Predictor-directed stream buffers
- 1 December 2000
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM)
Abstract
An effective method for reducing the effect of load la- tency in modern processors is data prefetching. One form of data prefetching, stream buffers, has been shown to be par- ticularly effective due to its' ability to detect data streams and run ahead of them, prefetching as it goes. Unfortu- nately, in the past, the applicability of streaming was limited to stride intensive code. In this paper we propose Predictor-Directed Stream Buffers (PSB), a scheme in which the stream buffer follows an address prediction stream instead of a fixed stride. In addition, we examine using confidence techniques to guide the allocation and prioritization of stream buffers and their prefetch requests. Our results show for pointer-based appli- cations that PSB provides a 30% speedup on ave rage over no prefetching, and provides an ave rage 10% speedup over using previously proposed stride-based stream buffers for pointer-intensive applications.Keywords
This publication has 15 references indexed in Scilit:
- Push vs. pullPublished by Association for Computing Machinery (ACM) ,2000
- Recency-based TLB preloadingPublished by Association for Computing Machinery (ACM) ,2000
- Load execution latency reductionPublished by Association for Computing Machinery (ACM) ,1998
- Hardware-driven prefetching for pointer data referencesPublished by Association for Computing Machinery (ACM) ,1998
- Prefetching using Markov predictorsPublished by Association for Computing Machinery (ACM) ,1997
- Memory-system design considerations for dynamically-scheduled processorsPublished by Association for Computing Machinery (ACM) ,1997
- Speculative execution via address prediction and data prefetchingPublished by Association for Computing Machinery (ACM) ,1997
- Effective hardware-based data prefetching for high-performance processorsIEEE Transactions on Computers, 1995
- A load-instruction unit for pipelined processorsIBM Journal of Research and Development, 1993
- Improving direct-mapped cache performance by the addition of a small fully-associative cache and prefetch buffersPublished by Association for Computing Machinery (ACM) ,1990