Reconfigurable Dataflow Optimization for Spatiotemporal Spiking Neural Computation on Systolic Array Accelerators
Spiking neural networks (SNNs) offer a promising biologically-plausible computing model and lend themselves to ultra-low-power event-driven processing on neuromorphic processors. Compared with the conventional artificial neural networks, SNNs are well-suited for processing complex spatiotemporal dat...
Uloženo v:
| Vydáno v: | Proceedings - IEEE International Conference on Computer Design s. 57 - 64 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
01.10.2020
|
| Témata: | |
| ISSN: | 2576-6996 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Spiking neural networks (SNNs) offer a promising biologically-plausible computing model and lend themselves to ultra-low-power event-driven processing on neuromorphic processors. Compared with the conventional artificial neural networks, SNNs are well-suited for processing complex spatiotemporal data. Despite its significance, dataflow optimization of spiking neural accelerator architectures has not been extensively studied. Recognizing the need for efficient processing of complex spatiotemporal data while considering the all-or-none nature of spiking activities, we propose holistic reconfigurable dataflow optimization for systolic array acceleration of spiking convolutional networks (S-CNNs). A novel scheme is introduced for parallel acceleration of computation across multiple time points, which further allows for systemic optimization of variable tiling for a large performance and efficiency gains. We show how variable tiling, in particular, the positioning of the temporal dimension, can be targeted to optimize data movement, throughput, and energy efficiency. Furthermore, we explore joint layer-dependent dataflow and accelerator hardware optimization to further boost performance and energy efficiency. To support systemic design space exploration, we develop an SNN dataflow simulator capable of analyzing the throughput and energy dissipation of systolic array accelerators for any targeted S-CNN while considering the inherent spatiotemporal characteristics of spiking neural computation. The proposed techniques deliver orders of magnitude of improvements on throughput, energy efficiency, and delay-energy product for accelerating deep Alexnet and VGG-16 SNNs. |
|---|---|
| AbstractList | Spiking neural networks (SNNs) offer a promising biologically-plausible computing model and lend themselves to ultra-low-power event-driven processing on neuromorphic processors. Compared with the conventional artificial neural networks, SNNs are well-suited for processing complex spatiotemporal data. Despite its significance, dataflow optimization of spiking neural accelerator architectures has not been extensively studied. Recognizing the need for efficient processing of complex spatiotemporal data while considering the all-or-none nature of spiking activities, we propose holistic reconfigurable dataflow optimization for systolic array acceleration of spiking convolutional networks (S-CNNs). A novel scheme is introduced for parallel acceleration of computation across multiple time points, which further allows for systemic optimization of variable tiling for a large performance and efficiency gains. We show how variable tiling, in particular, the positioning of the temporal dimension, can be targeted to optimize data movement, throughput, and energy efficiency. Furthermore, we explore joint layer-dependent dataflow and accelerator hardware optimization to further boost performance and energy efficiency. To support systemic design space exploration, we develop an SNN dataflow simulator capable of analyzing the throughput and energy dissipation of systolic array accelerators for any targeted S-CNN while considering the inherent spatiotemporal characteristics of spiking neural computation. The proposed techniques deliver orders of magnitude of improvements on throughput, energy efficiency, and delay-energy product for accelerating deep Alexnet and VGG-16 SNNs. |
| Author | Lee, Jeong-Jun Li, Peng |
| Author_xml | – sequence: 1 givenname: Jeong-Jun surname: Lee fullname: Lee, Jeong-Jun email: jeong-jun@ucsb.edu organization: Electrical and Computer Engineering, University of California,Santa Barbara,CA,USA – sequence: 2 givenname: Peng surname: Li fullname: Li, Peng email: lip@ucsb.edu organization: Electrical and Computer Engineering, University of California,Santa Barbara,CA,USA |
| BookMark | eNotT1FLwzAYjKLgNv0F-pA_0PklWZL2cXROB8OB0-eRtl9GtG1qmiHz19sx4eDu4O7gxuSq9S0S8sBgyhhkj6s8X0gQWk85cJgCANcXZMw0T1mmGcwuyYhLrRKVZeqGjPv-c8ikgukR-X7D0rfW7Q_BFDXShYnG1v6HbrroGvdrovMttT7QbXfSEZvOB1MP1n25dk9f8XCyuW-6QzynB2yPffS1K-k8BHOk87LEGoOJPvS35Nqause7f56Qj-XTe_6SrDfPq3y-ThwHEZOKD53UaAuyAAQttExBcpMN55StFFOAUgksGSsL0KawaVbNUAvDVGVsKSbk_rzrEHHXBdeYcNxlPBVyJsQfRPdeyQ |
| CODEN | IEEPAD |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/ICCD50377.2020.00027 |
| 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 |
| Discipline | Engineering |
| EISBN | 1728197104 9781728197104 |
| EISSN | 2576-6996 |
| EndPage | 64 |
| ExternalDocumentID | 9283543 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Science Foundation grantid: 1948201,1940761 funderid: 10.13039/501100001809 |
| GroupedDBID | -~X 29F 29O 6IE 6IF 6IH 6IK 6IL 6IM 6IN AAJGR AAWTH ACGFS ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IPLJI M43 OCL RIE RIL RIO RNS |
| ID | FETCH-LOGICAL-i203t-d2cce8a7f05b0e073758052a90276fd6160e563ec11cb07abf89d4e73a16dafc3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 15 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000652198500015&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 02:32:57 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i203t-d2cce8a7f05b0e073758052a90276fd6160e563ec11cb07abf89d4e73a16dafc3 |
| PageCount | 8 |
| ParticipantIDs | ieee_primary_9283543 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-Oct. |
| PublicationDateYYYYMMDD | 2020-10-01 |
| PublicationDate_xml | – month: 10 year: 2020 text: 2020-Oct. |
| PublicationDecade | 2020 |
| PublicationTitle | Proceedings - IEEE International Conference on Computer Design |
| PublicationTitleAbbrev | ICCD |
| PublicationYear | 2020 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0008317 |
| Score | 2.2189248 |
| Snippet | Spiking neural networks (SNNs) offer a promising biologically-plausible computing model and lend themselves to ultra-low-power event-driven processing on... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 57 |
| SubjectTerms | dataflow hardware accelerator neuromorphic computing spiking neural networks systolic array |
| Title | Reconfigurable Dataflow Optimization for Spatiotemporal Spiking Neural Computation on Systolic Array Accelerators |
| URI | https://ieeexplore.ieee.org/document/9283543 |
| WOSCitedRecordID | wos000652198500015&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/eLvHCXMwlV1LSwMxEA5t8aAXH634JgePrs3muTmWVtFLLajQW8kms7KgW922iv_eZHepCl6EHJIlEJiwM5lkvu9D6DwxoKjhIlLCJRHnQCLtlHeGAY1guUxJxiuxCTUeJ9OpnrTQxRoLAwBV8Rlchm71lu_mdhWuyvo6kINx1kZtpWSN1Vp73cQHwgYaFxPdvx0OR4IwpXwKSEP1FqG_BVSq-HG9_b-Vd1DvG4iHJ-sQs4taUOyhrR8cgl30FhLIIsufVmVAQeGRCYK88w98553BS4OyxP5oiu-r4umGi-rZD_NwTY4DPYcf1vIO9WzfApN5oAzGg7I0n3hgrY9P1ZP8oocer68ehjdRo6MQ5ZSwZeSon5MYlRGREvD_tM8RiKBGe5vIzMlYEhCSgY1jmxJl0izRjoNiJpbOZJbto04xL-AAYSNdwoXWqQTLY0tT0MIfYSxLpaF-mUPUDcabvdZUGbPGbkd_fz5Gm2F36tq4E9RZlis4RRv2fZkvyrNqf78AuxSpxw |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD7MKagvXjbxbh58tC5Nc2kex-bYcM6BE_Y20jSVgXbabYr_3qQtU8EXIQ9JCQRO6Dk5yfm-D-AyVEYQRZknWBx6lBrsyVhYZ-jQCJryCCc0F5sQg0E4HsthBa5WWBhjTF58Zq5dN3_Lj2d66a7KGtKRg9FgDdYZpQQXaK2V3w1tKCzBcT6WjV6r1WY4EMImgcTVb2HyW0IljyCdnf-tvQv1bygeGq6CzB5UTLoP2z9YBGvw5lLINJk-LTOHg0Jt5SR5Zx_o3rqDlxJniezhFD3k5dMlG9WzHU7dRTlyBB12WAg8FLNtc1zmjjQYNbNMfaKm1jZC5Y_y8zo8dm5Gra5XKil4U4KDhRcTOydUIsEswsb-1TZLwIwoaW3Ck5j7HBvGA6N9X0dYqCgJZUyNCJTPY5Xo4ACq6Sw1h4AUj0PKpIy40dTXJDKS2UOMDiKuiF3mCGrOeJPXgixjUtrt-O_PF7DZHd31J_3e4PYEttxOFZVyp1BdZEtzBhv6fTGdZ-f5Xn8BuPWtDg |
| 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+-+IEEE+International+Conference+on+Computer+Design&rft.atitle=Reconfigurable+Dataflow+Optimization+for+Spatiotemporal+Spiking+Neural+Computation+on+Systolic+Array+Accelerators&rft.au=Lee%2C+Jeong-Jun&rft.au=Li%2C+Peng&rft.date=2020-10-01&rft.pub=IEEE&rft.eissn=2576-6996&rft.spage=57&rft.epage=64&rft_id=info:doi/10.1109%2FICCD50377.2020.00027&rft.externalDocID=9283543 |