>>> create
> > > > >>> paths where you're going to emit the xor when it's not used.
> > > > >>>
> > > > >>> The whole point of the LCM algorithms is they are optimal in terms
> > > > >>>
t;> expression evaluations.
> > > >> We tried LCM and it didn't work well for this case. LCM places a
> > > >> single
> > > >> VXOR close to the location where it is needed, which can be inside a
> > > >> loop. Th
tions.
> > >> We tried LCM and it didn't work well for this case. LCM places a single
> > >> VXOR close to the location where it is needed, which can be inside a
> > >> loop. There is nothing wrong with the LCM algorithms. But this doesn't
> > >> so
t; >> loop. There is nothing wrong with the LCM algorithms. But this doesn't
> >> solve
> >>
> >> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=87007
> >>
> >> where VXOR is executed multiple times inside of a func
ke loop that contains the whole function:
>>
>> bb = nearest_common_dominator_for_set (CDI_DOMINATORS,
>> convert_bbs);
>> while (bb->loop_father->latch
>> != EXIT_BLOCK_PTR_FOR_FN (cfun))
>&
On Mon, Jan 7, 2019 at 5:55 AM H.J. Lu wrote:
>
> On Sun, Dec 30, 2018 at 8:40 AM H.J. Lu wrote:
> >
> > On Wed, Nov 28, 2018 at 12:17 PM Jeff Law wrote:
> > >
> > > On 11/28/18 12:48 PM, H.J. Lu wrote:
> > > > On Mon, Nov 5, 2018 at 7:29 AM Jan Hubicka wrote:
> > > >>
> > > >>> On 11/5/18 7:21
On 12/30/18 9:50 AM, H.J. Lu wrote:
> On Wed, Nov 28, 2018 at 12:21 PM Jan Hubicka wrote:
>>
>>> On 11/28/18 12:48 PM, H.J. Lu wrote:
On Mon, Nov 5, 2018 at 7:29 AM Jan Hubicka wrote:
>
>> On 11/5/18 7:21 AM, Jan Hubicka wrote:
Did you mean "the nearest common domin
://gcc.gnu.org/bugzilla/show_bug.cgi?id=87007
>
> where VXOR is executed multiple times inside of a function, instead of
> just once. We are investigating to generate a single VXOR at entry of the
> nearest dominator for basic blocks with SF/DF conversio
On Wed, Nov 28, 2018 at 12:21 PM Jan Hubicka wrote:
>
> > On 11/28/18 12:48 PM, H.J. Lu wrote:
> > > On Mon, Nov 5, 2018 at 7:29 AM Jan Hubicka wrote:
> > >>
> > >>> On 11/5/18 7:21 AM, Jan Hubicka wrote:
> > >
> > > Did you mean "the nearest common dominator"?
> >
> > If the ne
On Wed, Nov 28, 2018 at 12:17 PM Jeff Law wrote:
>
> On 11/28/18 12:48 PM, H.J. Lu wrote:
> > On Mon, Nov 5, 2018 at 7:29 AM Jan Hubicka wrote:
> >>
> >>> On 11/5/18 7:21 AM, Jan Hubicka wrote:
> >
> > Did you mean "the nearest common dominator"?
>
> If the nearest common domina
> On 11/28/18 12:48 PM, H.J. Lu wrote:
> > On Mon, Nov 5, 2018 at 7:29 AM Jan Hubicka wrote:
> >>
> >>> On 11/5/18 7:21 AM, Jan Hubicka wrote:
> >
> > Did you mean "the nearest common dominator"?
>
> If the nearest common dominator appears in the loop while all uses are
> ou
On 11/28/18 12:48 PM, H.J. Lu wrote:
> On Mon, Nov 5, 2018 at 7:29 AM Jan Hubicka wrote:
>>
>>> On 11/5/18 7:21 AM, Jan Hubicka wrote:
>
> Did you mean "the nearest common dominator"?
If the nearest common dominator appears in the loop while all uses are
out of loops, this w
On Mon, Nov 5, 2018 at 7:29 AM Jan Hubicka wrote:
>
> > On 11/5/18 7:21 AM, Jan Hubicka wrote:
> > >>
> > >> Did you mean "the nearest common dominator"?
> > >
> > > If the nearest common dominator appears in the loop while all uses are
> > > out of loops, this will result in suboptimal xor placem
> On 11/5/18 7:21 AM, Jan Hubicka wrote:
> >>
> >> Did you mean "the nearest common dominator"?
> >
> > If the nearest common dominator appears in the loop while all uses are
> > out of loops, this will result in suboptimal xor placement.
> > In this case you want to split edges out of the loop.
>
On 11/5/18 7:21 AM, Jan Hubicka wrote:
>>
>> Did you mean "the nearest common dominator"?
>
> If the nearest common dominator appears in the loop while all uses are
> out of loops, this will result in suboptimal xor placement.
> In this case you want to split edges out of the loop.
>
> In general
on dominator for basic blocks with SF/DF
> conversions. OK for trunk?
>
> Thanks.
>
>
> --
> H.J.
> From e2a437f48778ae9586f2038220840ecc41566f69 Mon Sep 17 00:00:00 2001
> From: "H.J. Lu"
> Date: Wed, 15 Aug 2018 09:58:31 -0700
> Subject: [PATCH] i386:
On Fri, Oct 19, 2018 at 1:44 AM H.J. Lu wrote:
>
> On 10/18/18, Jan Hubicka wrote:
> >> we need to generate
> >>
> >> vxorp[ds] %xmmN, %xmmN, %xmmN
> >> ...
> >> vcvtss2sd f(%rip), %xmmN, %xmmX
> >> ...
> >> vcvtsi2ss i(%rip), %xmmN, %xmmY
> >>
> >> to a
answer would be to look for the postdominance
> frontier
Did you mean "the nearest common dominator"?
> of the set of all uses of the zero register?
>
Here is the updated patch to adds a pass to generate a single
vxorps %xmmN, %xmmN, %xmmN
at entry of the
> we need to generate
>
> vxorp[ds] %xmmN, %xmmN, %xmmN
> ...
> vcvtss2sd f(%rip), %xmmN, %xmmX
> ...
> vcvtsi2ss i(%rip), %xmmN, %xmmY
>
> to avoid partial XMM register stall. This patch adds a pass to generate
> a single
>
> vxorps
On Tue, Sep 18, 2018 at 9:44 AM H.J. Lu wrote:
>
> On Tue, Sep 11, 2018 at 9:01 AM, H.J. Lu wrote:
> > On Tue, Sep 4, 2018 at 9:01 AM, H.J. Lu wrote:
> >> On Tue, Aug 28, 2018 at 11:04 AM, H.J. Lu wrote:
> >>> With -mavx, for
> >>>
> >>> [hjl@gnu-cfl-1 skx-2]$ cat foo.i
> >>> extern float f;
>
On Tue, Sep 11, 2018 at 9:01 AM, H.J. Lu wrote:
> On Tue, Sep 4, 2018 at 9:01 AM, H.J. Lu wrote:
>> On Tue, Aug 28, 2018 at 11:04 AM, H.J. Lu wrote:
>>> With -mavx, for
>>>
>>> [hjl@gnu-cfl-1 skx-2]$ cat foo.i
>>> extern float f;
>>> extern double d;
>>> extern int i;
>>>
>>> void
>>> foo (void)
On Tue, Sep 4, 2018 at 9:01 AM, H.J. Lu wrote:
> On Tue, Aug 28, 2018 at 11:04 AM, H.J. Lu wrote:
>> With -mavx, for
>>
>> [hjl@gnu-cfl-1 skx-2]$ cat foo.i
>> extern float f;
>> extern double d;
>> extern int i;
>>
>> void
>> foo (void)
>> {
>> d = f;
>> f = i;
>> }
>>
>> we need to generate
On Tue, Aug 28, 2018 at 11:04 AM, H.J. Lu wrote:
> With -mavx, for
>
> [hjl@gnu-cfl-1 skx-2]$ cat foo.i
> extern float f;
> extern double d;
> extern int i;
>
> void
> foo (void)
> {
> d = f;
> f = i;
> }
>
> we need to generate
>
> vxorp[ds] %xmmN, %xmmN, %xmmN
> ...
>
With -mavx, for
[hjl@gnu-cfl-1 skx-2]$ cat foo.i
extern float f;
extern double d;
extern int i;
void
foo (void)
{
d = f;
f = i;
}
we need to generate
vxorp[ds] %xmmN, %xmmN, %xmmN
...
vcvtss2sd f(%rip), %xmmN, %xmmX
...
vcvtsi2ss i(%
24 matches
Mail list logo
