On Fri, Feb 22, 2013 at 10:15 AM, Nilay <[email protected]> wrote:

> First, do you want to tackle the decode cache after we have parallelized
> the message buffers and ports?
>

Yea, that's what I was trying to say.


> Second, we use the PC of the currently executing thread to get a page from
> the decode cache. Since PC is a virtual address, why are we not required
> to carry out a translation first?
>

The decode cache is totally a hint... we always validate the decode
structure by comparing the instruction bytes fetched from the i-cache with
the undecoded bytes saved in the decode object.  That way we don't have to
try and detect all the myriad ways in which the decode cache could become
invalid: not just changes in virtual address mappings, but self-modifying
or auto-generated code, etc.

Steve


>
> --
> Nilay
>
> _______________________________________________
> gem5-dev mailing list
> [email protected]
> http://m5sim.org/mailman/listinfo/gem5-dev
>
_______________________________________________
gem5-dev mailing list
[email protected]
http://m5sim.org/mailman/listinfo/gem5-dev

Reply via email to