Please use this identifier to cite or link to this item: https://doi.org/10.1109/TCAD.2021.3132551
Title: HiMap: Fast and Scalable High-Quality Mapping on CGRA via Hierarchical Abstraction
Authors: Dhananjaya Wijerathne
Zhaoying Li
ANUJ PATHANIA 
TULIKA MITRA 
Lothar Thiele 
Issue Date: 5-Feb-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Citation: Dhananjaya Wijerathne, Zhaoying Li, ANUJ PATHANIA, TULIKA MITRA, Lothar Thiele (2021-02-05). HiMap: Fast and Scalable High-Quality Mapping on CGRA via Hierarchical Abstraction. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems : 1192-1197. ScholarBank@NUS Repository. https://doi.org/10.1109/TCAD.2021.3132551
Abstract: Coarse-Grained Reconfigurable Array (CGRA) has emerged as a promising hardware accelerator due to the excellent balance between reconfigurability, performance, and energy efficiency. The performance of a CGRA strongly depends on the existence of a high-quality compiler to map the application kernels on the architecture. Unfortunately, the state-of-the-art compiler technology falls short in generating high-performance mapping within an acceptable compilation time, especially with increasing CGRA size. We propose HiMap – a fast and scalable CGRA mapping approach – that is also adept at producing close-to-optimal solutions for regular computational kernels prevalent in existing and emerging application domains. The key strategy behind HiMap’s efficiency and scalability is to exploit the regularity in the computation by employing a virtual systolic array as an intermediate abstraction layer in a hierarchical mapping. HiMap first maps the loop iterations of the kernel onto a virtual systolic array and then distills out the unique patterns in the mapping. These unique patterns are subsequently mapped onto sub-spaces of the physical CGRA. They are arranged together according to the systolic array mapping to create a complete mapping of the kernel. Experimental results confirm that HiMap can generate application mappings that hit the performance envelope of the CGRA. HiMap offers 17.3x and 5x improvement in performance and energy efficiency of the mappings compared to the state-of-the-art. The compilation time of HiMap for near-optimal mappings is less than 15 minutes for 64x64 CGRA, while existing approaches take days to generate inferior mappings.
Source Title: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
URI: https://scholarbank.nus.edu.sg/handle/10635/213156
ISSN: 0278-0070
1937-4151
DOI: 10.1109/TCAD.2021.3132551
Appears in Collections:Staff Publications
Elements
Students Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
HiMap_DATE_2021.pdfHiMap: Fast and Scalable High-Quality Mapping on CGRA via Hierarchical Abstraction1.27 MBAdobe PDF

OPEN

Post-printView/Download

SCOPUSTM   
Citations

5
checked on Oct 1, 2022

Page view(s)

80
checked on Oct 6, 2022

Download(s)

3
checked on Oct 6, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.