I have basically the same patch setting in my simple-range-analysis tree.
https://cgit.freedesktop.org/~idr/mesa/commit/?h=simple-range-analysis&id=e9d29d71304347f8ff904294450a398e5838f49a
As Jason mentions, you don't need to explicitly mention the compares.
You don't need the @bool either... the source of b2[fi] is always bool.
IIRC, adding the b2f versions helps some other shaders too. I'm
(re-)gathering shader-db stats right now...
On 03/15/2018 08:53 PM, Timothy Arceri wrote:
> These can be found in the Tomb Raider shaders, eliminating them
> helps unroll more loops.
> ---
> src/compiler/nir/nir_opt_algebraic.py | 4 ++++
> 1 file changed, 4 insertions(+)
>
> diff --git a/src/compiler/nir/nir_opt_algebraic.py
> b/src/compiler/nir/nir_opt_algebraic.py
> index c9575e6be4..56dfc53043 100644
> --- a/src/compiler/nir/nir_opt_algebraic.py
> +++ b/src/compiler/nir/nir_opt_algebraic.py
> @@ -152,6 +152,10 @@ optimizations = [
> (('inot', ('ige', a, b)), ('ilt', a, b)),
> (('inot', ('ieq', a, b)), ('ine', a, b)),
> (('inot', ('ine', a, b)), ('ieq', a, b)),
> + (('ine', ('b2i', ('ige', a, b)), 0), ('ige', a, b)),
> + (('ine', ('b2i', ('ilt', a, b)), 0), ('ilt', a, b)),
> + (('ine', ('b2i', ('ult', a, b)), 0), ('ult', a, b)),
> + (('ine', ('b2i', ('ine', a, b)), 0), ('ine', a, b)),
>
> # 0.0 >= b2f(a)
> # b2f(a) <= 0.0
>
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
