A Taxonomy of Data Prefetching Mechanisms
Authors:
- Surendra BynaSBSurendra Byna
- Yong ChenYCYong Chen
- Xian-He SunXSXian-He Sun
- 1 May 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 12 (10874089) , 19-24
Abstract
Data prefetching has been considered an effective way to mask data access latency caused by cache misses and to bridge the performance gap between processor and memory. With hardware and/or software support, data prefetching brings data closer to a processor before it is actually needed. Many prefetching techniques have been proposed in the last few years to reduce data access latency by taking advantage of multi-core architectures. In this paper, we propose a taxonomy that classifies various design concerns in developing a prefetching strategy. We discuss various prefetching strategies and issues that have to be considered in designing a prefetching strategy for multi-core processors.Keywords
This publication has 22 references indexed in Scilit:
- Server-Based Data Push Architecture for Multi-Processor EnvironmentsJournal of Computer Science and Technology, 2007
- Tolerating memory latency through push prefetching for pointer-intensive applicationsACM Transactions on Architecture and Code Optimization, 2004
- Data forwarding through in-memory precomputation threads2004
- Data prefetching by dependence graph precomputation2001
- Tolerating memory latency through software-controlled pre-execution in simultaneous multithreading processors2001
- Data prefetch mechanismsACM Computing Surveys, 2000
- Branch-directed and pointer-based data cache prefetchingJournal of Systems Architecture, 1999
- Compiler-based prefetching for recursive data structures1996
- Effective hardware-based data prefetching for high-performance processorsIEEE Transactions on Computers, 1995
- Tolerating latency through software-controlled prefetching in shared-memory multiprocessorsJournal of Parallel and Distributed Computing, 1991