RDNA3 vs. NVIDIA OpenCL Compute

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 2212153-NE-RDNA3OPEN09
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
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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
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

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
RX 6800 XT
December 13 2022
  37 Minutes
RX 7900 XT
December 13 2022
  37 Minutes
RX 7900 XTX
December 14 2022
  45 Minutes
RX 6800
December 14 2022
  56 Minutes
RX 5700 XT
December 14 2022
  1 Hour, 17 Minutes
Radeon VII
December 14 2022
  59 Minutes
RTX 3080
December 14 2022
  36 Minutes
RTX 3090
December 14 2022
  33 Minutes
RTX 3080 Ti
December 14 2022
  33 Minutes
Invert Behavior (Only Show Selected Data)
  46 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):


RDNA3 vs. NVIDIA OpenCL ComputeProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionDisplay DriverRX 6800 XTRX 7900 XTRX 7900 XTXRX 6800RX 5700 XTRadeon VIIRTX 3080RTX 3090RTX 3080 TiAMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR X670E HERO (0805 BIOS)AMD Device 14d832GBWestern Digital WD_BLACK SN850X 1000GB + 2000GBAMD Radeon RX 6800 XT 16GB (2575/1000MHz)AMD Navi 21 HDMI AudioASUS MG28UIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 22.045.15.0-56-generic (x86_64)GNOME Shell 42.5X Server 1.21.1.3 + Wayland4.6 Mesa 22.3.0-devel (LLVM 15.0.3 DRM 3.49)OpenCL 2.1 AMD-APP (3513.0)1.3.232GCC 11.3.0ext43840x2160AMD Radeon RX 7900 XT 20GB (3125/1249MHz)AMD Device ab30AMD Radeon RX 7900 XTX 24GB (3220/1249MHz)AMD Radeon RX 6800 16GB (2475/1000MHz)AMD Navi 21 HDMI AudioAMD Radeon RX 5700 XT 8GB (2100/875MHz)AMD Navi 10 HDMI AudioAMD Radeon VII 16GB (1801/1000MHz)AMD Vega 20 HDMI AudioNVIDIA GeForce RTX 3080 10GBNVIDIA GA102 HD AudioX Server 1.21.1.3NVIDIA 525.60.114.6.0OpenCL 3.0 CUDA 12.0.89NVIDIA GeForce RTX 3090 24GBNVIDIA GeForce RTX 3080 Ti 12GBOpenBenchmarking.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,brig,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-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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- Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa601203Graphics Details- RX 6800 XT: BAR1 / Visible vRAM Size: 16368 MB - vBIOS Version: 113-D4120500-101- RX 7900 XT: BAR1 / Visible vRAM Size: 20464 MB - vBIOS Version: 113-D70401-00- RX 7900 XTX: BAR1 / Visible vRAM Size: 24560 MB - vBIOS Version: 113-D7020100-102- RX 6800: BAR1 / Visible vRAM Size: 16368 MB - vBIOS Version: 113-D4120900-101- RX 5700 XT: BAR1 / Visible vRAM Size: 8176 MB - vBIOS Version: 113-D1820501-101- Radeon VII: BAR1 / Visible vRAM Size: 16368 MB - vBIOS Version: 113-D3600200-106- RTX 3080: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 94.02.20.00.07- RTX 3090: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 94.02.27.00.02- RTX 3080 Ti: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 94.02.71.00.01Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected OpenCL Details- RTX 3080: GPU Compute Cores: 8704- RTX 3090: GPU Compute Cores: 10496- RTX 3080 Ti: GPU Compute Cores: 10240

RX 6800 XTRX 7900 XTRX 7900 XTXRX 6800RX 5700 XTRadeon VIIRTX 3080RTX 3090RTX 3080 TiResult OverviewPhoronix Test Suite100%208%316%424%LuxCoreRenderHashcatclpeakcl-mem

RX 6800 XTRX 7900 XTRX 7900 XTXRX 6800RX 5700 XTRadeon VIIRTX 3080RTX 3090RTX 3080 TiPer Watt Result OverviewPhoronix Test Suite100%201%301%402%503%clpeakMeta Performance Per WattsLuxCoreRenderHashcatcl-memP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.M

RDNA3 vs. NVIDIA OpenCL Computeluxcorerender: LuxCore Benchmark - GPUluxcorerender: DLSC - GPUluxcorerender: Orange Juice - GPUluxcorerender: Danish Mood - GPUshoc: OpenCL - S3Dviennacl: OpenCL BLAS - dGEMM-TTviennacl: OpenCL BLAS - dGEMV-Tviennacl: OpenCL BLAS - dAXPYviennacl: OpenCL BLAS - sAXPYviennacl: OpenCL BLAS - dGEMM-NTviennacl: OpenCL BLAS - dGEMM-NNviennacl: OpenCL BLAS - dGEMV-Nviennacl: OpenCL BLAS - dDOTviennacl: OpenCL BLAS - sDOTviennacl: OpenCL BLAS - sCOPYviennacl: OpenCL BLAS - dCOPYviennacl: OpenCL BLAS - dGEMM-TNshoc: OpenCL - Texture Read Bandwidthhashcat: SHA-512luxcorerender: Rainbow Colors and Prism - GPUclpeak: Transfer Bandwidth enqueueWriteBufferhashcat: MD5hashcat: SHA1shoc: OpenCL - GEMM SGEMM_Nhashcat: TrueCrypt RIPEMD160 + XTScl-mem: Copycl-mem: Writecl-mem: Readclpeak: Integer Compute INTshoc: OpenCL - Reductionhashcat: 7-Zipshoc: OpenCL - FFT SPshoc: OpenCL - MD5 Hashclpeak: Global Memory Bandwidthclpeak: Single-Precision FloatRX 6800 XTRX 7900 XTRX 7900 XTXRX 6800RX 5700 XTRadeon VIIRTX 3080RTX 3090RTX 3080 Ti6.495.372.315.7993.397812105328238101220119714755756455640611731092.71236795000017.8244.6851928800000204182000007352.00577387361.1437.1470.45626.23469.75410756001687.6728.3906457.1222446.788.066.962.857.61312.1427743595607997847871146435475645967761890.49298251666723.1158.9561382728571263681000007770.89806578431.4702.2715.37276.97591.19612586802263.1636.2169619.3626238.369.698.133.138.87367.9209134046588679269171186925906026778912213.05342088333327.6358.61697026142863029187142910295.69900640462.4842.3864.88208.52609.81614998302735.9440.3631716.4428891.625.044.232.104.5089.5783928474785752931919137553527517411904875.719192653333315.5044.1342083242857167006833335534.18487667345.5442.7459.94237.90432.2518856001673.7621.9934375.6615416.602.291.9311058500008.8944.72240026666679697950000299400326.7390.1403.72504.88507411342.409373.502.091.7312.02289.63714032665763771547148362.6484274296473952449.625145494666713.5344.4035047283333122868000005905.34430329302.6673.9251.26602.07312.2356285002395.1716.9376793.5213144.969.629.549.257.99340.3844983756304744994971916043753585564982181.51237256666726.7525.4859755885714188580166676372.37704678354.3645.5672.615440.11393.66110012441762.9637.1537662.2829425.4411.5511.4610.689.41430.0546063767245026116071896673833656096082200.19282518333331.5225.3671244283333225454333338222.30826657364.2749.3825.418086.12397.81711630332103.6043.8949813.4935185.0811.0110.9310.168.94418.6065603677054935665641856523693595935652134.29267805000031.1213.0767452750000213455166678131.99786900355.7737.1804.017437.50386.99611070562016.2541.6772794.6033704.79OpenBenchmarking.org

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: GPURadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 30803691215SE +/- 0.05, N = 12SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.12, N = 12SE +/- 0.12, N = 6SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 32.099.698.066.495.042.2911.5511.019.62MIN: 0.29 / MAX: 2.48MIN: 3.96 / MAX: 11.01MIN: 3.48 / MAX: 9.15MIN: 2.8 / MAX: 7.35MIN: 0.83 / MAX: 5.84MIN: 0.32 / MAX: 2.7MIN: 4.91 / MAX: 13.17MIN: 3.57 / MAX: 12.61MIN: 3.12 / MAX: 11.01

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: GPURadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 30803691215SE +/- 0.05, N = 12SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.12, N = 12SE +/- 0.06, N = 12SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 31.738.136.965.374.231.9311.4610.939.54MIN: 0.33 / MAX: 1.88MIN: 7.94 / MAX: 8.48MIN: 6.78 / MAX: 7.21MIN: 5.23 / MAX: 5.65MIN: 0.82 / MAX: 4.59MIN: 0.37 / MAX: 2.07MIN: 10.5 / MAX: 11.82MIN: 10.5 / MAX: 11.09MIN: 9.35 / MAX: 9.8

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: GPURadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 30803691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.11, N = 3SE +/- 0.02, N = 31.003.132.852.312.1010.6810.169.25MIN: 2.81 / MAX: 3.76MIN: 2.67 / MAX: 3.45MIN: 2.1 / MAX: 2.99MIN: 1.91 / MAX: 2.69MIN: 8.65 / MAX: 14.18MIN: 8.2 / MAX: 13.69MIN: 7.35 / MAX: 11.9

Scene: Orange Juice - Acceleration: GPU

RX 5700 XT: The test quit with a non-zero exit status. E: RUNTIME ERROR: OpenCL driver API error (code: -6, file:/home/vsts/work/1/s/LinuxCompile/LuxCore-sdk/src/luxrays/devices/ocldevice.cpp, line: 143): CL_OUT_OF_HOST_MEMORY

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Danish Mood - Acceleration: GPURadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 30803691215SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.13, N = 3SE +/- 0.07, N = 3SE +/- 0.11, N = 32.028.877.615.794.509.418.947.99MIN: 0.75 / MAX: 2.29MIN: 3.4 / MAX: 10.2MIN: 2.96 / MAX: 8.76MIN: 2.39 / MAX: 6.64MIN: 1.74 / MAX: 5.11MIN: 3.47 / MAX: 10.92MIN: 2.99 / MAX: 10.44MIN: 2.96 / MAX: 9.11

Scene: Danish Mood - Acceleration: GPU

RX 5700 XT: The test quit with a non-zero exit status. E: RUNTIME ERROR: OpenCL driver API error (code: -6, file:/home/vsts/work/1/s/LinuxCompile/LuxCore-sdk/src/luxrays/devices/ocldevice.cpp, line: 143): CL_OUT_OF_HOST_MEMORY

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: S3DRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 308090180270360450SE +/- 0.58, N = 3SE +/- 3.65, N = 15SE +/- 3.49, N = 4SE +/- 1.05, N = 3SE +/- 0.40, N = 3SE +/- 0.32, N = 13SE +/- 0.06, N = 13SE +/- 0.06, N = 13289.64367.92312.1493.4089.58430.05418.61340.381. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

Target: OpenCL - Benchmark: S3D

RX 5700 XT: The test run did not produce a result.

ViennaCL

ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile makes use of ViennaCL's built-in benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TTRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 308030060090012001500SE +/- 3.33, N = 3SE +/- 2.03, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 2SE +/- 1.00, N = 3140391377412109286065604981. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Test: OpenCL BLAS - dGEMM-TT

RX 5700 XT: The test quit with a non-zero exit status. E: what(): ViennaCL: FATAL ERROR: CL_OUT_OF_HOST_MEMORY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-TRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 3080120240360480600SE +/- 0.33, N = 3SE +/- 3.67, N = 3SE +/- 1.67, N = 3SE +/- 3.84, N = 3SE +/- 14.95, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 32664043595324743763673761. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Test: OpenCL BLAS - dGEMV-T

RX 5700 XT: The test quit with a non-zero exit status. E: what(): ViennaCL: FATAL ERROR: CL_OUT_OF_HOST_MEMORY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dAXPYRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 30802004006008001000SE +/- 1.53, N = 3SE +/- 6.17, N = 3SE +/- 2.00, N = 2SE +/- 5.46, N = 3SE +/- 2.52, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 35766585608237857247056311. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Test: OpenCL BLAS - dAXPY

RX 5700 XT: The test quit with a non-zero exit status. E: what(): ViennaCL: FATAL ERROR: CL_OUT_OF_HOST_MEMORY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sAXPYRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 30802004006008001000SE +/- 2.19, N = 3SE +/- 5.84, N = 3SE +/- 8.69, N = 3SE +/- 9.00, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 33778677998107525024934761. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Test: OpenCL BLAS - sAXPY

RX 5700 XT: The test quit with a non-zero exit status. E: what(): ViennaCL: FATAL ERROR: CL_OUT_OF_HOST_MEMORY

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NTRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 308030060090012001500SE +/- 3.33, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 5.77, N = 3SE +/- 0.67, N = 3SE +/- 1.20, N = 3SE +/- 1.00, N = 3154792678412209316115665021. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Test: OpenCL BLAS - dGEMM-NT

RX 5700 XT: The test quit with a non-zero exit status. E: what(): ViennaCL: FATAL ERROR: CL_OUT_OF_HOST_MEMORY

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NNRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 308030060090012001500SE +/- 3.33, N = 3SE +/- 0.58, N = 3SE +/- 0.88, N = 3SE +/- 3.33, N = 3SE +/- 2.19, N = 3SE +/- 0.58, N = 3SE +/- 1.33, N = 3SE +/- 1.00, N = 3148391778711979196075645001. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Test: OpenCL BLAS - dGEMM-NN

RX 5700 XT: The test quit with a non-zero exit status. E: what(): ViennaCL: FATAL ERROR: CL_OUT_OF_HOST_MEMORY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-NRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 30804080120160200SE +/- 0.09, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.67, N = 3SE +/- 1.67, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 362.6118.0114.0147.0137.0189.0185.0192.01. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Test: OpenCL BLAS - dGEMV-N

RX 5700 XT: The test quit with a non-zero exit status. E: what(): ViennaCL: FATAL ERROR: CL_OUT_OF_HOST_MEMORY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOTRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 3080150300450600750SE +/- 2.52, N = 3SE +/- 18.41, N = 3SE +/- 5.51, N = 3SE +/- 4.37, N = 3SE +/- 4.37, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 34846926435575536676526051. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Test: OpenCL BLAS - dDOT

RX 5700 XT: The test quit with a non-zero exit status. E: what(): ViennaCL: FATAL ERROR: CL_OUT_OF_HOST_MEMORY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sDOTRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 3080130260390520650SE +/- 3.33, N = 3SE +/- 10.68, N = 3SE +/- 9.35, N = 3SE +/- 14.00, N = 2SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 32745905475645273833693771. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Test: OpenCL BLAS - sDOT

RX 5700 XT: The test quit with a non-zero exit status. E: what(): ViennaCL: FATAL ERROR: CL_OUT_OF_HOST_MEMORY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sCOPYRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 3080130260390520650SE +/- 1.33, N = 3SE +/- 8.21, N = 3SE +/- 6.17, N = 3SE +/- 6.51, N = 3SE +/- 0.33, N = 3SE +/- 1.20, N = 3SE +/- 1.20, N = 3SE +/- 0.00, N = 32966025645565173653593581. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Test: OpenCL BLAS - sCOPY

RX 5700 XT: The test quit with a non-zero exit status. E: what(): ViennaCL: FATAL ERROR: CL_OUT_OF_HOST_MEMORY

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPYRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 3080150300450600750SE +/- 3.18, N = 3SE +/- 3.84, N = 3SE +/- 3.67, N = 3SE +/- 4.36, N = 3SE +/- 1.45, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.00, N = 34736775964064116095935571. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Test: OpenCL BLAS - dCOPY

RX 5700 XT: The test quit with a non-zero exit status. E: what(): ViennaCL: FATAL ERROR: CL_OUT_OF_HOST_MEMORY

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TNRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 308030060090012001500SE +/- 2.60, N = 3SE +/- 1.15, N = 3SE +/- 0.58, N = 3SE +/- 3.33, N = 3SE +/- 1.00, N = 3SE +/- 0.50, N = 2SE +/- 1.33, N = 395289177611739046085655001. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Test: OpenCL BLAS - dGEMM-TN

RX 5700 XT: The test quit with a non-zero exit status. E: what(): ViennaCL: FATAL ERROR: CL_OUT_OF_HOST_MEMORY

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 BandwidthRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 30805001000150020002500SE +/- 1.27, N = 4SE +/- 5.22, N = 10SE +/- 14.48, N = 10SE +/- 2.10, N = 8SE +/- 2.26, N = 8SE +/- 1.96, N = 3SE +/- 0.66, N = 3SE +/- 1.08, N = 3449.632213.051890.491092.71875.722200.192134.292181.511. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

Target: OpenCL - Benchmark: Texture Read Bandwidth

RX 5700 XT: The test run did not produce a result.

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-512Radeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 3080700M1400M2100M2800M3500MSE +/- 23473202.28, N = 15SE +/- 2918608.88, N = 6SE +/- 4470825.18, N = 6SE +/- 889475.50, N = 6SE +/- 1232522.26, N = 6SE +/- 1462589.03, N = 6SE +/- 3397589.01, N = 6SE +/- 2908120.81, N = 6SE +/- 1482040.64, N = 6145494666734208833332982516667236795000019265333331105850000282518333326780500002372566667

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: GPURadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 3080714212835SE +/- 0.08, N = 4SE +/- 0.00, N = 6SE +/- 0.07, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.03, N = 3SE +/- 0.16, N = 6SE +/- 0.08, N = 6SE +/- 0.11, N = 613.5327.6323.1117.8215.508.8931.5231.1226.75MIN: 10.02 / MAX: 15MIN: 25.23 / MAX: 29.44MIN: 21.35 / MAX: 24MIN: 16.51 / MAX: 18.34MIN: 14.54 / MAX: 15.99MIN: 8.58 / MAX: 9.11MIN: 28.71 / MAX: 34.92MIN: 28.53 / MAX: 34.16MIN: 23.62 / MAX: 29.35

clpeak

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

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueWriteBufferRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 30801326395265SE +/- 0.23, N = 6SE +/- 0.22, N = 8SE +/- 0.25, N = 7SE +/- 0.27, N = 6SE +/- 0.22, N = 6SE +/- 0.29, N = 5SE +/- 0.01, N = 7SE +/- 0.00, N = 3SE +/- 0.01, N = 444.4058.6158.9544.6844.1344.7225.3613.0725.481. (CXX) g++ options: -O3 -rdynamic -lOpenCL

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: MD5Radeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 308015000M30000M45000M60000M75000MSE +/- 4912936.44, N = 6SE +/- 84711702.76, N = 7SE +/- 92800753.57, N = 7SE +/- 43793302.38, N = 7SE +/- 34450211.54, N = 7SE +/- 29219339.11, N = 6SE +/- 90108517.60, N = 6SE +/- 75676635.54, N = 6SE +/- 83944276.95, N = 7350472833336970261428661382728571519288000004208324285724002666667712442833336745275000059755885714

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA1Radeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 30806000M12000M18000M24000M30000MSE +/- 848920.88, N = 6SE +/- 31736944.93, N = 7SE +/- 24335461.09, N = 6SE +/- 20754437.28, N = 6SE +/- 43663954.75, N = 6SE +/- 8939341.88, N = 6SE +/- 17806771.50, N = 6SE +/- 20586814.82, N = 6SE +/- 27656770.32, N = 612286800000302918714292636810000020418200000167006833339697950000225454333332134551666718858016667

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: GEMM SGEMM_NRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 30802K4K6K8K10KSE +/- 3.93, N = 9SE +/- 165.23, N = 15SE +/- 121.67, N = 15SE +/- 97.24, N = 15SE +/- 85.06, N = 15SE +/- 15.79, N = 12SE +/- 16.35, N = 11SE +/- 7.36, N = 115905.3410295.697770.897352.005534.188222.308131.996372.371. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

Target: OpenCL - Benchmark: GEMM SGEMM_N

RX 5700 XT: The test run did not produce a result.

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 + XTSRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 3080200K400K600K800K1000KSE +/- 1846.07, N = 7SE +/- 976.30, N = 10SE +/- 3079.13, N = 9SE +/- 7271.22, N = 15SE +/- 452.46, N = 9SE +/- 1606.13, N = 8SE +/- 4427.88, N = 7SE +/- 5315.17, N = 8SE +/- 1635.86, N = 9430329900640806578577387487667299400826657786900704678

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: CopyRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 3080100200300400500SE +/- 0.41, N = 8SE +/- 0.37, N = 10SE +/- 0.03, N = 10SE +/- 0.04, N = 8SE +/- 0.10, N = 8SE +/- 0.24, N = 8SE +/- 0.06, N = 10SE +/- 0.24, N = 10SE +/- 0.05, N = 9302.6462.4431.4361.1345.5326.7364.2355.7354.31. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 30802004006008001000SE +/- 0.62, N = 8SE +/- 0.37, N = 10SE +/- 0.16, N = 10SE +/- 1.35, N = 8SE +/- 0.26, N = 8SE +/- 2.21, N = 8SE +/- 0.23, N = 10SE +/- 0.32, N = 10SE +/- 0.31, N = 9673.9842.3702.2437.1442.7390.1749.3737.1645.51. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 30802004006008001000SE +/- 0.24, N = 8SE +/- 0.18, N = 10SE +/- 1.73, N = 10SE +/- 0.10, N = 8SE +/- 1.14, N = 8SE +/- 0.71, N = 8SE +/- 0.11, N = 10SE +/- 0.10, N = 9SE +/- 0.08, N = 9251.2864.8715.3470.4459.9403.7825.4804.0672.61. (CC) gcc options: -O2 -flto -lOpenCL

clpeak

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

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 30804K8K12K16K20KSE +/- 2.35, N = 8SE +/- 7.38, N = 8SE +/- 7.19, N = 8SE +/- 0.25, N = 7SE +/- 1.65, N = 8SE +/- 0.72, N = 7SE +/- 124.81, N = 13SE +/- 118.19, N = 15SE +/- 103.36, N = 156602.078208.527276.975626.234237.902504.8818086.1217437.5015440.111. (CXX) g++ options: -O3 -rdynamic -lOpenCL

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: ReductionRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 3080130260390520650SE +/- 0.19, N = 12SE +/- 0.99, N = 13SE +/- 1.06, N = 13SE +/- 2.96, N = 13SE +/- 2.73, N = 12SE +/- 0.08, N = 13SE +/- 0.06, N = 13SE +/- 0.07, N = 13312.24609.82591.20469.75432.25397.82387.00393.661. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

Target: OpenCL - Benchmark: Reduction

RX 5700 XT: The test run did not produce a result.

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-ZipRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 3080300K600K900K1200K1500KSE +/- 754.75, N = 8SE +/- 2789.55, N = 10SE +/- 2104.38, N = 10SE +/- 867.95, N = 9SE +/- 1045.23, N = 9SE +/- 835.40, N = 9SE +/- 618.24, N = 9SE +/- 456.16, N = 9SE +/- 608.30, N = 9628500149983012586801075600885600507411116303311070561001244

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 SPRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 30806001200180024003000SE +/- 2.34, N = 12SE +/- 3.26, N = 13SE +/- 1.13, N = 13SE +/- 0.93, N = 13SE +/- 0.69, N = 13SE +/- 0.16, N = 13SE +/- 0.12, N = 13SE +/- 0.13, N = 132395.172735.942263.161687.671673.762103.602016.251762.961. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

Target: OpenCL - Benchmark: FFT SP

RX 5700 XT: The test run did not produce a result.

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RTX 3090RTX 3080 TiRTX 30801020304050SE +/- 0.00, N = 12SE +/- 0.04, N = 14SE +/- 0.09, N = 13SE +/- 0.00, N = 13SE +/- 0.00, N = 13SE +/- 0.05, N = 14SE +/- 0.00, N = 14SE +/- 0.00, N = 1416.9440.3636.2228.3921.9943.8941.6837.151. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

Target: OpenCL - Benchmark: MD5 Hash

RX 5700 XT: The test run did not produce a result.

clpeak

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

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 30802004006008001000SE +/- 0.65, N = 9SE +/- 0.32, N = 10SE +/- 0.78, N = 9SE +/- 0.02, N = 9SE +/- 0.66, N = 9SE +/- 3.16, N = 7SE +/- 0.02, N = 14SE +/- 0.04, N = 13SE +/- 0.03, N = 14793.52716.44619.36457.12375.66342.40813.49794.60662.281. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 30808K16K24K32K40KSE +/- 5.01, N = 8SE +/- 75.34, N = 9SE +/- 37.62, N = 9SE +/- 2.29, N = 9SE +/- 22.92, N = 9SE +/- 11.77, N = 9SE +/- 24.18, N = 14SE +/- 22.78, N = 14SE +/- 82.27, N = 1313144.9628891.6226238.3622446.7815416.609373.5035185.0833704.7929425.441. (CXX) g++ options: -O3 -rdynamic -lOpenCL

Meta Performance Per Watts

OpenBenchmarking.orgPerformance Per Watts, More Is BetterMeta Performance Per WattsPerformance Per WattsRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 30803K6K9K12K15K2752.765627.904894.913724.233147.2312500.005608.155252.584351.03

GPU Temperature Monitor

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 30801530456075Min: 41 / Avg: 58.82 / Max: 72Min: 27 / Avg: 57.6 / Max: 73Min: 25 / Avg: 49.03 / Max: 65Min: 49 / Avg: 62.56 / Max: 78Min: 48 / Avg: 60.6 / Max: 68Min: 36 / Avg: 54.67 / Max: 69Min: 42 / Avg: 57.28 / Max: 70Min: 30 / Avg: 62.32 / Max: 79Min: 47 / Avg: 62.12 / Max: 77

GPU Power Consumption Monitor

OpenBenchmarking.orgWattsGPU Power Consumption MonitorPhoronix Test Suite System MonitoringRadeon VIIRX 7900 XTXRX 7900 XTRX 6800 XTRX 6800RX 5700 XTRTX 3090RTX 3080 TiRTX 308060120180240300Min: 21 / Avg: 85.96 / Max: 358Min: 12 / Avg: 118.81 / Max: 297Min: 11 / Avg: 110.62 / Max: 267Min: 6 / Avg: 92.22 / Max: 256Min: 5 / Avg: 90.04 / Max: 203Min: 7 / Avg: 67.46 / Max: 207Min: 16.47 / Avg: 184.74 / Max: 349.64Min: 18.98 / Avg: 185.58 / Max: 350.33Min: 15.6 / Avg: 153.55 / Max: 320.04