SAGe: A Lightweight Algorithm-Architecture Co-Design for Mitigating the Data Preparation Bottleneck in Large-Scale Genome Analysis
Journal:
arXiv
Published Date:
Mar 31, 2025
Abstract
Given the exponentially growing volumes of genomic data, there are extensive
efforts to accelerate genome analysis. We demonstrate a major bottleneck that
greatly limits and diminishes the benefits of state-of-the-art genome analysis
accelerators: the data preparation bottleneck, where genomic data is stored in
compressed form and needs to be decompressed and formatted first before an
accelerator can operate on it. To mitigate this bottleneck, we propose SAGe, an
algorithm-architecture co-design for highly-compressed storage and
high-performance access of large-scale genomic data. SAGe overcomes the
challenges of mitigating the data preparation bottleneck while maintaining high
compression ratios (comparable to genomic-specific compression algorithms) at
low hardware cost. This is enabled by leveraging key features of genomic
datasets to co-design (i) a new (de)compression algorithm, (ii) hardware, (iii)
storage data layout, and (iv) interface commands to access storage. SAGe stores
data in structures that can be rapidly interpreted and decompressed by
efficient streaming accesses and lightweight hardware. To achieve high
compression ratios using only these lightweight structures, SAGe exploits
unique features of genomic data. We show that SAGe can be seamlessly integrated
with a broad range of genome analysis hardware accelerators to mitigate their
data preparation bottlenecks. Our results demonstrate that SAGe improves the
average end-to-end performance and energy efficiency of two state-of-the-art
genome analysis accelerators by 3.0x-32.1x and 18.8x-49.6x, respectively,
compared to when the accelerators rely on state-of-the-art decompression tools.
