A time-domain wavefront computing accelerator with a 32 × 32 reconfigurable PE array

This work presents a hardware accelerator realizing true time-domain wavefront computing in a massive parallel two-dimensional (2-D) processing element (PE) array. The proposed 2-D time-domain PE array is designed for multiple applications based on its scalable and reconfigurable architecture. The s...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu, Chengshuo, Mu, Junjie, Su, Yuqi, Chai, Kevin Tshun Chuan, Kim, Tony Tae-Hyoung, Kim, Bongjin
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2023
Subjects:
Online Access:https://hdl.handle.net/10356/170677
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-170677
record_format dspace
spelling sg-ntu-dr.10356-1706772023-09-26T00:54:28Z A time-domain wavefront computing accelerator with a 32 × 32 reconfigurable PE array Yu, Chengshuo Mu, Junjie Su, Yuqi Chai, Kevin Tshun Chuan Kim, Tony Tae-Hyoung Kim, Bongjin School of Electrical and Electronic Engineering Institute of Microelectronics, A*STAR Engineering::Electrical and electronic engineering High Scalability King’s Graph This work presents a hardware accelerator realizing true time-domain wavefront computing in a massive parallel two-dimensional (2-D) processing element (PE) array. The proposed 2-D time-domain PE array is designed for multiple applications based on its scalable and reconfigurable architecture. The shortest path problem (a classical problem in graph theory) is one of the critical problems to solve using the proposed accelerator. Unlike the A∗ search algorithm, a heuristic method widely used in shortest path searching problems, the proposed accelerator requires only the propagation of rising-edge signals through the PE array without calculating or estimating the distances from the start to the goal. Hence, a single execution of the proposed time-domain wavefront computing provides all the optimal paths from a start point to an arbitrary goal. Besides the King's graph model used for solving the shortest path searching, the PE array is reconfigured to a simpler lattice graph model and solves other problems, such as maze solving we used in this article as a benchmark. In addition, we used the proposed accelerator to demonstrate a scientific simulation. The propagation of circular or planar wavefronts was simulated using single or multiple start points using King's graph configuration. A 1 × 1 mm2 test chip with a 32 × 32 reconfigurable time-domain PE array is fabricated using a 65-nm process. For a 2-D map with 32 × 32 vertices, the proposed PE array consumes 776 pJ per task and achieves 1.6 G edges/second search rate using 1.2-/1.0-V core supply voltages. Agency for Science, Technology and Research (A*STAR) This work was supported by the A∗STAR RIE2020 Advanced Manufacturing and Engineering (AME) Programmatic Fund under Grant A19E8b0102. 2023-09-26T00:54:28Z 2023-09-26T00:54:28Z 2023 Journal Article Yu, C., Mu, J., Su, Y., Chai, K. T. C., Kim, T. T. & Kim, B. (2023). A time-domain wavefront computing accelerator with a 32 × 32 reconfigurable PE array. IEEE Journal of Solid-State Circuits, 58(8), 2372-2382. https://dx.doi.org/10.1109/JSSC.2023.3236376 0018-9200 https://hdl.handle.net/10356/170677 10.1109/JSSC.2023.3236376 2-s2.0-85147304109 8 58 2372 2382 en A19E8b0102 IEEE Journal of Solid-State Circuits © 2023 IEEE. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
High Scalability
King’s Graph
spellingShingle Engineering::Electrical and electronic engineering
High Scalability
King’s Graph
Yu, Chengshuo
Mu, Junjie
Su, Yuqi
Chai, Kevin Tshun Chuan
Kim, Tony Tae-Hyoung
Kim, Bongjin
A time-domain wavefront computing accelerator with a 32 × 32 reconfigurable PE array
description This work presents a hardware accelerator realizing true time-domain wavefront computing in a massive parallel two-dimensional (2-D) processing element (PE) array. The proposed 2-D time-domain PE array is designed for multiple applications based on its scalable and reconfigurable architecture. The shortest path problem (a classical problem in graph theory) is one of the critical problems to solve using the proposed accelerator. Unlike the A∗ search algorithm, a heuristic method widely used in shortest path searching problems, the proposed accelerator requires only the propagation of rising-edge signals through the PE array without calculating or estimating the distances from the start to the goal. Hence, a single execution of the proposed time-domain wavefront computing provides all the optimal paths from a start point to an arbitrary goal. Besides the King's graph model used for solving the shortest path searching, the PE array is reconfigured to a simpler lattice graph model and solves other problems, such as maze solving we used in this article as a benchmark. In addition, we used the proposed accelerator to demonstrate a scientific simulation. The propagation of circular or planar wavefronts was simulated using single or multiple start points using King's graph configuration. A 1 × 1 mm2 test chip with a 32 × 32 reconfigurable time-domain PE array is fabricated using a 65-nm process. For a 2-D map with 32 × 32 vertices, the proposed PE array consumes 776 pJ per task and achieves 1.6 G edges/second search rate using 1.2-/1.0-V core supply voltages.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Yu, Chengshuo
Mu, Junjie
Su, Yuqi
Chai, Kevin Tshun Chuan
Kim, Tony Tae-Hyoung
Kim, Bongjin
format Article
author Yu, Chengshuo
Mu, Junjie
Su, Yuqi
Chai, Kevin Tshun Chuan
Kim, Tony Tae-Hyoung
Kim, Bongjin
author_sort Yu, Chengshuo
title A time-domain wavefront computing accelerator with a 32 × 32 reconfigurable PE array
title_short A time-domain wavefront computing accelerator with a 32 × 32 reconfigurable PE array
title_full A time-domain wavefront computing accelerator with a 32 × 32 reconfigurable PE array
title_fullStr A time-domain wavefront computing accelerator with a 32 × 32 reconfigurable PE array
title_full_unstemmed A time-domain wavefront computing accelerator with a 32 × 32 reconfigurable PE array
title_sort time-domain wavefront computing accelerator with a 32 × 32 reconfigurable pe array
publishDate 2023
url https://hdl.handle.net/10356/170677
_version_ 1779156628419903488