Cohesion: An adaptive hybrid memory model for accelerators

John H. Kelm; Daniel R. Johnson; William Tuohy; Steven S. Lumetta; Sanjay J. Patel

doi:10.1109/MM.2011.8

Cohesion: An adaptive hybrid memory model for accelerators

John H. Kelm, Daniel R. Johnson, William Tuohy, Steven S. Lumetta, Sanjay J. Patel

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

Abstract

Cohesion is a hybrid memory model that enables fine-grained temporal data reassignment between hardware-and software-managed coherence domains, allowing systems to support both. Cohesion can dynamically adapt to the sharing needs of both applications and runtimes requiring neither copy operations nor multiple address spaces.

Original language	English (US)
Article number	5713322
Pages (from-to)	42-55
Number of pages	14
Journal	IEEE Micro
Volume	31
Issue number	1
DOIs	https://doi.org/10.1109/MM.2011.8
State	Published - Jan 2011

Keywords

Accelerator
cache coherence
computer architecture

ASJC Scopus subject areas

Software
Hardware and Architecture
Electrical and Electronic Engineering

Online availability

10.1109/MM.2011.8

Library availability

Discover UIUC Full Text

Cite this

@article{aa5e0c0dd45840738a3df8e703f334be,

title = "Cohesion: An adaptive hybrid memory model for accelerators",

abstract = "Cohesion is a hybrid memory model that enables fine-grained temporal data reassignment between hardware-and software-managed coherence domains, allowing systems to support both. Cohesion can dynamically adapt to the sharing needs of both applications and runtimes requiring neither copy operations nor multiple address spaces.",

keywords = "Accelerator, cache coherence, computer architecture",

author = "Kelm, {John H.} and Johnson, {Daniel R.} and William Tuohy and Lumetta, {Steven S.} and Patel, {Sanjay J.}",

note = "Funding Information: This work was supported in part by the Intel/Microsoft Universal Parallel Computing Research Center at the University of Illinois at Urbana-Champaign. We thank the Trusted Illiac Center at the Information Trust Institute for the use of their computing cluster.",

year = "2011",

month = jan,

doi = "10.1109/MM.2011.8",

language = "English (US)",

volume = "31",

pages = "42--55",

journal = "IEEE Micro",

issn = "0272-1732",

publisher = "IEEE Computer Society",

number = "1",

}

TY - JOUR

T1 - Cohesion

T2 - An adaptive hybrid memory model for accelerators

AU - Kelm, John H.

AU - Johnson, Daniel R.

AU - Tuohy, William

AU - Lumetta, Steven S.

AU - Patel, Sanjay J.

N1 - Funding Information: This work was supported in part by the Intel/Microsoft Universal Parallel Computing Research Center at the University of Illinois at Urbana-Champaign. We thank the Trusted Illiac Center at the Information Trust Institute for the use of their computing cluster.

PY - 2011/1

Y1 - 2011/1

N2 - Cohesion is a hybrid memory model that enables fine-grained temporal data reassignment between hardware-and software-managed coherence domains, allowing systems to support both. Cohesion can dynamically adapt to the sharing needs of both applications and runtimes requiring neither copy operations nor multiple address spaces.

AB - Cohesion is a hybrid memory model that enables fine-grained temporal data reassignment between hardware-and software-managed coherence domains, allowing systems to support both. Cohesion can dynamically adapt to the sharing needs of both applications and runtimes requiring neither copy operations nor multiple address spaces.

KW - Accelerator

KW - cache coherence

KW - computer architecture

UR - http://www.scopus.com/inward/record.url?scp=79951831804&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951831804&partnerID=8YFLogxK

U2 - 10.1109/MM.2011.8

DO - 10.1109/MM.2011.8

M3 - Article

AN - SCOPUS:79951831804

SN - 0272-1732

VL - 31

SP - 42

EP - 55

JO - IEEE Micro

JF - IEEE Micro

IS - 1

M1 - 5713322

ER -

Cohesion: An adaptive hybrid memory model for accelerators

Abstract

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this