SCL-Chan: An Asynchronous Data-Parallel Language for Irregular Algorithms

Parallelism suffers from a lack of programming languages both simple to handle and able to take advantage of present parallel computer power. If parallelism expression is too high level, compilers have to perform complex optimizations leading often to poor performances. One the other hand, too low level parallelism transfers difficulties toward the programmer. In this paper, we propose a new programming language that integrates both a synchronous data-parallel programming model and an asynchronous execution model. The synchronous data-parallel programming model allows a single and safe program designing. The asynchronous execution model yields an efficient execution on present MIMD architectures without any program transformation. Our language relies on a logical instruction ordering exploited by specific send/receive communications. It allows to express only the effective data dependences between processors. This ability is enforced by a possible send/receive unmatching useful for irr..