ParLe—A Parallel Computing Learning Set for MPSOCs/NOCs
Martti J. Forsell · 2005
Programming and design skills in parallel computing related to systems on chip (SOC) will become increasingly important since future SOCs will have multiple processors interconnected via on-chip networks (NOC). Unfortunately there exist no easy-to-use tools for learning and experimenting with multiprocessor (MP)SOCs/NOCs, but one must use ad-hoc combinations of tools, methodologies and sample applications from very different sources. In this paper we introduce a parallel computing learning set (Parle) for configurable shared memory MPSOCs/NOCs and corresponding theoretical parallel random access machines (PRAM). The learning set consists of an experimental optimizing compiler for high-level parallel programming language e and assembler, linker, loader, simulator with a graphical user interface and statistical tools, and sample e/assembler code. Using the set, a student/designer can easily ivrite simple parallel programs, compile and load them into a configurable MPSOC/NOC platform, execute/debug them, gather statistics and explore the performance, utilization, and gate count estimations with different architectural parameters. The learning set runs on Mac OS X systems and is available for non-profit educational purposes.