FIST: A Feature-Importance Sampling and Tree-Based Method for Automatic Design Flow Parameter Tuning

Design flow parameters are of utmost importance to chip design quality and require a painfully long time to evaluate their effects. In reality, flow parameter tuning is usually performed manually based on designers' experience in an ad hoc manner. In this work, we introduce a machine learning-b...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the ASP-DAC ... Asia and South Pacific Design Automation Conference pp. 19 - 25
Main Authors: Xie, Zhiyao, Fang, Guan-Qi, Huang, Yu-Hung, Ren, Haoxing, Zhang, Yanqing, Khailany, Brucek, Fang, Shao-Yun, Hu, Jiang, Chen, Yiran, Barboza, Erick Carvajal
Format: Conference Proceeding
Language:English
Published: IEEE 01.01.2020
Subjects:
Integrated circuit modeling
Kernel
Random forests
Semisupervised learning
Task analysis
Tuning
Vegetation
ISSN:2153-697X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Design flow parameters are of utmost importance to chip design quality and require a painfully long time to evaluate their effects. In reality, flow parameter tuning is usually performed manually based on designers' experience in an ad hoc manner. In this work, we introduce a machine learning-based automatic parameter tuning methodology that aims to find the best design quality with a limited number of trials. Instead of merely plugging in machine learning engines, we develop clustering and approximate sampling techniques for improving tuning efficiency. The feature extraction in this method can reuse knowledge from prior designs. Furthermore, we leverage a state-of-the-art XGBoost model and propose a novel dynamic tree technique to overcome overfitting. Experimental results on benchmark circuits show that our approach achieves 25% improvement in design quality or 37% reduction in sampling cost compared to random forest method, which is the kernel of a highly cited previous work. Our approach is further validated on two industrial designs. By sampling less than 0.02% of possible parameter sets, it reduces area by 1.83% and 1.43% compared to the best solutions hand-tuned by experienced designers.
AbstractList Design flow parameters are of utmost importance to chip design quality and require a painfully long time to evaluate their effects. In reality, flow parameter tuning is usually performed manually based on designers' experience in an ad hoc manner. In this work, we introduce a machine learning-based automatic parameter tuning methodology that aims to find the best design quality with a limited number of trials. Instead of merely plugging in machine learning engines, we develop clustering and approximate sampling techniques for improving tuning efficiency. The feature extraction in this method can reuse knowledge from prior designs. Furthermore, we leverage a state-of-the-art XGBoost model and propose a novel dynamic tree technique to overcome overfitting. Experimental results on benchmark circuits show that our approach achieves 25% improvement in design quality or 37% reduction in sampling cost compared to random forest method, which is the kernel of a highly cited previous work. Our approach is further validated on two industrial designs. By sampling less than 0.02% of possible parameter sets, it reduces area by 1.83% and 1.43% compared to the best solutions hand-tuned by experienced designers.
Author Ren, Haoxing
Fang, Shao-Yun
Xie, Zhiyao
Khailany, Brucek
Hu, Jiang
Zhang, Yanqing
Fang, Guan-Qi
Barboza, Erick Carvajal
Chen, Yiran
Huang, Yu-Hung
Author_xml – sequence: 1
  givenname: Zhiyao
  surname: Xie
  fullname: Xie, Zhiyao
  organization: Duke University
– sequence: 2
  givenname: Guan-Qi
  surname: Fang
  fullname: Fang, Guan-Qi
  organization: National Taiwan University of Science and Technology
– sequence: 3
  givenname: Yu-Hung
  surname: Huang
  fullname: Huang, Yu-Hung
  organization: National Taiwan University of Science and Technology
– sequence: 4
  givenname: Haoxing
  surname: Ren
  fullname: Ren, Haoxing
  organization: Nvidia Corporation
– sequence: 5
  givenname: Yanqing
  surname: Zhang
  fullname: Zhang, Yanqing
  organization: Nvidia Corporation
– sequence: 6
  givenname: Brucek
  surname: Khailany
  fullname: Khailany, Brucek
  organization: Nvidia Corporation
– sequence: 7
  givenname: Shao-Yun
  surname: Fang
  fullname: Fang, Shao-Yun
  organization: National Taiwan University of Science and Technology
– sequence: 8
  givenname: Jiang
  surname: Hu
  fullname: Hu, Jiang
  organization: Texas A&M University
– sequence: 9
  givenname: Yiran
  surname: Chen
  fullname: Chen, Yiran
  organization: Duke University
– sequence: 10
  givenname: Erick Carvajal
  surname: Barboza
  fullname: Barboza, Erick Carvajal
  organization: Texas A&M University
BookMark eNotkMFKw0AURUdRsK39AjfjB6TOe8nMNO5iazRQsdAI7spL8lojTVImU8S_N2Dv5qzu4XLH4qrtWhbiHtQMQMUPyWYdLJNFZK02M1SoZrGKNCq4EGOwOIcIMFSXYoSgw8DE9vNGTPv-Ww3RCi2okajSbJM_ykSmTP7kOMiaY-c8tSXLDTXHQ93uJbWVzB1z8EQ9V_KN_VdXyV3nZHLyXUO-LuWS-3rfyvTQ_cg1OWrYs5P5qR0Et-J6R4eep2dOxEf6nC9eg9X7S7ZIVgFhrH1QmjmXwHM0w7TKGChVhcxYmlhbIFVYU-AOiwrYYAG6tIYYIuKCMBpa4UTc_XtrZt4eXd2Q-92eTwn_AO-CWLU
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ASP-DAC47756.2020.9045201
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISBN 1728141230
9781728141237
EISSN 2153-697X
EndPage 25
ExternalDocumentID 9045201
Genre orig-research
GroupedDBID 5VS
6IE
6IF
6IL
6IN
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
APO
AVWKF
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
I07
IEGSK
M43
OCL
RIE
RIL
ID FETCH-LOGICAL-a295t-c68ec1e826710d661c0d2ee2c69571a0b76b2f2bd1e62b15c76ae14aeba248263
IEDL.DBID RIE
ISICitedReferencesCount 31
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001235809500008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 05:55:40 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a295t-c68ec1e826710d661c0d2ee2c69571a0b76b2f2bd1e62b15c76ae14aeba248263
PageCount 7
ParticipantIDs ieee_primary_9045201
PublicationCentury 2000
PublicationDate 2020-Jan.
PublicationDateYYYYMMDD 2020-01-01
PublicationDate_xml – month: 01
  year: 2020
  text: 2020-Jan.
PublicationDecade 2020
PublicationTitle Proceedings of the ASP-DAC ... Asia and South Pacific Design Automation Conference
PublicationTitleAbbrev ASP-DAC
PublicationYear 2020
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000502710
ssib055574204
Score 1.9610631
Snippet Design flow parameters are of utmost importance to chip design quality and require a painfully long time to evaluate their effects. In reality, flow parameter...
SourceID ieee
SourceType Publisher
StartPage 19
SubjectTerms Integrated circuit modeling
Kernel
Random forests
Semisupervised learning
Task analysis
Tuning
Vegetation
Title FIST: A Feature-Importance Sampling and Tree-Based Method for Automatic Design Flow Parameter Tuning
URI https://ieeexplore.ieee.org/document/9045201
WOSCitedRecordID wos001235809500008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NT8IwFG-QGKMXFDB-pyYeLXRduzJvCBI5SEjAhBvpx8OY6DDI9N-3LQM18eJtWbJ2eW99X_u930PoygoKnoWFONsvCI9nmihrqDOGjCodm5gzFYZNyMGgNZmkwxK63vTCAEAAn0HDX4Z_-XZucl8qa6ae_9s3a21Jmax6tdbfjhDCJXlFarHi9XYJV0R30GVBq9lsj4ak2-5wKYXHJjDaKNb7NVgl-JVe5X9vtI_q3w16eLhxPQeoBFkVVdYTGnBxYKto7wfdYA3ZXn80vsFt7OO-fAGk_xqib7_aSHloefaEVWbxeAFAbp1_s_ghTJjGLrTF7Xw5DwSvuBtgH7j3Mv_EQ-XhXX7Xce5rLHX02Lsbd-5JMWWBKJaKJTFJC0wELs1w4rJOZYZaBsBMkgoZKaplotmMaRtBwnQkjEwURFyBVoy7p-JDVM7mGRwhLFKaaBdAWC44B2capGxxSGdUM23sLDlGNS_C6duKSGNaSO_k79unaNdraVXvOEPl5SKHc7RtPpbP74uLoP0vMMStCg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1ZS8NAEB5ExeOlHhVvV_DRtZvtbtL4Vo9isS2FRvCt7DEVQVOpjf59d7fxAl98C4Fswsxmrp35PoATKxl6FBbqbL-koj7SVFnDnDHkTOm6qQuuAtlE0us17u_T_hycfs3CIGJoPsMzfxnO8u3YFL5UVks9_rcf1lqQQnA2m9b63D1SSpfmlcnFDNnbpVwRW4LjEliz1hz06VXzUiSJ9N0JnJ2VK_6iVgmepVX53zetQfV7RI_0v5zPOsxhvgGVT44GUv6yG7D6A3BwE2yrPcjOSZP4yK-YIG0_h_jbrzZQvrk8fyAqtySbINIL5-Es6QaOaeKCW9IspuMA8UquQuMHaT2N30lf-QYv_9as8FWWKty1rrPLG1ryLFDFUzmlJm6gidAlGk5c1inNMMsRuYlTmUSK6STWfMS1jTDmOpImiRVGQqFWXLin6lswn49z3AYiUxZrF0JY4TSEzjgkSUNgOmKaa2NH8Q5sehEOX2ZQGsNSert_3z6C5Zus2xl22r3bPVjxGptVP_Zhfjop8AAWzdv08XVyGHbCB2DrsFE
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+of+the+ASP-DAC+...+Asia+and+South+Pacific+Design+Automation+Conference&rft.atitle=FIST%3A+A+Feature-Importance+Sampling+and+Tree-Based+Method+for+Automatic+Design+Flow+Parameter+Tuning&rft.au=Xie%2C+Zhiyao&rft.au=Fang%2C+Guan-Qi&rft.au=Huang%2C+Yu-Hung&rft.au=Ren%2C+Haoxing&rft.date=2020-01-01&rft.pub=IEEE&rft.eissn=2153-697X&rft.spage=19&rft.epage=25&rft_id=info:doi/10.1109%2FASP-DAC47756.2020.9045201&rft.externalDocID=9045201