Achieving TeraCUPS on Longest Common Subsequence Problem Using GPGPUs. Ozsoy, A., Chauhan, A., & Swany, M. In Parallel and Distributed Systems (ICPADS13), 2013 International Conference on, pages 69-77, 2013. IEEE.
Achieving TeraCUPS on Longest Common Subsequence Problem Using GPGPUs [link]Website  doi  abstract   bibtex   
In this paper, we describe a novel technique to optimize longest common subsequence (LCS) algorithm for one-to-many matching problem on GPUs by transforming the computation into bit-wise operations and a post-processing step. The former can be highly optimized and achieves more than a trillion operations (cell updates) per second (CUPS)-a first for LCS algorithms. The latter is more efficiently done on CPUs, in a fraction of the bit-wise computation time. The bit-wise step promises to be a foundational step and a fundamentally new approach to developing algorithms for increasingly popular heterogeneous environments that could dramatically increase the applicability of hybrid CPU-GPU environments. © 2013 IEEE.
@inproceedings{
 title = {Achieving TeraCUPS on Longest Common Subsequence Problem Using GPGPUs},
 type = {inproceedings},
 year = {2013},
 keywords = {2013,pti},
 pages = {69-77},
 websites = {http://dx.doi.org/10.1109/ICPADS.2013.22},
 publisher = {IEEE},
 city = {Seoul, South Korea},
 id = {b8825fa7-1530-3072-9ea1-3160af039121},
 created = {2019-10-01T17:21:00.821Z},
 file_attached = {false},
 profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d},
 last_modified = {2019-10-01T17:23:51.012Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Ozsoy2013},
 source_type = {inproceedings},
 folder_uuids = {73f994b4-a3be-4035-a6dd-3802077ce863},
 private_publication = {false},
 abstract = {In this paper, we describe a novel technique to optimize longest common subsequence (LCS) algorithm for one-to-many matching problem on GPUs by transforming the computation into bit-wise operations and a post-processing step. The former can be highly optimized and achieves more than a trillion operations (cell updates) per second (CUPS)-a first for LCS algorithms. The latter is more efficiently done on CPUs, in a fraction of the bit-wise computation time. The bit-wise step promises to be a foundational step and a fundamentally new approach to developing algorithms for increasingly popular heterogeneous environments that could dramatically increase the applicability of hybrid CPU-GPU environments. © 2013 IEEE.},
 bibtype = {inproceedings},
 author = {Ozsoy, Adnan and Chauhan, Arun and Swany, Martin},
 doi = {10.1109/ICPADS.2013.22},
 booktitle = {Parallel and Distributed Systems (ICPADS13), 2013 International Conference on}
}

Downloads: 0