gpu comp

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 2402256-PTS-GPUCOMP691
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

NVIDIA GPU Compute 2 Tests
Vulkan Compute 2 Tests

Statistics

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

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
4080 super a
February 25
  21 Minutes
b
February 25
  21 Minutes
c
February 25
  21 Minutes
d
February 25
  21 Minutes
RTX 4060
February 25
  38 Minutes
e
February 25
  1 Hour, 54 Minutes
f
February 25
  39 Minutes
g
February 25
  38 Minutes
4070 TI SUPER
February 25
  22 Minutes
h
February 25
  22 Minutes
i
February 25
  22 Minutes
4090
February 25
  18 Minutes
j
February 25
  18 Minutes
k
February 25
  18 Minutes
l
February 25
  18 Minutes
m
February 25
  18 Minutes
Invert Hiding All Results Option
  29 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


gpu compProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen Resolution4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklmAMD 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 SUPER 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 550.40.074.6.0OpenCL 3.0 CUDA 12.4.74GCC 13.2.0ext43840x2160MSI NVIDIA GeForce RTX 4060 8GBNVIDIA Device 22be4001GB Western Digital WD_BLACK SN850X 4000GB + 2000GB Samsung SSD 980 PRO 2TBASUS NVIDIA GeForce RTX 4070 Ti SUPER 16GBNVIDIA Device 22bb2000GB Samsung SSD 980 PRO 2TB + 4001GB Western Digital WD_BLACK SN850X 4000GBNVIDIA GeForce RTX 4090 24GBNVIDIA AD102 HD AudioOpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --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 --enable-libphobos-checking=release --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-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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 Details- 4080 super a: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203- b: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203- c: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203- d: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203- RTX 4060: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203- e: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203- f: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203- g: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203- 4070 TI SUPER: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203- h: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203- i: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203- 4090: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203- j: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203- k: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203- l: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203- m: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203Graphics Details- 4080 super a: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.44.00.01- b: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.44.00.01- c: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.44.00.01- d: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.44.00.01- RTX 4060: BAR1 / Visible vRAM Size: 8192 MiB - vBIOS Version: 95.07.31.00.e3- e: BAR1 / Visible vRAM Size: 8192 MiB - vBIOS Version: 95.07.31.00.e3- f: BAR1 / Visible vRAM Size: 8192 MiB - vBIOS Version: 95.07.31.00.e3- g: BAR1 / Visible vRAM Size: 8192 MiB - vBIOS Version: 95.07.31.00.e3- 4070 TI SUPER: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.45.00.9c- h: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.45.00.9c- i: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.45.00.9c- 4090: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.02.20.00.01- j: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.02.20.00.01- k: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.02.20.00.01- l: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.02.20.00.01- m: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.02.20.00.01OpenCL Details- 4080 super a: GPU Compute Cores: 10240- b: GPU Compute Cores: 10240- c: GPU Compute Cores: 10240- d: GPU Compute Cores: 10240- RTX 4060: GPU Compute Cores: 3072- e: GPU Compute Cores: 3072- f: GPU Compute Cores: 3072- g: GPU Compute Cores: 3072- 4070 TI SUPER: GPU Compute Cores: 8448- h: GPU Compute Cores: 8448- i: GPU Compute Cores: 8448- 4090: GPU Compute Cores: 16384- j: GPU Compute Cores: 16384- k: GPU Compute Cores: 16384- l: GPU Compute Cores: 16384- m: GPU Compute Cores: 16384Python Details- Python 3.11.6Security Details- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: 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

4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklmResult OverviewPhoronix Test Suite100%205%309%414%GpuOwlProjectPhysX OpenCL-BenchmarkFluidX3DLibplaceboVkFFT

gpu compvkfft: FFT + iFFT R2C / C2Rvkfft: FFT + iFFT C2C 1D batched in half precisionvkfft: FFT + iFFT C2C Bluestein in single precisionvkfft: FFT + iFFT C2C 1D batched in double precisionvkfft: FFT + iFFT C2C 1D batched in single precisionvkfft: FFT + iFFT C2C multidimensional in single precisionvkfft: FFT + iFFT C2C Bluestein benchmark in double precisionvkfft: FFT + iFFT C2C 1D batched in single precision, no reshufflinglibplacebo: deband_heavylibplacebo: polar_nocomputelibplacebo: hdr_peakdetectlibplacebo: hdr_lutlibplacebo: av1_grain_laplibplacebo: gaussiangpuowl: 57885161gpuowl: 77936867gpuowl: 332220523opencl-benchmark: FP64 Computeopencl-benchmark: FP32 Computeopencl-benchmark: INT64 Computeopencl-benchmark: INT32 Computeopencl-benchmark: INT16 Computeopencl-benchmark: INT8 Computeopencl-benchmark: Memory Bandwidth Coalesced Readopencl-benchmark: Memory Bandwidth Coalesced Writefluidx3d: FP32-FP32fluidx3d: FP32-FP16Cfluidx3d: FP32-FP16S4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm6725714318316388314641061727394856861076041529.331919.913002.982858.683475.583407.971191.89511323896.06189.680.86153.5044.23727.62923.98420.822680.51632.693972812780776395614696316963317751063487502957061077411527.651918.793260.622858.873476.353411.131190.48896.06189.830.86453.4894.25227.58123.97820.819680.56631.653968812180796388713942916838343461062086864257121078381528.481918.633184.62856.353476.233413.411191.89511323894.45189.610.86453.6314.23927.6323.98420.825680.77629.883967814580796764714705916831343561063007467456871077541530.761924.723251.952860.743189.613412.081191.89511323896.06189.830.86453.6554.23927.6323.98220.822680.67629.1396781288078356018282310715120254234737049237143062514.76655.961570.771525.071723.151512.45376.65278.5558.850.26416.5052.0878.4917.4146.179252.9258.47160931143038352018272510635120704233838684237343067517.52659.341546.471525.751725.791512.65378.36278.5558.850.26416.5062.0948.4917.4176.225252.89258.40160931133039351678299710593120964234138064238543079514.52655.721506.931522.31722.451511.72376.65277.3258.580.26416.5052.0898.4917.4176.215252.89258.4160831143039352198306510461121034234538609237343071514.7656.21503.721526.731724.711511.91376.65278.5558.850.26416.5052.0918.4917.4196.214252.89258.361609311430396755813871614512306771026066645448501042711323.81672.462874.752789.693538.353118.521003.01744.60159.820.72545.0684.2823.18620.21717.135619.31607.153831742066786684912780616243231991026926758749991042941324.361671.912882.562789.733516.563120.651004.016064257745.16159.870.72545.0674.27223.20720.21217.135619.28606.593830742066816687414116416357241251026826813749831042661324.841672.082872.212772.43487.013120.91003.01745.16159.820.72545.0714.30823.20220.19817.134619.29607.193830742166837919521416516151378121516118048981831522452294.942848.163880.873542.893470.094406.251926.781432.664756447304.511.38985.8314.34644.41138.33533.234927.96896.4657361106399067637221441819398375731496748534982111522202270.652845.613586.113546.093490.134364.761937.9844961241440.92304.791.38985.8714.34444.32938.36133.224927.85902.5857331088297857175519762918205464611505278025782231520662293.542856.183990.183545.363503.944407.681937.9844961241434.72304.511.38985.7974.34744.39838.51833.22928.04902.9257371098598067878020581318369506841503788420082101529862295.232851.233616.573536.983462.394405.211926.781434.72304.601.38985.8494.34944.34838.36133.232927.98903.8657391098298007591220680318619456651512347458782081524512293.812855.334000.043543.513453.744407.961934.241440.92305.341.38985.8094.34944.3338.34133.229928.1902.165737109839809OpenBenchmarking.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 R2C / C2R4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm20K40K60K80K100KSE +/- 24.98, N = 3672576395663887676473560135201351673521967558668496687479195763727175578780759121. (CXX) g++ options: -O3
OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT R2C / C2R4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm14K28K42K56K70KMin: 35153 / Avg: 35201 / Max: 352371. (CXX) g++ options: -O3

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in half precision4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm50K100K150K200K250KSE +/- 194.61, N = 3143183146963139429147059828238272582997830651387161278061411642141652144181976292058132068031. (CXX) g++ options: -O3
OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in half precision4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm40K80K120K160K200KMin: 82359 / Avg: 82724.67 / Max: 830231. (CXX) g++ options: -O3

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C Bluestein in single precision4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm4K8K12K16K20KSE +/- 43.25, N = 3163881696316838168311071510635105931046114512162431635716151193981820518369186191. (CXX) g++ options: -O3
OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C Bluestein in single precision4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm3K6K9K12K15KMin: 10549 / Avg: 10635 / Max: 106861. (CXX) g++ options: -O3

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in double precision4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm11K22K33K44K55KSE +/- 8.95, N = 3314643177534346343561202512070120961210330677231992412537812375734646150684456651. (CXX) g++ options: -O3
OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in double precision4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm9K18K27K36K45KMin: 12054 / Avg: 12069.67 / Max: 120851. (CXX) g++ options: -O3

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in single precision4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm30K60K90K120K150KSE +/- 0.67, N = 3106172106348106208106300423474233842341423451026061026921026821516111496741505271503781512341. (CXX) g++ options: -O3
OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in single precision4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm30K60K90K120K150KMin: 42337 / Avg: 42337.67 / Max: 423391. (CXX) g++ options: -O3

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C multidimensional in single precision4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm20K40K60K80K100KSE +/- 51.67, N = 3739487502968642746743704938684380643860966454675876813780489853498025784200745871. (CXX) g++ options: -O3
OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C multidimensional in single precision4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm15K30K45K60K75KMin: 38594 / Avg: 38683.67 / Max: 387731. (CXX) g++ options: -O3

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C Bluestein benchmark in double precision4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm2K4K6K8K10KSE +/- 2.40, N = 356865706571256872371237323852373485049994983818382118223821082081. (CXX) g++ options: -O3
OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C Bluestein benchmark in double precision4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm14002800420056007000Min: 2370 / Avg: 2373.33 / Max: 23781. (CXX) g++ options: -O3

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm30K60K90K120K150KSE +/- 2.03, N = 3107604107741107838107754430624306743079430711042711042941042661522451522201520661529861524511. (CXX) g++ options: -O3
OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm30K60K90K120K150KMin: 43064 / Avg: 43067.33 / Max: 430711. (CXX) g++ options: -O3

Libplacebo

Libplacebo is a multimedia rendering library based on the core rendering code of the MPV player. The libplacebo benchmark relies on the Vulkan API and tests various primitives. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: deband_heavy4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm5001000150020002500SE +/- 0.15, N = 31529.331527.651528.481530.76514.76517.52514.52514.701323.801324.361324.842294.942270.652293.542295.232293.811. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF
OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: deband_heavy4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm400800120016002000Min: 517.35 / Avg: 517.52 / Max: 517.811. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: polar_nocompute4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm6001200180024003000SE +/- 0.04, N = 31919.911918.791918.631924.72655.96659.34655.72656.201672.461671.911672.082848.162845.612856.182851.232855.331. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF
OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: polar_nocompute4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm5001000150020002500Min: 659.29 / Avg: 659.34 / Max: 659.421. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: hdr_peakdetect4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm9001800270036004500SE +/- 19.72, N = 33002.983260.623184.603251.951570.771546.471506.931503.722874.752882.562872.213880.873586.113990.183616.574000.041. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF
OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: hdr_peakdetect4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm7001400210028003500Min: 1507.05 / Avg: 1546.47 / Max: 1566.851. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: hdr_lut4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm8001600240032004000SE +/- 0.11, N = 32858.682858.872856.352860.741525.071525.751522.301526.732789.692789.732772.403542.893546.093545.363536.983543.511. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF
OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: hdr_lut4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm6001200180024003000Min: 1525.61 / Avg: 1525.75 / Max: 1525.971. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: av1_grain_lap4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm8001600240032004000SE +/- 0.40, N = 33475.583476.353476.233189.611723.151725.791722.451724.713538.353516.563487.013470.093490.133503.943462.393453.741. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF
OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: av1_grain_lap4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm6001200180024003000Min: 1725.08 / Avg: 1725.79 / Max: 1726.471. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: gaussian4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm9001800270036004500SE +/- 0.37, N = 33407.973411.133413.413412.081512.451512.651511.721511.913118.523120.653120.904406.254364.764407.684405.214407.961. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF
OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: gaussian4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm8001600240032004000Min: 1512.11 / Avg: 1512.65 / Max: 1513.351. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF

GpuOwl

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 578851614080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm400800120016002000SE +/- 0.00, N = 31191.901190.481191.901191.90376.65378.36376.65376.651003.011004.021003.011926.781937.981937.981926.781934.241. (CXX) g++ options: -O3 -lgmp -lOpenCL
OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 578851614080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm30060090012001500Min: 378.36 / Avg: 378.36 / Max: 378.361. (CXX) g++ options: -O3 -lgmp -lOpenCL

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 779368674080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm30060090012001500SE +/- 0.00, N = 3896.06896.06894.45896.06278.55278.55277.32278.55744.60745.16745.161432.661440.921434.721434.721440.921. (CXX) g++ options: -O3 -lgmp -lOpenCL
OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 779368674080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm30060090012001500Min: 278.55 / Avg: 278.55 / Max: 278.551. (CXX) g++ options: -O3 -lgmp -lOpenCL

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 3322205234080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm70140210280350SE +/- 0.00, N = 3189.68189.83189.61189.8358.8558.8558.5858.85159.82159.87159.82304.51304.79304.51304.60305.341. (CXX) g++ options: -O3 -lgmp -lOpenCL
OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 3322205234080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm50100150200250Min: 58.85 / Avg: 58.85 / Max: 58.851. (CXX) g++ options: -O3 -lgmp -lOpenCL

ProjectPhysX OpenCL-Benchmark

ProjectPhysX OpenCL-Benchmark provides various OpenCL compute and memory bandwidth micro-benchmarks Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: FP64 Compute4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm0.31250.6250.93751.251.5625SE +/- 0.000, N = 30.8610.8640.8640.8640.2640.2640.2640.2640.7250.7250.7251.3891.3891.3891.3891.3891. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: FP64 Compute4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm246810Min: 0.26 / Avg: 0.26 / Max: 0.261. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: FP32 Compute4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm20406080100SE +/- 0.00, N = 353.5053.4953.6353.6616.5116.5116.5116.5145.0745.0745.0785.8385.8785.8085.8585.811. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: FP32 Compute4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm1632486480Min: 16.51 / Avg: 16.51 / Max: 16.511. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT64 Compute4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm0.97851.9572.93553.9144.8925SE +/- 0.002, N = 34.2374.2524.2394.2392.0872.0942.0892.0914.2804.2724.3084.3464.3444.3474.3494.3491. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT64 Compute4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm246810Min: 2.09 / Avg: 2.09 / Max: 2.11. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT32 Compute4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm1020304050SE +/- 0.000, N = 327.62927.58127.63027.6308.4918.4918.4918.49123.18623.20723.20244.41144.32944.39844.34844.3301. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT32 Compute4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm918273645Min: 8.49 / Avg: 8.49 / Max: 8.491. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT16 Compute4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm918273645SE +/- 0.001, N = 323.98423.97823.98423.9827.4147.4177.4177.41920.21720.21220.19838.33538.36138.51838.36138.3411. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT16 Compute4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm816243240Min: 7.42 / Avg: 7.42 / Max: 7.421. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT8 Compute4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm816243240SE +/- 0.012, N = 320.82220.81920.82520.8226.1796.2256.2156.21417.13517.13517.13433.23433.22433.22033.23233.2291. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT8 Compute4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm714212835Min: 6.21 / Avg: 6.23 / Max: 6.251. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: Memory Bandwidth Coalesced Read4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm2004006008001000SE +/- 0.01, N = 3680.51680.56680.77680.67252.90252.89252.89252.89619.31619.28619.29927.96927.85928.04927.98928.101. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: Memory Bandwidth Coalesced Read4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm160320480640800Min: 252.88 / Avg: 252.89 / Max: 252.91. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: Memory Bandwidth Coalesced Write4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm2004006008001000SE +/- 0.01, N = 3632.69631.65629.88629.10258.47258.40258.40258.36607.15606.59607.19896.46902.58902.92903.86902.161. (CXX) g++ options: -std=c++17 -pthread -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: Memory Bandwidth Coalesced Write4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm160320480640800Min: 258.39 / Avg: 258.4 / Max: 258.421. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

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-FP324080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm12002400360048006000SE +/- 0.00, N = 33972396839673967160916091608160938313830383057365733573757395737
OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP324080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm10002000300040005000Min: 1609 / Avg: 1609 / Max: 1609

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP16C4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm2K4K6K8K10KSE +/- 0.33, N = 3812781218145812831143113311431147420742074211106310882109851098210983
OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP16C4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm2K4K6K8K10KMin: 3113 / Avg: 3113.33 / Max: 3114

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP16S4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm2K4K6K8K10KSE +/- 0.33, N = 38077807980798078303830393039303966786681668399069785980698009809
OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP16S4080 super abcdRTX 4060efg4070 TI SUPERhi4090jklm2K4K6K8K10KMin: 3038 / Avg: 3038.67 / Max: 3039