Streamline Integration Using MPI-Hybrid Parallelism on a Large Multicore Architecture

Streamline computation in a very large vector field data set represents a significant challenge due to the nonlocal and data-dependent nature of streamline integration. In this paper, we conduct a study of the performance characteristics of hybrid parallel programming and execution as applied to str...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on visualization and computer graphics 2011-11, Vol.17 (11), p.1702-1713
Main Authors: Camp, D., Garth, C., Childs, H., Pugmire, D., Joy, K.
Format: Article
Language:English
Subjects:
ALGORITHMS
Architecture
Clusters
COMMUNICATIONS
Complexity theory
Computation
COMPUTER ARCHITECTURE
Concurrent programming
Consumption
Data visualization
display algorithms
Distributed databases
DISTRIBUTION
HYBRID SYSTEMS
IMPLEMENTATION
Instruction sets
MATHEMATICS AND COMPUTING
modes of computation
MPI-hybrid, Multi-core, Streamline
Multicore processing
Parallel processing
parallel programming
parallelism and concurrency
picture/image generation
Processors
PROGRAMMING
Studies
SUPERCOMPUTERS
VECTOR FIELDS
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Streamline computation in a very large vector field data set represents a significant challenge due to the nonlocal and data-dependent nature of streamline integration. In this paper, we conduct a study of the performance characteristics of hybrid parallel programming and execution as applied to streamline integration on a large, multicore platform. With multicore processors now prevalent in clusters and supercomputers, there is a need to understand the impact of these hybrid systems in order to make the best implementation choice. We use two MPI-based distribution approaches based on established parallelization paradigms, parallelize over seeds and parallelize over blocks, and present a novel MPI-hybrid algorithm for each approach to compute streamlines. Our findings indicate that the work sharing between cores in the proposed MPI-hybrid parallel implementation results in much improved performance and consumes less communication and I/O bandwidth than a traditional, nonhybrid distributed implementation.
ISSN:1077-2626
1941-0506
DOI:10.1109/TVCG.2010.259