MeG2: In-Memory Acceleration for Genome Graphs Analysis
DescriptionGenome graphs analysis has emerged as an effective means to enable mapping DNA fragments to the reference genome, capturing genetic variations and diversity across individuals. The in-depth characterization of genome graphs analysis uncovers that it is bottlenecked by irregular seeding index accesses and intensive alignment operations, stressing both the memory system and computing resources. In this paper, we propose MeG$^{2}$, a commodity DRAM-compliant processing-in-memory solution to accelerate genome graphs analysis. MeG$^{2}$ is specifically integrated with the capabilities of both near-memory processing and bit-wise in-situ computation. Results show that MeG$^{2}$ can significantly outperform the state-of-the-art CPU, GPU, and accelerator solutions.
Event Type
Research Manuscript
TimeTuesday, July 11th1:40pm - 1:55pm PDT
Location3003, 3rd Floor
In-memory and Near-memory Computing Architectures, Applications and Systems