On Curro's suggestion, I tried reproducing the problem that the patch
fixes. Not only could I not reproduce it, but it seems like the
original workaround that Jason added back when he reworked the fs
backend ages ago is unnecessary at least on my ivybridge and broadwell
machines. Since reproducing
Connor Abbott writes:
> On Tue, May 3, 2016 at 6:16 PM, Francisco Jerez wrote:
>> Samuel Iglesias Gonsálvez writes:
>>
>>> From: Connor Abbott
>>>
>>> Work based on registers read/written instead of dispatch_width, so that
>>> the interferences are added for 64-bit sources/destinations as well
On Tue, May 3, 2016 at 6:16 PM, Francisco Jerez wrote:
> Samuel Iglesias Gonsálvez writes:
>
>> From: Connor Abbott
>>
>> Work based on registers read/written instead of dispatch_width, so that
>> the interferences are added for 64-bit sources/destinations as well.
>> ---
>> src/mesa/drivers/dr
Samuel Iglesias Gonsálvez writes:
> From: Connor Abbott
>
> Work based on registers read/written instead of dispatch_width, so that
> the interferences are added for 64-bit sources/destinations as well.
> ---
> src/mesa/drivers/dri/i965/brw_fs_reg_allocate.cpp | 67
> ---
>
On Tue, May 3, 2016 at 3:46 PM, Kenneth Graunke wrote:
> On Tuesday, May 3, 2016 3:13:26 PM PDT Connor Abbott wrote:
>> On Tue, May 3, 2016 at 2:52 PM, Kenneth Graunke
> wrote:
>> > On Friday, April 29, 2016 1:29:34 PM PDT Samuel Iglesias Gonsálvez wrote:
>> >> From: Connor Abbott
>> >>
>> >> Wo
On Fri, Apr 29, 2016 at 4:29 AM, Samuel Iglesias Gonsálvez
wrote:
> From: Connor Abbott
>
> Work based on registers read/written instead of dispatch_width, so that
> the interferences are added for 64-bit sources/destinations as well.
> ---
> src/mesa/drivers/dri/i965/brw_fs_reg_allocate.cpp | 6
On Tuesday, May 3, 2016 3:13:26 PM PDT Connor Abbott wrote:
> On Tue, May 3, 2016 at 2:52 PM, Kenneth Graunke
wrote:
> > On Friday, April 29, 2016 1:29:34 PM PDT Samuel Iglesias Gonsálvez wrote:
> >> From: Connor Abbott
> >>
> >> Work based on registers read/written instead of dispatch_width, so
On Tue, May 3, 2016 at 3:13 PM, Connor Abbott wrote:
> On Tue, May 3, 2016 at 2:52 PM, Kenneth Graunke wrote:
>> On Friday, April 29, 2016 1:29:34 PM PDT Samuel Iglesias Gonsálvez wrote:
>>> From: Connor Abbott
>>>
>>> Work based on registers read/written instead of dispatch_width, so that
>>> t
On Tue, May 3, 2016 at 2:52 PM, Kenneth Graunke wrote:
> On Friday, April 29, 2016 1:29:34 PM PDT Samuel Iglesias Gonsálvez wrote:
>> From: Connor Abbott
>>
>> Work based on registers read/written instead of dispatch_width, so that
>> the interferences are added for 64-bit sources/destinations as
On Friday, April 29, 2016 1:29:34 PM PDT Samuel Iglesias Gonsálvez wrote:
> From: Connor Abbott
>
> Work based on registers read/written instead of dispatch_width, so that
> the interferences are added for 64-bit sources/destinations as well.
> ---
> src/mesa/drivers/dri/i965/brw_fs_reg_allocate
From: Connor Abbott
Work based on registers read/written instead of dispatch_width, so that
the interferences are added for 64-bit sources/destinations as well.
---
src/mesa/drivers/dri/i965/brw_fs_reg_allocate.cpp | 67 ---
1 file changed, 48 insertions(+), 19 deletions(-)
11 matches
Mail list logo