Detecting multi-layer layout hotspots with adaptive squish patterns. Yang, H., Pathak, P., Gennari, F., Lai, Y., & Yu, B. In Proceedings of the 24th Asia and South Pacific Design Automation Conference on - ASPDAC '19, pages 299–304, Tokyo, Japan, 2019. ACM Press. ![Detecting multi-layer layout hotspots with adaptive squish patterns [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Layout hotpot detection is one of the critical steps in modern integrated circuit design flow. It aims to find potential weak points in layouts before feeding them into manufacturing stage. Rapid development of machine learning has made it a preferable alternative of traditional hotspot detection solutions. Recent researches range from layout feature extraction and learning model design. However, only single layer layout hotspots are considered in state-of-the-art hotspot detectors and certain defects such as metal-to-via failures are not naturally supported. In this paper, we propose an adaptive squish representation for multilayer layouts, which is storage efficient, lossless and compatible with deep neural networks. We conduct experiments on 14nm industrial designs with a metal layer and its two adjacent via layers that contain metal-to-via hotspots. Results show that the adaptive squish representation can achieve satisfactory hotspot detection accuracy by incorporating a mediumsized convolutional neural networks.
@inproceedings{yang_detecting_2019,
address = {Tokyo, Japan},
title = {Detecting multi-layer layout hotspots with adaptive squish patterns},
isbn = {978-1-4503-6007-4},
url = {http://dl.acm.org/citation.cfm?doid=3287624.3288747},
doi = {10.1145/3287624.3288747},
abstract = {Layout hotpot detection is one of the critical steps in modern integrated circuit design flow. It aims to find potential weak points in layouts before feeding them into manufacturing stage. Rapid development of machine learning has made it a preferable alternative of traditional hotspot detection solutions. Recent researches range from layout feature extraction and learning model design. However, only single layer layout hotspots are considered in state-of-the-art hotspot detectors and certain defects such as metal-to-via failures are not naturally supported. In this paper, we propose an adaptive squish representation for multilayer layouts, which is storage efficient, lossless and compatible with deep neural networks. We conduct experiments on 14nm industrial designs with a metal layer and its two adjacent via layers that contain metal-to-via hotspots. Results show that the adaptive squish representation can achieve satisfactory hotspot detection accuracy by incorporating a mediumsized convolutional neural networks.},
language = {en},
urldate = {2019-02-28},
booktitle = {Proceedings of the 24th {Asia} and {South} {Pacific} {Design} {Automation} {Conference} on - {ASPDAC} '19},
publisher = {ACM Press},
author = {Yang, Haoyu and Pathak, Piyush and Gennari, Frank and Lai, Ya-Chieh and Yu, Bei},
year = {2019},
keywords = {\#broken, Jab/\#ASPDAC},
pages = {299--304},
}
Downloads: 0
{"_id":"zbgZiXiiPxAsSh4TK","bibbaseid":"yang-pathak-gennari-lai-yu-detectingmultilayerlayouthotspotswithadaptivesquishpatterns-2019","author_short":["Yang, H.","Pathak, P.","Gennari, F.","Lai, Y.","Yu, B."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Tokyo, Japan","title":"Detecting multi-layer layout hotspots with adaptive squish patterns","isbn":"978-1-4503-6007-4","url":"http://dl.acm.org/citation.cfm?doid=3287624.3288747","doi":"10.1145/3287624.3288747","abstract":"Layout hotpot detection is one of the critical steps in modern integrated circuit design flow. It aims to find potential weak points in layouts before feeding them into manufacturing stage. Rapid development of machine learning has made it a preferable alternative of traditional hotspot detection solutions. Recent researches range from layout feature extraction and learning model design. However, only single layer layout hotspots are considered in state-of-the-art hotspot detectors and certain defects such as metal-to-via failures are not naturally supported. In this paper, we propose an adaptive squish representation for multilayer layouts, which is storage efficient, lossless and compatible with deep neural networks. We conduct experiments on 14nm industrial designs with a metal layer and its two adjacent via layers that contain metal-to-via hotspots. Results show that the adaptive squish representation can achieve satisfactory hotspot detection accuracy by incorporating a mediumsized convolutional neural networks.","language":"en","urldate":"2019-02-28","booktitle":"Proceedings of the 24th Asia and South Pacific Design Automation Conference on - ASPDAC '19","publisher":"ACM Press","author":[{"propositions":[],"lastnames":["Yang"],"firstnames":["Haoyu"],"suffixes":[]},{"propositions":[],"lastnames":["Pathak"],"firstnames":["Piyush"],"suffixes":[]},{"propositions":[],"lastnames":["Gennari"],"firstnames":["Frank"],"suffixes":[]},{"propositions":[],"lastnames":["Lai"],"firstnames":["Ya-Chieh"],"suffixes":[]},{"propositions":[],"lastnames":["Yu"],"firstnames":["Bei"],"suffixes":[]}],"year":"2019","keywords":"#broken, Jab/#ASPDAC","pages":"299–304","bibtex":"@inproceedings{yang_detecting_2019,\n\taddress = {Tokyo, Japan},\n\ttitle = {Detecting multi-layer layout hotspots with adaptive squish patterns},\n\tisbn = {978-1-4503-6007-4},\n\turl = {http://dl.acm.org/citation.cfm?doid=3287624.3288747},\n\tdoi = {10.1145/3287624.3288747},\n\tabstract = {Layout hotpot detection is one of the critical steps in modern integrated circuit design flow. It aims to find potential weak points in layouts before feeding them into manufacturing stage. Rapid development of machine learning has made it a preferable alternative of traditional hotspot detection solutions. Recent researches range from layout feature extraction and learning model design. However, only single layer layout hotspots are considered in state-of-the-art hotspot detectors and certain defects such as metal-to-via failures are not naturally supported. In this paper, we propose an adaptive squish representation for multilayer layouts, which is storage efficient, lossless and compatible with deep neural networks. We conduct experiments on 14nm industrial designs with a metal layer and its two adjacent via layers that contain metal-to-via hotspots. Results show that the adaptive squish representation can achieve satisfactory hotspot detection accuracy by incorporating a mediumsized convolutional neural networks.},\n\tlanguage = {en},\n\turldate = {2019-02-28},\n\tbooktitle = {Proceedings of the 24th {Asia} and {South} {Pacific} {Design} {Automation} {Conference} on - {ASPDAC} '19},\n\tpublisher = {ACM Press},\n\tauthor = {Yang, Haoyu and Pathak, Piyush and Gennari, Frank and Lai, Ya-Chieh and Yu, Bei},\n\tyear = {2019},\n\tkeywords = {\\#broken, Jab/\\#ASPDAC},\n\tpages = {299--304},\n}\n\n\n\n","author_short":["Yang, H.","Pathak, P.","Gennari, F.","Lai, Y.","Yu, B."],"key":"yang_detecting_2019","id":"yang_detecting_2019","bibbaseid":"yang-pathak-gennari-lai-yu-detectingmultilayerlayouthotspotswithadaptivesquishpatterns-2019","role":"author","urls":{"Paper":"http://dl.acm.org/citation.cfm?doid=3287624.3288747"},"keyword":["#broken","Jab/#ASPDAC"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/bxt101","dataSources":["Wsv2bQ4jPuc7qme8R"],"keywords":["#broken","jab/#aspdac"],"search_terms":["detecting","multi","layer","layout","hotspots","adaptive","squish","patterns","yang","pathak","gennari","lai","yu"],"title":"Detecting multi-layer layout hotspots with adaptive squish patterns","year":2019}