Machine-Learning Based Failure Binning for Debugging RTL Designs
碩士 === 國立交通大學 === 電機工程學系 === 106 === Verification and debugging have become the major pain-point in Register Transfer Level (RTL) design as design size and complexity increase. If there is a functional bug in RTL design, numerous and diverse failures would be exposed in the regression test. To diagn...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2017
|
Online Access: | http://ndltd.ncl.edu.tw/handle/8emha2 |
id |
ndltd-TW-106NCTU5442022 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-106NCTU54420222019-05-16T00:08:12Z http://ndltd.ncl.edu.tw/handle/8emha2 Machine-Learning Based Failure Binning for Debugging RTL Designs 適用於暫存器轉移層設計除錯之以機器學習為基礎的錯誤分流技術 Hsu, Chia-Hao 許家豪 碩士 國立交通大學 電機工程學系 106 Verification and debugging have become the major pain-point in Register Transfer Level (RTL) design as design size and complexity increase. If there is a functional bug in RTL design, numerous and diverse failures would be exposed in the regression test. To diagnose and fix design errors more efficiently, categorizing and prioritizing these failures is necessary. In this work, a machine learning based failure binning engine is proposed. First, the engine will collect failures from testbench simulation, and then try to explore suspect elements by SAT-based debugging technique. Next, a suspect data weighting scheme is defined to represent failures by a feature-based matrix. Finally, an advanced machine learning based clustering algorithm is applied to obtain the failure bins with respective confidence rank. Experimental results show the failure binning engine demonstrates an overall accuracy of 90% that obtains high-quality bins with the accurate confidence ranking. Wen, Hung-Pin 温宏斌 2017 學位論文 ; thesis 39 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立交通大學 === 電機工程學系 === 106 === Verification and debugging have become the major pain-point in Register Transfer Level (RTL) design as design size and complexity increase. If there is a functional bug in RTL design, numerous and diverse failures would be exposed in the regression test. To diagnose and fix design errors more efficiently, categorizing and prioritizing these failures is necessary. In this work, a machine learning based failure binning engine is proposed. First, the engine will collect failures from testbench simulation, and then try to explore suspect elements by SAT-based debugging technique. Next, a suspect data weighting scheme is defined to represent failures by a feature-based matrix. Finally, an advanced machine learning based clustering algorithm is applied to obtain the failure bins with respective confidence rank. Experimental results show the failure binning engine demonstrates an overall accuracy of 90% that obtains high-quality bins with the accurate confidence ranking.
|
author2 |
Wen, Hung-Pin |
author_facet |
Wen, Hung-Pin Hsu, Chia-Hao 許家豪 |
author |
Hsu, Chia-Hao 許家豪 |
spellingShingle |
Hsu, Chia-Hao 許家豪 Machine-Learning Based Failure Binning for Debugging RTL Designs |
author_sort |
Hsu, Chia-Hao |
title |
Machine-Learning Based Failure Binning for Debugging RTL Designs |
title_short |
Machine-Learning Based Failure Binning for Debugging RTL Designs |
title_full |
Machine-Learning Based Failure Binning for Debugging RTL Designs |
title_fullStr |
Machine-Learning Based Failure Binning for Debugging RTL Designs |
title_full_unstemmed |
Machine-Learning Based Failure Binning for Debugging RTL Designs |
title_sort |
machine-learning based failure binning for debugging rtl designs |
publishDate |
2017 |
url |
http://ndltd.ncl.edu.tw/handle/8emha2 |
work_keys_str_mv |
AT hsuchiahao machinelearningbasedfailurebinningfordebuggingrtldesigns AT xǔjiāháo machinelearningbasedfailurebinningfordebuggingrtldesigns AT hsuchiahao shìyòngyúzàncúnqìzhuǎnyícéngshèjìchúcuòzhīyǐjīqìxuéxíwèijīchǔdecuòwùfēnliújìshù AT xǔjiāháo shìyòngyúzàncúnqìzhuǎnyícéngshèjìchúcuòzhīyǐjīqìxuéxíwèijīchǔdecuòwùfēnliújìshù |
_version_ |
1719161799089061888 |