CASK - Open-source custom architectures for sparse kernels

File Description SizeFormat 
fpga16pg.pdfAccepted version457.91 kBAdobe PDFView/Open
Title: CASK - Open-source custom architectures for sparse kernels
Authors: Grigoras, P
Burovskiy, P
Luk, W
Item Type: Conference Paper
Abstract: © 2016 ACM.Sparse matrix vector multiplication (SpMV) is an impor- tant kernel in many scientific applications. To improve the performance and applicability of FPGA based SpMV, we propose an approach for exploiting properties of the input matrix to generate optimised custom architectures. The ar- chitectures generated by our approach are between 3.8 to 48 times faster than the worst case architectures for each matrix, showing the benefits of instance specific design for SpMV.
Issue Date: 21-Feb-2016
Date of Acceptance: 21-Feb-2016
URI: http://hdl.handle.net/10044/1/33329
DOI: http://dx.doi.org/10.1145/2847263.2847338
ISBN: 9781450338561
Publisher: ACM
Start Page: 179
End Page: 184
Journal / Book Title: Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays
Copyright Statement: © ACM 2016. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, http://dx.doi.org/10.1145/2847263.2847338.
Sponsor/Funder: Engineering & Physical Science Research Council (EPSRC)
Engineering & Physical Science Research Council (E
Commission of the European Communities
Funder's Grant Number: EP/I012036/1
PO 1553380
671653
Conference Name: 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA '16)
Publication Status: Published
Start Date: 2016-02-21
Finish Date: 2016-02-23
Conference Place: Monterey, CA, USA
Appears in Collections:Faculty of Engineering
Computing



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

Creative Commons