• DocumentCode
    586883
  • Title

    Methodology for fault grading high speed I/O interfaces used in complex Graphics Processing Unit

  • Author

    Khare, Ashish ; Kishore, P. ; Reddy, Swetha ; Rajan, K. ; Sanghani, A.

  • Author_Institution
    Nvidia Graphics, Bangalore, India
  • fYear
    2012
  • fDate
    5-8 Nov. 2012
  • Firstpage
    1
  • Lastpage
    8
  • Abstract
    Graphics Processing Unit (GPU) requires I/O bandwidth of the order of Gbps which can be met by implementation of High Speed Serializer/Deserializer differential I/Os with clock embedded in data stream, traditionally tested using functional Built In Self Test (BIST). Implementation of these I/Os on complex graphics chip poses requirement for fault grading these I/Os. This paper presents the challenges involved in fault grading SerDes I/Os used in Nvidia´s GPU chips and proposes methodology for extracting fault coverage numbers using industry standard tools.
  • Keywords
    built-in self test; clocks; fault diagnosis; graphics processing units; integrated circuit testing; BIST; GPU; Nvidia GPU chips; clock; complex graphics chip; complex graphics processing unit; data stream; deserializer differential I/O; fault coverage number extraction; fault grading SerDes I/O; fault grading high speed I/O interfaces; functional built-in self-test; high speed serializer I/O; industry standard tools; Built-in self-test; Circuit faults; Graphics processing units; Industries; Receivers; Standards; Transmitters;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Test Conference (ITC), 2012 IEEE International
  • Conference_Location
    Anaheim, CA
  • ISSN
    1089-3539
  • Print_ISBN
    978-1-4673-1594-4
  • Type

    conf

  • DOI
    10.1109/TEST.2012.6401585
  • Filename
    6401585