On 03/12/2014 01:28 AM, Kenneth Graunke wrote:
> Ideally, we'd like to never even attempt the SIMD16 compile if we could
> know ahead of time that it won't succeed---it's purely a waste of time.
> This is especially important for state-based recompiles, which happen at
> draw time.
>
> The fragmen
On 03/12/2014 11:30 AM, Kenneth Graunke wrote:
> On 03/12/2014 02:51 AM, Ilia Mirkin wrote:
>> On Wed, Mar 12, 2014 at 4:28 AM, Kenneth Graunke
>> wrote:
>>> Ideally, we'd like to never even attempt the SIMD16 compile if we could
>>> know ahead of time that it won't succeed---it's purely a waste
On 03/12/2014 02:51 AM, Ilia Mirkin wrote:
> On Wed, Mar 12, 2014 at 4:28 AM, Kenneth Graunke
> wrote:
>> Ideally, we'd like to never even attempt the SIMD16 compile if we could
>> know ahead of time that it won't succeed---it's purely a waste of time.
>> This is especially important for state-ba
On Wed, Mar 12, 2014 at 10:36 AM, Ian Romanick wrote:
> On 03/12/2014 02:51 AM, Ilia Mirkin wrote:
>> On Wed, Mar 12, 2014 at 4:28 AM, Kenneth Graunke
>> wrote:
>>> Ideally, we'd like to never even attempt the SIMD16 compile if we could
>>> know ahead of time that it won't succeed---it's purely
On 03/12/2014 02:51 AM, Ilia Mirkin wrote:
> On Wed, Mar 12, 2014 at 4:28 AM, Kenneth Graunke
> wrote:
>> Ideally, we'd like to never even attempt the SIMD16 compile if we could
>> know ahead of time that it won't succeed---it's purely a waste of time.
>> This is especially important for state-ba
On Wed, Mar 12, 2014 at 4:28 AM, Kenneth Graunke wrote:
> Ideally, we'd like to never even attempt the SIMD16 compile if we could
> know ahead of time that it won't succeed---it's purely a waste of time.
> This is especially important for state-based recompiles, which happen at
> draw time.
>
> Th
This patch is:
Reviewed-by: Chris Forbes
On Wed, Mar 12, 2014 at 9:28 PM, Kenneth Graunke wrote:
> Ideally, we'd like to never even attempt the SIMD16 compile if we could
> know ahead of time that it won't succeed---it's purely a waste of time.
> This is especially important for state-based rec
Ideally, we'd like to never even attempt the SIMD16 compile if we could
know ahead of time that it won't succeed---it's purely a waste of time.
This is especially important for state-based recompiles, which happen at
draw time.
The fragment shader compiler has a number of checks like:
if (disp
