Cache topology aware computation mapping for multicores

Mahmut Kandemir, Taylan Yemliha, Sai Prashanth Muralidhara, S. Srikantaiah, Mary Jane Irwin, Yuanrui Zhang

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

The main contribution of this paper is a compiler based, cache topology aware code optimization scheme for emerging multicore systems. This scheme distributes the iterations of a loop to be executed in parallel across the cores of a target multicore machine and schedules the iterations assigned to each core. Our goal is to improve the utilization of the on-chip multi-layer cache hierarchy and to maximize overall application performance. We evaluate our cache topology aware approach using a set of twelve applications and three different commercial multicore machines. In addition, to study some of our experimental parameters in detail and to explore future multicore machines (with higher core counts and deeper on-chip cache hierarchies), we also conduct a simulation based study. The results collected from our experiments with three Intel multicore machines show that the proposed compiler-based approach is very effective in enhancing performance. In addition, our simulation results indicate that optimizing for the on-chip cache hierarchy will be even more important in future multicores with increasing numbers of cores and cache levels.

Original languageEnglish (US)
Pages (from-to)74-85
Number of pages12
JournalACM SIGPLAN Notices
Volume45
Issue number6
DOIs
StatePublished - Jun 1 2010

Fingerprint

Topology
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Kandemir, M., Yemliha, T., Muralidhara, S. P., Srikantaiah, S., Irwin, M. J., & Zhang, Y. (2010). Cache topology aware computation mapping for multicores. ACM SIGPLAN Notices, 45(6), 74-85. https://doi.org/10.1145/1809028.1806605
Kandemir, Mahmut ; Yemliha, Taylan ; Muralidhara, Sai Prashanth ; Srikantaiah, S. ; Irwin, Mary Jane ; Zhang, Yuanrui. / Cache topology aware computation mapping for multicores. In: ACM SIGPLAN Notices. 2010 ; Vol. 45, No. 6. pp. 74-85.
@article{6118498bc2d944a5a675d02a6e6ca43a,
title = "Cache topology aware computation mapping for multicores",
abstract = "The main contribution of this paper is a compiler based, cache topology aware code optimization scheme for emerging multicore systems. This scheme distributes the iterations of a loop to be executed in parallel across the cores of a target multicore machine and schedules the iterations assigned to each core. Our goal is to improve the utilization of the on-chip multi-layer cache hierarchy and to maximize overall application performance. We evaluate our cache topology aware approach using a set of twelve applications and three different commercial multicore machines. In addition, to study some of our experimental parameters in detail and to explore future multicore machines (with higher core counts and deeper on-chip cache hierarchies), we also conduct a simulation based study. The results collected from our experiments with three Intel multicore machines show that the proposed compiler-based approach is very effective in enhancing performance. In addition, our simulation results indicate that optimizing for the on-chip cache hierarchy will be even more important in future multicores with increasing numbers of cores and cache levels.",
author = "Mahmut Kandemir and Taylan Yemliha and Muralidhara, {Sai Prashanth} and S. Srikantaiah and Irwin, {Mary Jane} and Yuanrui Zhang",
year = "2010",
month = "6",
day = "1",
doi = "10.1145/1809028.1806605",
language = "English (US)",
volume = "45",
pages = "74--85",
journal = "ACM SIGPLAN Notices",
issn = "1523-2867",
publisher = "Association for Computing Machinery (ACM)",
number = "6",

}

Kandemir, M, Yemliha, T, Muralidhara, SP, Srikantaiah, S, Irwin, MJ & Zhang, Y 2010, 'Cache topology aware computation mapping for multicores', ACM SIGPLAN Notices, vol. 45, no. 6, pp. 74-85. https://doi.org/10.1145/1809028.1806605

Cache topology aware computation mapping for multicores. / Kandemir, Mahmut; Yemliha, Taylan; Muralidhara, Sai Prashanth; Srikantaiah, S.; Irwin, Mary Jane; Zhang, Yuanrui.

In: ACM SIGPLAN Notices, Vol. 45, No. 6, 01.06.2010, p. 74-85.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Cache topology aware computation mapping for multicores

AU - Kandemir, Mahmut

AU - Yemliha, Taylan

AU - Muralidhara, Sai Prashanth

AU - Srikantaiah, S.

AU - Irwin, Mary Jane

AU - Zhang, Yuanrui

PY - 2010/6/1

Y1 - 2010/6/1

N2 - The main contribution of this paper is a compiler based, cache topology aware code optimization scheme for emerging multicore systems. This scheme distributes the iterations of a loop to be executed in parallel across the cores of a target multicore machine and schedules the iterations assigned to each core. Our goal is to improve the utilization of the on-chip multi-layer cache hierarchy and to maximize overall application performance. We evaluate our cache topology aware approach using a set of twelve applications and three different commercial multicore machines. In addition, to study some of our experimental parameters in detail and to explore future multicore machines (with higher core counts and deeper on-chip cache hierarchies), we also conduct a simulation based study. The results collected from our experiments with three Intel multicore machines show that the proposed compiler-based approach is very effective in enhancing performance. In addition, our simulation results indicate that optimizing for the on-chip cache hierarchy will be even more important in future multicores with increasing numbers of cores and cache levels.

AB - The main contribution of this paper is a compiler based, cache topology aware code optimization scheme for emerging multicore systems. This scheme distributes the iterations of a loop to be executed in parallel across the cores of a target multicore machine and schedules the iterations assigned to each core. Our goal is to improve the utilization of the on-chip multi-layer cache hierarchy and to maximize overall application performance. We evaluate our cache topology aware approach using a set of twelve applications and three different commercial multicore machines. In addition, to study some of our experimental parameters in detail and to explore future multicore machines (with higher core counts and deeper on-chip cache hierarchies), we also conduct a simulation based study. The results collected from our experiments with three Intel multicore machines show that the proposed compiler-based approach is very effective in enhancing performance. In addition, our simulation results indicate that optimizing for the on-chip cache hierarchy will be even more important in future multicores with increasing numbers of cores and cache levels.

UR - http://www.scopus.com/inward/record.url?scp=77957584378&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957584378&partnerID=8YFLogxK

U2 - 10.1145/1809028.1806605

DO - 10.1145/1809028.1806605

M3 - Article

AN - SCOPUS:77957584378

VL - 45

SP - 74

EP - 85

JO - ACM SIGPLAN Notices

JF - ACM SIGPLAN Notices

SN - 1523-2867

IS - 6

ER -

Kandemir M, Yemliha T, Muralidhara SP, Srikantaiah S, Irwin MJ, Zhang Y. Cache topology aware computation mapping for multicores. ACM SIGPLAN Notices. 2010 Jun 1;45(6):74-85. https://doi.org/10.1145/1809028.1806605