OpenCL™ is an important new standard for heterogeneous computing. With OpenCL, a software developer can write a single program running on everything: from cell phones to nodes in a supercomputer. To reach its full potential, however, OpenCL needs to deliver more than portability. It needs to deliver "performance portability". In this presentation, we discuss the "performance portability" of OpenCL programs.
Frankly, achieving good "performance portability" can be challenging with the current release of Intel® OpenCL SDK, so in addition to tips for writing "performance portable" code today, it discusses possible future enhancements of Intel® OpenCL SDK to improve "performance portability". You can download the Intel® OpenCL SDK (versions for Linux* and Windows* OS) at: http://www.intel.com/go/opencl.
This intends to be hands-on tutorial build upon the Windows* release from Intel, but we invite to use Linux* version as well.
Click the Download below button to see the tutorial..
Tim Mattson is a parallel programmer (Ph.D. Chemistry, UCSC, 1985). The recurring theme of his career is to do whatever it takes to meet the needs of ...
Page viewed 1442 times since Thu 6 Oct 2011, 23:42.