一句话：提出 GenStore 存储内处理系统，通过减少基因组读映射中的数据搬移来提升端到端性能。
读映射是许多基因组学应用的基础步骤，需要在测序读取片段与参考基因组之间进行近似字符串匹配（ASM），数据量大且计算代价高。已有工作通过高精度过滤器、启发式方法和硬件加速来减少昂贵计算，但仍需将大量数据从存储搬到系统其他部分，数据搬移严重限制传统及新兴基因组学系统的端到端性能。为此，论文提出 GenStore，一个面向基因组序列分析的高性能存储内处理（in-storage processing）系统，其核心思路是在存储侧完成部分处理，以减少数据搬移。给出的摘要主要阐述问题与动机，未展开具体架构、算法及评估结果。
Read mapping is a fundamental step in many genomics applications. It is used to identify potential matches and differences between fragments (called reads) of a sequenced genome and an already known genome (called a reference genome). Read mapping is costly because it needs to perform approximate string matching (ASM) on large amounts of data. To address the computational challenges in genome analysis, many prior works propose various approaches such as accurate filters that select the reads within a dataset of genomic reads (called a read set) that must undergo expensive computation, efficient heuristics, and hardware acceleration. While effective at reducing the amount of expensive computation, all such approaches still require the costly movement of a large amount of data from storage to the rest of the system, which can significantly lower the end-to-end performance of read mapping in conventional and emerging genomics systems.
@inproceedings{Mansouri-Ghiasi22,
title = {GenStore: a high-performance in-storage processing system for genome sequence analysis},
author = {Nika Mansouri Ghiasi and Jisung Park and Harun Mustafa and Jeremie Kim and Ataberk Olgun and Arvid Gollwitzer and Damla Senol Cali and Can Firtina and Haiyu Mao and Nour Almadhoun Alserr and Rachata Ausavarungnirun and Nandita Vijaykumar and Mohammed Alser and Onur Mutlu},
booktitle = {ASPLOS},
year = {2022},
doi = {10.1145/3503222.3507702}
}