SplitSync: Bank Group-Level Split-Synchronization for High-Performance DRAM PIM

Processing in Memory (PIM) architectures enhance memory bandwidth by utilizing bank-level parallelism, typically implemented with a SIMD structure where all banks operate simultaneously under a single command. However, this synchronous approach requires the activation of all banks before computation...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2025 62nd ACM/IEEE Design Automation Conference (DAC) S. 1 - 7
Hauptverfasser: Yoon, Byungkuk, Han, Sanghyeok, Park, Gyeonghwan, Kim, Jae-Joon
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 22.06.2025
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Processing in Memory (PIM) architectures enhance memory bandwidth by utilizing bank-level parallelism, typically implemented with a SIMD structure where all banks operate simultaneously under a single command. However, this synchronous approach requires the activation of all banks before computation, leading to activation times that exceed computation times, limiting performance gain. Recently, asynchronous execution PIM has been proposed as an alternative, allowing banks to operate asynchronously and overlap activation with processing to hide the row activation overhead. While effective at reducing row activation overhead, the independent operation requires large shared accumulators for each bank group, increasing area overhead. To address the issues, we propose bank group (BG)-level split synchronization DRAM PIM, where each bank group operates asynchronously to hide row activation overhead while operating synchronously within the bank group to eliminate the need for shared accumulators. Evaluation results show that our proposed design achieves an average throughput improvement of 1.70 x and 1.06 x compared to conventional PIM and asynchronous execution PIM. Furthermore, the area overhead per processing unit (PU) increases by only 1.5 \% compared to conventional PIM and is significantly lower than that of asynchronous execution PIM.
AbstractList Processing in Memory (PIM) architectures enhance memory bandwidth by utilizing bank-level parallelism, typically implemented with a SIMD structure where all banks operate simultaneously under a single command. However, this synchronous approach requires the activation of all banks before computation, leading to activation times that exceed computation times, limiting performance gain. Recently, asynchronous execution PIM has been proposed as an alternative, allowing banks to operate asynchronously and overlap activation with processing to hide the row activation overhead. While effective at reducing row activation overhead, the independent operation requires large shared accumulators for each bank group, increasing area overhead. To address the issues, we propose bank group (BG)-level split synchronization DRAM PIM, where each bank group operates asynchronously to hide row activation overhead while operating synchronously within the bank group to eliminate the need for shared accumulators. Evaluation results show that our proposed design achieves an average throughput improvement of 1.70 x and 1.06 x compared to conventional PIM and asynchronous execution PIM. Furthermore, the area overhead per processing unit (PU) increases by only 1.5 \% compared to conventional PIM and is significantly lower than that of asynchronous execution PIM.
Author Kim, Jae-Joon
Yoon, Byungkuk
Han, Sanghyeok
Park, Gyeonghwan
Author_xml – sequence: 1
  givenname: Byungkuk
  surname: Yoon
  fullname: Yoon, Byungkuk
  email: bkyoon@snu.ac.kr
  organization: Seoul National University,Republic of Korea
– sequence: 2
  givenname: Sanghyeok
  surname: Han
  fullname: Han, Sanghyeok
  email: hansh778@snu.ac.kr
  organization: Seoul National University,Republic of Korea
– sequence: 3
  givenname: Gyeonghwan
  surname: Park
  fullname: Park, Gyeonghwan
  email: gyeonghwan.park@snu.ac.kr
  organization: Seoul National University,Republic of Korea
– sequence: 4
  givenname: Jae-Joon
  surname: Kim
  fullname: Kim, Jae-Joon
  email: kimjaejoon@snu.ac.kr
  organization: Seoul National University,Republic of Korea
BookMark eNo1j8tOwzAURI0ECyj9A4T8Ay6-dh42u9BCWylVKwrrynGuqUXqRCYgla8nvFYzmiONZi7IaWgDEnINfALA9c2smGZSJXoiuEiHCKRQAk7IWOdaSQkplzxR52S97Rrfb4_B3tI7E17pPLbvHSvxAxv6w9g33Mc2-E_T-zZQ10a68C97tsE4-IMJFunssVjRzXJ1Sc6cad5w_Kcj8vxw_zRdsHI9X06LkhnIdc_S2rq6slWiK2csKnCpFqDyWlWAqQYwxtlhMq8lQg0ZmGEzZrqSNuMCuRyRq99ej4i7LvqDicfd_0_5BdftTK4
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC63849.2025.11132821
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 11132821
Genre orig-research
GrantInformation_xml – fundername: Seoul National University
  funderid: 10.13039/501100002551
– fundername: IC Design Education Center
  funderid: 10.13039/501100003836
GroupedDBID 6IE
6IH
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a179t-5dcfdbcb49bface81f592187d8b1e5911aafc3280d3e1d161a331e69b3c602e03
IEDL.DBID RIE
IngestDate Wed Oct 01 07:05:15 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a179t-5dcfdbcb49bface81f592187d8b1e5911aafc3280d3e1d161a331e69b3c602e03
PageCount 7
ParticipantIDs ieee_primary_11132821
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 2.2956104
Snippet Processing in Memory (PIM) architectures enhance memory bandwidth by utilizing bank-level parallelism, typically implemented with a SIMD structure where all...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Design automation
Limiting
Memory architecture
Performance gain
Periodic structures
Random access memory
Reservoirs
Single instruction multiple data
Synchronization
Throughput
Title SplitSync: Bank Group-Level Split-Synchronization for High-Performance DRAM PIM
URI https://ieeexplore.ieee.org/document/11132821
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ1LSwMxEICDFg-eVKz4JgevabOb7G7irbYWBVsXq9BbyWMCImylbgX_vUm2tXjw4C3kQcLkMUMyXwahK5pbrZgxJOUgCVdUE82UJUJ4a12DVRZcDDZRjMdiOpXlClaPLAwAROcz6IRkfMu3c7MMV2XdGBZdBGx8uyiKBtZaUb8Jld1Br-9XEw_4SZp11pV_hU2JWmO498_-9lF7w9_h8kezHKAtqA7R48Tbi_XkqzLX-EZVbzheG5GH4PWDYxkJhfGz24atxN4gxcGRg5QbPAAPnnojXN6P2uhlePvcvyOrcAhE-V1Tk8waZ7XRXGqnDIjEZdIr6MIKnUDmDy2lnPHjpZZBYr0lpxhLIJeamZymQNkRalXzCo4RViC4o9Jq7VKe-TY2zylXhcyVszLJTlA7SGP23vx4MVsL4vSP_DO0G2QeXKjS9By16sUSLtCO-axfPxaXcZ6-ASE7lkA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ1LTwIxEIAbgyZ6UiPGtz14LXR3u0vrDUECEXAjmHAjfUwTYrIYXEz897YFJB48eGv6SJvpYybtfB2E7mhmlEy0JjEDQZikiqhEGsK5s9YVGGnAhmATjeGQTyYiX8PqgYUBgOB8BjWfDG_5Zq6X_qqsHsKic4-N76aMxdEK11pzvxEV9Xaz5dYT8wBKnNY21X8FTgl6o3P4zx6PUHVL4OH8R7ccox0oTtDzyFmM5eir0Pf4QRZvOFwckb73-8GhjPjC8N3tiq7EziTF3pWD5FtAALdfmgOc9wZV9Np5HLe6ZB0QgUi3b0qSGm2N0ooJZaUGHtlUOBXdMFxFkLpjS0qr3XipSSAyzpaTSRJBJlSiMxoDTU5RpZgXcIawBM4sFUYpG7PUtTFZRplsiExaI6L0HFW9NKbvqz8vphtBXPyRf4v2u-NBf9rvDZ8u0YGXv3eoiuMrVCkXS7hGe_qznH0sbsKcfQMjJZmH
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=SplitSync%3A+Bank+Group-Level+Split-Synchronization+for+High-Performance+DRAM+PIM&rft.au=Yoon%2C+Byungkuk&rft.au=Han%2C+Sanghyeok&rft.au=Park%2C+Gyeonghwan&rft.au=Kim%2C+Jae-Joon&rft.date=2025-06-22&rft.pub=IEEE&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FDAC63849.2025.11132821&rft.externalDocID=11132821