Hardware-software co-design and optimization for point-to-point network-on-chip based many-core systems
Many-core systems, which consist of numerous processing elements (PEs), provide high execution parallelism. To connect these PEs, network-on-chip (NoC) is proposed as an efficient on-chip communication paradigm. Nevertheless, NoC faces two challenges in reducing communication overheads. Firstly, the...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis-Doctor of Philosophy |
Language: | English |
Published: |
Nanyang Technological University
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/156762 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-156762 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1567622022-05-04T10:23:16Z Hardware-software co-design and optimization for point-to-point network-on-chip based many-core systems Chen, Hui Weichen Liu School of Computer Science and Engineering liu@ntu.edu.sg Engineering::Computer science and engineering::Computer systems organization::Computer-communication networks Many-core systems, which consist of numerous processing elements (PEs), provide high execution parallelism. To connect these PEs, network-on-chip (NoC) is proposed as an efficient on-chip communication paradigm. Nevertheless, NoC faces two challenges in reducing communication overheads. Firstly, the hop-by-hop buffering and arbitration in NoC lead to huge transmission delay and energy consumption. Secondly, NoC resource management strategies, e.g., mapping and routing, are not fully optimized. To address these challenges, we propose software and hardware collaborated methodologies. (1) We propose a software-defined point-to-point NoC architecture, ArSMART, enabling single-cycle multi-hop transmission and application-specific communication optimization. (2) We present a method to co-optimize task mapping and routing to accelerate computation and communication simultaneously, extending ArSMART to heterogeneous systems. (3) We fully utilize the parallelism that exists in NoCs through parallel multipath transmission, further reducing transmission latency in ArSMART. Experiments show our solutions achieve remarkable performance improvement in terms of latency, area, and power. Doctor of Philosophy 2022-04-20T08:52:17Z 2022-04-20T08:52:17Z 2022 Thesis-Doctor of Philosophy Chen, H. (2022). Hardware-software co-design and optimization for point-to-point network-on-chip based many-core systems. Doctoral thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/156762 https://hdl.handle.net/10356/156762 10.32657/10356/156762 en This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0). application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering::Computer systems organization::Computer-communication networks |
spellingShingle |
Engineering::Computer science and engineering::Computer systems organization::Computer-communication networks Chen, Hui Hardware-software co-design and optimization for point-to-point network-on-chip based many-core systems |
description |
Many-core systems, which consist of numerous processing elements (PEs), provide high execution parallelism. To connect these PEs, network-on-chip (NoC) is proposed as an efficient on-chip communication paradigm. Nevertheless, NoC faces two challenges in reducing communication overheads. Firstly, the hop-by-hop buffering and arbitration in NoC lead to huge transmission delay and energy consumption. Secondly, NoC resource management strategies, e.g., mapping and routing, are not fully optimized. To address these challenges, we propose software and hardware collaborated methodologies.
(1) We propose a software-defined point-to-point NoC architecture, ArSMART, enabling single-cycle multi-hop transmission and application-specific communication optimization.
(2) We present a method to co-optimize task mapping and routing to accelerate computation and communication simultaneously, extending ArSMART to heterogeneous systems.
(3) We fully utilize the parallelism that exists in NoCs through parallel multipath transmission, further reducing transmission latency in ArSMART.
Experiments show our solutions achieve remarkable performance improvement in terms of latency, area, and power. |
author2 |
Weichen Liu |
author_facet |
Weichen Liu Chen, Hui |
format |
Thesis-Doctor of Philosophy |
author |
Chen, Hui |
author_sort |
Chen, Hui |
title |
Hardware-software co-design and optimization for point-to-point network-on-chip based many-core systems |
title_short |
Hardware-software co-design and optimization for point-to-point network-on-chip based many-core systems |
title_full |
Hardware-software co-design and optimization for point-to-point network-on-chip based many-core systems |
title_fullStr |
Hardware-software co-design and optimization for point-to-point network-on-chip based many-core systems |
title_full_unstemmed |
Hardware-software co-design and optimization for point-to-point network-on-chip based many-core systems |
title_sort |
hardware-software co-design and optimization for point-to-point network-on-chip based many-core systems |
publisher |
Nanyang Technological University |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/156762 |
_version_ |
1734310298331906048 |