On Mon, Mar 19, 2018 at 10:21 AM, Dylan Baker wrote:
> Quoting Jason Ekstrand (2018-03-17 23:37:51)
> > On Sat, Mar 17, 2018 at 10:32 PM, Dylan Baker
> wrote:
> >
> > Quoting Jason Ekstrand (2018-03-17 09:53:13)
> > > On March 16, 2018 23:36:50 Dylan Baker
> wrote:
> > >
> > > >
Quoting Jason Ekstrand (2018-03-17 23:37:51)
> On Sat, Mar 17, 2018 at 10:32 PM, Dylan Baker wrote:
>
> Quoting Jason Ekstrand (2018-03-17 09:53:13)
> > On March 16, 2018 23:36:50 Dylan Baker wrote:
> >
> > > Quoting Rob Clark (2018-03-16 14:25:09)
> > >> On Fri, Mar 16, 2018
On Sat, Mar 17, 2018 at 10:32 PM, Dylan Baker wrote:
> Quoting Jason Ekstrand (2018-03-17 09:53:13)
> > On March 16, 2018 23:36:50 Dylan Baker wrote:
> >
> > > Quoting Rob Clark (2018-03-16 14:25:09)
> > >> On Fri, Mar 16, 2018 at 4:30 PM, Dylan Baker
> wrote:
> > >> > Quoting Rob Clark (2018-0
Quoting Jason Ekstrand (2018-03-17 09:53:13)
> On March 16, 2018 23:36:50 Dylan Baker wrote:
>
> > Quoting Rob Clark (2018-03-16 14:25:09)
> >> On Fri, Mar 16, 2018 at 4:30 PM, Dylan Baker wrote:
> >> > Quoting Rob Clark (2018-03-16 12:20:10)
> >> >> On Fri, Mar 16, 2018 at 3:13 PM, Jason Ekstra
On Fri, Mar 16, 2018 at 2:28 PM, Dylan Baker wrote:
> Quoting Rob Clark (2018-03-15 18:43:28)
>> I threatened to do this a long time ago.. I probably *should* have done
>> it a long time ago when there where many fewer intrinsics. But the
>> system of macro/#include magic for dealing with intrins
On March 16, 2018 23:36:50 Dylan Baker wrote:
Quoting Rob Clark (2018-03-16 14:25:09)
On Fri, Mar 16, 2018 at 4:30 PM, Dylan Baker wrote:
> Quoting Rob Clark (2018-03-16 12:20:10)
>> On Fri, Mar 16, 2018 at 3:13 PM, Jason Ekstrand
wrote:
>> > On Fri, Mar 16, 2018 at 11:53 AM, Dylan Baker
Quoting Rob Clark (2018-03-16 14:25:09)
> On Fri, Mar 16, 2018 at 4:30 PM, Dylan Baker wrote:
> > Quoting Rob Clark (2018-03-16 12:20:10)
> >> On Fri, Mar 16, 2018 at 3:13 PM, Jason Ekstrand
> >> wrote:
> >> > On Fri, Mar 16, 2018 at 11:53 AM, Dylan Baker
> >> > wrote:
> >> >>
> >> >> Quoting
On Fri, Mar 16, 2018 at 4:30 PM, Dylan Baker wrote:
> Quoting Rob Clark (2018-03-16 12:20:10)
>> On Fri, Mar 16, 2018 at 3:13 PM, Jason Ekstrand wrote:
>> > On Fri, Mar 16, 2018 at 11:53 AM, Dylan Baker wrote:
>> >>
>> >> Quoting Jason Ekstrand (2018-03-16 11:38:47)
>> >> > On Fri, Mar 16, 2018
Quoting Rob Clark (2018-03-16 12:20:10)
> On Fri, Mar 16, 2018 at 3:13 PM, Jason Ekstrand wrote:
> > On Fri, Mar 16, 2018 at 11:53 AM, Dylan Baker wrote:
> >>
> >> Quoting Jason Ekstrand (2018-03-16 11:38:47)
> >> > On Fri, Mar 16, 2018 at 11:28 AM, Dylan Baker
> >> > wrote:
> >> >
> >> > in
On Fri, Mar 16, 2018 at 3:13 PM, Jason Ekstrand wrote:
> On Fri, Mar 16, 2018 at 11:53 AM, Dylan Baker wrote:
>>
>> Quoting Jason Ekstrand (2018-03-16 11:38:47)
>> > On Fri, Mar 16, 2018 at 11:28 AM, Dylan Baker
>> > wrote:
>> >
>> > intr_opcodes = {
>> > 'nop': Intrinsic('nop', flag
On Fri, Mar 16, 2018 at 11:53 AM, Dylan Baker wrote:
> Quoting Jason Ekstrand (2018-03-16 11:38:47)
> > On Fri, Mar 16, 2018 at 11:28 AM, Dylan Baker
> wrote:
> >
> > intr_opcodes = {
> > 'nop': Intrinsic('nop', flags=[CAN_ELIMINATE]),
> > ...
> > }
> >
> > I prefer t
Quoting Rob Clark (2018-03-16 11:45:56)
> On Fri, Mar 16, 2018 at 2:28 PM, Dylan Baker wrote:
> > Quoting Rob Clark (2018-03-15 18:43:28)
> >> I threatened to do this a long time ago.. I probably *should* have done
> >> it a long time ago when there where many fewer intrinsics. But the
> >> syste
Quoting Jason Ekstrand (2018-03-16 11:38:47)
> On Fri, Mar 16, 2018 at 11:28 AM, Dylan Baker wrote:
>
> intr_opcodes = {
> 'nop': Intrinsic('nop', flags=[CAN_ELIMINATE]),
> ...
> }
>
> I prefer this since each dictionary is clearly created without a function
> obs
On Fri, Mar 16, 2018 at 2:28 PM, Dylan Baker wrote:
> Quoting Rob Clark (2018-03-15 18:43:28)
>> I threatened to do this a long time ago.. I probably *should* have done
>> it a long time ago when there where many fewer intrinsics. But the
>> system of macro/#include magic for dealing with intrins
On Fri, Mar 16, 2018 at 11:28 AM, Dylan Baker wrote:
> Quoting Rob Clark (2018-03-15 18:43:28)
>
> > diff --git a/src/compiler/nir/nir_intrinsics.py b/src/compiler/nir/nir_
> intrinsics.py
> > new file mode 100644
> > index 000..6bb6603586e
> > --- /dev/null
> > +++ b/src/compiler/nir/nir
Quoting Rob Clark (2018-03-15 18:43:28)
> I threatened to do this a long time ago.. I probably *should* have done
> it a long time ago when there where many fewer intrinsics. But the
> system of macro/#include magic for dealing with intrinsics is a bit
> annoying, and python has the nice property
On Fri, Mar 16, 2018 at 11:18 AM, Emil Velikov wrote:
> On 16 March 2018 at 12:41, Rob Clark wrote:
>> Ok, I came up with:
>>
>> https://hastebin.com/bulilojupo.cpp
>>
>> if you want to double check my methodology.
>>
>> It spotted a couple small mistakes, which I've fixed up locally. Will
>>
On 16 March 2018 at 12:41, Rob Clark wrote:
> Ok, I came up with:
>
> https://hastebin.com/bulilojupo.cpp
>
> if you want to double check my methodology.
>
> It spotted a couple small mistakes, which I've fixed up locally. Will
> resend once I finish autotools build support.. hmm, and I guess t
Ok, I came up with:
https://hastebin.com/bulilojupo.cpp
if you want to double check my methodology.
It spotted a couple small mistakes, which I've fixed up locally. Will
resend once I finish autotools build support.. hmm, and I guess there
is scons too.. *sigh*
Fwiw, one if the bugs was from
I haven't done anything to verify yet, but I was thinking along the
same lines of just hacking up a .c program to compare both sets of
tables. There are enough intrinsics, that somewhere I probably
transcribed one wrong and visual inspection of the tables doesn't seem
sane ;-)
BR,
-R
On Fri, Mar
I think I like this in principal. One question would be what have you done
to verify everything is the same? When I've done things like this in the
past, I've written a bit of C code to compare all the info struct to ensure
that the two generate the same thing.
On March 15, 2018 18:43:59 Rob
I threatened to do this a long time ago.. I probably *should* have done
it a long time ago when there where many fewer intrinsics. But the
system of macro/#include magic for dealing with intrinsics is a bit
annoying, and python has the nice property of optional fxn params,
making it possible to de
22 matches
Mail list logo
