Review Board 2.0.15


O3: Fix bug when a squash occurs right before TLB miss returns.

Review Request #480 - Created Feb. 11, 2011 and submitted

Information
Ali Saidi
gem5
Reviewers
Default
ali, gblack, nate, stever
O3: Fix bug when a squash occurs right before TLB miss returns.

In this case we need to throw away the TLB miss, not assume it was the
one we were waiting for.

   
Posted (Feb. 11, 2011, 3:19 p.m.)



  
src/cpu/o3/fetch_impl.hh (Diff revision 1)
 
 
I don't think this stat is very useful, and it adds an extra point of divergence for stats in the future and means they'll all have to be rerun for O3.
  1. It mirrors a fetchIcacheSquash stat we have and I think it's interesting to know how many times a translation was ended by a branch mispredict. 
src/cpu/o3/fetch_impl.hh (Diff revision 1)
 
 
This vaddr check seems dangerous. There's nothing I'm aware of that ensures two different requests won't have the same vaddr.
  1. The point is to verify that the translation we got back is actually the one we requested. It slices the bug and breaks nothing. 
src/cpu/o3/fetch_impl.hh (Diff revision 1)
 
 
Don't add random blank lines.