Maximizing multiprocessor performance with the SUIF compiler
- 1 December 1996
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Computer
- Vol. 29 (12), 84-89
- https://doi.org/10.1109/2.546613
Abstract
This article describes automatic parallelization techniques in the SUIF (Stanford University Intermediate Format) compiler that result in good multiprocessor performance for array-based numerical programs. Parallelizing compilers for multiprocessors face many hurdles. However, SUIF's robust analysis and memory optimization techniques enabled speedups on three fourths of the NAS and SPECfp95 benchmark programs.Keywords
This publication has 7 references indexed in Scilit:
- Compiler-directed page coloring for multiprocessorsPublished by Association for Computing Machinery (ACM) ,1996
- Symbolic analysis for parallelizing compilersACM Transactions on Programming Languages and Systems, 1996
- The Paradigm compiler for distributed-memory multicomputersComputer, 1995
- Automatic data layout for high performance FortranPublished by Association for Computing Machinery (ACM) ,1995
- Global optimizations for parallelism and locality on scalable parallel machinesPublished by Association for Computing Machinery (ACM) ,1993
- The ParaScope parallel programming environmentProceedings of the IEEE, 1993
- Semantical interprocedural parallelizationPublished by Association for Computing Machinery (ACM) ,1991