Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

A Primer on Hardware PrefetchingData Prefetching

A Primer on Hardware Prefetching: Data Prefetching [Data miss patterns arise from the inherent structure that algorithms and high-level programming constructs impose to organize and traverse data in memory. Whereas instruction miss patterns in conventional von Neumann computer systems tend to be quite simple, following either sequential patterns or repetitive control transfers in a well-structured control flow graph, data access patterns can be far more diverse, particularly in pointer-linked data structures that enable multiple traversals. Moreover, whereas code tends to be static and hence easy to prefetch (with the exception of recent virtualization and just-in-time compilation mechanisms, which tend to thwart instruction prefetching), data structures morph over the course of execution, causing traversal patterns to change. This greater complexity in access patterns has led to a rich and diverse design space for data prefetching schemes that is much broader than instruction prefetchers.] http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

A Primer on Hardware PrefetchingData Prefetching

Download PDF
22 pages

Loading next page...
 
/lp/springer-journals/a-primer-on-hardware-prefetching-data-prefetching-4y8VjWiW2j
Publisher
Springer International Publishing
Copyright
© Springer Nature Switzerland AG 2014
ISBN
978-3-031-00615-9
Pages
15 –37
DOI
10.1007/978-3-031-01743-8_3
Publisher site
See Chapter on Publisher Site

Abstract

[Data miss patterns arise from the inherent structure that algorithms and high-level programming constructs impose to organize and traverse data in memory. Whereas instruction miss patterns in conventional von Neumann computer systems tend to be quite simple, following either sequential patterns or repetitive control transfers in a well-structured control flow graph, data access patterns can be far more diverse, particularly in pointer-linked data structures that enable multiple traversals. Moreover, whereas code tends to be static and hence easy to prefetch (with the exception of recent virtualization and just-in-time compilation mechanisms, which tend to thwart instruction prefetching), data structures morph over the course of execution, causing traversal patterns to change. This greater complexity in access patterns has led to a rich and diverse design space for data prefetching schemes that is much broader than instruction prefetchers.]

Published: Jan 1, 2014

There are no references for this article.