You are currently viewing SemiWiki as a guest which gives you limited access to the site. To view blog comments and experience other SemiWiki features you must be a registered member. Registration is fast, simple, and absolutely free so please, join our community today!




Results 1 to 4 of 4

Thread: Survey of Spintronic Architectures for Processing-in-Memory and Neural Networks

  1. #1
    Member
    Join Date
    Feb 2015
    Posts
    20
    Thumbs Up
    Received: 7
    Given: 4

    Survey of Spintronic Architectures for Processing-in-Memory and Neural Networks

    Spintronic memories such as STT-RAM (spin transfer torque RAM), SOT-RAM (spin orbit torque RAM) and DWM (domain wall memory) facilitate efficient implementation of PIM (processing-in-memory) approach and NN (neural network) accelerators and offer several advantages over conventional memories.


    Our survey reviews 75+ papers on spintronic-architectures for PIM and NNs. This paper will be useful for researchers in the area of artificial intelligence, hardware architecture, chip design and memory system.


    Accepted in Journal of Systems Architecture 2018. Available here.

    1 Not allowed!
     

  2. #2
    Expert
    Join Date
    Mar 2012
    Posts
    622
    Thumbs Up
    Received: 225
    Given: 207
    Quote Originally Posted by sparsh View Post
    Spintronic memories such as STT-RAM (spin transfer torque RAM), SOT-RAM (spin orbit torque RAM) and DWM (domain wall memory) facilitate efficient implementation of PIM (processing-in-memory) approach and NN (neural network) accelerators and offer several advantages over conventional memories.


    Our survey reviews 75+ papers on spintronic-architectures for PIM and NNs. This paper will be useful for researchers in the area of artificial intelligence, hardware architecture, chip design and memory system.


    Accepted in Journal of Systems Architecture 2018. Available here.
    Access at Research Gate could be easier: (PDF) A Survey of Spintronic Architectures for Processing-in-Memory and Neural Networks

    1 Not allowed!
     

  3. #3
    Blogger Eric Esteve's Avatar
    Join Date
    Nov 2010
    Location
    Marseille, France
    Posts
    855
    Thumbs Up
    Received: 125
    Given: 141
    Thank you for sharing! This is certainly a great work, to be honest, I didn't carefully read each of the 37 pages document... Do you think that it could make sense to build a 2 pages summary out of this great work?
    Anyway, please feel free to share your work!

    1 Not allowed!
    Eric Esteve - IPnest (IP Marketing & Survey & Strategy)
    +33 608 130 656

  4. #4
    Member
    Join Date
    Feb 2015
    Posts
    20
    Thumbs Up
    Received: 7
    Given: 4
    Thanks for your suggestion and encouragement. But I think summarizing it in 2 pages will be very difficult.

    0 Not allowed!
     

Tags for this Thread

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •