@inproceedings{c0ecb5a3554c476f9cc014b8ad091182,
title = "Achieving teraCUPS on longest common subsequence problem using GPGPUs",
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.",
keywords = "CUDA, GPU, Longest Common Subsequence, Semi-regular algorithms",
author = "Adnan Ozsoy and Arun Chauhan and Martin Swany",
year = "2013",
doi = "10.1109/ICPADS.2013.22",
language = "English",
isbn = "9781479920815",
series = "Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS",
publisher = "IEEE Computer Society",
pages = "69--77",
booktitle = "Proceedings - 2013 19th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2013",
address = "United States",
note = "2013 19th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2013 ; Conference date: 15-12-2013 Through 18-12-2013",
}