Helix: Making the extraction of thread-level parallelism mainstream

Simone Campanoni; Timothy M. Jones; Glenn Holloway; Gu Yeon Wei; David Brooks

doi:10.1109/MM.2012.50

Helix: Making the extraction of thread-level parallelism mainstream

Simone Campanoni^*, Timothy M. Jones, Glenn Holloway, Gu Yeon Wei, David Brooks

^*Corresponding author for this work

Computer Science

Research output: Contribution to journal › Article › peer-review

14 Scopus citations

Abstract

Improving system performance increasingly depends on exploiting microprocessor parallelism, yet mainstream compilers still don't parallelize code automatically. Helix automatically parallelizes general-purpose programs without requiring any special hardware; avoids slowing down compiled programs, making it a suitable candidate for mainstream compilers; and outperforms the most similar historical technique that has been implemented in production compilers.

Original language	English (US)
Article number	6226338
Pages (from-to)	8-18
Number of pages	11
Journal	IEEE Micro
Volume	32
Issue number	4
DOIs	https://doi.org/10.1109/MM.2012.50
State	Published - Sep 10 2012

Keywords

DOACROSS parallelism
extraction of coarse-grained parallelism
robustness of code optimization

ASJC Scopus subject areas

Software
Hardware and Architecture
Electrical and Electronic Engineering

Access to Document

10.1109/MM.2012.50

Fingerprint Dive into the research topics of 'Helix: Making the extraction of thread-level parallelism mainstream'. Together they form a unique fingerprint.

Cite this

@article{682e14e2523f4899b9af96c69e47f2a0,

title = "Helix: Making the extraction of thread-level parallelism mainstream",

abstract = "Improving system performance increasingly depends on exploiting microprocessor parallelism, yet mainstream compilers still don't parallelize code automatically. Helix automatically parallelizes general-purpose programs without requiring any special hardware; avoids slowing down compiled programs, making it a suitable candidate for mainstream compilers; and outperforms the most similar historical technique that has been implemented in production compilers.",

keywords = "DOACROSS parallelism, extraction of coarse-grained parallelism, robustness of code optimization",

author = "Simone Campanoni and Jones, {Timothy M.} and Glenn Holloway and Wei, {Gu Yeon} and David Brooks",

year = "2012",

month = sep,

day = "10",

doi = "10.1109/MM.2012.50",

language = "English (US)",

volume = "32",

pages = "8--18",

journal = "IEEE Micro",

issn = "0272-1732",

publisher = "IEEE Computer Society",

number = "4",

}

TY - JOUR

T1 - Helix

T2 - Making the extraction of thread-level parallelism mainstream

AU - Campanoni, Simone

AU - Jones, Timothy M.

AU - Holloway, Glenn

AU - Wei, Gu Yeon

AU - Brooks, David

PY - 2012/9/10

Y1 - 2012/9/10

N2 - Improving system performance increasingly depends on exploiting microprocessor parallelism, yet mainstream compilers still don't parallelize code automatically. Helix automatically parallelizes general-purpose programs without requiring any special hardware; avoids slowing down compiled programs, making it a suitable candidate for mainstream compilers; and outperforms the most similar historical technique that has been implemented in production compilers.

AB - Improving system performance increasingly depends on exploiting microprocessor parallelism, yet mainstream compilers still don't parallelize code automatically. Helix automatically parallelizes general-purpose programs without requiring any special hardware; avoids slowing down compiled programs, making it a suitable candidate for mainstream compilers; and outperforms the most similar historical technique that has been implemented in production compilers.

KW - DOACROSS parallelism

KW - extraction of coarse-grained parallelism

KW - robustness of code optimization

UR - http://www.scopus.com/inward/record.url?scp=84865762484&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865762484&partnerID=8YFLogxK

U2 - 10.1109/MM.2012.50

DO - 10.1109/MM.2012.50

M3 - Article

AN - SCOPUS:84865762484

VL - 32

SP - 8

EP - 18

JO - IEEE Micro

JF - IEEE Micro

SN - 0272-1732

IS - 4

M1 - 6226338

ER -

Helix: Making the extraction of thread-level parallelism mainstream

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this