Storage Reliability of Multi-bit Flash Oriented to Deep Neural Network
The storage reliability of multi-bit flash is of vital importance for the flash based deep neural network (DNN). In this work, the critical concerns correlated with the storage reliability (I d distribution and data retention) of multi-bit flash and its impacts on the DNN are investigated for the fi...
Saved in:
Published in | 2019 IEEE International Electron Devices Meeting (IEDM) pp. 38.2.1 - 38.2.4 |
---|---|
Main Authors | , , , , , , , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.12.2019
|
Online Access | Get full text |
Cover
Loading…
Abstract | The storage reliability of multi-bit flash is of vital importance for the flash based deep neural network (DNN). In this work, the critical concerns correlated with the storage reliability (I d distribution and data retention) of multi-bit flash and its impacts on the DNN are investigated for the first time. The key achievements include: (1) A dynamic drain-voltage (V d ) programming method is proposed to achieve adequately tight (error rate <; 0.5%) and spaced drain-current (I d ) distributions in a reasonable time, which leads to comparable accuracy with the software (only 0.25% loss) for the CIFAR-10 recognition. (2) The statistical I d evolution of 16 states over time at different temperatures is studied in a 1Mb flash array, and a physical model is developed to characterize the retention of multi-bit flash. (3) Leveraging the physical model, the device and system co-design is proposed to enhance the reliability of the flash based DNN significantly. |
---|---|
AbstractList | The storage reliability of multi-bit flash is of vital importance for the flash based deep neural network (DNN). In this work, the critical concerns correlated with the storage reliability (I d distribution and data retention) of multi-bit flash and its impacts on the DNN are investigated for the first time. The key achievements include: (1) A dynamic drain-voltage (V d ) programming method is proposed to achieve adequately tight (error rate <; 0.5%) and spaced drain-current (I d ) distributions in a reasonable time, which leads to comparable accuracy with the software (only 0.25% loss) for the CIFAR-10 recognition. (2) The statistical I d evolution of 16 states over time at different temperatures is studied in a 1Mb flash array, and a physical model is developed to characterize the retention of multi-bit flash. (3) Leveraging the physical model, the device and system co-design is proposed to enhance the reliability of the flash based DNN significantly. |
Author | Liu, X. Y. Xiang, Y. C. Han, R. Z. Huang, P. Wang, K. L. Yang, H. Z. Kang, J. F. Shen, W. S. Liu, C. Feng, Y. L. |
Author_xml | – sequence: 1 givenname: Y. C. surname: Xiang fullname: Xiang, Y. C. organization: Peking University,Institute of Microelectronics,Beijing,China – sequence: 2 givenname: J. F. surname: Kang fullname: Kang, J. F. organization: Peking University,Institute of Microelectronics,Beijing,China – sequence: 3 givenname: P. surname: Huang fullname: Huang, P. organization: Peking University,Institute of Microelectronics,Beijing,China – sequence: 4 givenname: H. Z. surname: Yang fullname: Yang, H. Z. organization: Peking University,Institute of Microelectronics,Beijing,China – sequence: 5 givenname: K. L. surname: Wang fullname: Wang, K. L. organization: Peking University,Institute of Microelectronics,Beijing,China – sequence: 6 givenname: R. Z. surname: Han fullname: Han, R. Z. organization: Peking University,Institute of Microelectronics,Beijing,China – sequence: 7 givenname: W. S. surname: Shen fullname: Shen, W. S. organization: Peking University,Institute of Microelectronics,Beijing,China – sequence: 8 givenname: Y. L. surname: Feng fullname: Feng, Y. L. organization: Peking University,Institute of Microelectronics,Beijing,China – sequence: 9 givenname: C. surname: Liu fullname: Liu, C. organization: Peking University,Institute of Microelectronics,Beijing,China – sequence: 10 givenname: X. Y. surname: Liu fullname: Liu, X. Y. organization: Peking University,Institute of Microelectronics,Beijing,China |
BookMark | eNotz8tKw0AUgOFRFGyqTyDIvEDiOXPJZJbSNlpoLXgBd2UmOdHRmJRkivTtFezq2_3wJ-ys6zti7AYhQwR7u1zM12i1kZkAtFlhrdRQnLAEjShQgRTylE0E6jwFNG8XLBnHTwBhtNUTVj7HfnDvxJ-oDc6HNsQD7xu-3rcxpD5EXrZu_OCbIVAXqeax53OiHX-k_eDaP-JPP3xdsvPGtSNdHZ2y13LxMntIV5v75exulVZC5zHFvGoQDAnIUalce6cKVUtTKWu8AoFkLDSOigpyhzUa9GSMtd4LWRW6llN2_d8NRLTdDeHbDYft8Vn-AsOjTME |
CitedBy_id | crossref_primary_10_1088_1674_1056_ab90e7 crossref_primary_10_1109_LED_2022_3183111 crossref_primary_10_1007_s11432_021_3381_3 crossref_primary_10_1109_LED_2023_3269080 crossref_primary_10_1088_1674_4926_42_1_013104 crossref_primary_10_1109_TCSI_2022_3194918 crossref_primary_10_1109_LED_2021_3114407 crossref_primary_10_1109_TED_2022_3227529 |
ContentType | Conference Proceeding |
DBID | 6IE 6IH CBEJK RIE RIO |
DOI | 10.1109/IEDM19573.2019.8993508 |
DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library Online IEEE Proceedings Order Plans (POP) 1998-present |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library Online url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering |
EISBN | 1728140323 9781728140322 |
EISSN | 2156-017X |
EndPage | 38.2.4 |
ExternalDocumentID | 8993508 |
Genre | orig-research |
GroupedDBID | 29Q 6IE 6IF 6IH 6IK 6IL 6IM 6IN AAJGR ABLEC ACGFS ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP IPLJI JC5 M43 OCL RIE RIG RIL RIO RNS |
ID | FETCH-LOGICAL-c256t-16cf107e20614465ba484d37c497b4021e790fae8c06a1d171be7799bb23c85d3 |
IEDL.DBID | RIE |
IngestDate | Wed Jun 26 19:27:16 EDT 2024 |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c256t-16cf107e20614465ba484d37c497b4021e790fae8c06a1d171be7799bb23c85d3 |
ParticipantIDs | ieee_primary_8993508 |
PublicationCentury | 2000 |
PublicationDate | 2019-Dec. |
PublicationDateYYYYMMDD | 2019-12-01 |
PublicationDate_xml | – month: 12 year: 2019 text: 2019-Dec. |
PublicationDecade | 2010 |
PublicationTitle | 2019 IEEE International Electron Devices Meeting (IEDM) |
PublicationTitleAbbrev | IEDM |
PublicationYear | 2019 |
Publisher | IEEE |
Publisher_xml | – name: IEEE |
SSID | ssj0027595 |
Score | 1.8360295 |
Snippet | The storage reliability of multi-bit flash is of vital importance for the flash based deep neural network (DNN). In this work, the critical concerns correlated... |
SourceID | ieee |
SourceType | Publisher |
StartPage | 38.2.1 |
Title | Storage Reliability of Multi-bit Flash Oriented to Deep Neural Network |
URI | https://ieeexplore.ieee.org/document/8993508 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3NS8MwHA1zJ734sYnf5ODRbk3bNM3ZrUxhKuhgt5GPXxCUdUh30L_eX9K5qXjw1FAILUnT33vtey-EXLq0KGyemUhYniBBwZZm3EXCaSkAl1_sQtrnXT6aZLdTPm2Rq7UXBgCC-Ax6vhn-5dvKLP2nsj5yg5R7Z-9WESeNV2tDrrjkKwcwi2X_ZjgYM8lF6tVb-Dg0PX9soRIqSLlLxl_XboQjL71lrXvm41cs439vbo90N149-rCuQvukBfMDsvMtZrBDykck1vjeoF5_3ORyv9PK0WC-RWpc0xIx9DO995nHiEBpXdEBwIL65A71iocgFe-SSTl8uh5Fq_0TIoNApo5YbhyyO0ga1se1yorMpsJkUmjkjQyEjJ2CwsS5YpYJpkEIKbVOUlNwmx6S9ryawxGhzCijfJAMi3WmpUZQmTObJ4kAhZDMHpOOH5HZoonImK0G4-Tv06dk289Kowo5I-36bQnnWNtrfREm9ROPxKK_ |
link.rule.ids | 310,311,786,790,795,796,802,23958,23959,25170,27956,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1NT8JAFHwheFAvfoDx2z14tNBtu93uWWhAAU2EhBvpfjQmGkpMOeiv9-0WQY0HT900adq8bftm2plZgOs8TBIdR8rjmgVIUHAkKcs9nkvBDT5-fu7SPkdxbxLdTdm0BjdrL4wxxonPTMsO3b98Xail_VTWRm4QMuvs3cI-7_PKrbWhV0ywlQeY-qLd73aGVDAeWv0W3hDVsT8WUXE9JN2D4dfZK-nIS2tZypb6-BXM-N_L24fmxq1HHtd96ABqZn4Iu9-CBhuQPiG1xjcHsQrkKpn7nRQ5cfZbJMclSRFFP5MHm3qMGJSUBekYsyA2uyN7xY0TizdhknbHtz1vtYKCpxDKlB6NVY6FMkHF-5jMoiTSIVeR4BKZIzVc-HlmEuXHGdWUU2k4F0LKIFQJ0-ER1OfF3BwDoSpTmY2Sob6MpJAIK2Oq4yDgJkNQpk-gYSsyW1QhGbNVMU7_3n0F273xcDAb9Ef3Z7BjZ6jSiJxDvXxbmgvs9KW8dBP8CVVmphM |
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=2019+IEEE+International+Electron+Devices+Meeting+%28IEDM%29&rft.atitle=Storage+Reliability+of+Multi-bit+Flash+Oriented+to+Deep+Neural+Network&rft.au=Xiang%2C+Y.+C.&rft.au=Kang%2C+J.+F.&rft.au=Huang%2C+P.&rft.au=Yang%2C+H.+Z.&rft.date=2019-12-01&rft.pub=IEEE&rft.eissn=2156-017X&rft.spage=38.2.1&rft.epage=38.2.4&rft_id=info:doi/10.1109%2FIEDM19573.2019.8993508&rft.externalDocID=8993508 |