On Tue, Sep 27, 2011 at 12:30 AM, Jeff Law wrote:
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> On 08/18/11 15:59, Richard Henderson wrote:
>> On 08/17/2011 12:21 AM, Richard Guenther wrote:
>>> The patch itself looks sensible, though I am surprised ifcvt
>>> doesn't run in cfglayout mode
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 08/18/11 15:59, Richard Henderson wrote:
> On 08/17/2011 12:21 AM, Richard Guenther wrote:
>> The patch itself looks sensible, though I am surprised ifcvt
>> doesn't run in cfglayout mode (so you have to use reg notes to
>> find probabilities ...)
>
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 08/18/11 15:59, Richard Henderson wrote:
> On 08/17/2011 12:21 AM, Richard Guenther wrote:
>> The patch itself looks sensible, though I am surprised ifcvt
>> doesn't run in cfglayout mode (so you have to use reg notes to find
>> probabilities ...)
>
On 08/17/2011 12:21 AM, Richard Guenther wrote:
> The patch itself looks sensible, though I am surprised ifcvt doesn't run in
> cfglayout mode (so you have to use reg notes to find probabilities ...)
It does run in cfglayout mode.
Jeff, I believe you're supposed to get the probabilities from some
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 08/17/11 01:21, Richard Guenther wrote:
>
> We don't have a way to distinguish branch-taken vs. branch-not-take
> costs, right?
Not that I'm aware of. However, BRANCH_COST does allow the backend to
change the cost of a branch based on its predic
On Tue, Aug 16, 2011 at 11:14 PM, Jeff Law wrote:
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
>
> ifcvt.c is sometimes over-aggressive in speculating instructions from a
> not-predicted path.
>
> Given:
>
> if (test) goto E; // x not live
> x = big();
> goto L;
>
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
ifcvt.c is sometimes over-aggressive in speculating instructions from a
not-predicted path.
Given:
if (test) goto E; // x not live
x = big();
goto L;
E:
x = b;
goto M;
ifcvt wants to turn it into:
