On Thu, Apr 25, 2013 at 9:06 PM, Eric Anholt <e...@anholt.net> wrote:
> Improves GLB2.7 performance on my HSW by 0.671455% +/- 0.225037% (n=62).
> ---
> src/mesa/drivers/dri/i965/brw_fs_visitor.cpp | 11 ++++++++++-
> 1 file changed, 10 insertions(+), 1 deletion(-)
>
> diff --git a/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
> b/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
> index f1539d5..8aae516 100644
> --- a/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
> +++ b/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
> @@ -198,10 +198,19 @@ fs_visitor::visit(ir_dereference_array *ir)
> this->result = src;
> }
>
> +static bool
> +is_valid_3src(fs_reg reg)
> +{
> + return reg.file == GRF || reg.file == UNIFORM;
> +}
> +
> void
> fs_visitor::emit_lrp(fs_reg dst, fs_reg x, fs_reg y, fs_reg a)
> {
> - if (intel->gen < 6 || x.file != GRF || y.file != GRF || a.file != GRF) {
> + if (intel->gen < 6 ||
> + !is_valid_3src(x) ||
> + !is_valid_3src(y) ||
> + !is_valid_3src(a)) {
> /* We can't use the LRP instruction. Emit x*(1-a) + y*a. */
> fs_reg y_times_a = fs_reg(this, glsl_type::float_type);
> fs_reg one_minus_a = fs_reg(this, glsl_type::float_type);
> --
> 1.7.10.4
Reviewed-by: Matt Turner <matts...@gmail.com>
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
