TALCO: Tiling Genome Sequence Alignment Using Convergence of Traceback Pointers

Walia, Sumit; Ye, Cheng; Bera, Arkid; Lodhavia, Dhruvi; Turakhia, Yatish

doi:10.1109/hpca57654.2024.00044

Cited by 2 publications

References 97 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

BIMSA: Accelerating Long Sequence Alignment Using Processing-In-Memory

Alonso-Marín,

Fernandez,

Aguado-Puig

et al. 2024

Preprint

View full text Add to dashboard Cite

Motivation: Recent advances in sequencing technologies pose sequence analysis algorithms as fundamental tools for genomics and healthcare research. In particular, sequence alignment is a fundamental building block present in numerous sequence analysis pipelines. Commonly used sequence alignment algorithms are based on dynamic programming and often require quadratic time and memory concerning the sequence length. As a result, classic sequence alignment algorithms fail to scale with increasing sequence lengths and quickly become memory-bound due to data-movement penalties. Results: Processing-In-Memory (PIM) is an emerging architectural paradigm that seeks to accelerate memory-bound algorithms, bringing computation closer to the data to mitigate data-movement penalties. This work presents BIMSA (Bidirectional In-Memory Sequence Alignment), a PIM-optimized implementation of the state-of-the-art sequence alignment algorithm BiWFA (Bidirectional Wavefront Alignment), incorporating hardware-aware optimizations for a production-ready PIM architecture (UPMEM). BIMSA achieves speedups up to 22.24x compared to state-of-the-art PIM-enabled implementations of sequence alignment algorithms and up to 5.84x compared to the most efficient CPU implementation of BiWFA. In addition, BIMSA exhibits linear scalability with the number of compute units, enabling further performance improvements with upcoming PIM architectures equipped with more compute units.

show abstract