LOGIN   :::   RECOVER PASS   :::   GET ACCOUNT    
Browse
  • Projects
  • Code (CVS)
  • Forums
  • News
  • Articles
  • Polls
  •  
    OpenCores
  • FAQ
  • CVS HowTo
  • Mission
  • Media
  • Tools
  • Advertise
  • Mirrors
  • Logos
  • Contact us
  • Find Resources
  • Job Opportunity
  •  
    Tools
  • Search
      
  • Download Cores (CVSGet)
  •  
    More
  • Wishbone
  • Perlilog
  • EDA tools
  • OpenTech CD
  •  
    Navigation: All forums > Openrisc > Message List > Message Post

    Message

    Reply | Reply all
    Date Prev | Date Next | Thread Prev | Thread Next Date Index | Thread Index

    From: Ben A. Abderazek<ben@s...>
    Date: Wed Dec 10 06:45:34 CET 2003
    Subject: Fw: [openrisc] Branch Target Buffer Hardware Implementation
    Top
    Thanks Kugan,

    >>AFIK, for this implementation, you need to decode the instruction type
    first.

    Do you mean that I have to add a "branch type" field in the BTB?

    /Ben

    ----- Original Message -----
    From: "#KUGAN VIVEKANANDARAJAH#" <kugan@p...>
    To: "Ben A. Abderazek" <ben@i...>; "List about OpenRISC cores,free
    microprocessors" <openrisc@o...>
    Sent: Wednesday, December 10, 2003 3:24 PM
    Subject: RE: [openrisc] Branch Target Buffer Hardware Implementation





    >I know that a BTB entry may consist of: branch tag, prediction
    >information, the branch target address, and instructions at the branch
    >target. But, how about call and return instructions?

    Call/return is predicted with a return address stack.

    >Do they have also to be in the BTB ? If so, how do the fetch unit make
    >difference between a call, return or branch instructions.

    AFIK, for this implementation, you need to decode the instruction type
    first.
    Kugan



     
    Copyright (c) 1999 OPENCORES.ORG. All rights reserved.