Fernando Elson Mourão

dblp:66/5523 · DBLP profile ↗
← Back
1ranked-venue papers
0as first author
0since 2021 · last 2000
—ORCID · none

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

Systems, architecture and hardware · 1

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 · 100%

Topics — the 4 heaviest of 4, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Parallel and multicore computing › parallel libraries
communication library
0.012000
Single sided MPI implementations for SUN MPI · SC 2000
Parallel and multicore computing › parallel programming models
message passing
0.012000
Single sided MPI implementations for SUN MPI · SC 2000
Parallel and multicore computing › parallel programming models › message passing
MPI one-sided communication
0.012000
Single sided MPI implementations for SUN MPI · SC 2000
Parallel and multicore computing › parallel computing › parallel communication
shared-memory communication
0.012000
Single sided MPI implementations for SUN MPI · SC 2000

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

type packing · 0.0caching · 0.0
YearPublicationVenuePosition
2000 Single sided MPI implementations for SUN MPI
abstract
This paper describes an implementation of generic MPI-2 single sided communications for SUN-MPI. Our implementation is layered on top of point-to-point MPI communications and therefore can be adapted to other MPI implementations. The code is designed to co-exist with other MPI-2 single sided implementations (for example direct use of shared memory) providing a generic fall-back implementation for those communication paths where an optimised single-sided implementation is not available. MPI-2 single sided communications require the transfer of data-type information as well as user data. We describe a type packing and caching mechanism used to optimise the transfer of data-type information. The performance of this implementation is measured in comparison to equivalent point to point operations and the shared memory implementation provided by SUN.
Stephen Booth, Fernando Elson Mourão
SC2