Thread scheduling for cache locality

J. Philbin; J. Edler; O. J. Anshus; C. C. Douglas; K. Li

doi:10.1145/237090.237151

Thread scheduling for cache locality

J. Philbin, J. Edler, O. J. Anshus, C. C. Douglas, K. Li

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

16 Scopus citations

Abstract

This paper describes a method to improve the cache locality of sequential programs by scheduling fine-grained threads. The algorithm relies upon hints provided at the time of thread creation to determine a thread execution order likely to reduce cache misses. This technique may be particularly valuable when compiler-directed tiling is not feasible. Experiments with several application programs, on two systems with different cache structures, show that our thread scheduling method can improve program performance by reducing second-level cache misses.

Original language	English (US)
Pages (from-to)	60-71
Number of pages	12
Journal	Computer architecture news
Volume	24
Issue number	Special Issu
DOIs	https://doi.org/10.1145/237090.237151
State	Published - 1996
Externally published	Yes
Event	Proceedings of the 1996 7th International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS-VII - Cambridge, MA, USA Duration: Oct 1 1996 → Oct 5 1996

All Science Journal Classification (ASJC) codes

General Engineering

Access to Document

10.1145/237090.237151

Cite this

@article{4039a6553c2c4f2b8def324f8519d3b8,

title = "Thread scheduling for cache locality",

abstract = "This paper describes a method to improve the cache locality of sequential programs by scheduling fine-grained threads. The algorithm relies upon hints provided at the time of thread creation to determine a thread execution order likely to reduce cache misses. This technique may be particularly valuable when compiler-directed tiling is not feasible. Experiments with several application programs, on two systems with different cache structures, show that our thread scheduling method can improve program performance by reducing second-level cache misses.",

author = "J. Philbin and J. Edler and Anshus, {O. J.} and Douglas, {C. C.} and K. Li",

year = "1996",

doi = "10.1145/237090.237151",

language = "English (US)",

volume = "24",

pages = "60--71",

journal = "Computer architecture news",

issn = "0163-5964",

number = "Special Issu",

note = "Proceedings of the 1996 7th International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS-VII ; Conference date: 01-10-1996 Through 05-10-1996",

}

TY - JOUR

T1 - Thread scheduling for cache locality

AU - Philbin, J.

AU - Edler, J.

AU - Anshus, O. J.

AU - Douglas, C. C.

AU - Li, K.

PY - 1996

Y1 - 1996

N2 - This paper describes a method to improve the cache locality of sequential programs by scheduling fine-grained threads. The algorithm relies upon hints provided at the time of thread creation to determine a thread execution order likely to reduce cache misses. This technique may be particularly valuable when compiler-directed tiling is not feasible. Experiments with several application programs, on two systems with different cache structures, show that our thread scheduling method can improve program performance by reducing second-level cache misses.

AB - This paper describes a method to improve the cache locality of sequential programs by scheduling fine-grained threads. The algorithm relies upon hints provided at the time of thread creation to determine a thread execution order likely to reduce cache misses. This technique may be particularly valuable when compiler-directed tiling is not feasible. Experiments with several application programs, on two systems with different cache structures, show that our thread scheduling method can improve program performance by reducing second-level cache misses.

UR - http://www.scopus.com/inward/record.url?scp=0030259746&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030259746&partnerID=8YFLogxK

U2 - 10.1145/237090.237151

DO - 10.1145/237090.237151

M3 - Conference article

AN - SCOPUS:0030259746

SN - 0163-5964

VL - 24

SP - 60

EP - 71

JO - Computer architecture news

JF - Computer architecture news

IS - Special Issu

T2 - Proceedings of the 1996 7th International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS-VII

Y2 - 1 October 1996 through 5 October 1996

ER -

Thread scheduling for cache locality

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this