[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121185-en":3,"doc-seo-121185-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121185,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Machine Learning Techniques for Early Identification of Timing Critical Flip-Flops in Digital IC Designs - A Thesis","Timing criticality of flip-flops directly affects combinational circuit timing optimization and clock network power reduction, and these steps are commonly executed before CTS and routing. Since CTS/routing can change timing criticality, optimizing only from pre-CTS critical paths may lead to incorrect decisions. This thesis studies machine learning approaches that identify post-routing timing-critical flip-flops early, using training data from vendor synthesis-flow tools, and evaluates multiple ML engines. Experiments report 99.7% accuracy, 0.98 AUROC, and average speedups of 62,000x–73,000x compared with CTS/routing estimation.","MACHINE LEARNING TECHNIQUES FOR EARLY IDENTIFICATION OF TIMING CRITICAL FLIP-FLOPS IN DIGITAL IC DESIGNS  \nA Thesis  \nby  \nCHUNKAI FU  \nSubmitted to the Graduate and Professional School of  \nTexas A&M University  \nin partial fulfillment of the requirements for the degree of MASTER OF SCIENCE  \nChair of Committee, Jiang Hu Committee Members, Anxiao Jiang  \nDuncan Walker  \nWeiping Shi  \nHead of Department, Scott Schaefer  \nDecember 2023  \nMajor Subject: Computer Science  \nCopyright 2023 Chunkai Fu  \nABSTRACT  \nThe timing criticality of flip-flops is a key factor for combinational circuit timing optimization and clock network power reduction, both of which are often performed prior to CTS (Clock Tree Synthesis) and routing. However, timing criticality is often changed by CTS/routing and therefore optimizations according to pre-CTS criticality may deviate from the correct directions.  \nThis work investigates machine learning techniques for pre-CTS identification of post-routing timing critical flip-flops. The training data will be extracted from vendor tools used for the synthesis flow and different types of machine learning engines will be evaluated and compared.  \nResults show that the ML-based early identification can achieve 99 .7% accuracy and 0 .98 area under ROC (Receiver Operating Characteristic) curve, and is 62000 × to 73000 × faster than the estimate with CTS and routing flow on average.  \nDEDICATION  \nTo my wife Yang Chen.  \nACKNOWLEDGMENTS  \nAs a graduate student who is pursuing another graduate degree with little background in Computer Science, I would like to express my sincere gratitude to my advisor Dr. Jiang Hu, who has been an extraordinary mentor during my study. He always went extra miles to tutor me in my interested field of research as well as sparing no efforts in helping me build my career.  \nI would like to thank Dr. Botacin and the Department of Computer Science and Engineering for the scholarship and assistantship opportunities throughout my study, which has greatly helped me to complete my degree.  \nI would like to thank my wife Yang Chen who has always been supportive of my career, who has been through the ups and downs with me no matter what, who has been taking care of our family.  \nCONTRIBUTORS AND FUNDING SOURCES  \nContributors  \nThis work was supported by a thesis committee consisting of Dr. Anxiao Jiang and Dr. Duncan Walker from the Department of Computer Science & Engineering, and Dr. Weiping Shi from the Electrical and Computer Engineering.  \nThe synthesis workflow scripts were partially contributed by Dr. Rongjian Liang.  \nAll other work conducted for the thesis (or) dissertation was completed by the student independently.  \nFunding Sources  \nThis work is partially supported by Semiconductor Research Corporation GRC-CADT 3103 .001/3104.001 and National Science Foundation CCF-2106725/2106828, and by the Department of Computer Science & Engineering at Texas A&M University through assistantship and scholarship.  \nNOMENCLATURE  \nCTS  \nROC  \nML  \nGNN  \nTP  \nθ  \nTPR  \nFPR  \nAUROC  \nMLP  \nXGBoost  \nGAT  \nVLSI  \nDFF  \nCL  \nClock Tree Synthesis  \nReceiver Operating Characteristic Machine Learning  \nGraph Neural Network True Positive  \nSlack threshold  \nTrue Positive Rate  \nFalse Positive Rate  \nArea Under the ROC curve  \nMulti-Layer Perceptron Extreme Gradient Boost  \nGraph Attention Network Very Large Scale Integration D Flip-Flop Combinational Logic  \nTABLE OF CONTENTS  \nPage  \nABSTRACT ......................................................................................... ii  \nDEDICATION ....................................................................................... iii  \nACKNOWLEDGMENTS .......................................................................... iv  \nCONTRIBUTORS AND FUNDING SOURCES ................................................. v  \n[NOMENCLATURE ................................................................................. vi](NOMENCLATURE .........................","cbCaigPuAyjRyOPe","https://ap.wps.com/l/cbCaigPuAyjRyOPe","pdf",875101,1,49,"English","en",105,"# Abstract\n# Dedication\n# Acknowledgments\n# Contributors and Funding Sources\n# Nomenclature\n# Table of Contents\n# List of Figures\n# List of Tables\n# 1. Introduction and Literature Review\n## 1.1 Introduction\n## 1.2 Challenges in modern VLSI\n## 1.3 Literature Review\n# 2. Problem Formulation\n## 2.1 Problem Statement\n## 2.2 Performance Metrics","[{\"question\":\"Why can pre-CTS timing criticality lead to suboptimal optimization decisions?\",\"answer\":\"Timing criticality of flip-flops can change after CTS and routing, so optimizations based on pre-CTS results may deviate from the true post-routing critical behavior.\"},{\"question\":\"How does this thesis enable early identification of post-routing timing-critical flip-flops?\",\"answer\":\"It investigates machine learning techniques using training data extracted from vendor tools in the synthesis flow, then evaluates different ML engines for the identification task.\"},{\"question\":\"What performance results does the ML-based approach achieve compared with CTS and routing estimation?\",\"answer\":\"The results show 99.7% accuracy and 0.98 AUROC, with an average speedup of about 62,000x to 73,000x versus estimation using CTS and routing.\"}]","Machine Learning Techniques for Early Identification of Timing Critical Flip-Flops in Digital IC Designs - A Thesis | PDF",1785734254,123,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-techniques-for-early-identification-of-timing-critical-flip-flops-in-digital-ic-designs-a-thesis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-techniques-for-early-identification-of-timing-critical-flip-flops-in-digital-ic-designs-a-thesis/121185/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why can pre-CTS timing criticality lead to suboptimal optimization decisions?","Question",{"text":75,"@type":76},"Timing criticality of flip-flops can change after CTS and routing, so optimizations based on pre-CTS results may deviate from the true post-routing critical behavior.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does this thesis enable early identification of post-routing timing-critical flip-flops?",{"text":80,"@type":76},"It investigates machine learning techniques using training data extracted from vendor tools in the synthesis flow, then evaluates different ML engines for the identification task.",{"name":82,"@type":73,"acceptedAnswer":83},"What performance results does the ML-based approach achieve compared with CTS and routing estimation?",{"text":84,"@type":76},"The results show 99.7% accuracy and 0.98 AUROC, with an average speedup of about 62,000x to 73,000x versus estimation using CTS and routing.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]