Stream Programming on General-Purpose Processors

Jayanth Gummaraju and Mendel Rosenblum

in Proceedings of the 38th annual international symposium on microarchitecture (MICRO-38), November 2005, Barcelona Spain

Abstract:

In this paper we investigate mapping stream programs (i.e. programs written in a streaming style for streaming architectures such as Imagine and Raw) onto a general-purpose CPU. We develop and explore a novel way of mapping these programs onto the CPU. We show how the salient features of stream programming such as computation kernels, local memories, and asynchronous bulk memory loads and stores can be easily mapped by a simple compilation system to CPU features such as the processor caches, simultaneous multi-threading, and fast inter-thread communication support, resulting in an executable that makes efficient use of the CPU resources. We present an evaluation of our mapping on a hyper-threaded Intel Pentium 4 CPU as a canonical example of a general-purpose processor. We compare the mapped stream program against the same program coded in a more conventional style for the general-purpose processor. We show the results using both micro-benchmarks and real scientific applications that programs written in a streaming style can run as fast or faster than equivalent programs written in traditional C code. Our results show that coding programs in a streaming style can improve performance on today's machines and smooth the way for significant performance improvements with the deployment of streaming architectures.

Paper:

Adobe Acrobat PDF

BibTeX:

@conference{ref:gummaraju_micro_05,
   author = {Jayanth Gummaraju and Mendel Rosenblum},
   title = {{Stream Programming on General-Purpose Processors}},
   booktitle = {MICRO 38: Proceedings of the 38th annual ACM/IEEE international symposium on Microarchitecture},    year = {2005},
   address = {Barcelona, Spain},
   month = {November}
}

(c) ACM, 2005. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in the Proceedings of MICRO-38, November, 2005, Barcelona, Spain.