FiltPIM: In-Memory Filter for DNA Sequencing

TL;DR

FiltPIM introduces a memristive processing-in-memory design for DNA sequencing filters, achieving a 100x speedup by reducing data transfer and leveraging parallelism, thus significantly accelerating genome alignment tasks.

Contribution

The paper presents a novel memristive processing-in-memory implementation of the base-count filter, enhancing filtering efficiency for genome alignment.

Findings

Reduces filtering time by 100x compared to CPU implementation.

Filters over 68% of potential genome alignment locations.

Utilizes memristive crossbar arrays for parallel in-memory computation.

Abstract

Aligning the entire genome of an organism is a compute-intensive task. Pre-alignment filters substantially reduce computation complexity by filtering potential alignment locations. The base-count filter successfully removes over 68% of the potential locations through a histogram-based heuristic. This paper presents FiltPIM, an efficient design of the basecount filter that is based on memristive processing-in-memory. The in-memory design reduces CPU-to-memory data transfer and utilizes both intra-crossbar and inter-crossbar memristive stateful-logic parallelism. The reduction in data transfer and the efficient stateful-logic computation together improve filtering time by 100x compared to a CPU implementation of the filter.