Use vec<> for constant permute masks

This patch makes can_vec_perm_p & co. take a vec<>, wrapped in new
typedefs vec_perm_indices and auto_vec_perm_indices.  There are two
reasons for doing this for SVE:

(1) it means that the number of elements is bundled with the elements
    themselves, and is obviously constant.

(2) it makes it easier to change the "unsigned char" element type to
    something wider.

Changing the target hook is left as follow-on work.

2017-09-14  Richard Sandiford  <richard.sandiford@linaro.org>
	    Alan Hayward  <alan.hayward@arm.com>
	    David Sherwood  <david.sherwood@arm.com>

gcc/
	* target.h (vec_perm_indices): New typedef.
	(auto_vec_perm_indices): Likewise.
	* optabs-query.h: Include target.h
	(can_vec_perm_p): Take a vec_perm_indices *.
	* optabs-query.c (can_vec_perm_p): Likewise.
	(can_mult_highpart_p): Update accordingly.  Use auto_vec_perm_indices.
	* tree-ssa-forwprop.c (simplify_vector_constructor): Likewise.
	* tree-vect-generic.c (lower_vec_perm): Likewise.
	* tree-vect-data-refs.c (vect_grouped_store_supported): Likewise.
	(vect_grouped_load_supported): Likewise.
	(vect_shift_permute_load_chain): Likewise.
	(vect_permute_store_chain): Use auto_vec_perm_indices.
	(vect_permute_load_chain): Likewise.
	* fold-const.c (fold_vec_perm): Take vec_perm_indices.
	(fold_ternary_loc): Update accordingly.  Use auto_vec_perm_indices.
	Update uses of can_vec_perm_p.
	* tree-vect-loop.c (calc_vec_perm_mask_for_shift): Replace the
	mode with a number of elements.  Take a vec_perm_indices *.
	(vect_create_epilog_for_reduction): Update accordingly.
	Use auto_vec_perm_indices.
	(have_whole_vector_shift): Likewise.  Update call to can_vec_perm_p.
	* tree-vect-slp.c (vect_build_slp_tree_1): Likewise.
	(vect_transform_slp_perm_load): Likewise.
	(vect_schedule_slp_instance): Use auto_vec_perm_indices.
	* tree-vectorizer.h (vect_gen_perm_mask_any): Take a vec_perm_indices.
	(vect_gen_perm_mask_checked): Likewise.
	* tree-vect-stmts.c (vect_gen_perm_mask_any): Take a vec_perm_indices.
	(vect_gen_perm_mask_checked): Likewise.
	(vectorizable_mask_load_store): Use auto_vec_perm_indices.
	(vectorizable_store): Likewise.
	(vectorizable_load): Likewise.
	(perm_mask_for_reverse): Likewise.  Update call to can_vec_perm_p.
	(vectorizable_bswap): Likewise.

Co-Authored-By: Alan Hayward <alan.hayward@arm.com>
Co-Authored-By: David Sherwood <david.sherwood@arm.com>

From-SVN: r252761

1 files changed, 13 insertions, 11 deletions

diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
index 3b4a71e..8135219 100644
--- a/gcc/tree-vect-loop.c
+++ b/gcc/tree-vect-loop.c
@@ -3698,15 +3698,15 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo,
 }
 
 /* Writes into SEL a mask for a vec_perm, equivalent to a vec_shr by OFFSET
-   vector elements (not bits) for a vector of mode MODE.  */
+   vector elements (not bits) for a vector with NELT elements.  */
 static void
-calc_vec_perm_mask_for_shift (machine_mode mode, unsigned int offset,
-			      unsigned char *sel)
+calc_vec_perm_mask_for_shift (unsigned int offset, unsigned int nelt,
+			      vec_perm_indices *sel)
 {
-  unsigned int i, nelt = GET_MODE_NUNITS (mode);
+  unsigned int i;
 
   for (i = 0; i < nelt; i++)
-    sel[i] = (i + offset) & (2*nelt - 1);
+    sel->quick_push ((i + offset) & (2 * nelt - 1));
 }
 
 /* Checks whether the target supports whole-vector shifts for vectors of mode
@@ -3722,12 +3722,13 @@ have_whole_vector_shift (machine_mode mode)
     return false;
 
   unsigned int i, nelt = GET_MODE_NUNITS (mode);
-  unsigned char *sel = XALLOCAVEC (unsigned char, nelt);
+  auto_vec_perm_indices sel (nelt);
 
   for (i = nelt/2; i >= 1; i/=2)
     {
-      calc_vec_perm_mask_for_shift (mode, i, sel);
-      if (!can_vec_perm_p (mode, false, sel))
+      sel.truncate (0);
+      calc_vec_perm_mask_for_shift (i, nelt, &sel);
+      if (!can_vec_perm_p (mode, false, &sel))
 	return false;
     }
   return true;
@@ -5059,7 +5060,7 @@ vect_create_epilog_for_reduction (vec<tree> vect_defs, gimple *stmt,
       if (reduce_with_shift && !slp_reduc)
         {
           int nelements = vec_size_in_bits / element_bitsize;
-          unsigned char *sel = XALLOCAVEC (unsigned char, nelements);
+          auto_vec_perm_indices sel (nelements);
 
           int elt_offset;
 
@@ -5083,8 +5084,9 @@ vect_create_epilog_for_reduction (vec<tree> vect_defs, gimple *stmt,
                elt_offset >= 1;
                elt_offset /= 2)
             {
-              calc_vec_perm_mask_for_shift (mode, elt_offset, sel);
-              tree mask = vect_gen_perm_mask_any (vectype, sel);
+	      sel.truncate (0);
+	      calc_vec_perm_mask_for_shift (elt_offset, nelements, &sel);
+	      tree mask = vect_gen_perm_mask_any (vectype, sel);
 	      epilog_stmt = gimple_build_assign (vec_dest, VEC_PERM_EXPR,
 						 new_temp, zero_vec, mask);
               new_name = make_ssa_name (vec_dest, epilog_stmt);