dc.contributor.author | Sasnayake Mudiyanselage, Lahiru Kasun Rasnayake | |
dc.contributor.author | Själander, Magnus | |
dc.date.accessioned | 2020-09-14T13:35:17Z | |
dc.date.available | 2020-09-14T13:35:17Z | |
dc.date.created | 2020-06-09T09:13:34Z | |
dc.date.issued | 2019 | |
dc.identifier.isbn | 978-1-7281-2943-3 | |
dc.identifier.uri | https://hdl.handle.net/11250/2677748 | |
dc.description.abstract | Low-precision matrix multiplication has gained significant interest in the research community due to its applicability in the quantized neural network domain. As a result, a multitude of variable precision hardware designs have been proposed since fixed-precision hardware causes under-utilization of the hardware resources due to the low and varying precision in such applications. Bit-serial hardware takes advantage of the frugal nature of bit-serial computations that can operate on only as many bits as necessary. A bit-serial matrix multiplication consists of a summation of weighted binary matrix multiplications. In this work, we study the inherent locality of bit-serial matrix multiplications and propose a locality-aware scheduling algorithm that eliminates redundant data fetches from memory. The proposed schedule improves with up to 76% compared to a schedule that computes each binary matrix multiplication in sequence. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en_US |
dc.relation.ispartof | The International Conference on Field-Programmable Technology | |
dc.title | Improving Memory Access Locality for Vectorized Bit-Serial Matrix Multiplication in Reconfigurable Computing | en_US |
dc.type | Chapter | en_US |
dc.description.version | acceptedVersion | en_US |
dc.identifier.doi | 10.1109/ICFPT47387.2019.00081 | |
dc.identifier.cristin | 1814469 | |
dc.description.localcode | © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | en_US |
cristin.ispublished | true | |
cristin.fulltext | postprint | |
cristin.qualitycode | 1 | |