[Mesa-dev] [PATCH v2 5/6] nv50/ir: optimize SHLADD(a, b, c) to MOV((a << b) + c)

[Ilia Mirkin]

Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu>

On Mon, Sep 26, 2016 at 5:02 PM, Samuel Pitoiset
<samuel.pitoiset at gmail.com> wrote:
> Signed-off-by: Samuel Pitoiset <samuel.pitoiset at gmail.com>
> ---
>  src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp | 3 +++
>  1 file changed, 3 insertions(+)
>
> diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
> index cbbe34d..9875738 100644
> --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
> +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
> @@ -778,6 +778,9 @@ ConstantFolding::expr(Instruction *i,
>        }
>        break;
>     }
> +   case OP_SHLADD:
> +      res.data.u32 = (a->data.u32 << b->data.u32) + c->data.u32;
> +      break;
>     default:
>        return;
>     }
> --
> 2.10.0
>
> _______________________________________________
> mesa-dev mailing list
> mesa-dev at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/mesa-dev