(Created page with " == Abstract == We consider the class of “left-looking” sequential matrix algorithms: consumer-driven algorithms that are characterized by “lazy” propagation of data. Lef...")
 
 
(One intermediate revision by the same user not shown)
Line 2: Line 2:
 
== Abstract ==
 
== Abstract ==
  
We consider the class of “left-looking” sequential matrix algorithms: consumer-driven algorithms that are characterized by “lazy” propagation of data. Left-looking algorithms are difficult to parallelize using the message-passing or distributed shared memory models because they only possess pipeline parallelism. We show that these algorithms can be directly parallelized using mobile pipelines provided by the Navigational Programming methodology. We present performance data demonstrating the effectiveness of our approach.
+
We consider the class of “left-looking” sequential matrix algorithms: consumer-driven algorithms that are characterized by “lazy” propagation of data. Left-looking algorithms are difficult to parallelize using the message-passing or distributed shared memory models because they only possess pipeline parallelism. We show that these algorithms can be directly parallelized using mobile pipelines provided by the Navigational Programming methodology. We present performance data demonstrating the effectiveness of our approach.
 
+
Document type: Part of book or chapter of book
+
 
+
== Full document ==
+
<pdf>Media:Draft_Content_563030481-beopen974-2365-document.pdf</pdf>
+
  
  
Line 15: Line 10:
  
 
* [http://www.ics.uci.edu/~bic/messengers/papers/TR05-12.pdf http://www.ics.uci.edu/~bic/messengers/papers/TR05-12.pdf]
 
* [http://www.ics.uci.edu/~bic/messengers/papers/TR05-12.pdf http://www.ics.uci.edu/~bic/messengers/papers/TR05-12.pdf]
 +
 +
* [http://link.springer.com/content/pdf/10.1007/11602569_24.pdf http://link.springer.com/content/pdf/10.1007/11602569_24.pdf],
 +
: [http://dx.doi.org/10.1007/11602569_24 http://dx.doi.org/10.1007/11602569_24]
 +
 +
* [http://www.ics.uci.edu/~bic/messengers/papers/TR05-12.pdf http://www.ics.uci.edu/~bic/messengers/papers/TR05-12.pdf],
 +
: [https://link.springer.com/chapter/10.1007/11602569_24 https://link.springer.com/chapter/10.1007/11602569_24],
 +
: [http://core.ac.uk/display/24576471 http://core.ac.uk/display/24576471],
 +
: [https://dblp.uni-trier.de/db/conf/hipc/hipc2005.html#PanLDB05 https://dblp.uni-trier.de/db/conf/hipc/hipc2005.html#PanLDB05],
 +
: [https://www.scipedia.com/public/Pan_et_al_2006a https://www.scipedia.com/public/Pan_et_al_2006a],
 +
: [https://dl.acm.org/citation.cfm?id=2099331 https://dl.acm.org/citation.cfm?id=2099331],
 +
: [https://rd.springer.com/chapter/10.1007/11602569_24 https://rd.springer.com/chapter/10.1007/11602569_24],
 +
: [https://core.ac.uk/display/24576471 https://core.ac.uk/display/24576471],
 +
: [https://academic.microsoft.com/#/detail/1500980468 https://academic.microsoft.com/#/detail/1500980468]

Latest revision as of 16:24, 21 January 2021

Abstract

We consider the class of “left-looking” sequential matrix algorithms: consumer-driven algorithms that are characterized by “lazy” propagation of data. Left-looking algorithms are difficult to parallelize using the message-passing or distributed shared memory models because they only possess pipeline parallelism. We show that these algorithms can be directly parallelized using mobile pipelines provided by the Navigational Programming methodology. We present performance data demonstrating the effectiveness of our approach.


Original document

The different versions of the original document can be found in:

http://dx.doi.org/10.1007/11602569_24
https://link.springer.com/chapter/10.1007/11602569_24,
http://core.ac.uk/display/24576471,
https://dblp.uni-trier.de/db/conf/hipc/hipc2005.html#PanLDB05,
https://www.scipedia.com/public/Pan_et_al_2006a,
https://dl.acm.org/citation.cfm?id=2099331,
https://rd.springer.com/chapter/10.1007/11602569_24,
https://core.ac.uk/display/24576471,
https://academic.microsoft.com/#/detail/1500980468
Back to Top

Document information

Published on 01/01/2006

Volume 2006, 2006
DOI: 10.1007/11602569_24
Licence: CC BY-NC-SA license

Document Score

0

Views 2
Recommendations 0

Share this document

claim authorship

Are you one of the authors of this document?