ACM Home Page
Please provide us with feedback. Feedback
Access map pattern matching for data cache prefetch
Full text PdfPdf (407 KB)
Source
International Conference on Supercomputing archive
Proceedings of the 23rd international conference on Supercomputing table of contents
Yorktown Heights, NY, USA
POSTER SESSION: Posters table of contents
Pages 499-500  
Year of Publication: 2009
ISBN:978-1-60558-498-0
Authors
Yasuo Ishii  NEC Corporation, Tokyo, Japan
Mary Inaba  The University of Tokyo, Tokyo, Japan
Kei Hiraki  The University of Tokyo, Tokyo, Japan
Sponsors
ACM: Association for Computing Machinery
SIGARCH: ACM Special Interest Group on Computer Architecture
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 18,   Downloads (12 Months): 46,   Citation Count: 1
Additional Information:

abstract   references   cited by   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1542275.1542349
What is a DOI?

ABSTRACT

A novel data prefetching method -- access map pattern matching (AMPM) -- that uses "memory access map" is proposed. The AMPM prefetching concentrate hardware resources on collecting the access footprint of the frequently accessed area which we called "hot zones". 2-bit state is associated with each cache lines of hot zone. A set of these states is called "memory access map". Prefetch requests are generated from the pattern matching of the memory access map. The pattern matching detects multiple memory access patterns in parallel and generates more prefetch requests than conventional prefetchers. The evaluation result shows that the AMPM prefetcher improves performance by 42.0% in FP benchmarks.




Collaborative Colleagues:
Yasuo Ishii: colleagues
Mary Inaba: colleagues
Kei Hiraki: colleagues