@proceedings{18176,
  keywords = {Proteins, performance evaluation, Instruction sets, scalability, Pipelines, DNA, Graphics processing units},
  author = {Max Zhao and Luk Burchard and Daniel Schroeder and Johannes Langguth and Xing Cai},
  title = {iPuma: High-Performance Sequence Alignment on the Graphcore IPU},
  abstract = {String alignment algorithms are an essential tool for understanding DNA and protein sequences. They demand substantial computation in real-world applications, and are thus a prime target for hardware acceleration. However, GPUs struggle to provide sufficient acceleration. Meanwhile, the recent MIMD-capable AI accelerators such as the Graphcore Intelligence Processing Unit (IPU) have become technologically viable. In this paper we present iPuma, a new implementation of Smith-Waterman sequence alignment for the IPU, which offers generalized short and medium length, one-to-one, and many-to-many high-throughput alignments for both DNA and protein sequences. iPuma is integrated into two bioinformatics pipelines, MetaHipMer2 and PASTIS. On protein datasets, iPuma shows speedups of 2.7 {\texttimes} and 1.6 {\texttimes} over state-of-the-art GPU and CPU implementations, respectively. We test the scalability on up to 64 IPUs, attaining a peak scoring performance of 1763 GCUPS for protein and 1168 GCUPS for DNA sequences.},
  year = {2024},
  journal = {ISC High Performance 2024 Research Paper Proceedings (39th International Conference)},
  month = {05/2024},
  publisher = {Prometeus GmbH, IEEEE},
  isbn = {978-3-9826336-0-2},
  url = {https://ieeexplore.ieee.org/abstract/document/10528941},
  doi = {10.23919/ISC.2024.10528941},
}