Synchronous And Asynchronous Algorithms For Matrix Transposition On MCAP

Azari, Nasser G.; Bojańczyk, Adam W.; Lee, Sang Yup

doi:10.1117/12.948511

Search citation statements

Order By: Relevance

Paper Sections

Select...

Fig 1 Illustration Of Sdr Technique and Routing Algorithms1

Basic Short Dimension Routing (Sdr)1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2010

Publication Types

Select...

Book1

Other1

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The transpose problem has been well-studied on other interconnection architectures [7,4,1,5]. The basic idea of intermediate-node routing goes back to the work of Valiant [12].…”

Section: Fig 1 Illustration Of Sdr Technique and Routing Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Optimizing Matrix Transpose on Torus Interconnects

Chakaravarthy

Jain

Sabharwal

2010

Euro-Par 2010 - Parallel Processing

View full text Add to dashboard Cite

Abstract. Matrix transpose is a fundamental matrix operation that arises in many scientific and engineering applications. Communication is the main bottleneck in performing matrix transpose on most multiprocessor systems. In this paper, we focus on torus interconnection networks and propose application-level routing techniques that improve load balancing, resulting in better performance. Our basic idea is to route the data via carefully selected intermediate nodes. However, directly employing this technique may lead to worsening of the congestion. We overcome this issue by employing the routing only for selected set of communicating pairs. We implement our optimizations on the Blue Gene/P supercomputer and demonstrate up to 35% improvement in performance.

show abstract

“…The transpose problem has been well-studied on other interconnection architectures [7,4,1,5]. The basic idea of intermediate-node routing goes back to the work of Valiant [12].…”

Section: Fig 1 Illustration Of Sdr Technique and Routing Algorithmsmentioning

confidence: 99%

“…We exploit the above fact and design a heuristic that achieves better load balancing. Namely, for sending a packet from a source u 1 to a destination u 2 , we will choose a suitable intermediate node u lying on the same column as u 1 . This ensures that the data from u 1 to u traverses only the Y -links.…”

Section: Basic Short Dimension Routing (Sdr)mentioning

confidence: 99%