TY - GEN
T1 - PIM-Assembler
T2 - 57th ACM/IEEE Design Automation Conference, DAC 2020
AU - Angizi, Shaahin
AU - Fahmi, Naima Ahmed
AU - Zhang, Wei
AU - Fan, Deliang
N1 - Funding Information:
V. CONCLUSION In this work, we presented PIM-Assembler, as a new PIM architecture to address some of the existing issues in state-of-the-art DRAM-based acceleration solutions for performing bulk bit-wise X(N)OR-based operations. Accordingly, we show how PIM-Assembler can accelerate the comparison/addition-extensive genome assembly application using PIM-friendly operations. The simulation results on human-ch14 shows that this new platform reduces the execution time and power by ∼5× and ∼7.5× compared to GPU. VI. ACKNOWLEDGEMENT This work is supported in part by the National Science Foundation under Grant No.2005209, No.2003749, No. 1755761 and Semiconductor Research Corporation nCORE.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/7
Y1 - 2020/7
N2 - In this paper, for the first time, we propose a high-throughput and energy-efficient Processing-in-DRAM-accelerated genome assembler called PIM-Assembler based on an optimized and hardware-friendly genome assembly algorithm. PIM-Assembler can assemble large-scale DNA sequence dataset from all-pair overlaps. We first develop PIM-Assembler platform that harnesses DRAM as computational memory and transforms it to a fundamental processing unit for genome assembly. PIM-Assembler can perform efficient X(N)OR-based operations inside DRAM incurring low cost on top of commodity DRAM designs (~5% of chip area). PIM-Assembler is then optimized through a correlated data partitioning and mapping methodology that allows local storage and processing of DNA short reads to fully exploit the genome assembly algorithm-level's parallelism. The simulation results show that PIM-Assembler achieves on average 8.4× and 2.3 wise× higher throughput for performing bulk bit-XNOR-based comparison operations compared with CPU and recent processing-in-DRAM platforms, respectively. As for comparison/addition-extensive genome assembly application, it reduces the execution time and power by ~5× and ~ 7.5× compared to GPU.
AB - In this paper, for the first time, we propose a high-throughput and energy-efficient Processing-in-DRAM-accelerated genome assembler called PIM-Assembler based on an optimized and hardware-friendly genome assembly algorithm. PIM-Assembler can assemble large-scale DNA sequence dataset from all-pair overlaps. We first develop PIM-Assembler platform that harnesses DRAM as computational memory and transforms it to a fundamental processing unit for genome assembly. PIM-Assembler can perform efficient X(N)OR-based operations inside DRAM incurring low cost on top of commodity DRAM designs (~5% of chip area). PIM-Assembler is then optimized through a correlated data partitioning and mapping methodology that allows local storage and processing of DNA short reads to fully exploit the genome assembly algorithm-level's parallelism. The simulation results show that PIM-Assembler achieves on average 8.4× and 2.3 wise× higher throughput for performing bulk bit-XNOR-based comparison operations compared with CPU and recent processing-in-DRAM platforms, respectively. As for comparison/addition-extensive genome assembly application, it reduces the execution time and power by ~5× and ~ 7.5× compared to GPU.
UR - http://www.scopus.com/inward/record.url?scp=85093936281&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85093936281&partnerID=8YFLogxK
U2 - 10.1109/DAC18072.2020.9218653
DO - 10.1109/DAC18072.2020.9218653
M3 - Conference contribution
AN - SCOPUS:85093936281
T3 - Proceedings - Design Automation Conference
BT - 2020 57th ACM/IEEE Design Automation Conference, DAC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 20 July 2020 through 24 July 2020
ER -