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):


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 2025blender: BMW27 - NVIDIA CUDAblender: BMW27 - NVIDIA OptiXblender: Classroom - NVIDIA CUDAblender: Classroom - NVIDIA OptiXblender: Fishy Cat - NVIDIA CUDAblender: Fishy Cat - NVIDIA OptiXblender: Pabellon Barcelona - NVIDIA CUDAblender: Pabellon Barcelona - NVIDIA OptiXblender: Barbershop - NVIDIA CUDAblender: Barbershop - NVIDIA OptiXblender: Junkshop - NVIDIA CUDAblender: Junkshop - NVIDIA OptiXv-ray: NVIDIA CUDA GPUv-ray: NVIDIA RTX GPUindigobench: OpenCL GPU - Supercarindigobench: OpenCL GPU - Bedroomshoc: OpenCL - Max SP Flopsshoc: OpenCL - Texture Read Bandwidthshoc: OpenCL - FFT SPshoc: OpenCL - GEMM SGEMM_Nshoc: OpenCL - MD5 Hashshoc: OpenCL - S3Dclpeak: Global Memory Bandwidthclpeak: Single-Precision Computeclpeak: Double-Precision Computeclpeak: Integer Computeclpeak: Integer 24-bit Computecl-mem: Readcl-mem: Writecl-mem: Copyfahbench: financebench: Black-Scholes OpenCLfinancebench: Monte-Carlo OpenCLhashcat: SHA1hashcat: SHA-512hashcat: 7-Ziphashcat: TrueCrypt RIPEMD160 + XTSfluidx3d: FP32-FP32fluidx3d: FP32-FP16Sfluidx3d: FP32-FP16Cgpuowl: 57885161gpuowl: 77936867gpuowl: 332220523vkfft: FFT + iFFT C2C 1D batched in single precisionvkfft: FFT + iFFT C2C 1D batched in double precisionvkfft: FFT + iFFT C2C 1D batched in half precisionvkfft: FFT + iFFT C2C multidimensional in single precisionvkfft: FFT + iFFT C2C 1D batched in single precision, no reshufflingvkfft: FFT + iFFT R2C / C2Rvkfft: FFT + iFFT C2C Bluestein in single precisionvkfft: FFT + iFFT C2C Bluestein benchmark in double precisionvkpeak: fp32-scalarvkpeak: fp32-vec4vkpeak: fp16-scalarvkpeak: fp16-vec4vkpeak: fp64-scalarvkpeak: fp64-vec4vkpeak: int32-scalarvkpeak: int32-vec4vkpeak: int16-scalarvkpeak: int16-vec4opencl-benchmark: FP64 Computeopencl-benchmark: FP32 Computeopencl-benchmark: FP16 Computeopencl-benchmark: INT64 Computeopencl-benchmark: INT32 Computeopencl-benchmark: INT16 Computeopencl-benchmark: INT8 Computeopencl-benchmark: Memory Bandwidth Coalesced Readopencl-benchmark: Memory Bandwidth Coalesced WriteRTX 509020.322.928.366.138.904.5317.336.9935.1524.558.975.6348821191893.01742.7921243872874.754403.7335979.9142.4431121.871565.85121683.051973.5362214.1961979.761309.01551.4350.3478.80682.06162.14471468896325000887845000032694002768860951718400191532415.461834.86417.072339946378529884214370924315316452235982993062849.5983116.5662479.9972700.551967.621966.4562182.8262007.9840041.9743825.031.945117.802122.6304.37861.65053.52641.5231607.731690.14OpenBenchmarking.org

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: NVIDIA CUDARTX 5090510152025SE +/- 15.68, N = 1220.32

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: NVIDIA OptiXRTX 50900.6571.3141.9712.6283.285SE +/- 0.04, N = 152.92

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: NVIDIA CUDARTX 5090246810SE +/- 0.01, N = 58.36

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: NVIDIA OptiXRTX 5090246810SE +/- 0.01, N = 66.13

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: NVIDIA CUDARTX 5090246810SE +/- 0.01, N = 58.90

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 50901.01932.03863.05794.07725.0965SE +/- 0.04, N = 154.53

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: NVIDIA CUDARTX 509048121620SE +/- 0.03, N = 317.33

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXRTX 5090246810SE +/- 0.01, N = 66.99

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: NVIDIA CUDARTX 5090816243240SE +/- 0.07, N = 335.15

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: NVIDIA OptiXRTX 5090612182430SE +/- 0.07, N = 324.55

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: NVIDIA CUDARTX 50903691215SE +/- 0.02, N = 58.97

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: NVIDIA OptiXRTX 50901.26682.53363.80045.06726.334SE +/- 0.01, N = 75.63

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

OpenBenchmarking.orgvpaths, More Is BetterChaos Group V-RAY 6.0Mode: NVIDIA RTX GPURTX 50903K6K9K12K15KSE +/- 5.33, N = 311918

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.

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

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: BedroomRTX 50901020304050SE +/- 0.10, N = 342.79

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.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

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

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

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

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

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

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Single-Precision ComputeRTX 509030K60K90K120K150KSE +/- 4.12, N = 13121683.051. (CXX) g++ options: -O3

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Double-Precision ComputeRTX 5090400800120016002000SE +/- 0.35, N = 61973.531. (CXX) g++ options: -O3

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer ComputeRTX 509013K26K39K52K65KSE +/- 5.22, N = 1362214.191. (CXX) g++ options: -O3

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer 24-bit ComputeRTX 509013K26K39K52K65KSE +/- 5.50, N = 1361979.761. (CXX) g++ options: -O3

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

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteRTX 509030060090012001500SE +/- 1.81, N = 101551.41. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyRTX 509080160240320400SE +/- 0.11, N = 10350.31. (CC) gcc options: -O2 -flto -lOpenCL

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

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

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Monte-Carlo OpenCLRTX 50901428425670SE +/- 0.10, N = 762.141. (CXX) g++ options: -O3 -march=native -fopenmp

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: SHA1RTX 509015000M30000M45000M60000M75000MSE +/- 72445857.66, N = 468896325000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA-512RTX 50902000M4000M6000M8000M10000MSE +/- 3733072.91, N = 48878450000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: 7-ZipRTX 5090700K1400K2100K2800K3500KSE +/- 4312.96, N = 43269400

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: TrueCrypt RIPEMD160 + XTSRTX 5090600K1200K1800K2400K3000KSE +/- 5285.13, N = 52768860

FluidX3D

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 3.0Test: FP32-FP32RTX 50902K4K6K8K10KSE +/- 0.88, N = 39517

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 3.0Test: FP32-FP16SRTX 50904K8K12K16K20KSE +/- 1.14, N = 518400

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 3.0Test: FP32-FP16CRTX 50904K8K12K16K20KSE +/- 8.41, N = 519153

GpuOwl

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

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 57885161RTX 50905001000150020002500SE +/- 0.00, N = 32415.461. (CXX) g++ options: -O3 -lgmp -lOpenCL

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 77936867RTX 5090400800120016002000SE +/- 0.00, N = 31834.861. (CXX) g++ options: -O3 -lgmp -lOpenCL

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 332220523RTX 509090180270360450SE +/- 0.06, N = 3417.071. (CXX) g++ options: -O3 -lgmp -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 C2C 1D batched in single precisionRTX 509050K100K150K200K250KSE +/- 2849.67, N = 42339941. (CXX) g++ options: -O3

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

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

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

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

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT R2C / C2RRTX 509040K80K120K160K200KSE +/- 660.95, N = 61645221. (CXX) g++ options: -O3

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

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

vkpeak

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

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

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

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

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

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

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

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

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

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int16-vec4RTX 50909K18K27K36K45KSE +/- 74.96, N = 343825.03

ProjectPhysX OpenCL-Benchmark

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

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: FP16 ComputeRTX 5090306090120150SE +/- 0.01, N = 6122.631. (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.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: 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: INT8 ComputeRTX 5090918273645SE +/- 0.06, N = 641.521. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

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.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

70 Results Shown

Blender:
  BMW27 - NVIDIA CUDA
  BMW27 - NVIDIA OptiX
  Classroom - NVIDIA CUDA
  Classroom - NVIDIA OptiX
  Fishy Cat - NVIDIA CUDA
  Fishy Cat - NVIDIA OptiX
  Pabellon Barcelona - NVIDIA CUDA
  Pabellon Barcelona - NVIDIA OptiX
  Barbershop - NVIDIA CUDA
  Barbershop - NVIDIA OptiX
  Junkshop - NVIDIA CUDA
  Junkshop - NVIDIA OptiX
Chaos Group V-RAY:
  NVIDIA CUDA GPU
  NVIDIA RTX GPU
IndigoBench:
  OpenCL GPU - Supercar
  OpenCL GPU - Bedroom
SHOC Scalable HeterOgeneous Computing:
  OpenCL - Max SP Flops
  OpenCL - Texture Read Bandwidth
  OpenCL - FFT SP
  OpenCL - GEMM SGEMM_N
  OpenCL - MD5 Hash
  OpenCL - S3D
clpeak:
  Global Memory Bandwidth
  Single-Precision Compute
  Double-Precision Compute
  Integer Compute
  Integer 24-bit Compute
cl-mem:
  Read
  Write
  Copy
FAHBench
FinanceBench:
  Black-Scholes OpenCL
  Monte-Carlo OpenCL
Hashcat:
  SHA1
  SHA-512
  7-Zip
  TrueCrypt RIPEMD160 + XTS
FluidX3D:
  FP32-FP32
  FP32-FP16S
  FP32-FP16C
GpuOwl:
  57885161
  77936867
  332220523
VkFFT:
  FFT + iFFT C2C 1D batched in single precision
  FFT + iFFT C2C 1D batched in double precision
  FFT + iFFT C2C 1D batched in half precision
  FFT + iFFT C2C multidimensional in single precision
  FFT + iFFT C2C 1D batched in single precision, no reshuffling
  FFT + iFFT R2C / C2R
  FFT + iFFT C2C Bluestein in single precision
  FFT + iFFT C2C Bluestein benchmark in double precision
vkpeak:
  fp32-scalar
  fp32-vec4
  fp16-scalar
  fp16-vec4
  fp64-scalar
  fp64-vec4
  int32-scalar
  int32-vec4
  int16-scalar
  int16-vec4
ProjectPhysX OpenCL-Benchmark:
  FP64 Compute
  FP32 Compute
  FP16 Compute
  INT64 Compute
  INT32 Compute
  INT16 Compute
  INT8 Compute
  Memory Bandwidth Coalesced Read
  Memory Bandwidth Coalesced Write