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 RNAseq 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. This talk is about how to improve the performance of RNA-seq

quantification by fully exploiting the strengths of DPU. I will present a novel DPU-

aware pipeline design “UpPipe” built on the software layer to address the hardware

constraints of DPU. In addition, DPU-friendly transcriptome allocation policy and

DPU-aware pipeline management with considering the quantification characteristics

and DPU’s constraints are also presented.

Bio.

Dr. Ho is an Assistant Professor in the Department of Computer Science and

Information Engineering (CSIE), National Cheng Kung University (NCKU). Before

joining NCKU CSIE, he worked in the Department of Computer Science and

Information Engineering (CSIE), National Chung Cheng University (CCU) from 2017 to

2021, and as a Postdoctoral Researcher in the Institute of Information Science (IIS),

Academia Sinica from 2016 to 2017. He received his Ph.D. degree in the Department

of Computer Science and Information Engineering from National Taiwan University

in June 2016. His primary research interests include emerging non-volatile memory

and storage technologies, memory and storage systems, and next-generation

memory/storage architecture designs.

faculty and students are welcome to join.