A GPGPU compiler for memory optimization and parallelism management
Dept. of ECE, North Carolina State University
In PLDI ’10: Proceedings of the 2010 ACM SIGPLAN conference on Programming language design and implementation (2010), pp. 86-97.
@conference{yang2010gpgpu,
title={A GPGPU compiler for memory optimization and parallelism management},
author={Yang, Y. and Xiang, P. and Kong, J. and Zhou, H.},
booktitle={Proceedings of the 2010 ACM SIGPLAN conference on Programming language design and implementation},
pages={86–97},
year={2010},
organization={ACM}
}
This paper presents a novel optimizing compiler for general purpose computation on graphics processing units (GPGPU). It addresses two major challenges of developing high performance GPGPU programs: effective utilization of GPU memory hierarchy and judicious management of parallelism.
November 18, 2010 by hgpu
