Stream Register Files with Indexed Access

Nuwan Jayasena, Mattan Erez, and Jung Ho Ahn, and William J. Dally

in Proceedings of the Tenth International Symposium on High Performance Computer Architecture (HPCA-X), February 2004, Madrid, Spain

Abstract:

Many current programmable architectures designed to exploit data parallelism require computation to be structured to operate on sequentially accessed vectors or streams of data. Applications with less regular data access patterns perform sub-optimally on such architectures. This paper presents a register file for streams (SRF) that allows arbitrary, indexed accesses. Compared to sequential SRF access, indexed access captures more temporal locality, reduces data replication in the SRF, and provides efficient support for certain types of complex access patterns. Our simulations show that indexed SRF access provides speedups of 1.03x to 4.1x and memory bandwidth reductions of up to 95% over sequential SRF access for a set of benchmarks representative of data-parallel applications with irregular accesses. Indexed SRF access also provides greater speedups than caches for a number of application classes despite significantly lower hardware costs. The area overhead of our indexed SRF implementation is 11%-22% over a sequentially accessed SRF, which corresponds to a modest 1.5%-3% increase in the total die area of a typical stream processor.

Paper:

Adobe Acrobat PDF

BibTeX:

@InProceedings{ ref:ISRF_hpca04,    author = {Nuwan Jayasena and Mattan Erez and Jung Ho Ahn and William J. Dally},
   title = {Stream Register Files with Indexed Access},
   booktitle = {Proceedings of the Tenth International Symposium on High Performance Computer Architecture},
   year = {2004},
   month = {February},
   address = {Madrid, Spain}
}