A Practical OpenMP Compiler for System on Chips
With the advent of modern System-on-Chip (SOC) design, the integration of multiple-processors into one die has become the trend. By far there are no standard programming paradigms for SOCs or heterogeneous chip multiprocessors. Users are required to write complex assembly language and/or C programs for SOCs. Developing a standard programming model for this new parallel architecture is necessary. In this paper, we propose a practical OpenMP compiler for SOCs, especially targeting 3SoC. We also present our solutions to extend OpenMP directives to incorporate advanced architectural features of SOCs. Preliminary performance evaluation shows scalable speedup using different types of processors and effectiveness of performance improvement through optimization.
KeywordsLocal Memory Memory Allocation Parallel Region Chip Multiprocessor Parallel Construct
Unable to display preview. Download preview PDF.
- OpenMP Architecture Review Board OpenMP C and C++ Application Program Interface, Version 2.0, March, 2002. http://www.openmp.org
- OpenMP Architecture Review Board, OpenMP: An Industry-Standard API for Shared-Memory Programming. IEEE Computational Science & Engineering, Vol. 5, No. 1, January/March 1998, http://www.openmp.org
- 3SOC Documentation — 3SOC 2003 Hardware Architecture, Cradle Technologies, Inc. March. 2002Google Scholar
- 3SOC Programmer’s Guide, Cradle Technologies, Inc., Mar. 2002, http://www.cradle.com
- Christian Brunschen, Mats Brorsson, OdinMP/CCp — A portable implementation of OpenMP for C, Lund Universtiy, Sweden, 1999 Google Scholar
- R. Chandra, L. Dagum, D. Kohr, D. Maydan, J. McDonald, and R. Menon. Parallel Programming in OpenMP. Morgan Kaufmann Publishers, 2001Google Scholar
- Chong-Liang Ooi, Seon Wook Kim, and Il Park. Multiplex: Unifying conventional and speculative thread-level parallelism on a chip multiprocessor, Proceedings of the 15th international conference on Supercomputing June 2001Google Scholar
- Non-Uniform Control Structures for C/C++ Explicit Parallelism, Joe Throop, Kuck & Associates, USA Poster Session at ISCOPE’98Google Scholar
- SPEC OMP Benchmark Suite, http://www.specbench.org/hpg/omp2001