Scaling Algebraic Multigrid Solvers: On the Road to Exascale

Allison Baker; Robert D. Falgout; Todd Gamblin; Tzanio V. Kolev; Martin Schulz; Ulrike Meier Yang

Scaling Algebraic Multigrid Solvers: On the Road to Exascale

Allison Baker, Robert D. Falgout, Todd Gamblin, Tzanio V. Kolev, Martin Schulz, Ulrike Meier Yang

Application Scalability and Performance Group

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

Algebraic Multigrid (AMG) solvers are an essential component of many large-scale scientific simulation codes. Their continued numerical scalability and efficient implementation is critical for preparing these codes for exascale. Our experiences on modern multi-core machines show that significant challenges must be addressed for AMG to perform well on such machines. We discuss our experiences and describe the techniques we have used to overcome scalability challenges for AMG on hybrid architectures in preparation for exascale.

Original language	American English
Title of host publication	Competence in High Performance Computing 2010
Pages	215-226
ISBN (Electronic)	978-3-642-24025-6
State	Published - Dec 8 2011

Cite this

@inbook{05256bfc8f924a238adc1108b32f6b88,

title = "Scaling Algebraic Multigrid Solvers: On the Road to Exascale",

abstract = "Algebraic Multigrid (AMG) solvers are an essential component of many large-scale scientific simulation codes. Their continued numerical scalability and efficient implementation is critical for preparing these codes for exascale. Our experiences on modern multi-core machines show that significant challenges must be addressed for AMG to perform well on such machines. We discuss our experiences and describe the techniques we have used to overcome scalability challenges for AMG on hybrid architectures in preparation for exascale.",

author = "Allison Baker and Falgout, \{Robert D.\} and Todd Gamblin and Kolev, \{Tzanio V.\} and Martin Schulz and Yang, \{Ulrike Meier\}",

year = "2011",

month = dec,

day = "8",

language = "American English",

isbn = "978-3-642-24024-9",

pages = "215--226",

booktitle = "Competence in High Performance Computing 2010",

}

TY - CHAP

T1 - Scaling Algebraic Multigrid Solvers: On the Road to Exascale

AU - Baker, Allison

AU - Falgout, Robert D.

AU - Gamblin, Todd

AU - Kolev, Tzanio V.

AU - Schulz, Martin

AU - Yang, Ulrike Meier

PY - 2011/12/8

Y1 - 2011/12/8

N2 - Algebraic Multigrid (AMG) solvers are an essential component of many large-scale scientific simulation codes. Their continued numerical scalability and efficient implementation is critical for preparing these codes for exascale. Our experiences on modern multi-core machines show that significant challenges must be addressed for AMG to perform well on such machines. We discuss our experiences and describe the techniques we have used to overcome scalability challenges for AMG on hybrid architectures in preparation for exascale.

AB - Algebraic Multigrid (AMG) solvers are an essential component of many large-scale scientific simulation codes. Their continued numerical scalability and efficient implementation is critical for preparing these codes for exascale. Our experiences on modern multi-core machines show that significant challenges must be addressed for AMG to perform well on such machines. We discuss our experiences and describe the techniques we have used to overcome scalability challenges for AMG on hybrid architectures in preparation for exascale.

M3 - Chapter

SN - 978-3-642-24024-9

SP - 215

EP - 226

BT - Competence in High Performance Computing 2010

ER -

Scaling Algebraic Multigrid Solvers: On the Road to Exascale

Abstract

Fingerprint

Cite this