Abstract

Multi-cores and multi-processors became ubiquitous during the last few years, and the trend is to increase the number of simple, power-efficient, and slower cores per chip. One of the results is that the performance of single-threaded applications did not significantly im- prove, or even declined, on new processors, which heightened the interest in compiler automatic paral- lelization techniques.

Our objective is to develop a framework in GCC to transform loops into pipelines of concurrent tasks using streams to communicate and synchronize. This trans- formation can either rely on user hints (pragmas) or on static analysis of control and data dependences. Our fo- cus is to fully automate this transformation, which re- quires an integration with the Graphite polyhedral loop optimization framework and will lead to the develop- ment of runtime optimizations based on this polyhedral representation. This approach is complementary with the existing parallelization passes. This paper presents the steamization technique, the optimizations it enables, the interaction with other optimizations, and the neces- sary extensions to Graphite/PCP (polyhedral compila- tion package) for its integration.