Hi all,
I have found some bug related to the RAS in the branch predictor. It
happens that some returns are predicted with the correct PC but not with
the correct PCState structure. Then when the mispredicted status is
checked (in src/cpu/base_dyn_inst.hh:505), these instructions are
detected as mispredicted because the PCState structure are not equal
(the _pc is the same but not the _npc).
I think this is due to how the target PC is computed by the RAS.
In my code, I have fixed this doing a comparison on the value of the PC
instead of a comparison of the PCState structures:
src/cpu/base_dyn_inst.hh:505
- return !(tempPC == predPC);
+ return !(tempPC.instAddr() == predPC.instAddr());
However, I am not sure that this the best way to correct this bug.
Nathanaël Prémillieu
_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
