Kenneth Graunke writes:
> On 02/25/2014 09:38 AM, Eric Anholt wrote:
>> Matt Turner writes:
>>
>>> On Mon, Feb 24, 2014 at 10:15 AM, Eric Anholt wrote:
I think we would do better by emitting
ADD(y_minus_x, y, negate(x))
MAC(dst, x, y_minus_x, a)
>>>
>>> MAC only takes two argume
On 02/25/2014 09:38 AM, Eric Anholt wrote:
> Matt Turner writes:
>
>> On Mon, Feb 24, 2014 at 10:15 AM, Eric Anholt wrote:
>>> I think we would do better by emitting
>>> ADD(y_minus_x, y, negate(x))
>>> MAC(dst, x, y_minus_x, a)
>>
>> MAC only takes two arguments, so
>> - if you meant MAD, ther
Matt Turner writes:
> On Mon, Feb 24, 2014 at 10:15 AM, Eric Anholt wrote:
>> I think we would do better by emitting
>> ADD(y_minus_x, y, negate(x))
>> MAC(dst, x, y_minus_x, a)
>
> MAC only takes two arguments, so
> - if you meant MAD, there's no MAD on platforms that don't have LRP
> - if yo
On Mon, Feb 24, 2014 at 10:15 AM, Eric Anholt wrote:
> I think we would do better by emitting
> ADD(y_minus_x, y, negate(x))
> MAC(dst, x, y_minus_x, a)
MAC only takes two arguments, so
- if you meant MAD, there's no MAD on platforms that don't have LRP
- if you meant MAC(dst, ...) I don't see
Kenneth Graunke writes:
> When the vec4 backend encountered an ir_triop_lrp, it always emitted an
> actual LRP instruction, which only exists on Gen6+. Gen4-5 used
> lower_instructions() to decompose ir_triop_lrp at the IR level.
>
> Since commit 8d37e9915a3b21 ("glsl: Optimize open-coded lrp in
When the vec4 backend encountered an ir_triop_lrp, it always emitted an
actual LRP instruction, which only exists on Gen6+. Gen4-5 used
lower_instructions() to decompose ir_triop_lrp at the IR level.
Since commit 8d37e9915a3b21 ("glsl: Optimize open-coded lrp into lrp."),
we've had an bug where l
