OpenCL ROCm vs. AMDGPU-PRO 17.40 + 2MB FS

AMDGPU-PRO 17.40 vs. ROCm. Linux OpenCL compute performance. Tests for a future article.

HTML result view exported from: https://openbenchmarking.org/result/1710282-AL-OPENCLNEW89&grt&rdt.

ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen ResolutionAMDGPU-PRO 17.40ROCm RX Vega 64 R9 Fury RX 560 RX 580 RX Vega 56 RX 580 RX 560 R9 Fury RX Vega 56 RX Vega 64Intel Core i7-7700K @ 4.50GHz (4 Cores / 8 Threads)MSI Z270-A PRO (MS-7A71) v1.0Intel Device 591f16384MB128GB THNSN5128GPU7 TOSHIBAAMD Radeon RX Vega 8176MBRealtek ALC892DELL P2415QRealtek RTL8111/8168/8411Ubuntu 16.044.10.0-37-generic (x86_64)Unity 7.4.0amdgpu 1.3.994.5.13496OpenCL 2.0 AMD-APP (2482.3)GCC 5.4.0 20160609ext43840x2160Sapphire AMD Radeon 4096MBmodesetting 1.19.3AMD Radeon RX 560 4096MBamdgpu 1.3.99MSI AMD Radeon RX 580 8192MBmodesetting 1.19.3AMD Radeon RX Vega 8176MBamdgpu 1.3.99MSI AMD POLARIS10 8192MB4.11.0-kfd-compute-rocm-rel-1.6-180 (x86_64)modesetting 1.19.34.5 Mesa 17.0.7 Gallium 0.4 (LLVM 4.0.0)OpenCL 2.0 AMD-APP (2508.0)AMD POLARIS11 4096MBamdgpu 1.3.0Sapphire AMD Radeon R9 FURY / NANO 4096MBmodesetting 1.19.3LLVMpipe3.3 Mesa 17.0.7 Gallium 0.4 (LLVM 4.0 256 bits)OpenBenchmarking.orgCompiler 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- AMDGPU-PRO 17.40: RX Vega 64, AMDGPU-PRO 17.40: R9 Fury, AMDGPU-PRO 17.40: RX 560, AMDGPU-PRO 17.40: RX 580, AMDGPU-PRO 17.40: RX Vega 56, ROCm: RX 580, ROCm: RX 560, ROCm: R9 Fury: GLAMOREnvironment Details- ROCm: RX Vega 56, ROCm: RX Vega 64: LIBGL_ALWAYS_SOFTWARE=1

cl-mem: Copycl-mem: Readcl-mem: Writeethminer: GPU OpenCLluxmark: GPU - Hotelluxmark: GPU - Luxball HDRAMDGPU-PRO 17.40ROCm RX Vega 64 R9 Fury RX 560 RX 580 RX Vega 56 RX 580 RX 560 R9 Fury RX Vega 56 RX Vega 64363.77397.50378.2332309247424422178330.10447.90374.072544544424682076477.0790.2080.301091247210906314173.20208.33177.9721963298252914622306.63337.00321.6029370321370821543184.27166.43180.331689518013841448180.9793.5080.8384978335846309206.30123.50390.9724804647156119647204.17178.47317.5029552366156123058222.20189.13389.1332990822183523626OpenBenchmarking.org

cl-mem

Benchmark: Copy

AMDGPU-PRO 17.40ROCmOpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyRX Vega 64R9 FuryRX 560RX 580RX Vega 5680160240320400SE +/- 0.03, N = 3SE +/- 1.55, N = 3SE +/- 0.52, N = 3SE +/- 0.75, N = 3SE +/- 1.56, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 3363.77330.1077.07173.20306.63184.2780.97206.30204.17222.201. (CC) gcc options: -O2 -flto -lOpenCL

cl-mem

Benchmark: Read

AMDGPU-PRO 17.40ROCmOpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadRX Vega 64R9 FuryRX 560RX 580RX Vega 56100200300400500SE +/- 0.00, N = 3SE +/- 0.12, N = 3SE +/- 0.66, N = 3SE +/- 0.20, N = 3SE +/- 1.71, N = 3SE +/- 1.95, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 3SE +/- 0.19, N = 3397.50447.9090.20208.33337.00166.4393.50123.50178.47189.131. (CC) gcc options: -O2 -flto -lOpenCL

cl-mem

Benchmark: Write

AMDGPU-PRO 17.40ROCmOpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteRX Vega 64R9 FuryRX 560RX 580RX Vega 5680160240320400SE +/- 0.03, N = 3SE +/- 2.49, N = 3SE +/- 0.06, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.26, N = 3SE +/- 0.03, N = 3SE +/- 3.08, N = 3SE +/- 3.10, N = 3SE +/- 0.09, N = 3378.23374.0780.30177.97321.60180.3380.83390.97317.50389.131. (CC) gcc options: -O2 -flto -lOpenCL

Ethereum Ethminer

Device: GPU OpenCL

AMDGPU-PRO 17.40ROCmOpenBenchmarking.orgH/s, More Is BetterEthereum Ethminer 1.2.9Device: GPU OpenCLRX Vega 64R9 FuryRX 560RX 580RX Vega 567M14M21M28M35MSE +/- 446721.48, N = 3SE +/- 100519.99, N = 3SE +/- 39105.19, N = 3SE +/- 51510.63, N = 3SE +/- 131902.80, N = 3SE +/- 65584.53, N = 3SE +/- 39402.49, N = 3SE +/- 121114.30, N = 3SE +/- 126928.78, N = 3SE +/- 578374.82, N = 33230924725445444109124722196329829370321168951808497833248046472955236632990822

LuxMark

OpenCL Device: GPU - Scene: Hotel

AMDGPU-PRO 17.40ROCmOpenBenchmarking.orgScore, More Is BetterLuxMark 3.0OpenCL Device: GPU - Scene: HotelRX Vega 64R9 FuryRX 560RX 580RX Vega 569001800270036004500SE +/- 15.59, N = 3SE +/- 8.17, N = 3SE +/- 2.33, N = 3SE +/- 4.81, N = 3SE +/- 20.37, N = 3SE +/- 2.85, N = 3SE +/- 1.20, N = 3SE +/- 3.00, N = 3SE +/- 3.18, N = 3SE +/- 7.22, N = 3424424681090252937081384584156115611835

LuxMark

OpenCL Device: GPU - Scene: Luxball HDR

AMDGPU-PRO 17.40ROCmOpenBenchmarking.orgScore, More Is BetterLuxMark 3.0OpenCL Device: GPU - Scene: Luxball HDRRX Vega 64R9 FuryRX 560RX 580RX Vega 565K10K15K20K25KSE +/- 194.29, N = 3SE +/- 112.25, N = 3SE +/- 8.76, N = 3SE +/- 62.00, N = 3SE +/- 3.84, N = 3SE +/- 17.85, N = 3SE +/- 12.14, N = 3SE +/- 99.50, N = 3SE +/- 15.19, N = 3SE +/- 157.33, N = 3221782076463141462221543144816309196472305823626


Phoronix Test Suite v10.8.4