Address trace compression through loop detection and reduction

E. N. Elnozahy

doi:10.1145/301464.301577

Address trace compression through loop detection and reduction

E. N. Elnozahy^*

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

18 Scopus citations

Abstract

This paper introduces a new technique for compressing memory address traces. The technique relies on the simple observation that most programs spend their time executing loops, and therefore the trace will follow the structures of such loops. We adapt classic control flow analysis to detect the loops within an address trace, then analyze them to identify constant and loop-varying memory references. These references are efficiently encoded to reduce the size of the trace, often resulting in an order of magnitude reduction in size compared to the most compact trace format known to date.

Original language	English (US)
Pages (from-to)	214-215
Number of pages	2
Journal	Performance Evaluation Review
Volume	27
Issue number	1
DOIs	https://doi.org/10.1145/301464.301577
State	Published - Jun 1999
Externally published	Yes
Event	Proceedings of the 1999 International Conference on Measurement and Modeling of Computer Systems, ACM SIGMETRICS '99 - Atlata, GA, USA Duration: May 1 1999 → May 4 1999

ASJC Scopus subject areas

Software
Hardware and Architecture
Computer Networks and Communications

Access to Document

10.1145/301464.301577

Cite this

@article{79bc98fdfcde4ddfbf5df48a146a3ae3,

title = "Address trace compression through loop detection and reduction",

abstract = "This paper introduces a new technique for compressing memory address traces. The technique relies on the simple observation that most programs spend their time executing loops, and therefore the trace will follow the structures of such loops. We adapt classic control flow analysis to detect the loops within an address trace, then analyze them to identify constant and loop-varying memory references. These references are efficiently encoded to reduce the size of the trace, often resulting in an order of magnitude reduction in size compared to the most compact trace format known to date.",

author = "Elnozahy, {E. N.}",

year = "1999",

month = jun,

doi = "10.1145/301464.301577",

language = "English (US)",

volume = "27",

pages = "214--215",

journal = "Performance Evaluation Review",

issn = "0163-5999",

publisher = "Association for Computing Machinery (ACM)",

number = "1",

note = "Proceedings of the 1999 International Conference on Measurement and Modeling of Computer Systems, ACM SIGMETRICS '99 ; Conference date: 01-05-1999 Through 04-05-1999",

}

TY - JOUR

T1 - Address trace compression through loop detection and reduction

AU - Elnozahy, E. N.

PY - 1999/6

Y1 - 1999/6

N2 - This paper introduces a new technique for compressing memory address traces. The technique relies on the simple observation that most programs spend their time executing loops, and therefore the trace will follow the structures of such loops. We adapt classic control flow analysis to detect the loops within an address trace, then analyze them to identify constant and loop-varying memory references. These references are efficiently encoded to reduce the size of the trace, often resulting in an order of magnitude reduction in size compared to the most compact trace format known to date.

AB - This paper introduces a new technique for compressing memory address traces. The technique relies on the simple observation that most programs spend their time executing loops, and therefore the trace will follow the structures of such loops. We adapt classic control flow analysis to detect the loops within an address trace, then analyze them to identify constant and loop-varying memory references. These references are efficiently encoded to reduce the size of the trace, often resulting in an order of magnitude reduction in size compared to the most compact trace format known to date.

UR - http://www.scopus.com/inward/record.url?scp=0032649499&partnerID=8YFLogxK

U2 - 10.1145/301464.301577

DO - 10.1145/301464.301577

M3 - Conference article

AN - SCOPUS:0032649499

SN - 0163-5999

VL - 27

SP - 214

EP - 215

JO - Performance Evaluation Review

JF - Performance Evaluation Review

IS - 1

T2 - Proceedings of the 1999 International Conference on Measurement and Modeling of Computer Systems, ACM SIGMETRICS '99

Y2 - 1 May 1999 through 4 May 1999

ER -

Address trace compression through loop detection and reduction

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this