Efficient Stream Compaction on Wide SIMD Many-Core Architectures
View/
Date
2009Author
Billeter, Markus 
Assarsson, Ulf
Pay-Per-View via TIB Hannover:
Try if this item/paper is available.
Metadata
Show full item recordAbstract
Stream compaction is a common parallel primitive used to remove unwanted elements in sparse data. This allows highly parallel algorithms to maintain performance over several processing steps and reduces overall memory usage. For wide SIMD many-core architectures, we present a novel stream compaction algorithm and explore several variations thereof. Our algorithm is designed to maximize concurrent execution, with minimal use of synchronization. Bandwidth and auxiliary storage requirements are reduced significantly, which allows for substantially better performance. We have tested our algorithms using CUDA on a PC with an NVIDIA GeForce GTX280 GPU. On this hardware, our reference implementation provides a 3× speedup over previous published algorithms.
BibTeX
@inproceedings {10.1145:1572769.1572795,
booktitle = {High-Performance Graphics},
editor = {David Luebke and Philipp Slusallek},
title = {{Efficient Stream Compaction on Wide SIMD Many-Core Architectures}},
author = {Billeter, Markus and Olsson, Ola and Assarsson, Ulf},
year = {2009},
publisher = {The Eurographics Association},
ISSN = {2079-8687},
ISBN = {978-1-60558-603-8},
DOI = {10.1145/1572769.1572795}
}
booktitle = {High-Performance Graphics},
editor = {David Luebke and Philipp Slusallek},
title = {{Efficient Stream Compaction on Wide SIMD Many-Core Architectures}},
author = {Billeter, Markus and Olsson, Ola and Assarsson, Ulf},
year = {2009},
publisher = {The Eurographics Association},
ISSN = {2079-8687},
ISBN = {978-1-60558-603-8},
DOI = {10.1145/1572769.1572795}
}