Alejandro Martinez Vicente <alejandro.martinezvice...@arm.com> writes:
> @@ -5885,6 +5885,56 @@ is_nonwrapping_integer_induction (stmt_vec_info
> stmt_vinfo, struct loop *loop)
> <= TYPE_PRECISION (lhs_type));
> }
>
> +/* Check if masking can be supported by inserting a condional expression.
conditional
> + CODE is the code for the operation. COND_FN is the conditional internal
> + function, if it exists. VECTYPE_IN is the type of the vector input. */
> +static bool
> +use_mask_by_cond_expr_p (enum tree_code code, internal_fn cond_fn,
> + tree vectype_in)
> +{
> + if (cond_fn != IFN_LAST
> + && direct_internal_fn_supported_p (cond_fn, vectype_in,
> + OPTIMIZE_FOR_SPEED))
> + return false;
> +
> + switch (code)
> + {
> + case DOT_PROD_EXPR:
> + return true;
> +
> + default:
> + return false;
> + }
> +}
> +
> +/* Insert a condional expression to enable masked vectorization. CODE is the
Same here.
> + code for the operation. VOP is the array of operands. MASK is the loop
> + mask. GSI is a statement iterator used to place the new conditional
> + expression. */
> +static void
> +build_vect_cond_expr (enum tree_code code, tree vop[3], tree mask,
> + gimple_stmt_iterator *gsi)
> +{
> + switch (code)
> + {
> + case DOT_PROD_EXPR:
> + {
> + tree vectype = TREE_TYPE (vop[1]);
> + tree zero = build_zero_cst (vectype);
> + zero = build_vector_from_val (vectype, zero);
This last line isn't right -- should just delete it.
tree zero = build_zero_cst (vectype);
builds a zero vector in one go.
OK with those changes, thanks. (This version didn't include the testcase,
but I assume that's because it didn't change from last time.)
Richard
