A Full-system, Programmable, and Extensible In-Memory Computing Simulation Framework for Deep Learning

In-memory computing (IMC) has established itself as an attractive alternative to hardware accelerators in addressing the memory wall problem for artificial intelligence (AI) workloads. However, designing programmable IMC-based computing platforms for today's large generative AI models, such as...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2025 62nd ACM/IEEE Design Automation Conference (DAC) s. 1 - 7
Hlavní autori: Zhou, Kaining, Huang, Jian, Kim, Nam Sung, Shanbhag, Naresh
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 22.06.2025
Predmet:
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract In-memory computing (IMC) has established itself as an attractive alternative to hardware accelerators in addressing the memory wall problem for artificial intelligence (AI) workloads. However, designing programmable IMC-based computing platforms for today's large generative AI models, such as large language models (LLMs) and diffusion transformers (DiTs), is hindered by the absence of a simulator that is able to address the associated scalability challenges while simultaneously incorporating device and circuit-level behaviors intrinsic to IMCs. To address this challenge, we present IMCsim, a versatile fullsystem IMC simulation framework. IMCsim integrates software runtime libraries for AI models, introduces a new set of ISA extensions to express common tensor operators, and provides flexibility in mapping these operators to various IMC architectures. As such, IMCsim enables designers to explore trade-offs between performance, energy, area, and computational accuracy for various IMC design choices. To demonstrate the functionality, efficiency, and versatility of IMCsim, we model three types of IMCs: (1) embedded non-volatile memory (eNVM)-based, (2) SRAM-based, and (3) digital IMCs. We validate IMCsim using measured data from two laboratory-tested IMC prototype ICs-a 22 nm MRAM-based IMC and a 28 nm SRAM-based IMC-and a digital IMC design in 28 nm. Next, we demonstrate the utility of IMCsim by exploring the architectural design space to obtain insights for maximizing utilization of IMC-based processors for diverse workloads-ResNet-18, Llama, and a DiT-using the three IMC types. Finally, we employ IMCsim as a design tool to obtain an efficient chip architecture and layout in 28 nm for a lightweight DiT.
AbstractList In-memory computing (IMC) has established itself as an attractive alternative to hardware accelerators in addressing the memory wall problem for artificial intelligence (AI) workloads. However, designing programmable IMC-based computing platforms for today's large generative AI models, such as large language models (LLMs) and diffusion transformers (DiTs), is hindered by the absence of a simulator that is able to address the associated scalability challenges while simultaneously incorporating device and circuit-level behaviors intrinsic to IMCs. To address this challenge, we present IMCsim, a versatile fullsystem IMC simulation framework. IMCsim integrates software runtime libraries for AI models, introduces a new set of ISA extensions to express common tensor operators, and provides flexibility in mapping these operators to various IMC architectures. As such, IMCsim enables designers to explore trade-offs between performance, energy, area, and computational accuracy for various IMC design choices. To demonstrate the functionality, efficiency, and versatility of IMCsim, we model three types of IMCs: (1) embedded non-volatile memory (eNVM)-based, (2) SRAM-based, and (3) digital IMCs. We validate IMCsim using measured data from two laboratory-tested IMC prototype ICs-a 22 nm MRAM-based IMC and a 28 nm SRAM-based IMC-and a digital IMC design in 28 nm. Next, we demonstrate the utility of IMCsim by exploring the architectural design space to obtain insights for maximizing utilization of IMC-based processors for diverse workloads-ResNet-18, Llama, and a DiT-using the three IMC types. Finally, we employ IMCsim as a design tool to obtain an efficient chip architecture and layout in 28 nm for a lightweight DiT.
Author Shanbhag, Naresh
Huang, Jian
Kim, Nam Sung
Zhou, Kaining
Author_xml – sequence: 1
  givenname: Kaining
  surname: Zhou
  fullname: Zhou, Kaining
  email: kainingz@illinois.edu
  organization: University of Illinois at Urbana-Champaign,IL,USA
– sequence: 2
  givenname: Jian
  surname: Huang
  fullname: Huang, Jian
  email: jianh@illinois.edu
  organization: University of Illinois at Urbana-Champaign,IL,USA
– sequence: 3
  givenname: Nam Sung
  surname: Kim
  fullname: Kim, Nam Sung
  email: nskim@illinois.edu
  organization: University of Illinois at Urbana-Champaign,IL,USA
– sequence: 4
  givenname: Naresh
  surname: Shanbhag
  fullname: Shanbhag, Naresh
  email: shanbhag@illinois.edu
  organization: University of Illinois at Urbana-Champaign,IL,USA
BookMark eNo1j1FLwzAUhSPog879A5H8gHXm5rZr8ji6TQcTBfV5pMvNKDbJSFt0_96C-nQ4h-8cODfsMsRAjN2DmAMI_bBaVgtUuZ5LIYsxApT5Ai_YVJdaIUIhUOTqmrkl3wxtm3Xnric_468pHpPx3tQtzbgJlq-_ewpdM3q-Ddkz-ZjOvIr-NPRNOPK3xg-t6ZsY-GYs0ldMn9zFxFdEJ74jk8KI3bIrZ9qOpn86YR-b9Xv1lO1eHrfVcpcZKHWfkYXcCQLjtCl1QUDK1nAAcLIWaJVDK11hdG0XQiI6VI5kCVYdVGkwz3HC7n53GyLan1LjTTrv_-_jD24QVZU
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC63849.2025.11132463
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331503048
EndPage 7
ExternalDocumentID 11132463
Genre orig-research
GrantInformation_xml – fundername: Defense Advanced Research Projects Agency
  funderid: 10.13039/100000185
GroupedDBID 6IE
6IH
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a179t-ed14f0e1af9a795e1e8db1c11f2b03d8f3d2f5a9bd60233f38fe271d8c87a3443
IEDL.DBID RIE
IngestDate Wed Oct 01 07:05:15 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a179t-ed14f0e1af9a795e1e8db1c11f2b03d8f3d2f5a9bd60233f38fe271d8c87a3443
PageCount 7
ParticipantIDs ieee_primary_11132463
PublicationCentury 2000
PublicationDate 2025-June-22
PublicationDateYYYYMMDD 2025-06-22
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-June-22
  day: 22
PublicationDecade 2020
PublicationTitle 2025 62nd ACM/IEEE Design Automation Conference (DAC)
PublicationTitleAbbrev DAC
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
Score 2.295424
Snippet In-memory computing (IMC) has established itself as an attractive alternative to hardware accelerators in addressing the memory wall problem for artificial...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Computational modeling
Computer architecture
Deep learning
Design tools
In-memory computing
Integrated circuit modeling
Signal to noise ratio
Software
Tensors
Transformers
Title A Full-system, Programmable, and Extensible In-Memory Computing Simulation Framework for Deep Learning
URI https://ieeexplore.ieee.org/document/11132463
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwMhECa28eBJjTW-w8FjaReWLnBs-ogm2jTxkd4aFgbTQ7dNH0b_vcBuNR48eANCIGEgw8D3zYfQLTUqU1oLAt7ehAudECVySpx3DoKC0jJyYV4fxGgkJxM1rsjqkQsDABF8Bq1QjH_5dmG24amsHWXReZbWUE2IrCRrVaxfmqh2v9vzu4kH-gnrtHadf8mmRK8xPPznfEeo8cO_w-Nvz3KM9qA4Qa6LQ7xIytzLzdAhIKvmgfvUxLqwePAR4ei-ju8L8hgwtJ-4lG3ww-Cn2bzS6sLDHSQL-zsr7gMscZVo9a2BXoaD594dqVQSiPaHaUPAUu4SoNopLVQHKEibU0OpY3mSWulSy1xHq9xm3j-nLpUOmKBWGil0ynl6iurFooAzhGWeWO4jDCdMzpkPlFTijMyZvyVKbTJ3jhphkabLMhHGdLc-F3-0X6KDYIqArGLsCtU3qy1co33zvpmtVzfRfF_ZmZ1k
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LTgMhFCVaTXSlxhrfsnBZ6sAwAyybPtLGtmliNd01DA_TRadNbY3-vcBMNS5cuANCIOFCLhfOuQeAe6xEKqRkyDh7I8pkhATLMLLOOTBshOSBC_PSZ8Mhn0zEqCSrBy6MMSaAz0zdF8Nfvl6ojX8qewiy6DSNd8FeQimJCrpWyfvFkXhoNZpuP1FPQCFJfdv9l3BK8Budo3_OeAyqPww8OPr2LSdgx-SnwDagjxhRkX255jt4bNXcs59qUOYatj8CIN3VYS9HA4-i_YSFcIMbBj7N5qVaF-xsQVnQ3Vphy5glLFOtvlbBc6c9bnZRqZOApDtOa2Q0pjYyWFohmUgMNlxnWGFsSRbFmttYE5tIkenUeejYxtwawrDmijMZUxqfgUq-yM05gDyLNHUxhmUqo8SFSiKyimfE3RO5VKm9AFW_SNNlkQpjul2fyz_a78BBdzzoT_u94eMVOPRm8TgrQq5BZb3amBuwr97Xs7fVbTDlFzZroKs
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%3Abook&rft.genre=proceeding&rft.title=2025+62nd+ACM%2FIEEE+Design+Automation+Conference+%28DAC%29&rft.atitle=A+Full-system%2C+Programmable%2C+and+Extensible+In-Memory+Computing+Simulation+Framework+for+Deep+Learning&rft.au=Zhou%2C+Kaining&rft.au=Huang%2C+Jian&rft.au=Kim%2C+Nam+Sung&rft.au=Shanbhag%2C+Naresh&rft.date=2025-06-22&rft.pub=IEEE&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FDAC63849.2025.11132463&rft.externalDocID=11132463