OpenCL Radeon Open-Source

Radeon R600g and RadeonSI Gallium3D Clover OpenCL benchmarks with SHOC and clpeak. Benchmark results by Michael Larabel of Phoronix.com.

HTML result view exported from: https://openbenchmarking.org/result/1602020-GA-OPENCLRAD51&gru.

OpenCL Radeon Open-SourceProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionRadeon HD 6870Radeon HD 6950Radeon HD 7950Radeon R9 285Radeon R9 290Radeon R7 370Intel Core i7-5960X @ 3.50GHz (16 Cores)Gigabyte X99-UD4-CFIntel Xeon E7 v3/Xeon16384MB2 x 120GB SanDisk SDSSDA12 + 120GB Samsung SSD 850Sapphire AMD Radeon HD 6870 1024MBRealtek ALC1150DELL P2415QIntel ConnectionUbuntu 15.104.5.0-rc2amdgpu-pp+ (x86_64) 20160201UnityX Server 1.17.2radeon 7.6.993.3 Mesa 11.2.0-devel (padoka PPA) Gallium 0.4GCC 5.2.1 20151010ext43840x2160Sapphire AMD Radeon HD 6950 2048MB4.1 Mesa 11.2.0-devel (padoka PPA) Gallium 0.4XFX AMD Radeon HD 7950/8950 OEM / R9 280 3072MBXFX AMD Radeon R9 285/380 2048MBamdgpu 1.0.99XFX AMD Radeon R9 290 4096MBradeon 7.6.99MSI AMD Radeon R7 370 / R9 270/370 OEM 4096MBOpenBenchmarking.orgKernel Details- amdgpu.powerplay=1Compiler Details- --build=x86_64-linux-gnu --disable-browser-plugin --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-arch-directory=amd64 --with-default-libstdcxx-abi=new --with-multilib-list=m32,m64,mx32 --with-tune=generic -v Processor Details- Scaling Governor: intel_pstate performanceGraphics Details- Radeon HD 6870: EXA- Radeon HD 6950: EXA- Radeon HD 7950: GLAMOR- Radeon R9 285: GLAMOR- Radeon R9 290: GLAMOR- Radeon R7 370: GLAMOR

OpenCL Radeon Open-Sourceshoc: OpenCL - Bus Speed Downloadshoc: OpenCL - Bus Speed Readbackclpeak: Transfer Bandwidth enqueueReadBufferclpeak: Transfer Bandwidth enqueueWriteBufferclpeak: Single-Precision Floatclpeak: Double-Precision Doubleclpeak: Integer Compute INTclpeak: Kernel LatencyRadeon HD 6870Radeon HD 6950Radeon HD 7950Radeon R9 285Radeon R9 290Radeon R7 3703.585.26360.92182.44145.8510.215.5910.4015.722345.12547.03491.62105.5410.145.9410.0914.823102.60204.75650.80143.397.723.029.8212.324608.55596.551578.01118.7110.215.0510.4115.772031.91131.49418.74110.24OpenBenchmarking.org

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Download

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed DownloadRadeon HD 7950Radeon R9 285Radeon R9 290Radeon R7 3703691215SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.17, N = 6SE +/- 0.00, N = 310.2110.147.7210.211. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi -ldl -lhwloc

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Readback

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed ReadbackRadeon HD 7950Radeon R9 285Radeon R9 290Radeon R7 3701.33652.6734.00955.3466.6825SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 6SE +/- 0.03, N = 35.595.943.025.051. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi -ldl -lhwloc

clpeak

OpenCL Test: Transfer Bandwidth enqueueReadBuffer

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueReadBufferRadeon HD 6870Radeon HD 7950Radeon R9 285Radeon R9 290Radeon R7 3703691215SE +/- 0.10, N = 6SE +/- 0.03, N = 3SE +/- 0.30, N = 6SE +/- 0.25, N = 6SE +/- 0.02, N = 33.5810.4010.099.8210.41

clpeak

OpenCL Test: Transfer Bandwidth enqueueWriteBuffer

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueWriteBufferRadeon HD 6870Radeon HD 7950Radeon R9 285Radeon R9 290Radeon R7 37048121620SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.59, N = 6SE +/- 0.06, N = 3SE +/- 0.00, N = 35.2615.7214.8212.3215.77

clpeak

OpenCL Test: Single-Precision Float

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatRadeon HD 6870Radeon HD 7950Radeon R9 285Radeon R9 290Radeon R7 37010002000300040005000SE +/- 0.08, N = 3SE +/- 47.92, N = 6SE +/- 1.52, N = 3SE +/- 2.13, N = 3SE +/- 0.22, N = 3360.922345.123102.604608.552031.91

clpeak

OpenCL Test: Double-Precision Double

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleRadeon HD 7950Radeon R9 285Radeon R9 290Radeon R7 370130260390520650SE +/- 16.28, N = 6SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.00, N = 3547.03204.75596.55131.49

clpeak

OpenCL Test: Integer Compute INT

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTRadeon HD 6870Radeon HD 7950Radeon R9 285Radeon R9 290Radeon R7 37030060090012001500SE +/- 0.16, N = 3SE +/- 7.09, N = 6SE +/- 0.05, N = 3SE +/- 0.49, N = 3SE +/- 0.01, N = 3182.44491.62650.801578.01418.74

clpeak

OpenCL Test: Kernel Latency

OpenBenchmarking.orgus, More Is BetterclpeakOpenCL Test: Kernel LatencyRadeon HD 6870Radeon HD 7950Radeon R9 285Radeon R9 290Radeon R7 370306090120150SE +/- 8.80, N = 6SE +/- 1.78, N = 6SE +/- 14.32, N = 6SE +/- 2.08, N = 6SE +/- 3.85, N = 6145.85105.54143.39118.71110.24

Phoronix Test Suite v10.8.4