• Locked Locked
  • Replies 2 replies
  • Subscribers 119 subscribers
  • Views 2821 views
  • Users 0 members are here
Options
Related
How was your experience today?
This discussion has been locked.
You can no longer post new replies to this discussion. If you have a question you can start a new discussion

Newbies on how to deal with more than 16 wait states in AHB lites?

Jerry Feng
Note: This was originally posted on 29th October 2011 at http://forums.arm.com

I found an answer for more than 16 wait state problem:
"[color=#222222][font=Verdana, sans-serif][size=2]For some slaves it is acceptable to insert more than 16wait states. For example, a serial boot ROM which is only ever accessed atinitial power up could insert a larger number of wait states and it would notaffect the calculation of the system performance and latency once system powerup has been completed."[/size][/font][/color]
[color=#222222][font=Verdana, sans-serif][size=2]
[/size][/font][/color]
[size=2]Questions:[/size]
[size=2]Who is responsible for it? The master or the software? if it is the master, does it mean that I have to add some logic for the start-up process for the special slave? or just use software to mask it?[/size]
[size=2]
[/size]
[size=2]
[/size]
[color=#222222][font=Verdana, sans-serif][size=2]"For other slaves a number of options exist. A SPLIT orRETRY response could be used to indicate that the slave is not yet able toperform the requested data transfer, or the slave could be accessed either inresponse to interrupts or after polling a status register, in either caseindicating that the slave is now able to respond in an acceptable number ofcycles.[/size][/font][/color]"

questions:
SPLIT and RETRY do not exist in AHB Lite.
For other options, such as interrupts or polling,
I do not understand how to use such methods,
For example, when using interrupts, does it mean that the master only can access when gets an interrupt? For polling, the slave sets a flag in a status register, and the master will know when he checks it?

But if do so, it means that the mechanism discards the 16 wait states restriction and moves to a new method, right?

Can anybody give me some advices?

I am totally confused about it.

Thanks a lot and Happy Halloween.
Parents
  • Arm Employee Badge
    Note: This was originally posted on 29th October 2011 at http://forums.arm.com

    There is no "16 waitstate problem". This is just a recommendation and does not form part of the specification. A slave is free to insert as may waitstates as it wants any time it wants. For example an AHB-Lite bridge from a 1GHz domain to a 33MHz domain will always have to respond with more than 16 waitstates.

    hth
    s.
Reply
  • Arm Employee Badge
    Note: This was originally posted on 29th October 2011 at http://forums.arm.com

    There is no "16 waitstate problem". This is just a recommendation and does not form part of the specification. A slave is free to insert as may waitstates as it wants any time it wants. For example an AHB-Lite bridge from a 1GHz domain to a 33MHz domain will always have to respond with more than 16 waitstates.

    hth
    s.
Children
No data