Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data.

Charles M. Burns

dblp:79/1980 · DBLP profile ↗
← Back
1ranked-venue papers
1as first author
0since 2021 · last 1992
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Systems, architecture and hardware · 1 · 1 first-author

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Computer architecture, parallel and distributed computing, and storage systems
1 paper
Parallel and multicore computing · 50% High-performance computing · 22% Interconnection networks and networks-on-chip · 22%

Topics — the 6 heaviest of 6, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
High-performance computing
cluster computing
0.011992
Low Copy Message Passing on the Alliant CAMPUS/800 · SC 1992
Parallel and multicore computing › parallel programming models
message passing
0.011992
Low Copy Message Passing on the Alliant CAMPUS/800 · SC 1992
Interconnection networks and networks-on-chip › interprocessor communication
message passing protocol
0.011992
Low Copy Message Passing on the Alliant CAMPUS/800 · SC 1992
Parallel and multicore computing
parallel programming models
0.011992
Low Copy Message Passing on the Alliant CAMPUS/800 · SC 1992
Parallel and multicore computing › parallel architecture
massively parallel processor
0.011992
Low Copy Message Passing on the Alliant CAMPUS/800 · SC 1992
Processor architecture and microarchitecture › instruction set architecture › RISC
RISC processor
0.011992
Low Copy Message Passing on the Alliant CAMPUS/800 · SC 1992

Methods — techniques the papers use, named apart from their topics

protocol optimization · 0.0low copy message passing · 0.0
YearPublicationVenuePosition
1992 Low Copy Message Passing on the Alliant CAMPUS/800
abstract
With modern massively parallel processors consisting of hundreds of RISC (reduced instruction set computer) processors, a significant portion of program run time is being spent in passing messages between processors. The authors address the problem of reducing unnecessary copies in message passing protocols. Message passing that avoids using copies in the application program and the transport mechanism is called low copy message passing. The authors describe the low copy message passing library on the Alliant CAMPUS/800 system. First, a way to reduce the number of copies in a message passing protocol is proposed. In gross machine independent terms, the message passing protocol can be reduced from seven major steps to one. The authors then describe how application programmers can use the low copy message passing library. Finally, a brief survey of applications is presented which shows how applications use the low copy library.>
Charles M. Burns, Robert H. Kuhn, Eric J. Werme
SC1