Anatomy of a globally recursive embedded LINPACK benchmark

Jack Dongarra; Piotr Luszczek

doi:10.1109/HPEC.2012.6408679

Anatomy of a globally recursive embedded LINPACK benchmark

Jack Dongarra, Piotr Luszczek

Computer Science and Mathematics Div

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

22 Scopus citations

Abstract

We present a complete bottom-up implementation of an embedded LINPACK benchmark on iPad 2. We use a novel formulation of a recursive LU factorization that is recursive and parallel at the global scope. We be believe our new algorithm presents an alternative to existing linear algebra parallelization techniques such as master-worker and DAG-based approaches. We show a assembly API that allows us a much higher level of abstraction and provides rapid code development within the confines of mobile device SDK. We use performance modeling to help with the limitation of the device and the limited access to device from the development environment not geared for HPC application tuning.

Original language	English
Title of host publication	2012 IEEE Conference on High Performance Extreme Computing, HPEC 2012
DOIs	https://doi.org/10.1109/HPEC.2012.6408679
State	Published - 2012
Event	2012 IEEE Conference on High Performance Extreme Computing, HPEC 2012 - Waltham, MA, United States Duration: Sep 10 2012 → Sep 12 2012

Publication series

Name	2012 IEEE Conference on High Performance Extreme Computing, HPEC 2012

Conference

Conference	2012 IEEE Conference on High Performance Extreme Computing, HPEC 2012
Country/Territory	United States
City	Waltham, MA
Period	09/10/12 → 09/12/12

Access to Document

10.1109/HPEC.2012.6408679

Cite this

@inproceedings{05617c4d5b044b569629cb0be14c9f36,

title = "Anatomy of a globally recursive embedded LINPACK benchmark",

abstract = "We present a complete bottom-up implementation of an embedded LINPACK benchmark on iPad 2. We use a novel formulation of a recursive LU factorization that is recursive and parallel at the global scope. We be believe our new algorithm presents an alternative to existing linear algebra parallelization techniques such as master-worker and DAG-based approaches. We show a assembly API that allows us a much higher level of abstraction and provides rapid code development within the confines of mobile device SDK. We use performance modeling to help with the limitation of the device and the limited access to device from the development environment not geared for HPC application tuning.",

author = "Jack Dongarra and Piotr Luszczek",

year = "2012",

doi = "10.1109/HPEC.2012.6408679",

language = "English",

isbn = "9781467315760",

series = "2012 IEEE Conference on High Performance Extreme Computing, HPEC 2012",

booktitle = "2012 IEEE Conference on High Performance Extreme Computing, HPEC 2012",

note = "2012 IEEE Conference on High Performance Extreme Computing, HPEC 2012 ; Conference date: 10-09-2012 Through 12-09-2012",

}

Dongarra, J & Luszczek, P 2012, Anatomy of a globally recursive embedded LINPACK benchmark. in 2012 IEEE Conference on High Performance Extreme Computing, HPEC 2012., 6408679, 2012 IEEE Conference on High Performance Extreme Computing, HPEC 2012, 2012 IEEE Conference on High Performance Extreme Computing, HPEC 2012, Waltham, MA, United States, 09/10/12. https://doi.org/10.1109/HPEC.2012.6408679

TY - GEN

T1 - Anatomy of a globally recursive embedded LINPACK benchmark

AU - Dongarra, Jack

AU - Luszczek, Piotr

PY - 2012

Y1 - 2012

N2 - We present a complete bottom-up implementation of an embedded LINPACK benchmark on iPad 2. We use a novel formulation of a recursive LU factorization that is recursive and parallel at the global scope. We be believe our new algorithm presents an alternative to existing linear algebra parallelization techniques such as master-worker and DAG-based approaches. We show a assembly API that allows us a much higher level of abstraction and provides rapid code development within the confines of mobile device SDK. We use performance modeling to help with the limitation of the device and the limited access to device from the development environment not geared for HPC application tuning.

AB - We present a complete bottom-up implementation of an embedded LINPACK benchmark on iPad 2. We use a novel formulation of a recursive LU factorization that is recursive and parallel at the global scope. We be believe our new algorithm presents an alternative to existing linear algebra parallelization techniques such as master-worker and DAG-based approaches. We show a assembly API that allows us a much higher level of abstraction and provides rapid code development within the confines of mobile device SDK. We use performance modeling to help with the limitation of the device and the limited access to device from the development environment not geared for HPC application tuning.

UR - http://www.scopus.com/inward/record.url?scp=84873530904&partnerID=8YFLogxK

U2 - 10.1109/HPEC.2012.6408679

DO - 10.1109/HPEC.2012.6408679

M3 - Conference contribution

AN - SCOPUS:84873530904

SN - 9781467315760

T3 - 2012 IEEE Conference on High Performance Extreme Computing, HPEC 2012

BT - 2012 IEEE Conference on High Performance Extreme Computing, HPEC 2012

T2 - 2012 IEEE Conference on High Performance Extreme Computing, HPEC 2012

Y2 - 10 September 2012 through 12 September 2012

ER -

Anatomy of a globally recursive embedded LINPACK benchmark

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this