120150SE +/- 0.32, N = 3157.31MIN: 153 / MAX: 162

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 2560 x 1440 - Demo: Furmark Knot Vulkan - MSAA: 8Smoke1122334455SE +/- 0.11, N = 346.91MIN: 46 / MAX: 49

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 1920 x 1080 - Demo: FurMark Vulkan - MSAA: 8Smoke20406080100SE +/- 0.47, N = 3101.86MIN: 94.66 / MAX: 108

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 2560 x 1440 - Demo: FurMark Vulkan - MSAA: 8Smoke1224364860SE +/- 0.29, N = 354.28MIN: 51.71 / MAX: 57

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 3840 x 2160 - Demo: FurMark Knot OpenGL - MSAA: 8Smoke1020304050SE +/- 0.03, N = 341.67MAX: 43

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 1920 x 1080 - Demo: Furmark Knot Vulkan - MSAA: 8Smoke20406080100SE +/- 1.15, N = 384.75MIN: 81 / MAX: 90

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 3840 x 2160 - Demo: FurMark Knot OpenGL - MSAA: OffSmoke918273645SE +/- 0.01, N = 341.61MAX: 43

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 1920 x 1080 - Demo: Furmark Knot Vulkan - MSAA: OffSmoke4080120160200SE +/- 0.69, N = 3164.01MIN: 155.84 / MAX: 169

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 2560 x 1440 - Demo: FurMark Vulkan - MSAA: OffSmoke60120180240300SE +/- 0.07, N = 3271.61MIN: 259.58 / MAX: 277

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 2560 x 1440 - Demo: Furmark Knot Vulkan - MSAA: OffSmoke306090120150SE +/- 0.73, N = 3131.84MIN: 126.6 / MAX: 136

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 1920 x 1080 - Demo: FurMark Vulkan - MSAA: OffSmoke80160240320400SE +/- 0.23, N = 3360.84MIN: 343.5 / MAX: 367

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 3840 x 2160 - Demo: FurMark OpenGL - MSAA: OffSmoke4080120160200SE +/- 0.10, N = 3174.76MIN: 168.41 / MAX: 179

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 3840 x 2160 - Demo: FurMark OpenGL - MSAA: 8Smoke4080120160200SE +/- 0.17, N = 3175.19MIN: 169.1 / MAX: 180

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: SupercarSmoke1530456075SE +/- 0.04, N = 365.56

FurMark

FurMark 2 is a cross-platform GPU stress test that can exercise both OpenGL and Vulkan drivers/GPUs. FurMark 2 is the successor to the original FurMark benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 2560 x 1440 - Demo: FurMark Knot OpenGL - MSAA: 8Smoke20406080100SE +/- 0.03, N = 387.90MIN: 84.88 / MAX: 89

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 2560 x 1440 - Demo: FurMark Knot OpenGL - MSAA: OffSmoke20406080100SE +/- 0.07, N = 387.99MIN: 85.35 / MAX: 90

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 1920 x 1080 - Demo: FurMark Knot OpenGL - MSAA: OffSmoke306090120150SE +/- 0.05, N = 3127.26MIN: 122.1 / MAX: 130

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 1920 x 1080 - Demo: FurMark Knot OpenGL - MSAA: 8Smoke306090120150SE +/- 0.17, N = 3127.53MIN: 122.03 / MAX: 130

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 2560 x 1440 - Demo: FurMark OpenGL - MSAA: OffSmoke70140210280350SE +/- 0.15, N = 3310.20MIN: 296.1 / MAX: 316

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 1920 x 1080 - Demo: FurMark OpenGL - MSAA: 8Smoke90180270360450SE +/- 0.37, N = 3416.24MIN: 397.2 / MAX: 424

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 2560 x 1440 - Demo: FurMark OpenGL - MSAA: 8Smoke70140210280350SE +/- 0.13, N = 3310.00MIN: 296.43 / MAX: 316

OpenBenchmarking.orgFPS, More Is BetterFurMark 2.1Resolution: 1920 x 1080 - Demo: FurMark OpenGL - MSAA: OffSmoke90180270360450SE +/- 0.42, N = 3416.17MIN: 395.78 / MAX: 424

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: GPUSmoke3691215SE +/- 0.00, N = 312.68MIN: 10.89 / MAX: 16.54

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in single precisionSmoke20K40K60K80K100KSE +/- 0.88, N = 31038161. (CXX) g++ options: -O3

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: GPUSmoke3691215SE +/- 0.06, N = 312.94MIN: 4.06 / MAX: 15.19

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 4.0Blend File: Barbershop - Compute: NVIDIA CUDASmoke1428425670SE +/- 0.11, N = 360.78

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in single precision, no reshufflingSmoke20K40K60K80K100KSE +/- 136.86, N = 31052071. (CXX) g++ options: -O3

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C Bluestein in single precisionSmoke4K8K12K16K20KSE +/- 104.24, N = 3169241. (CXX) g++ options: -O3

Cyberpunk 2077

This is a benchmark of Cyberpunk 2077 running under Steam Play (Proton) on Linux. The test profile assumes you have a Steam account, have Steam installed for the system, and that the game is already purchased/installed. This automates the process of executing the game and using a standardized scene. Learn more via the OpenBenchmarking.org test page.

Resolution: 3840 x 2160 - Graphics Setting: High

Smoke: The test run did not produce a result. E: cat: '/home/phoronix//.steam/steam/steamapps/compatdata/1091500/pfx/drive_c/users/steamuser/Documents/CD Projekt Red/Cyberpunk 2077/benchmarkResults/*/summary.json': No such file or directory

Resolution: 2560 x 1440 - Graphics Setting: Ultra

Smoke: The test run did not produce a result. E: cat: '/home/phoronix//.steam/steam/steamapps/compatdata/1091500/pfx/drive_c/users/steamuser/Documents/CD Projekt Red/Cyberpunk 2077/benchmarkResults/*/summary.json': No such file or directory

Resolution: 1920 x 1080 - Graphics Setting: Ultra

Smoke: The test run did not produce a result. E: cat: '/home/phoronix//.steam/steam/steamapps/compatdata/1091500/pfx/drive_c/users/steamuser/Documents/CD Projekt Red/Cyberpunk 2077/benchmarkResults/*/summary.json': No such file or directory

Resolution: 2560 x 1440 - Graphics Setting: High

Smoke: The test run did not produce a result. E: cat: '/home/phoronix//.steam/steam/steamapps/compatdata/1091500/pfx/drive_c/users/steamuser/Documents/CD Projekt Red/Cyberpunk 2077/benchmarkResults/*/summary.json': No such file or directory

Resolution: 3840 x 2160 - Graphics Setting: Ultra

Smoke: The test run did not produce a result. E: cat: '/home/phoronix//.steam/steam/steamapps/compatdata/1091500/pfx/drive_c/users/steamuser/Documents/CD Projekt Red/Cyberpunk 2077/benchmarkResults/*/summary.json': No such file or directory

Resolution: 1920 x 1080 - Graphics Setting: High

Smoke: The test run did not produce a result. E: cat: '/home/phoronix//.steam/steam/steamapps/compatdata/1091500/pfx/drive_c/users/steamuser/Documents/CD Projekt Red/Cyberpunk 2077/benchmarkResults/*/summary.json': No such file or directory

Counter-Strike 2

This is a benchmark of Valve's Counter-Strike 2 game. The test profile assumes you have a Steam account, have Steam installed for the system, and that Counter-Strike 2 is already installed. This automates the process of executing the game and using a standardized time demo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterCounter-Strike 2Resolution: 2560 x 1440Smoke70140210280350SE +/- 0.79, N = 3308.7MIN: 307.1 / MAX: 309.6

FluidX3D

FluidX3D is a speedy and memory efficient Boltzmann CFD (Computational Fluid Dynamics) software package implemented using OpenCL and intended for GPU acceleration. FluidX3D is developed by Moritz Lehmann and written free for non-commercial use. This is a test profile measuring the system OpenCL performance using the FluidX3D benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP32Smoke8001600240032004000SE +/- 8.76, N = 33844

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 4.0Blend File: Barbershop - Compute: NVIDIA OptiXSmoke918273645SE +/- 0.06, N = 340.86

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Fishy Cat - Compute: NVIDIA OptiXSmoke246810SE +/- 0.07, N = 137.77

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in half precisionSmoke30K60K90K120K150KSE +/- 849.35, N = 31366871. (CXX) g++ options: -O3

Grand Theft Auto V

This is a benchmark of GTA 5 (Grand Theft Auto V) running under Steam Play (Proton) on Linux. The test profile assumes you have a Steam account, have Steam installed for the system, and that the game is already purchased/installed. This automates the process of executing the game and using a standardized time demo. Learn more via the OpenBenchmarking.org test page.

Resolution: 2560 x 1440 - Quality: Very High

Smoke: The test run did not produce a result. E: MESA: error: Use of VkSurfacePresentModeCompatibilityEXT without a VkSurfacePresentModeEXT set. This is an application bug.

Resolution: 3840 x 2160 - Quality: Very High

Smoke: The test run did not produce a result. E: MESA: error: Use of VkSurfacePresentModeCompatibilityEXT without a VkSurfacePresentModeEXT set. This is an application bug.

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 4.0Blend File: Pabellon Barcelona - Compute: NVIDIA CUDASmoke714212835SE +/- 0.02, N = 332.29

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: BMW27 - Compute: NVIDIA OptiXSmoke1.0352.073.1054.145.175SE +/- 0.06, N = 144.60

FluidX3D

FluidX3D is a speedy and memory efficient Boltzmann CFD (Computational Fluid Dynamics) software package implemented using OpenCL and intended for GPU acceleration. FluidX3D is developed by Moritz Lehmann and written free for non-commercial use. This is a test profile measuring the system OpenCL performance using the FluidX3D benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP16SSmoke17003400510068008500SE +/- 0.33, N = 37707

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP16CSmoke2K4K6K8K10KSE +/- 5.67, N = 37858

Quake II RTX

NVIDIA's Quake II RTX ray-traced (RTX path-traced global illumination) version of the original Quake II game. Quake II RTX makes use of Vulkan ray-tracing extensions on Windows and Linux. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterQuake II RTX 1.6Resolution: 3840 x 2160 - Global Illumination: High - Denoiser: On - Ray Tracing API: VK_KHR_ray_tracing_pipelineSmoke1224364860SE +/- 0.05, N = 355.11

OpenBenchmarking.orgFrames Per Second, More Is BetterQuake II RTX 1.6Resolution: 3840 x 2160 - Global Illumination: High - Denoiser: On - Ray Tracing API: VK_NV_ray_tracingSmoke1326395265SE +/- 0.28, N = 358.94

OpenBenchmarking.orgFrames Per Second, More Is BetterQuake II RTX 1.6Resolution: 3840 x 2160 - Global Illumination: High - Denoiser: On - Ray Tracing API: VK_KHR_ray_querySmoke1326395265SE +/- 0.32, N = 359.19

OpenBenchmarking.orgFrames Per Second, More Is BetterQuake II RTX 1.6Resolution: 3840 x 2160 - Global Illumination: Off - Denoiser: On - Ray Tracing API: VK_KHR_ray_tracing_pipelineSmoke20406080100SE +/- 0.16, N = 374.86

OpenBenchmarking.orgFrames Per Second, More Is BetterQuake II RTX 1.6Resolution: 3840 x 2160 - Global Illumination: High - Denoiser: Off - Ray Tracing API: VK_KHR_ray_tracing_pipelineSmoke20406080100SE +/- 0.10, N = 376.21

OpenBenchmarking.orgFrames Per Second, More Is BetterQuake II RTX 1.6Resolution: 3840 x 2160 - Global Illumination: Off - Denoiser: Off - Ray Tracing API: VK_KHR_ray_querySmoke306090120150SE +/- 1.39, N = 4132.80

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 4.0Blend File: Fishy Cat - Compute: NVIDIA CUDASmoke48121620SE +/- 0.01, N = 315.75

Quake II RTX

NVIDIA's Quake II RTX ray-traced (RTX path-traced global illumination) version of the original Quake II game. Quake II RTX makes use of Vulkan ray-tracing extensions on Windows and Linux. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterQuake II RTX 1.6Resolution: 3840 x 2160 - Global Illumination: Off - Denoiser: Off - Ray Tracing API: VK_KHR_ray_tracing_pipelineSmoke306090120150SE +/- 1.23, N = 3113.43

OpenBenchmarking.orgFrames Per Second, More Is BetterQuake II RTX 1.6Resolution: 3840 x 2160 - Global Illumination: Off - Denoiser: On - Ray Tracing API: VK_KHR_ray_querySmoke20406080100SE +/- 0.90, N = 384.38

OpenBenchmarking.orgFrames Per Second, More Is BetterQuake II RTX 1.6Resolution: 3840 x 2160 - Global Illumination: Off - Denoiser: On - Ray Tracing API: VK_NV_ray_tracingSmoke20406080100SE +/- 0.79, N = 383.86

OpenBenchmarking.orgFrames Per Second, More Is BetterQuake II RTX 1.6Resolution: 3840 x 2160 - Global Illumination: High - Denoiser: Off - Ray Tracing API: VK_KHR_ray_querySmoke20406080100SE +/- 0.86, N = 385.21

OpenBenchmarking.orgFrames Per Second, More Is BetterQuake II RTX 1.6Resolution: 3840 x 2160 - Global Illumination: High - Denoiser: Off - Ray Tracing API: VK_NV_ray_tracingSmoke20406080100SE +/- 0.73, N = 386.10

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 4.0Blend File: Classroom - Compute: NVIDIA CUDASmoke48121620SE +/- 0.01, N = 314.56

Quake II RTX

NVIDIA's Quake II RTX ray-traced (RTX path-traced global illumination) version of the original Quake II game. Quake II RTX makes use of Vulkan ray-tracing extensions on Windows and Linux. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterQuake II RTX 1.6Resolution: 3840 x 2160 - Global Illumination: Off - Denoiser: Off - Ray Tracing API: VK_NV_ray_tracingSmoke306090120150SE +/- 1.42, N = 3134.90

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 4.0Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXSmoke3691215SE +/- 0.01, N = 311.13

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 WriteSmoke130260390520650SE +/- 0.21, N = 3614.661. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: Memory Bandwidth Coalesced ReadSmoke140280420560700SE +/- 0.03, N = 3652.321. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT8 ComputeSmoke510152025SE +/- 0.02, N = 320.151. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT16 ComputeSmoke612182430SE +/- 0.00, N = 323.161. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT32 ComputeSmoke612182430SE +/- 0.01, N = 326.661. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT64 ComputeSmoke1.01972.03943.05914.07885.0985SE +/- 0.002, N = 34.5321. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: FP32 ComputeSmoke1224364860SE +/- 0.01, N = 351.681. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: FP64 ComputeSmoke0.18720.37440.56160.74880.936SE +/- 0.001, N = 30.8321. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

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 4.0Blend File: Classroom - Compute: NVIDIA OptiXSmoke3691215SE +/- 0.01, N = 310.03

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: BMW27 - Compute: NVIDIA CUDASmoke246810SE +/- 0.03, N = 37.83

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: GPUSmoke816243240SE +/- 0.01, N = 333.81MIN: 30.37 / MAX: 36.23

100 Results Shown

VkFFT
HITMAN 3
HITMAN 3
FurMark
Shadow of the Tomb Raider:
  1920 x 1080 - Highest - Off
  3840 x 2160 - Highest - Off
DiRT Rally 2.0:
  2560 x 1080 - Ultra
  2880 x 1620 - Ultra
  3840 x 1600 - Ultra
Unigine Superposition:
  3840 x 2160 - Fullscreen - Ultra - OpenGL
  1920 x 1080 - Fullscreen - Ultra - OpenGL
  2560 x 1440 - Fullscreen - Ultra - OpenGL
Counter-Strike 2
F1 22
F1 22
F1 22
F1 22
OctaneBench
VkFFT
HITMAN 3
HITMAN 3
VKMark:
  3840 x 2160 - Immediate
  2560 x 1440 - Immediate
  1920 x 1080 - Immediate
HITMAN 3
HITMAN 3
GLmark2
VkFFT
LuxCoreRender
Chaos Group V-RAY
LuxCoreRender
Chaos Group V-RAY
Counter-Strike 2
VkFFT
FurMark:
  3840 x 2160 - FurMark Vulkan - 8
  3840 x 2160 - Furmark Knot Vulkan - Off
IndigoBench
FurMark:
  3840 x 2160 - FurMark Vulkan - Off
  2560 x 1440 - Furmark Knot Vulkan - 8
  1920 x 1080 - FurMark Vulkan - 8
  2560 x 1440 - FurMark Vulkan - 8
  3840 x 2160 - FurMark Knot OpenGL - 8
  1920 x 1080 - Furmark Knot Vulkan - 8
  3840 x 2160 - FurMark Knot OpenGL - Off
  1920 x 1080 - Furmark Knot Vulkan - Off
  2560 x 1440 - FurMark Vulkan - Off
  2560 x 1440 - Furmark Knot Vulkan - Off
  1920 x 1080 - FurMark Vulkan - Off
  3840 x 2160 - FurMark OpenGL - Off
  3840 x 2160 - FurMark OpenGL - 8
IndigoBench
FurMark:
  2560 x 1440 - FurMark Knot OpenGL - 8
  2560 x 1440 - FurMark Knot OpenGL - Off
  1920 x 1080 - FurMark Knot OpenGL - Off
  1920 x 1080 - FurMark Knot OpenGL - 8
  2560 x 1440 - FurMark OpenGL - Off
  1920 x 1080 - FurMark OpenGL - 8
  2560 x 1440 - FurMark OpenGL - 8
  1920 x 1080 - FurMark OpenGL - Off
LuxCoreRender
VkFFT
LuxCoreRender
Blender
VkFFT:
  FFT + iFFT C2C 1D batched in single precision, no reshuffling
  FFT + iFFT C2C Bluestein in single precision
Counter-Strike 2
FluidX3D
Blender:
  Barbershop - NVIDIA OptiX
  Fishy Cat - NVIDIA OptiX
VkFFT
Blender:
  Pabellon Barcelona - NVIDIA CUDA
  BMW27 - NVIDIA OptiX
FluidX3D:
  FP32-FP16S
  FP32-FP16C
Quake II RTX:
  3840 x 2160 - High - On - VK_KHR_ray_tracing_pipeline
  3840 x 2160 - High - On - VK_NV_ray_tracing
  3840 x 2160 - High - On - VK_KHR_ray_query
  3840 x 2160 - Off - On - VK_KHR_ray_tracing_pipeline
  3840 x 2160 - High - Off - VK_KHR_ray_tracing_pipeline
  3840 x 2160 - Off - Off - VK_KHR_ray_query
Blender
Quake II RTX:
  3840 x 2160 - Off - Off - VK_KHR_ray_tracing_pipeline
  3840 x 2160 - Off - On - VK_KHR_ray_query
  3840 x 2160 - Off - On - VK_NV_ray_tracing
  3840 x 2160 - High - Off - VK_KHR_ray_query
  3840 x 2160 - High - Off - VK_NV_ray_tracing
Blender
Quake II RTX
Blender
ProjectPhysX OpenCL-Benchmark:
  Memory Bandwidth Coalesced Write
  Memory Bandwidth Coalesced Read
  INT8 Compute
  INT16 Compute
  INT32 Compute
  INT64 Compute
  FP32 Compute
  FP64 Compute
Blender:
  Classroom - NVIDIA OptiX
  BMW27 - NVIDIA CUDA
LuxCoreRender