On 22 Mar 2010, at 17:44, Ian Bolton wrote:
>> Enabling BB-reorder only if profile info is available, is not the
>> right way to go. The compiler really doesn't place blocks in sane
>> places without it -- and it shouldn't have to, either. For example if
>> you split an edge at some point, the las
> Enabling BB-reorder only if profile info is available, is not the
> right way to go. The compiler really doesn't place blocks in sane
> places without it -- and it shouldn't have to, either. For example if
> you split an edge at some point, the last thing you want to worry
> about, is where the n
On 03/19/10 10:47, Ian Bolton wrote:
I mention all this because I was wondering which other architectures
have turned off sched1 for -Os? More importantly, I was wondering
if anyone else had considered creating some kind of clever hybrid
that only uses sched1 when it will increase performance wi
On 03/19/2010 12:47 PM, Ian Bolton wrote:
I mention all this because I was wondering which other architectures
have turned off sched1 for -Os? More importantly, I was wondering
if anyone else had considered creating some kind of clever hybrid
that only uses sched1 when it will increase performan
> > I mention all this because I was wondering which other architectures
> > have turned off sched1 for -Os? More importantly, I was wondering
> > if anyone else had considered creating some kind of clever hybrid
> > that only uses sched1 when it will increase performance without
> > increasing re
On Fri, Mar 19, 2010 at 5:09 PM, Ian Bolton wrote:
> Anyway, the reason I mention interblock-scheduling is that I see it
> doing seemingly intelligent moves, but then the later BB-reorder pass
> is juggling blocks around such that we end up with extra code inside
> hot loops! I assume this is bec
> > Let's start with sched1 ...
> >
> > For our architecture at least, it seems like Richard Earnshaw is
> > right that sched1 is generally bad when you are using -Os, because
> > it can increase register pressure and cause extra spill/fill code
> when
> > you move independent instructions in betwe
On 03/19/2010 12:09 PM, Ian Bolton wrote:
Hi folks!
I've moved on from register allocation (see Understanding IRA thread)
and onto scheduling.
In particular, I am investigating the effectiveness of the sched1
pass on our architecture and the associated interblock-scheduling
optimisation.
Let'
On Fri, 19 Mar 2010, Ian Bolton wrote:
> Let's start with sched1 ...
>
> For our architecture at least, it seems like Richard Earnshaw is
> right that sched1 is generally bad when you are using -Os, because
> it can increase register pressure and cause extra spill/fill code when
> you move indep
Hi folks!
I've moved on from register allocation (see Understanding IRA thread)
and onto scheduling.
In particular, I am investigating the effectiveness of the sched1
pass on our architecture and the associated interblock-scheduling
optimisation.
Let's start with sched1 ...
For our architectur
10 matches
Mail list logo
