Please use this identifier to cite or link to this item: https://doi.org/10.1145/1146909.1146924
Title: Exploiting forwarding to improve data bandwidth of instruction-set extensions
Authors: Jayaseelan, R.
Liu, H. 
Mitra, T. 
Keywords: Data forwarding
Instruction-set extensions
Issue Date: 2006
Source: Jayaseelan, R.,Liu, H.,Mitra, T. (2006). Exploiting forwarding to improve data bandwidth of instruction-set extensions. Proceedings - Design Automation Conference : 43-48. ScholarBank@NUS Repository. https://doi.org/10.1145/1146909.1146924
Abstract: Application-specific instruction-set extensions (custom instructions) help embedded processors achieve higher performance. Most custom instructions offering significant performance benefit require multiple input operands. Unfortunately, RISC-style embedded processors are designed to support at most two input operands per instruction. This data bandwidth problem is due to the limited number of read ports in the register file per instruction as well as the fixed-length instruction encoding. We propose to overcome this restriction by exploiting the data forwarding feature present in processor pipelines. With minimal modifications to the pipeline and the instruction encoding along with cooperation from the compiler, we can supply up to two additional input operands per custom instruction. Experimental results indicate that our approach achieves 87 - 100% of the ideal performance limit for standard benchmark programs. Additionally, our scheme saves 25% energy on an average by avoiding unnecessary accesses to the register file. Copyright 2006 ACM.
Source Title: Proceedings - Design Automation Conference
URI: http://scholarbank.nus.edu.sg/handle/10635/41328
ISBN: 1595933816
ISSN: 0738100X
DOI: 10.1145/1146909.1146924
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

24
checked on Nov 29, 2017

Page view(s)

51
checked on Dec 9, 2017

Google ScholarTM

Check

Altmetric


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