High-Accuracy Approximate Addition based on Carry Speculation

碩士 === 國立交通大學 === 資訊科學與工程研究所 === 106 === Approximate computing has been proposed as an approach to break through the limitations of traditional designs. Since nowadays a lot of applications can tolerate a certain degree of errors, it provides a new trade-off between computation quality and performan...

Full description

Bibliographic Details
Main Authors: Chen, Szu-Ying, 陳思穎
Other Authors: Wu, Kai-Chiang
Format: Others
Language:en_US
Published: 2017
Online Access:http://ndltd.ncl.edu.tw/handle/npzmuc
id ndltd-TW-106NCTU5394067
record_format oai_dc
spelling ndltd-TW-106NCTU53940672019-05-16T00:22:51Z http://ndltd.ncl.edu.tw/handle/npzmuc High-Accuracy Approximate Addition based on Carry Speculation 基於進位預測的高準確度近似加法 Chen, Szu-Ying 陳思穎 碩士 國立交通大學 資訊科學與工程研究所 106 Approximate computing has been proposed as an approach to break through the limitations of traditional designs. Since nowadays a lot of applications can tolerate a certain degree of errors, it provides a new trade-off between computation quality and performance. In this thesis, we propose a carry truncate adder (CTA), which can achieve high performance with limited area overhead and well-controlled low error magnitude. The experimental results show that with only 23% area overhead and small loss in accuracy, CTA can achieve up to 2.17X throughput improvement compared to traditional adder. The strength of CTA in error magnitude is also demonstrated using three error-tolerant applications. Experimental results show that the approximate addition based on CTA can achieve almost the same quality of results as accurate addition. Wu, Kai-Chiang 吳凱強 2017 學位論文 ; thesis 41 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 國立交通大學 === 資訊科學與工程研究所 === 106 === Approximate computing has been proposed as an approach to break through the limitations of traditional designs. Since nowadays a lot of applications can tolerate a certain degree of errors, it provides a new trade-off between computation quality and performance. In this thesis, we propose a carry truncate adder (CTA), which can achieve high performance with limited area overhead and well-controlled low error magnitude. The experimental results show that with only 23% area overhead and small loss in accuracy, CTA can achieve up to 2.17X throughput improvement compared to traditional adder. The strength of CTA in error magnitude is also demonstrated using three error-tolerant applications. Experimental results show that the approximate addition based on CTA can achieve almost the same quality of results as accurate addition.
author2 Wu, Kai-Chiang
author_facet Wu, Kai-Chiang
Chen, Szu-Ying
陳思穎
author Chen, Szu-Ying
陳思穎
spellingShingle Chen, Szu-Ying
陳思穎
High-Accuracy Approximate Addition based on Carry Speculation
author_sort Chen, Szu-Ying
title High-Accuracy Approximate Addition based on Carry Speculation
title_short High-Accuracy Approximate Addition based on Carry Speculation
title_full High-Accuracy Approximate Addition based on Carry Speculation
title_fullStr High-Accuracy Approximate Addition based on Carry Speculation
title_full_unstemmed High-Accuracy Approximate Addition based on Carry Speculation
title_sort high-accuracy approximate addition based on carry speculation
publishDate 2017
url http://ndltd.ncl.edu.tw/handle/npzmuc
work_keys_str_mv AT chenszuying highaccuracyapproximateadditionbasedoncarryspeculation
AT chénsīyǐng highaccuracyapproximateadditionbasedoncarryspeculation
AT chenszuying jīyújìnwèiyùcèdegāozhǔnquèdùjìnshìjiāfǎ
AT chénsīyǐng jīyújìnwèiyùcèdegāozhǔnquèdùjìnshìjiāfǎ
_version_ 1719164238155481088