Towards Metaprogramming for Parallel Systems on a Chip

We demonstrate that the performance of commodity parallel systems significantly depends on low-level details, such as storage layout and iteration space mapping, which motivates the need for tools and techniques that separate a high-level algorithm description from low-level mapping and tuning. We propose to build a tool based on the concept of decoupled Access/Execute metadata which allow the programmer to specify both execution constraints and memory access pattern of a computation kernel.

• Type: Conference
• Year: 2009
• Where: EUROPAR
• Authors: Lee W. Howes, Anton Lokhmotov, Alastair F. Donaldson, Paul H. J. Kelly
• Keywords: Commodity Parallel Systems, EUROPAR 2009, Iteration Space Mapping, Low-level Mapping