[Mesa-dev] [PATCH 3/3] glsl: Optimize (v.x + v.y) + (v.z + v.w) into dot(v, 1.0).

[Ian Romanick]

On 06/09/2014 02:11 PM, Matt Turner wrote:
> Cuts five instructions out of SynMark's Gl32VSInstancing benchmark.
> ---
>  src/glsl/opt_algebraic.cpp | 46 ++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 46 insertions(+)
> 
> diff --git a/src/glsl/opt_algebraic.cpp b/src/glsl/opt_algebraic.cpp
> index d57c3e8..be65799 100644
> --- a/src/glsl/opt_algebraic.cpp
> +++ b/src/glsl/opt_algebraic.cpp
> @@ -119,6 +119,44 @@ update_type(ir_expression *ir)
>        ir->type = ir->operands[1]->type;
>  }
>  
> +/* Recognize (v.x + v.y) + (v.z + v.w) as dot(v, 1.0) */
> +static ir_expression *
> +try_replace_with_dot(ir_expression *expr0, ir_expression *expr1, void *mem_ctx)
> +{
> +   if (expr0 && expr0->operation == ir_binop_add &&
> +       expr1 && expr1->operation == ir_binop_add) {
> +      ir_swizzle *x = expr0->operands[0]->as_swizzle();
> +      ir_swizzle *y = expr0->operands[1]->as_swizzle();
> +      ir_swizzle *z = expr1->operands[0]->as_swizzle();
> +      ir_swizzle *w = expr1->operands[1]->as_swizzle();
> +
> +      if (!x || x->mask.num_components != 1 || x->mask.has_duplicates ||
> +          !y || y->mask.num_components != 1 || y->mask.has_duplicates ||
> +          !z || z->mask.num_components != 1 || z->mask.has_duplicates ||
> +          !w || w->mask.num_components != 1 || w->mask.has_duplicates) {

Are the has_duplicates checks necessary?  If num_components must be 1,
it's not obvious to me what the extra checks are doing.

> +         return NULL;
> +      }
> +
> +      bool swiz_seen[4] = {false, false, false, false};
> +      swiz_seen[x->mask.x] = true;
> +      swiz_seen[y->mask.x] = true;
> +      swiz_seen[z->mask.x] = true;
> +      swiz_seen[w->mask.x] = true;
> +
> +      if (!swiz_seen[0] || !swiz_seen[1] ||
> +          !swiz_seen[2] || !swiz_seen[3]) {
> +         return NULL;
> +      }
> +
> +      if (x->val->equals(y->val) &&
> +          x->val->equals(z->val) &&
> +          x->val->equals(w->val)) {
> +         return dot(x->val, new(mem_ctx) ir_constant(1.0f, 4));
> +      }
> +   }
> +   return NULL;
> +}
> +
>  void
>  ir_algebraic_visitor::reassociate_operands(ir_expression *ir1,
>  					   int op1,
> @@ -332,6 +370,14 @@ ir_algebraic_visitor::handle_expression(ir_expression *ir)
>        if (op_const[1] && !op_const[0])
>  	 reassociate_constant(ir, 1, op_const[1], op_expr[0]);
>  
> +      /* Recognize (v.x + v.y) + (v.z + v.w) as dot(v, 1.0) */
> +      if (options->OptimizeForAOS) {
> +         ir_expression *expr = try_replace_with_dot(op_expr[0], op_expr[1],
> +                                                    mem_ctx);
> +         if (expr)
> +            return expr;
> +      }
> +
>        /* Replace (-x + y) * a + x and commutative variations with lrp(x, y, a).
>         *
>         * (-x + y) * a + x
>