On Wed, Dec 2, 2009 at 2:01 AM, Timothy M Jones <[email protected]> wrote:
> Well, the problem is when you get speculative memory accesses.  Even in
> the ISAs that don't need split loads and stores, an address on a
> speculative path can generated that requires splitting.  Of course, these
> instructions are later squashed, but their DTB and Dcache accesses might
> have already been performed, leading to more accesses than in the
> reference stats.

I'd think that even without limiting splits to specific ISAs, these
cases should be handled like we just saw in PowerPC: that they would
trigger alignment faults before reaching the DTB or Dcache, and then
those alignment faults would get suppressed when the instructions were
found to be speculative.  Is there a reason this isn't happening this
way?

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

Reply via email to