loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
1999 IEEE International Conference on Computer Design (ICCD'99)
Pursuing the Performance Potential of Dynamic Cache Line Sizes
Austin, Texas
October 10-October 13
ISBN: 0-7695-0406-X
ASCII Text
x 
 
Peter van Vleet, Eric Anderson, Lindsay Brown, Jean-Loup Baer, Anna Karlin, "Pursuing the Performance Potential of Dynamic Cache Line Sizes," Computer Design, International Conference on, pp. 528, 1999 IEEE International Conference on Computer Design (ICCD'99), 1999.
 
 
BibTex
x
 
@article{ 10.1109/ICCD.1999.808592,
author = {Peter van Vleet and Eric Anderson and Lindsay Brown and Jean-Loup Baer and Anna Karlin},
title = {Pursuing the Performance Potential of Dynamic Cache Line Sizes},
journal ={Computer Design, International Conference on},
volume = {0},
year = {1999},
issn = {1063-6404},
pages = {528},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICCD.1999.808592},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Computer Design, International Conference on
TI - Pursuing the Performance Potential of Dynamic Cache Line Sizes
SN - 1063-6404
SP
EP
A1 - Peter van Vleet,
A1 - Eric Anderson,
A1 - Lindsay Brown,
A1 - Jean-Loup Baer,
A1 - Anna Karlin,
PY - 1999
KW - Cache Performance
KW - Line Size
KW - Optimal Algorithm
KW - Prediction
KW - Profiling
VL - 0
JA - Computer Design, International Conference on
ER -
 
Peter van Vleet, University of Washington
Eric Anderson, University of Washington
Lindsay Brown, University of Washington
Jean-Loup Baer, University of Washington
Anna Karlin, University of Washington
In this paper we examine the application of offline algorithms for determining the optimal sequence of loads and superloads (a load of multiple consecutive cache lines) for direct-mapped caches. We evaluate potential gains in terms of miss rate and bandwidth and find that in many cases optimal superloading can noticeably reduce the miss rate without appreciably increasing bandwidth. Then we examine how this performance potential might be realized. We examine the effectiveness of a dynamic online algorithm and of static analysis (profiling) for superloading and compare these to next-line prefetching. Experimental results show improvements comparable to those of the optimal algorithm in terms of miss rates.
Index Terms:
Cache Performance, Line Size, Optimal Algorithm, Prediction, Profiling
Citation:
Peter van Vleet, Eric Anderson, Lindsay Brown, Jean-Loup Baer, Anna Karlin, "Pursuing the Performance Potential of Dynamic Cache Line Sizes," iccd, pp.528, 1999 IEEE International Conference on Computer Design (ICCD'99), 1999
Usage of this product signifies your acceptance of the Terms of Use.