Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/71057
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | Approximate multiplication and division for arithmetic data value speculation in a RISC processor |
Author: | Kelly, D. Phillips, B. Al-Sarawi, S. |
Citation: | Lecture Notes in Electrical Engineering, 2011; 73 LNEE:95-116 |
Publisher: | Springer |
Issue Date: | 2011 |
ISSN: | 1876-1100 1876-1119 |
Statement of Responsibility: | Daniel R. Kelly, Braden J. Phillips and Said Al-Sarawi |
Abstract: | Arithmetic data value speculation increases the throughput of a processor by using approximation to speculatively issue instructions dependent on an arithmetic result. This chapter describes new approximate multipliers and dividers. The performance advantage of these units is demonstrated in a practical context through simulation of a 32 bit RISC processor, modified to use these approximate units for arithmetic data value speculation. Instruction throughput improved by more than 15% for some media benchmarks. |
Keywords: | Speculation approximation estimation arithmetic value speculation prediction probabilistic computing probability multiplication division mediabench simplescalar |
Rights: | © Springer Science+Business Media B.V. 2011 |
DOI: | 10.1007/978-90-481-9965-5_5 |
Published version: | http://dx.doi.org/10.1007/978-90-481-9965-5_5 |
Appears in Collections: | Aurora harvest 5 Electrical and Electronic Engineering publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.