Lowering IrGL to CUDA
The University of Texas at Austin
arXiv:1607.05707 [cs.PL], (19 Jul 2016)
@article{pai2016lowering,
title={Lowering IrGL to CUDA},
author={Pai, Sreepathi and Pingali, Keshav},
year={2016},
month={jul},
archivePrefix={"arXiv"},
primaryClass={cs.PL}
}
The IrGL intermediate representation is an explicitly parallel representation for irregular programs that targets GPUs. In this report, we describe IrGL constructs, examples of their use and how IrGL is compiled to CUDA by the Galois GPU compiler.
July 20, 2016 by hgpu
