Hey,

Op 13-mrt-10, om 21:03 heeft Korey Sewell het volgende geschreven:

>
> Because I want to model the branch penalty of an in-order core this
> will probably not affect the total number of inpredicted branches, nor
> the state of the branch predictor.
> I'm a little confused here. Are you are saying that you want to know  
> many cycles do mispredicted branches contribute to overall execution?
>
That's correct. And you can do that by using the InOrderCPU and  
looking at the produced statistics.
However, I want to get the number of mispredicted branches by using  
the SimpleCPU model since it's much faster.

In the mean time I digged into the code a little deeper. Since we can  
get the PC from SimpleThread (which is an object in the SimpleCPU), we  
can use this as an argument for the functions in src/cpu/pred.
These functions  will get me the statistics I need.

Max

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

Reply via email to