AnySeq/GPU: A Novel Approach for Faster Sequence Alignment on GPUs

TL;DR

AnySeq/GPU introduces a GPU-optimized sequence alignment library that significantly outperforms existing tools by leveraging warp shuffles and half-precision arithmetic for high-throughput bioinformatics applications.

Contribution

The paper presents a novel GPU-based sequence alignment approach using warp shuffles and half-precision arithmetic, achieving near-peak performance and substantial speedups over prior libraries.

Findings

Achieves over 80% of GPU peak performance.

Outperforms existing libraries by at least 3.6x.

Reaches up to 3.8 TCUPS throughput on AMD GPUs.

Abstract

In recent years, the rapidly increasing number of reads produced by next-generation sequencing (NGS) technologies has driven the demand for efficient implementations of sequence alignments in bioinformatics. However, current state-of-the-art approaches are not able to leverage the massively parallel processing capabilities of modern GPUs with close-to-peak performance. We present AnySeq/GPU-a sequence alignment library that augments the AnySeq1 library with a novel approach for accelerating dynamic programming (DP) alignment on GPUs by minimizing memory accesses using warp shuffles and half-precision arithmetic. Our implementation is based on the AnyDSL compiler framework which allows for convenient zero-cost abstractions through guaranteed partial evaluation. We show that our approach achieves over 80% of the peak performance on both NVIDIA and AMD GPUs thereby outperforming the GPU-based alignment libraries AnySeq1, GASAL2, ADEPT, and NVBIO by a factor of at least 3.6 while achieving a median speedup of 19.2x over these tools across different alignment scenarios and sequence lengths when running on the same hardware. This leads to throughputs of up to 1.7 TCUPS (tera cell updates per second) on an NVIDIA GV100, up to 3.3 TCUPS with half-precision arithmetic on a single NVIDIA A100, and up to 3.8 TCUPS on an AMD MI100.