A GPU-based implementation for the gamma multiset rewriting paradigm
Rubens H. P. de Almeida, Rui Rodrigues de Mello Junior, Gabriel Antoine Louis Paillard, Felipe M. G. França · 2016
This work presents a GPU-based implementation of the Gamma multiset rewriting paradigm. Inspired by the chemical reaction metaphor, Gamma was conceived as a highlevel abstract language for programs specification in a very simple, concise, and naturally parallel way, making clearer the distinction between the problem itself and the underlying implementation issues. We believe that the computational model adopted by Gamma matches naturally with the Graphics Processing Units execution mode, once both concepts consist basically in parallel processing of data. We extended an earlier distributed and parallel implementation of the Gamma language called Gamma-Base, adding support to execution of Gamma programs over the GPUs, and we called this new implementation Gamma-GPU. Practical experiments were conducted in a GPU cluster, which showed us the correctness of the new implementation, besides good speedups comparing to a sequential Gamma implementation, proving the contributions introduced by our work.