The file I'm referring to is arch/alpha/tlb.cc and specifically the
translateAtomic() function implemented there.

Basically, having the "Read" mode is irrelevant there since it's given a
default type of "write" when it calls translateData(). Then in the
translateData() function it goes ahead and gets the mode from a system
register.

So either I'm mixing up what "mode" means or that extra mode (at least for
translateAtomic()) is just extra there.

On Thu, Apr 9, 2009 at 11:59 AM, nathan binkert <[email protected]> wrote:

> > can someone elaborate on what the 3 modes mean {Read, Write, Execute}?
> They correspond to the access types that come from the CPU.
>
> > I ask because in the translateAtomic function it seems as if the only
> modes
> > that matter are Write and Execute. Why does Read not matter?
> It does.  Which translateAtomic function do you think it doesn't matter
> for?
>
> > I might be missing something simple, but it seems as if there are only 2
> > necessary modes (Inst/Data) and for the data portion we read the alpha
> > system register to figure out if it's a read/write access.
> You don't read a register to find out if its a read or a write, the
> instruction itself tells you that.
>
> > Thus, the 3rd argument to that function looks unnecessary since it is
> always
> > the value "Write". If it is unneccessary, then does that not mess up the
> > stats in that function who play off the "write" variable instead of maybe
> > more appropriately the "mode" variable?
> Which file exactly are you liking in.  There are multiple
> implementations of this function.
>
> > Again, I might just be overlooking something.  Can someone give me some
> > insight into what's going on here?
> _______________________________________________
> m5-dev mailing list
> [email protected]
> http://m5sim.org/mailman/listinfo/m5-dev
>



-- 
----------
Korey L Sewell
Graduate Student - PhD Candidate
Computer Science & Engineering
University of Michigan
_______________________________________________
m5-dev mailing list
[email protected]
http://m5sim.org/mailman/listinfo/m5-dev

Reply via email to