Ghent University Academic Bibliography

Advanced

A performance counter architecture for computing accurate CPI components

Stijn Eyerman, Lieven Eeckhout UGent, Tejas Karkhanis and James E Smith (2006) ACM SIGPLAN NOTICES. 41(11). p.175-184
abstract
A common way of representing processor performance is to use Cycles per Instruction (CPI) `stacks' which break performance into a baseline CPI plus a number of individual miss event CPI components. CPI stacks can be very helpful in gaining insight into the behavior of an application on a given microprocessor; consequently, they are widely used by software application developers and computer architects. However, computing CPI stacks on superscalar out-of-order processors is challenging because of various overlaps among execution and miss events ( cache misses, TLB misses, and branch mispredictions). This paper shows that meaningful and accurate CPI stacks can be computed for superscalar out-of-order processors. Using interval analysis, a novel method for analyzing out-of-order processor performance, we gain understanding into the performance impact of the various miss events. Based on this understanding, we propose a novel way of architecting hardware performance counters for building accurate CPI stacks. The additional hardware for implementing these counters is limited and comparable to existing hardware performance counter architectures while being significantly more accurate than previous approaches.
Please use this url to cite or link to this publication:
author
organization
year
type
journalArticle (original)
publication status
published
subject
keyword
super-scalar processor performance modeling, hardware performance counter architecture
journal title
ACM SIGPLAN NOTICES
ACM Sigplan Not.
volume
41
issue
11
pages
175 - 184
Web of Science type
Article
Web of Science id
000202972600017
JCR category
COMPUTER SCIENCE, SOFTWARE ENGINEERING
JCR impact factor
0.129 (2006)
JCR rank
80/82 (2006)
JCR quartile
4 (2006)
ISSN
0362-1340
DOI
10.1145/1168918.1168880
language
English
UGent publication?
yes
classification
A1
copyright statement
I have transferred the copyright for this publication to the publisher
id
1579395
handle
http://hdl.handle.net/1854/LU-1579395
date created
2011-06-27 13:21:20
date last changed
2016-12-19 15:44:35
@article{1579395,
  abstract     = {A common way of representing processor performance is to use Cycles per Instruction (CPI) `stacks' which break performance into a baseline CPI plus a number of individual miss event CPI components. CPI stacks can be very helpful in gaining insight into the behavior of an application on a given microprocessor; consequently, they are widely used by software application developers and computer architects. However, computing CPI stacks on superscalar out-of-order processors is challenging because of various overlaps among execution and miss events ( cache misses, TLB misses, and branch mispredictions). This paper shows that meaningful and accurate CPI stacks can be computed for superscalar out-of-order processors. Using interval analysis, a novel method for analyzing out-of-order processor performance, we gain understanding into the performance impact of the various miss events. Based on this understanding, we propose a novel way of architecting hardware performance counters for building accurate CPI stacks. The additional hardware for implementing these counters is limited and comparable to existing hardware performance counter architectures while being significantly more accurate than previous approaches.},
  author       = {Eyerman, Stijn and Eeckhout, Lieven and Karkhanis, Tejas and Smith, James E},
  issn         = {0362-1340},
  journal      = {ACM SIGPLAN NOTICES},
  keyword      = {super-scalar processor performance modeling,hardware performance counter architecture},
  language     = {eng},
  number       = {11},
  pages        = {175--184},
  title        = {A performance counter architecture for computing accurate CPI components},
  url          = {http://dx.doi.org/10.1145/1168918.1168880},
  volume       = {41},
  year         = {2006},
}

Chicago
Eyerman, Stijn, Lieven Eeckhout, Tejas Karkhanis, and James E Smith. 2006. “A Performance Counter Architecture for Computing Accurate CPI Components.” Acm Sigplan Notices 41 (11): 175–184.
APA
Eyerman, S., Eeckhout, L., Karkhanis, T., & Smith, J. E. (2006). A performance counter architecture for computing accurate CPI components. ACM SIGPLAN NOTICES, 41(11), 175–184.
Vancouver
1.
Eyerman S, Eeckhout L, Karkhanis T, Smith JE. A performance counter architecture for computing accurate CPI components. ACM SIGPLAN NOTICES. 2006;41(11):175–84.
MLA
Eyerman, Stijn, Lieven Eeckhout, Tejas Karkhanis, et al. “A Performance Counter Architecture for Computing Accurate CPI Components.” ACM SIGPLAN NOTICES 41.11 (2006): 175–184. Print.