Automatic fusions of CUDA-GPU kernels for parallel map

Abstract

When implementing a function mapping on the contemporary GPU, several contradictory performance factors affecting distribution of computation into GPU kernels have to be balanced. A decomposition-fusion scheme suggests to decompose the computational problem to be solved by several simple functions implemented as standalone kernels and to fuse some of these functions later into more complex kernels to improve memory locality. In this paper, a prototype of source-to-source compiler automating the fusion phase is presented and the impact of fusions generated by the compiler as well as compiler efficiency is experimentally evaluated.