DOPA: GPU-based protein alignment using database and memory access optimizations
2011
DOPA: A Fast GPU-Based Protein Alignment Tool
publication
Evidence: high
Author Information
Author(s): Hasan Laiq, Marijn Kentie, Zaid Al-Ars
Primary Institution: Delft University of Technology
Hypothesis
The study aims to improve the performance of the Smith-Waterman algorithm for protein sequence alignment using GPU optimizations.
Conclusion
The DOPA implementation achieves a performance of 21.4 GCUPS, outperforming the fastest existing GPU implementation by 1.13 times.
Supporting Evidence
- DOPA improves performance by optimizing database organization and reducing memory accesses.
- The implementation achieves 21.4 GCUPS, which is significantly faster than previous methods.
- DOPA's design allows for equal workload distribution among GPU threads.
Takeaway
DOPA is a new tool that helps compare protein sequences much faster by using special computer chips called GPUs, making it easier for scientists to find similarities.
Methodology
The study developed a GPU-based implementation of the Smith-Waterman algorithm, optimizing database organization and memory access.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website