UpPipe: A Novel Pipeline Management on In-Memory Processors for RNA-seq Quantification
Liang-Chi Chen, Chien-Chung Ho, Yuan-Hao Chang
Abstract
RNA sequence quantification is an important analysis method to measure transcript abundances. A key overhead in RNA-seq quantification is to map a set of RNA reads to multiple reference transcripts, i.e., transcriptome. Besides, the performance of RNA-seq quantification is strictly limited by the excessive amounts of data movement between CPU and memory, i.e., memory wall problem on the conventional architecture. As the first publicly commercial processing-in-memory (PIM) system, UPMEM DPU, is proposed, the PIM gradually becomes a promising solution to overcome the memory wall problem. DPUs show great potential to accelerate data-intensive workloads by minimizing off-chip data movement between CPU and memory. Thus, this paper aims to improve the performance of RNA-seq quantification by fully exploiting the strengths of DPU. To achieve that, we propose a novel DPU-aware pipeline design "UpPipe" built on the software layer to address the hardware constraints of DPU. To the best of our knowledge, this is the first work to enable pipeline management on the DPU system. The evaluation results demonstrate the feasibility of our proposed design and provide a comprehensive study on how to utilize the limited hardware resources of DPUs efficiently.