[Mesa-dev] [PATCH v2 4/6] nv50/ir: optimize SHLADD(a, b, 0x0) to SHL(a, b)

[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 | 8 ++++++++
>  1 file changed, 8 insertions(+)
>
> diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
> index c9d5b5f..cbbe34d 100644
> --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
> +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
> @@ -907,6 +907,14 @@ ConstantFolding::opnd3(Instruction *i, ImmediateValue &imm2)
>           return;
>        }
>        break;
> +   case OP_SHLADD:
> +      if (imm2.isInteger(0)) {
> +         i->op = OP_SHL;
> +         i->setSrc(2, NULL);
> +         foldCount++;
> +         return;
> +      }
> +      break;
>     default:
>        return;
>     }
> --
> 2.10.0
>
> _______________________________________________
> mesa-dev mailing list
> mesa-dev at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/mesa-dev