Steve Reinhardt wrote:
> On Sat, Mar 27, 2010 at 12:20 AM, Gabe Black <[email protected]> wrote:
>   
>> What about one way packets that don't collapse back to the sender? Do we
>> have any of those? Or do we always collapse back at least with the ack?
>>     
>
> I'm not sure what you're referring to, Gabe... are you talking about
> atomic mode (that's what "collapse back" makes me think of), or
> packets that don't have responses, or both?
>
> Generally SenderState isn't used in atomic mode, since your stack
> frame does just as good a job.  Also it's not useful if there's no
> reply.
>
> We should make sure that we don't assume that SenderState objects are
> always dynamically allocated... I don't know if we ever statically
> allocate them, but we could.  Overwriting the pointer with NULL just
> to signify that we're done with it in that case seems OK to me though.
>
> Steve
> _______________________________________________
> m5-dev mailing list
> [email protected]
> http://m5sim.org/mailman/listinfo/m5-dev
>   
Me either :). I just wasn't sure with my somewhat limited and/or rusty
knowledge of how that worked that something like that -couldn't- happen,
and I wanted to make sure you guys had considered it.

Gabe
_______________________________________________
m5-dev mailing list
[email protected]
http://m5sim.org/mailman/listinfo/m5-dev

Reply via email to