Converting Data-Parallelism to Task-Parallelism by Rewrites: Purely Functional Programs Across Multiple GPUs
Indiana University
The 20th ACM SIGPLAN International Conference on Functional Programming (ICFP), 2015
@article{svensson2015converting,
title={Converting Data-Parallelism to Task-Parallelism by Rewrites},
author={Svensson, Bo Joel and Vollmer, Michael and Holk, Eric and McDonell, Trevor L and Newton, Ryan R},
year={2015}
}
High-level domain-specific languages for array processing on the GPU are increasingly common, but they typically only run on a single GPU. As computational power is distributed across more devices, languages must target multiple devices simultaneously. To this end, we present a compositional translation that fissions data-parallel programs in the Accelerate language, allowing subsequent compiler and runtime stages to map computations onto multiple devices for improved performance-even programs that begin as a single data-parallel kernel.
March 8, 2015 by hgpu
