MUGNoC A Software-Configured Multicast-Unicast-Gather NoC for Accelerating CNN Dataflows
Current communication infrastructures for convolutional neural networks (CNNs) only focus on specific transmission patterns, not applicable to benefit the whole system if the dataflow changes or different dataflows run in one system. To reduce data movement, various CNN dataflows are presented. For...
Uloženo v:
| Vydáno v: | 2023 28th Asia and South Pacific Design Automation Conference (ASP-DAC) s. 308 - 313 |
|---|---|
| Hlavní autoři: | , , , , , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
New York, NY, USA
ACM
16.01.2023
|
| Edice: | ACM Conferences |
| Témata: | |
| ISBN: | 9781450397834, 1450397832 |
| ISSN: | 2153-697X |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Current communication infrastructures for convolutional neural networks (CNNs) only focus on specific transmission patterns, not applicable to benefit the whole system if the dataflow changes or different dataflows run in one system. To reduce data movement, various CNN dataflows are presented. For these dataflows, parameters and results are delivered using different traffic patterns, i.e., multicast, unicast, and gather, preventing dataflow-specific communication backbones from benefiting the entire system if the dataflow changes or different dataflows run in the same system. Thus, in this paper, we propose MUG-NoC to support typical traffic patterns and accelerate them, therefore boosting multiple dataflows. Specifically, (i) we for the first time support multicast in 2D-mesh software configurable NoC by revising router configuration and proposing the efficient multicast routing; (ii) we decrease unicast latency by transmitting data through the different routes in parallel; (iii) we reduce output gather overheads by pipelining basic dataflow units. Experiments show that at least our proposed design can reduce 39.2% total data transmission time compared with the state-of-the-art CNN communication backbone. |
|---|---|
| AbstractList | Current communication infrastructures for convolutional neural networks (CNNs) only focus on specific transmission patterns, not applicable to benefit the whole system if the dataflow changes or different dataflows run in one system. To reduce data movement, various CNN dataflows are presented. For these dataflows, param-eters and results are delivered using different traffic patterns, i.e., multicast, unicast, and gather, preventing dataflow-specific commu-nication backbones from benefiting the entire system if the dataflow changes or different dataflows run in the same system. Thus, in this paper, we propose MUG-NoC to support typical traffic patterns and accelerate them, therefore boosting multiple dataflows. Specifically, (i) we for the first time support multicast in 2D-mesh software configurable NoC by revising router configuration and proposing the efficient multicast routing; (ii) we decrease unicast latency by transmitting data through the different routes in parallel; (iii) we reduce output gather overheads by pipelining basic dataflow units. Experiments show that at least our proposed design can reduce 39.2% total data transmission time compared with the state-of-the-art CNN communication backbone. Current communication infrastructures for convolutional neural networks (CNNs) only focus on specific transmission patterns, not applicable to benefit the whole system if the dataflow changes or different dataflows run in one system. To reduce data movement, various CNN dataflows are presented. For these dataflows, parameters and results are delivered using different traffic patterns, i.e., multicast, unicast, and gather, preventing dataflow-specific communication backbones from benefiting the entire system if the dataflow changes or different dataflows run in the same system. Thus, in this paper, we propose MUG-NoC to support typical traffic patterns and accelerate them, therefore boosting multiple dataflows. Specifically, (i) we for the first time support multicast in 2D-mesh software configurable NoC by revising router configuration and proposing the efficient multicast routing; (ii) we decrease unicast latency by transmitting data through the different routes in parallel; (iii) we reduce output gather overheads by pipelining basic dataflow units. Experiments show that at least our proposed design can reduce 39.2% total data transmission time compared with the state-of-the-art CNN communication backbone. |
| Author | Luo, Xiangzhong Li, Shiqing Liu, Di Chen, Hui Liu, Weichen Huai, Shuo |
| Author_xml | – sequence: 1 givenname: Hui surname: Chen fullname: Chen, Hui email: hui.chen@ntu.edu.sg organization: Nanyang Technological University, Singapore – sequence: 2 givenname: Di surname: Liu fullname: Liu, Di email: liu.di@ntu.edu.sg organization: Nanyang Technological University, Singapore – sequence: 3 givenname: Shiqing surname: Li fullname: Li, Shiqing email: shiqing.li@ntu.edu.sg organization: Nanyang Technological University, Singapore – sequence: 4 givenname: Shuo surname: Huai fullname: Huai, Shuo email: shuo.huai@ntu.edu.sg organization: Nanyang Technological University, Singapore – sequence: 5 givenname: Xiangzhong surname: Luo fullname: Luo, Xiangzhong email: xiangzho001@ntu.edu.sg organization: Nanyang Technological University, Singapore – sequence: 6 givenname: Weichen surname: Liu fullname: Liu, Weichen email: liu@ntu.edu.sg organization: Nanyang Technological University, Singapore |
| BookMark | eNqNj7tOw0AQRZenEoJrGj6AxmZ2Z18ukRVCpAANkehW-xhLBhIjm4a_Z1FcUVGd4lyN5lyw032_J8auOFScS3WLSmuoTZVprNRHrKiNzQIwE-UxmwuusNS1eT3542asGMc3ABDWAHCcs_PH7eqpby7ZWes_RiomLtj2fvnSPJSb59W6uduUXkj7VQYRVYpWgdSRkzUiJSKBbesDjwZUUvkpoT3VSRGmGDBqEyVG5WXIU1yw68Pdjojc59Dt_PDtOICUVpusbw7ax50Lff8-Zud-q91U7abqPK3-OXVh6KjFH7mbUho |
| ContentType | Conference Proceeding |
| Copyright | 2023 ACM |
| Copyright_xml | – notice: 2023 ACM |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1145/3566097.3567846 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Xplore POP ALL IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library (IEL) (UW System Shared) 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 | 9781450397834 1450397832 |
| EISSN | 2153-697X |
| EndPage | 313 |
| ExternalDocumentID | 10044867 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IF 6IL 6IN AAWTH ABLEC ACM ALMA_UNASSIGNED_HOLDINGS APO BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK IEGSK LHSKQ OCL RIE RIL |
| ID | FETCH-LOGICAL-a248t-b2c5dc85046c1e872ddee23ffab1c705d535626ae9d5e3dcb3c67c43c5a4bdee3 |
| IEDL.DBID | RIE |
| ISBN | 9781450397834 1450397832 |
| ISICitedReferencesCount | 4 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000981940000054&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 02:14:16 EDT 2025 Thu Jul 10 05:53:01 EDT 2025 Thu Jul 10 05:53:00 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | false |
| Keywords | parallel multipath transmission CNN dataflow network-on-chips |
| Language | English |
| License | Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from Permissions@acm.org |
| LinkModel | DirectLink |
| MeetingName | ASPDAC '23: 28th Asia and South Pacific Design Automation Conference |
| MergedId | FETCHMERGED-LOGICAL-a248t-b2c5dc85046c1e872ddee23ffab1c705d535626ae9d5e3dcb3c67c43c5a4bdee3 |
| PageCount | 6 |
| ParticipantIDs | acm_books_10_1145_3566097_3567846 acm_books_10_1145_3566097_3567846_brief ieee_primary_10044867 |
| PublicationCentury | 2000 |
| PublicationDate | 20230116 2023-Jan.-16 |
| PublicationDateYYYYMMDD | 2023-01-16 |
| PublicationDate_xml | – month: 01 year: 2023 text: 20230116 day: 16 |
| PublicationDecade | 2020 |
| PublicationPlace | New York, NY, USA |
| PublicationPlace_xml | – name: New York, NY, USA |
| PublicationSeriesTitle | ACM Conferences |
| PublicationTitle | 2023 28th Asia and South Pacific Design Automation Conference (ASP-DAC) |
| PublicationTitleAbbrev | ASP-DAC |
| PublicationYear | 2023 |
| Publisher | ACM |
| Publisher_xml | – name: ACM |
| SSID | ssj0002870013 ssj0000502710 |
| Score | 1.848405 |
| Snippet | Current communication infrastructures for convolutional neural networks (CNNs) only focus on specific transmission patterns, not applicable to benefit the... |
| SourceID | ieee acm |
| SourceType | Publisher |
| StartPage | 308 |
| SubjectTerms | Boosting CNN Dataflow Design automation Network-on-chips Networks Networks -- Network algorithms Networks -- Network algorithms -- Control path algorithms Networks -- Network algorithms -- Control path algorithms -- Network control algorithms Networks -- Network architectures Networks -- Network architectures -- Network design principles Networks -- Network components Networks -- Network protocols Networks -- Network protocols -- Network layer protocols Networks -- Network services Networks -- Network services -- Programmable networks Networks -- Network types Networks -- Network types -- Packet-switching networks Parallel multipath transmission Routing Software System performance Traffic control Unicast |
| Subtitle | A Software-Configured Multicast-Unicast-Gather NoC for Accelerating CNN Dataflows |
| Title | MUGNoC |
| URI | https://ieeexplore.ieee.org/document/10044867 |
| WOSCitedRecordID | wos000981940000054&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/eLvHCXMwlV3Pb9MwFH6iEwe4DEYR3RgyEhInb0kc1w63qWPjANEkKBqnyHl-nopEOqXt9u_z7GYDDghxchQ5UuLP8fthf-8DeOOwUiV5JUNWFbJEFaSzliRRi6UOaPKksfT1o6lre3lZXQxk9cSFIaJ0-IyO4mXay_dL3MRU2XGqbmanZgQjY8yWrHWfUMk0R1iDLfueskZxS1UN5XzyUh8rdl2yyhxxa2z0eEcOf_yhqpKMytnuf77OExj_oueJi3vD8xQeULcHu3f6DGL4Xffg8W_FBp_Bt0_z83o5eydOxGdee29dT5KD4bC42vTkRWLiolut5bzbtufJORT8jGDPVpwgsomKE6a7ErO6FqcuSv8ub1djmJ-9_zL7IAdhBemK0q5lW6D2aDXHxpiTNQWvcVSoEFybo8m01zxExdRR5TUpj63CqcFSoXZly13Vc9jplh29AMGfz1DnzriCsS1sW1W-DZQFT-xYoJrAax7kJkYMq2ZLgtbNAEQzADGBt__s07T9gsIExhGG5npbiaO5Q2D_L_cP4FGUh48pk3z6EnbW_YYO4SHerBer_lWaPz8Ba6_A6w |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3Pb9MwFH5iAwm4DEYnChsYCYmTt8SOa2e3qWMboosmsaJxipzn56lIpCht2b-P7WYDDghxchQ5UuLP8fthf-8DeGuxlAU5yX1WCl6g9NwaQ5yowUJ51HnSWPo80VVlrq7Ki56snrgwRJQOn9F-vEx7-W6Oq5gqO0jVzcxIb8B9VRQiX9O17lIqmQoxVm_Nvqa8UdxUlX1Bn7xQBzI4L1mp90OrTfR5Nyx--0NXJZmVk63_fKEnMPhF0GMXd6bnKdyjdhu2bhUaWP_DbsPj38oNPoMv59PTaj4-ZEfsU1h9b2xHPITDfna96sixxMVFu1jyabtuT5N7yMIzLPi27AgxGKk4ZdprNq4qdmyj-O_8ZjGA6cn7y_EZ76UVuBWFWfJGoHJoVIiOMSejRVjlSEjvbZOjzpRTYYjEyFLpFEmHjcSRxkKiskUTusod2GznLT0HFj4_gJ1bbUVAV5imLF3jKfOOgmuBcghvwiDXMWZY1GsatKp7IOoeiCG8-2efuulm5IcwiDDU39e1OOpbBF785f5reHh2eT6pJx-qjy_hURSLjwmUfLQLm8tuRXvwAH8sZ4vuVZpLPwGkQcQy |
| 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=2023+28th+Asia+and+South+Pacific+Design+Automation+Conference+%28ASP-DAC%29&rft.atitle=MUGNoC%3A+A+Software-configured+Multicast-Unicast-Gather+NoC+for+Accelerating+CNN+Dataflows&rft.au=Chen%2C+Hui&rft.au=Liu%2C+Di&rft.au=Li%2C+Shiqing&rft.au=Huai%2C+Shuo&rft.date=2023-01-16&rft.pub=ACM&rft.eissn=2153-697X&rft.spage=308&rft.epage=313&rft_id=info:doi/10.1145%2F3566097.3567846&rft.externalDocID=10044867 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781450397834/lc.gif&client=summon&freeimage=true |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781450397834/mc.gif&client=summon&freeimage=true |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781450397834/sc.gif&client=summon&freeimage=true |