NVIDIA 5090 Compute January 2025

Benchmarks 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 2501240-PTS-5090COMP22
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
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Sensor Monitoring

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

Run Management

Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
RTX 5090
January 23
  4 Hours, 15 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):

RTX 5090

Processor: Intel Core Ultra 9 285K @ 5.10GHz (24 Cores), Motherboard: ASUS ROG MAXIMUS Z890 HERO (1203 BIOS), Chipset: Intel Device ae7f, Memory: 2 x 16GB DDR5-6400MT/s Micron CP16G64C38U5B.M8D1, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 4001GB Western Digital WD_BLACK SN850X 4000GB, Graphics: ASUS NVIDIA GeForce RTX 5090 32GB, Audio: Intel Device 7f50, Monitor: ASUS VP28U, Network: Realtek Device 8126 + Intel I226-V + Intel Wi-Fi 7

OS: Ubuntu 24.10, Kernel: 6.11.0-13-generic (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server 1.21.1.13, Display Driver: NVIDIA 570.86.10, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.8.51 + OpenCL 3.0, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: nouveau.modeset=0 - Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: intel_pstate performance (EPP: default) - CPU Microcode: 0x114 - Thermald 2.5.8
Graphics Notes: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 98.02.2e.00.03
OpenCL Notes: GPU Compute Cores: 21760
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

NVIDIA 5090 Compute January 2025OpenBenchmarking.orgPhoronix Test SuiteIntel Core Ultra 9 285K @ 5.10GHz (24 Cores)ASUS ROG MAXIMUS Z890 HERO (1203 BIOS)Intel Device ae7f2 x 16GB DDR5-6400MT/s Micron CP16G64C38U5B.M8D11000GB Western Digital WDS100T1X0E-00AFY0 + 4001GB Western Digital WD_BLACK SN850X 4000GBASUS NVIDIA GeForce RTX 5090 32GBIntel Device 7f50ASUS VP28URealtek Device 8126 + Intel I226-V + Intel Wi-Fi 7Ubuntu 24.106.11.0-13-generic (x86_64)GNOME Shell 47.0X Server 1.21.1.13NVIDIA 570.86.104.6.0OpenCL 3.0 CUDA 12.8.51 + OpenCL 3.0GCC 14.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen ResolutionNVIDIA 5090 Compute January 2025 BenchmarksSystem Logs- nouveau.modeset=0 - Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: intel_pstate performance (EPP: default) - CPU Microcode: 0x114 - Thermald 2.5.8- BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 98.02.2e.00.03- GPU Compute Cores: 21760- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

NVIDIA 5090 Compute January 2025shoc: OpenCL - Max SP Flopsvkpeak: int16-vec4vkpeak: int16-scalarvkpeak: int32-vec4vkpeak: int32-scalarvkpeak: fp64-vec4vkpeak: fp64-scalarvkpeak: fp16-vec4vkpeak: fp16-scalarvkpeak: fp32-vec4vkpeak: fp32-scalarfahbench: v-ray: NVIDIA CUDA GPUblender: BMW27 - NVIDIA CUDAv-ray: NVIDIA RTX GPUvkfft: FFT + iFFT C2C 1D batched in double precisionindigobench: OpenCL GPU - Supercarindigobench: OpenCL GPU - Bedroomgpuowl: 77936867vkfft: FFT + iFFT C2C 1D batched in single precisiongpuowl: 332220523gpuowl: 57885161vkfft: FFT + iFFT C2C Bluestein benchmark in double precisionvkfft: FFT + iFFT C2C 1D batched in single precision, no reshufflingblender: Barbershop - NVIDIA CUDAblender: Barbershop - NVIDIA OptiXblender: Fishy Cat - NVIDIA OptiXvkfft: FFT + iFFT C2C 1D batched in half precisionhashcat: 7-Zipfluidx3d: FP32-FP32vkfft: FFT + iFFT C2C Bluestein in single precisionhashcat: TrueCrypt RIPEMD160 + XTShashcat: SHA1blender: Pabellon Barcelona - NVIDIA CUDAhashcat: SHA-512vkfft: FFT + iFFT C2C multidimensional in single precisionfluidx3d: FP32-FP16Sblender: BMW27 - NVIDIA OptiXblender: Fishy Cat - NVIDIA CUDAblender: Junkshop - NVIDIA CUDAclpeak: Double-Precision Computefluidx3d: FP32-FP16Cblender: Pabellon Barcelona - NVIDIA OptiXblender: Classroom - NVIDIA CUDAblender: Junkshop - NVIDIA OptiXfinancebench: Monte-Carlo OpenCLshoc: OpenCL - Texture Read Bandwidthopencl-benchmark: Memory Bandwidth Coalesced Writeopencl-benchmark: Memory Bandwidth Coalesced Readopencl-benchmark: INT8 Computeopencl-benchmark: INT16 Computeopencl-benchmark: INT32 Computeopencl-benchmark: INT64 Computeopencl-benchmark: FP16 Computeopencl-benchmark: FP32 Computeopencl-benchmark: FP64 Computevkfft: FFT + iFFT R2C / C2Rblender: Classroom - NVIDIA OptiXcl-mem: Readcl-mem: Copycl-mem: Writeshoc: OpenCL - FFT SPclpeak: Global Memory Bandwidthshoc: OpenCL - S3Dshoc: OpenCL - GEMM SGEMM_Nclpeak: Single-Precision Computeclpeak: Integer 24-bit Computeclpeak: Integer Computeshoc: OpenCL - MD5 Hashfinancebench: Black-Scholes OpenCLRTX 509012438743825.0340041.9762007.9862182.821966.451967.6272700.5562479.9983116.5662849.59478.8068488220.32119186378593.01742.7921834.86233994417.072415.46993024315335.1524.554.53298842326940095173598227688606889632500017.338878450000143709184002.928.908.971973.53191536.998.365.6362.1447142874.751690.141607.7341.52353.52661.6504.378122.630117.8021.9451645226.131309.0350.31551.44403.731565.851121.8735979.9121683.0561979.7662214.19142.4432.061OpenBenchmarking.org

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP FlopsRTX 509030K60K90K120K150KSE +/- 20.95, N = 31243871. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Power Consumption MonitorRTX 5090100200300400500Min: 23.24 / Avg: 196.48 / Max: 579.64
OpenBenchmarking.orgCelsius, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Temperature MonitorRTX 50901326395265Min: 43 / Avg: 49.27 / Max: 67

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.

Total Score

RTX 5090: The test run did not produce a result.

vkpeak

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int16-vec4RTX 50909K18K27K36K45KSE +/- 74.96, N = 343825.03
MinAvgMaxRTX 509017.8444.1583.2OpenBenchmarking.orgWatts, Fewer Is Bettervkpeak 20240505GPU Power Consumption Monitor160320480640800
MinAvgMaxRTX 509037.067.378.0OpenBenchmarking.orgCelsius, Fewer Is Bettervkpeak 20240505GPU Temperature Monitor20406080100

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int16-scalarRTX 50909K18K27K36K45KSE +/- 92.26, N = 340041.97

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int32-vec4RTX 509013K26K39K52K65KSE +/- 104.05, N = 362007.98

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int32-scalarRTX 509013K26K39K52K65KSE +/- 16.80, N = 362182.82

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp64-vec4RTX 5090400800120016002000SE +/- 0.40, N = 31966.45

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp64-scalarRTX 5090400800120016002000SE +/- 0.05, N = 31967.62

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp16-vec4RTX 509016K32K48K64K80KSE +/- 68.93, N = 372700.55

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp16-scalarRTX 509013K26K39K52K65KSE +/- 62.98, N = 362479.99

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp32-vec4RTX 509020K40K60K80K100KSE +/- 74.83, N = 383116.56

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp32-scalarRTX 509013K26K39K52K65KSE +/- 119.36, N = 362849.59

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 5090100200300400500SE +/- 0.29, N = 3478.81
MinAvgMaxRTX 509015.0144.9208.5OpenBenchmarking.orgWatts, Fewer Is BetterFAHBench 2.3.2GPU Power Consumption Monitor60120180240300
MinAvgMaxRTX 509032.040.446.0OpenBenchmarking.orgCelsius, Fewer Is BetterFAHBench 2.3.2GPU Temperature Monitor1224364860

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 509010002000300040005000SE +/- 0.00, N = 34882
MinAvgMaxRTX 509013.5194.2283.4OpenBenchmarking.orgWatts, Fewer Is BetterChaos Group V-RAY 6.0GPU Power Consumption Monitor70140210280350
MinAvgMaxRTX 509036.046.753.0OpenBenchmarking.orgCelsius, Fewer Is BetterChaos Group V-RAY 6.0GPU Temperature Monitor1530456075

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: NVIDIA CUDARTX 5090510152025SE +/- 15.68, N = 1220.32
MinAvgMaxRTX 50909.181.1407.8OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.3GPU Power Consumption Monitor110220330440550
MinAvgMaxRTX 509030.036.352.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.3GPU Temperature Monitor1530456075

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 50903K6K9K12K15KSE +/- 5.33, N = 311918
MinAvgMaxRTX 509018.4314.3439.4OpenBenchmarking.orgWatts, Fewer Is BetterChaos Group V-RAY 6.0GPU Power Consumption Monitor120240360480600
MinAvgMaxRTX 509039.054.864.0OpenBenchmarking.orgCelsius, Fewer Is BetterChaos Group V-RAY 6.0GPU Temperature Monitor20406080100

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 precisionRTX 509014K28K42K56K70KSE +/- 487.66, N = 3637851. (CXX) g++ options: -O3
MinAvgMaxRTX 509012.759.5120.6OpenBenchmarking.orgWatts, Fewer Is BetterVkFFT 1.3.4GPU Power Consumption Monitor4080120160200
MinAvgMaxRTX 509031.034.138.0OpenBenchmarking.orgCelsius, Fewer Is BetterVkFFT 1.3.4GPU Temperature Monitor1122334455

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 509020406080100SE +/- 0.06, N = 393.02
MinAvgMaxRTX 509021.5256.5298.5OpenBenchmarking.orgWatts, Fewer Is BetterIndigoBench 4.4GPU Power Consumption Monitor80160240320400
MinAvgMaxRTX 509037.050.856.0OpenBenchmarking.orgCelsius, Fewer Is BetterIndigoBench 4.4GPU Temperature Monitor1632486480

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: BedroomRTX 50901020304050SE +/- 0.10, N = 342.79
MinAvgMaxRTX 509021.6313.5372.2OpenBenchmarking.orgWatts, Fewer Is BetterIndigoBench 4.4GPU Power Consumption Monitor100200300400500
MinAvgMaxRTX 509043.056.261.0OpenBenchmarking.orgCelsius, Fewer Is BetterIndigoBench 4.4GPU Temperature Monitor20406080100

GpuOwl

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

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 77936867RTX 5090400800120016002000SE +/- 0.00, N = 31834.861. (CXX) g++ options: -O3 -lgmp -lOpenCL
MinAvgMaxRTX 509015.0278.1302.4OpenBenchmarking.orgWatts, Fewer Is BetterGpuOwl 7.5GPU Power Consumption Monitor80160240320400
MinAvgMaxRTX 509043.054.858.0OpenBenchmarking.orgCelsius, Fewer Is BetterGpuOwl 7.5GPU Temperature Monitor1632486480

VkFFT

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

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in single precisionRTX 509050K100K150K200K250KSE +/- 2849.67, N = 42339941. (CXX) g++ options: -O3
MinAvgMaxRTX 509021.4119.3175.1OpenBenchmarking.orgWatts, Fewer Is BetterVkFFT 1.3.4GPU Power Consumption Monitor50100150200250
MinAvgMaxRTX 509039.042.748.0OpenBenchmarking.orgCelsius, Fewer Is BetterVkFFT 1.3.4GPU Temperature Monitor1428425670

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 509090180270360450SE +/- 0.06, N = 3417.071. (CXX) g++ options: -O3 -lgmp -lOpenCL
MinAvgMaxRTX 509018.0315.7347.6OpenBenchmarking.orgWatts, Fewer Is BetterGpuOwl 7.5GPU Power Consumption Monitor100200300400500
MinAvgMaxRTX 509045.057.661.0OpenBenchmarking.orgCelsius, Fewer Is BetterGpuOwl 7.5GPU Temperature Monitor20406080100

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 57885161RTX 50905001000150020002500SE +/- 0.00, N = 32415.461. (CXX) g++ options: -O3 -lgmp -lOpenCL
MinAvgMaxRTX 509018.8263.8290.1OpenBenchmarking.orgWatts, Fewer Is BetterGpuOwl 7.5GPU Power Consumption Monitor70140210280350
MinAvgMaxRTX 509047.054.656.0OpenBenchmarking.orgCelsius, Fewer Is BetterGpuOwl 7.5GPU Temperature Monitor1632486480

VkFFT

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

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C Bluestein benchmark in double precisionRTX 50902K4K6K8K10KSE +/- 3.33, N = 399301. (CXX) g++ options: -O3
MinAvgMaxRTX 509014.8150.0280.5OpenBenchmarking.orgWatts, Fewer Is BetterVkFFT 1.3.4GPU Power Consumption Monitor70140210280350
MinAvgMaxRTX 509034.040.046.0OpenBenchmarking.orgCelsius, Fewer Is BetterVkFFT 1.3.4GPU Temperature Monitor1224364860

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in single precision, no reshufflingRTX 509050K100K150K200K250KSE +/- 1769.18, N = 32431531. (CXX) g++ options: -O3
MinAvgMaxRTX 509014.0110.5182.2OpenBenchmarking.orgWatts, Fewer Is BetterVkFFT 1.3.4GPU Power Consumption Monitor50100150200250
MinAvgMaxRTX 509032.035.940.0OpenBenchmarking.orgCelsius, Fewer Is BetterVkFFT 1.3.4GPU Temperature Monitor1122334455

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: NVIDIA CUDARTX 5090816243240SE +/- 0.07, N = 335.15
MinAvgMaxRTX 509015.0327.8452.0OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.3GPU Power Consumption Monitor120240360480600
MinAvgMaxRTX 509042.055.964.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.3GPU Temperature Monitor20406080100

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: NVIDIA OptiXRTX 5090612182430SE +/- 0.07, N = 324.55
MinAvgMaxRTX 509021.6314.9434.5OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.3GPU Power Consumption Monitor110220330440550
MinAvgMaxRTX 509046.056.062.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.3GPU Temperature Monitor20406080100

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 50901.01932.03863.05794.07725.0965SE +/- 0.04, N = 154.53
MinAvgMaxRTX 509016.2196.8429.8OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.3GPU Power Consumption Monitor110220330440550
MinAvgMaxRTX 509041.046.955.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.3GPU Temperature Monitor1530456075

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 precisionRTX 509060K120K180K240K300KSE +/- 3063.93, N = 32988421. (CXX) g++ options: -O3
MinAvgMaxRTX 509011.677.2125.0OpenBenchmarking.orgWatts, Fewer Is BetterVkFFT 1.3.4GPU Power Consumption Monitor4080120160200
MinAvgMaxRTX 509031.032.634.0OpenBenchmarking.orgCelsius, Fewer Is BetterVkFFT 1.3.4GPU Temperature Monitor1020304050

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: 7-ZipRTX 5090700K1400K2100K2800K3500KSE +/- 4312.96, N = 43269400
MinAvgMaxRTX 509017.095.7340.5OpenBenchmarking.orgWatts, Fewer Is BetterHashcat 6.2.4GPU Power Consumption Monitor80160240320400
MinAvgMaxRTX 509037.039.251.0OpenBenchmarking.orgCelsius, Fewer Is BetterHashcat 6.2.4GPU Temperature Monitor1530456075

FluidX3D

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 3.0Test: FP32-FP32RTX 50902K4K6K8K10KSE +/- 0.88, N = 39517
MinAvgMaxRTX 509015.7289.8366.3OpenBenchmarking.orgWatts, Fewer Is BetterFluidX3D 3.0GPU Power Consumption Monitor100200300400500
MinAvgMaxRTX 509034.045.553.0OpenBenchmarking.orgCelsius, Fewer Is BetterFluidX3D 3.0GPU Temperature Monitor1530456075

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 in single precisionRTX 50908K16K24K32K40KSE +/- 3.53, N = 3359821. (CXX) g++ options: -O3
MinAvgMaxRTX 509012.2123.6284.8OpenBenchmarking.orgWatts, Fewer Is BetterVkFFT 1.3.4GPU Power Consumption Monitor70140210280350
MinAvgMaxRTX 509033.037.046.0OpenBenchmarking.orgCelsius, Fewer Is BetterVkFFT 1.3.4GPU Temperature Monitor1224364860

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: TrueCrypt RIPEMD160 + XTSRTX 5090600K1200K1800K2400K3000KSE +/- 5285.13, N = 52768860
MinAvgMaxRTX 509015.3108.2504.5OpenBenchmarking.orgWatts, Fewer Is BetterHashcat 6.2.4GPU Power Consumption Monitor130260390520650
MinAvgMaxRTX 509035.037.351.0OpenBenchmarking.orgCelsius, Fewer Is BetterHashcat 6.2.4GPU Temperature Monitor1530456075

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA1RTX 509015000M30000M45000M60000M75000MSE +/- 72445857.66, N = 468896325000
MinAvgMaxRTX 509013.8170.6532.7OpenBenchmarking.orgWatts, Fewer Is BetterHashcat 6.2.4GPU Power Consumption Monitor140280420560700
MinAvgMaxRTX 509035.042.657.0OpenBenchmarking.orgCelsius, Fewer Is BetterHashcat 6.2.4GPU Temperature Monitor1632486480

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: NVIDIA CUDARTX 509048121620SE +/- 0.03, N = 317.33
MinAvgMaxRTX 509017.7328.6444.9OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.3GPU Power Consumption Monitor120240360480600
MinAvgMaxRTX 509040.053.561.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.3GPU Temperature Monitor20406080100

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA-512RTX 50902000M4000M6000M8000M10000MSE +/- 3733072.91, N = 48878450000
MinAvgMaxRTX 509015.6232.4584.8OpenBenchmarking.orgWatts, Fewer Is BetterHashcat 6.2.4GPU Power Consumption Monitor160320480640800
MinAvgMaxRTX 509038.046.460.0OpenBenchmarking.orgCelsius, Fewer Is BetterHashcat 6.2.4GPU Temperature Monitor1632486480

VkFFT

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

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C multidimensional in single precisionRTX 509030K60K90K120K150KSE +/- 509.43, N = 41437091. (CXX) g++ options: -O3
MinAvgMaxRTX 509012.2101.1199.8OpenBenchmarking.orgWatts, Fewer Is BetterVkFFT 1.3.4GPU Power Consumption Monitor50100150200250
MinAvgMaxRTX 509031.034.439.0OpenBenchmarking.orgCelsius, Fewer Is BetterVkFFT 1.3.4GPU Temperature Monitor1122334455

FluidX3D

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 3.0Test: FP32-FP16SRTX 50904K8K12K16K20KSE +/- 1.14, N = 518400
MinAvgMaxRTX 509019.6303.3442.4OpenBenchmarking.orgWatts, Fewer Is BetterFluidX3D 3.0GPU Power Consumption Monitor120240360480600
MinAvgMaxRTX 509042.051.758.0OpenBenchmarking.orgCelsius, Fewer Is BetterFluidX3D 3.0GPU Temperature Monitor1632486480

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: NVIDIA OptiXRTX 50900.6571.3141.9712.6283.285SE +/- 0.04, N = 152.92
MinAvgMaxRTX 509015.1158.5386.1OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.3GPU Power Consumption Monitor100200300400500
MinAvgMaxRTX 509038.042.247.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.3GPU Temperature Monitor1428425670

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: NVIDIA CUDARTX 5090246810SE +/- 0.01, N = 58.90
MinAvgMaxRTX 509014.7219.4411.4OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.3GPU Power Consumption Monitor110220330440550
MinAvgMaxRTX 509042.048.856.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.3GPU Temperature Monitor1632486480

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: NVIDIA CUDARTX 50903691215SE +/- 0.02, N = 58.97
MinAvgMaxRTX 509018.8189.4397.6OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.3GPU Power Consumption Monitor110220330440550
MinAvgMaxRTX 509045.049.255.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.3GPU Temperature Monitor1530456075

clpeak

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

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Double-Precision ComputeRTX 5090400800120016002000SE +/- 0.35, N = 61973.531. (CXX) g++ options: -O3
MinAvgMaxRTX 509017.1139.1198.5OpenBenchmarking.orgWatts, Fewer Is Betterclpeak 1.1.2GPU Power Consumption Monitor50100150200250
MinAvgMaxRTX 509033.038.842.0OpenBenchmarking.orgCelsius, Fewer Is Betterclpeak 1.1.2GPU Temperature Monitor1224364860

FluidX3D

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 3.0Test: FP32-FP16CRTX 50904K8K12K16K20KSE +/- 8.41, N = 519153
MinAvgMaxRTX 509018.1376.7557.2OpenBenchmarking.orgWatts, Fewer Is BetterFluidX3D 3.0GPU Power Consumption Monitor140280420560700
MinAvgMaxRTX 509044.057.466.0OpenBenchmarking.orgCelsius, Fewer Is BetterFluidX3D 3.0GPU Temperature Monitor20406080100

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXRTX 5090246810SE +/- 0.01, N = 66.99
MinAvgMaxRTX 509017.5263.0461.0OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.3GPU Power Consumption Monitor120240360480600
MinAvgMaxRTX 509044.051.257.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.3GPU Temperature Monitor1632486480

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: NVIDIA CUDARTX 5090246810SE +/- 0.01, N = 58.36
MinAvgMaxRTX 509013.6274.0428.6OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.3GPU Power Consumption Monitor110220330440550
MinAvgMaxRTX 509037.047.956.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.3GPU Temperature Monitor1632486480

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: NVIDIA OptiXRTX 50901.26682.53363.80045.06726.334SE +/- 0.01, N = 75.63
MinAvgMaxRTX 509017.1178.6408.3OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.3GPU Power Consumption Monitor110220330440550
MinAvgMaxRTX 509041.045.451.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.3GPU Temperature Monitor1530456075

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 50901428425670SE +/- 0.10, N = 762.141. (CXX) g++ options: -O3 -march=native -fopenmp
MinAvgMaxRTX 509013.240.384.1OpenBenchmarking.orgWatts, Fewer Is BetterFinanceBench 2016-07-25GPU Power Consumption Monitor20406080100
MinAvgMaxRTX 509032.034.136.0OpenBenchmarking.orgCelsius, Fewer Is BetterFinanceBench 2016-07-25GPU Temperature Monitor1020304050

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read BandwidthRTX 50906001200180024003000SE +/- 0.58, N = 72874.751. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
MinAvgMaxRTX 509021.0183.5316.5OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Power Consumption Monitor80160240320400
MinAvgMaxRTX 509040.045.651.0OpenBenchmarking.orgCelsius, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Temperature Monitor1530456075

ProjectPhysX OpenCL-Benchmark

OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: Memory Bandwidth Coalesced WriteRTX 5090400800120016002000SE +/- 1.93, N = 61690.141. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
MinAvgMaxRTX 509024.0150.9391.8OpenBenchmarking.orgWatts, Fewer Is BetterProjectPhysX OpenCL-Benchmark 1.6GPU Power Consumption Monitor100200300400500
MinAvgMaxRTX 509044.051.167.0OpenBenchmarking.orgCelsius, Fewer Is BetterProjectPhysX OpenCL-Benchmark 1.6GPU Temperature Monitor20406080100

OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: Memory Bandwidth Coalesced ReadRTX 509030060090012001500SE +/- 2.56, N = 61607.731. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: INT8 ComputeRTX 5090918273645SE +/- 0.06, N = 641.521. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: INT16 ComputeRTX 50901224364860SE +/- 0.07, N = 653.531. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: INT32 ComputeRTX 50901428425670SE +/- 0.04, N = 661.651. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: INT64 ComputeRTX 50900.98511.97022.95533.94044.9255SE +/- 0.002, N = 64.3781. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: FP16 ComputeRTX 5090306090120150SE +/- 0.01, N = 6122.631. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: FP32 ComputeRTX 5090306090120150SE +/- 0.06, N = 6117.801. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: FP64 ComputeRTX 50900.43760.87521.31281.75042.188SE +/- 0.000, N = 61.9451. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

VkFFT

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

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT R2C / C2RRTX 509040K80K120K160K200KSE +/- 660.95, N = 61645221. (CXX) g++ options: -O3
MinAvgMaxRTX 509013.894.8222.2OpenBenchmarking.orgWatts, Fewer Is BetterVkFFT 1.3.4GPU Power Consumption Monitor60120180240300
MinAvgMaxRTX 509034.036.042.0OpenBenchmarking.orgCelsius, Fewer Is BetterVkFFT 1.3.4GPU Temperature Monitor1224364860

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: NVIDIA OptiXRTX 5090246810SE +/- 0.01, N = 66.13
MinAvgMaxRTX 509018.7243.6434.3OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.3GPU Power Consumption Monitor110220330440550
MinAvgMaxRTX 509042.049.056.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.3GPU Temperature Monitor1632486480

cl-mem

A basic OpenCL memory benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadRTX 509030060090012001500SE +/- 0.69, N = 101309.01. (CC) gcc options: -O2 -flto -lOpenCL
MinAvgMaxRTX 509012.6116.6274.1OpenBenchmarking.orgWatts, Fewer Is Bettercl-mem 2017-01-13GPU Power Consumption Monitor70140210280350
MinAvgMaxRTX 509033.036.139.0OpenBenchmarking.orgCelsius, Fewer Is Bettercl-mem 2017-01-13GPU Temperature Monitor1122334455

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyRTX 509080160240320400SE +/- 0.11, N = 10350.31. (CC) gcc options: -O2 -flto -lOpenCL
MinAvgMaxRTX 509013.9115.2275.4OpenBenchmarking.orgWatts, Fewer Is Bettercl-mem 2017-01-13GPU Power Consumption Monitor70140210280350
MinAvgMaxRTX 509034.036.439.0OpenBenchmarking.orgCelsius, Fewer Is Bettercl-mem 2017-01-13GPU Temperature Monitor1122334455

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteRTX 509030060090012001500SE +/- 1.81, N = 101551.41. (CC) gcc options: -O2 -flto -lOpenCL
MinAvgMaxRTX 509014.8116.8277.0OpenBenchmarking.orgWatts, Fewer Is Bettercl-mem 2017-01-13GPU Power Consumption Monitor70140210280350
MinAvgMaxRTX 509034.036.439.0OpenBenchmarking.orgCelsius, Fewer Is Bettercl-mem 2017-01-13GPU Temperature Monitor1122334455

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPRTX 50909001800270036004500SE +/- 8.96, N = 154403.731. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
MinAvgMaxRTX 509020.355.795.0OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Power Consumption Monitor20406080100
MinAvgMaxRTX 509034.037.041.0OpenBenchmarking.orgCelsius, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Temperature Monitor1122334455

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 509030060090012001500SE +/- 1.10, N = 111565.851. (CXX) g++ options: -O3
MinAvgMaxRTX 509017.392.9280.9OpenBenchmarking.orgWatts, Fewer Is Betterclpeak 1.1.2GPU Power Consumption Monitor70140210280350
MinAvgMaxRTX 509030.034.842.0OpenBenchmarking.orgCelsius, Fewer Is Betterclpeak 1.1.2GPU Temperature Monitor1224364860

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3DRTX 50902004006008001000SE +/- 0.66, N = 121121.871. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
MinAvgMaxRTX 509013.845.270.8OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Power Consumption Monitor20406080100
MinAvgMaxRTX 509030.030.932.0OpenBenchmarking.orgCelsius, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Temperature Monitor918273645

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NRTX 50908K16K24K32K40KSE +/- 15.77, N = 1235979.91. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
MinAvgMaxRTX 509016.970.3153.4OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Power Consumption Monitor4080120160200
MinAvgMaxRTX 509033.034.238.0OpenBenchmarking.orgCelsius, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Temperature Monitor1122334455

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 509030K60K90K120K150KSE +/- 4.12, N = 13121683.051. (CXX) g++ options: -O3
MinAvgMaxRTX 509018.898.2266.3OpenBenchmarking.orgWatts, Fewer Is Betterclpeak 1.1.2GPU Power Consumption Monitor70140210280350
MinAvgMaxRTX 509034.036.845.0OpenBenchmarking.orgCelsius, Fewer Is Betterclpeak 1.1.2GPU Temperature Monitor1224364860

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer 24-bit ComputeRTX 509013K26K39K52K65KSE +/- 5.50, N = 1361979.761. (CXX) g++ options: -O3
MinAvgMaxRTX 509019.5107.9307.3OpenBenchmarking.orgWatts, Fewer Is Betterclpeak 1.1.2GPU Power Consumption Monitor80160240320400
MinAvgMaxRTX 509034.036.948.0OpenBenchmarking.orgCelsius, Fewer Is Betterclpeak 1.1.2GPU Temperature Monitor1428425670

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer ComputeRTX 509013K26K39K52K65KSE +/- 5.22, N = 1362214.191. (CXX) g++ options: -O3
MinAvgMaxRTX 509022.7108.0310.6OpenBenchmarking.orgWatts, Fewer Is Betterclpeak 1.1.2GPU Power Consumption Monitor80160240320400
MinAvgMaxRTX 509035.037.651.0OpenBenchmarking.orgCelsius, Fewer Is Betterclpeak 1.1.2GPU Temperature Monitor1530456075

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashRTX 5090306090120150SE +/- 0.02, N = 13142.441. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi
MinAvgMaxRTX 509015.155.7138.0OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Power Consumption Monitor4080120160200
MinAvgMaxRTX 509031.032.643.0OpenBenchmarking.orgCelsius, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Temperature Monitor1224364860

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 50900.46370.92741.39111.85482.3185SE +/- 0.003, N = 132.0611. (CXX) g++ options: -O3 -march=native -fopenmp
MinAvgMaxRTX 509017.042.071.3OpenBenchmarking.orgWatts, Fewer Is BetterFinanceBench 2016-07-25GPU Power Consumption Monitor20406080100
MinAvgMaxRTX 509033.035.639.0OpenBenchmarking.orgCelsius, Fewer Is BetterFinanceBench 2016-07-25GPU Temperature Monitor1122334455

RTX 5090

Processor: Intel Core Ultra 9 285K @ 5.10GHz (24 Cores), Motherboard: ASUS ROG MAXIMUS Z890 HERO (1203 BIOS), Chipset: Intel Device ae7f, Memory: 2 x 16GB DDR5-6400MT/s Micron CP16G64C38U5B.M8D1, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 4001GB Western Digital WD_BLACK SN850X 4000GB, Graphics: ASUS NVIDIA GeForce RTX 5090 32GB, Audio: Intel Device 7f50, Monitor: ASUS VP28U, Network: Realtek Device 8126 + Intel I226-V + Intel Wi-Fi 7

OS: Ubuntu 24.10, Kernel: 6.11.0-13-generic (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server 1.21.1.13, Display Driver: NVIDIA 570.86.10, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.8.51 + OpenCL 3.0, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: nouveau.modeset=0 - Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: intel_pstate performance (EPP: default) - CPU Microcode: 0x114 - Thermald 2.5.8
Graphics Notes: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 98.02.2e.00.03
OpenCL Notes: GPU Compute Cores: 21760
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 23 January 2025 22:11 by user pts.