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, 35 insertions, 27 deletions

diff --git a/gcc/tree-vect-data-refs.c b/gcc/tree-vect-data-refs.c
index 070c707..0b3b968 100644
--- a/gcc/tree-vect-data-refs.c
+++ b/gcc/tree-vect-data-refs.c
@@ -4547,7 +4547,8 @@ vect_grouped_store_supported (tree vectype, unsigned HOST_WIDE_INT count)
   if (VECTOR_MODE_P (mode))
     {
       unsigned int i, nelt = GET_MODE_NUNITS (mode);
-      unsigned char *sel = XALLOCAVEC (unsigned char, nelt);
+      auto_vec_perm_indices sel (nelt);
+      sel.quick_grow (nelt);
 
       if (count == 3)
 	{
@@ -4568,7 +4569,7 @@ vect_grouped_store_supported (tree vectype, unsigned HOST_WIDE_INT count)
 		  if (3 * i + nelt2 < nelt)
 		    sel[3 * i + nelt2] = 0;
 		}
-	      if (!can_vec_perm_p (mode, false, sel))
+	      if (!can_vec_perm_p (mode, false, &sel))
 		{
 		  if (dump_enabled_p ())
 		    dump_printf (MSG_MISSED_OPTIMIZATION,
@@ -4585,7 +4586,7 @@ vect_grouped_store_supported (tree vectype, unsigned HOST_WIDE_INT count)
 		  if (3 * i + nelt2 < nelt)
 		    sel[3 * i + nelt2] = nelt + j2++;
 		}
-	      if (!can_vec_perm_p (mode, false, sel))
+	      if (!can_vec_perm_p (mode, false, &sel))
 		{
 		  if (dump_enabled_p ())
 		    dump_printf (MSG_MISSED_OPTIMIZATION,
@@ -4605,13 +4606,13 @@ vect_grouped_store_supported (tree vectype, unsigned HOST_WIDE_INT count)
 	      sel[i * 2] = i;
 	      sel[i * 2 + 1] = i + nelt;
 	    }
-	    if (can_vec_perm_p (mode, false, sel))
-	      {
-		for (i = 0; i < nelt; i++)
-		  sel[i] += nelt / 2;
-		if (can_vec_perm_p (mode, false, sel))
-		  return true;
-	      }
+	  if (can_vec_perm_p (mode, false, &sel))
+	    {
+	      for (i = 0; i < nelt; i++)
+		sel[i] += nelt / 2;
+	      if (can_vec_perm_p (mode, false, &sel))
+		return true;
+	    }
 	}
     }
 
@@ -4710,7 +4711,9 @@ vect_permute_store_chain (vec<tree> dr_chain,
   tree perm3_mask_low, perm3_mask_high;
   unsigned int i, n, log_length = exact_log2 (length);
   unsigned int j, nelt = TYPE_VECTOR_SUBPARTS (vectype);
-  unsigned char *sel = XALLOCAVEC (unsigned char, nelt);
+
+  auto_vec_perm_indices sel (nelt);
+  sel.quick_grow (nelt);
 
   result_chain->quick_grow (length);
   memcpy (result_chain->address (), dr_chain.address (),
@@ -5132,7 +5135,8 @@ vect_grouped_load_supported (tree vectype, bool single_element_p,
   if (VECTOR_MODE_P (mode))
     {
       unsigned int i, j, nelt = GET_MODE_NUNITS (mode);
-      unsigned char *sel = XALLOCAVEC (unsigned char, nelt);
+      auto_vec_perm_indices sel (nelt);
+      sel.quick_grow (nelt);
 
       if (count == 3)
 	{
@@ -5144,7 +5148,7 @@ vect_grouped_load_supported (tree vectype, bool single_element_p,
 		  sel[i] = 3 * i + k;
 		else
 		  sel[i] = 0;
-	      if (!can_vec_perm_p (mode, false, sel))
+	      if (!can_vec_perm_p (mode, false, &sel))
 		{
 		  if (dump_enabled_p ())
 		    dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
@@ -5157,7 +5161,7 @@ vect_grouped_load_supported (tree vectype, bool single_element_p,
 		  sel[i] = i;
 		else
 		  sel[i] = nelt + ((nelt + k) % 3) + 3 * (j++);
-	      if (!can_vec_perm_p (mode, false, sel))
+	      if (!can_vec_perm_p (mode, false, &sel))
 		{
 		  if (dump_enabled_p ())
 		    dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
@@ -5174,11 +5178,11 @@ vect_grouped_load_supported (tree vectype, bool single_element_p,
 	  gcc_assert (pow2p_hwi (count));
 	  for (i = 0; i < nelt; i++)
 	    sel[i] = i * 2;
-	  if (can_vec_perm_p (mode, false, sel))
+	  if (can_vec_perm_p (mode, false, &sel))
 	    {
 	      for (i = 0; i < nelt; i++)
 		sel[i] = i * 2 + 1;
-	      if (can_vec_perm_p (mode, false, sel))
+	      if (can_vec_perm_p (mode, false, &sel))
 		return true;
 	    }
         }
@@ -5292,7 +5296,9 @@ vect_permute_load_chain (vec<tree> dr_chain,
   tree vectype = STMT_VINFO_VECTYPE (vinfo_for_stmt (stmt));
   unsigned int i, j, log_length = exact_log2 (length);
   unsigned nelt = TYPE_VECTOR_SUBPARTS (vectype);
-  unsigned char *sel = XALLOCAVEC (unsigned char, nelt);
+
+  auto_vec_perm_indices sel (nelt);
+  sel.quick_grow (nelt);
 
   result_chain->quick_grow (length);
   memcpy (result_chain->address (), dr_chain.address (),
@@ -5486,10 +5492,12 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
   tree vectype = STMT_VINFO_VECTYPE (vinfo_for_stmt (stmt));
   unsigned int i;
   unsigned nelt = TYPE_VECTOR_SUBPARTS (vectype);
-  unsigned char *sel = XALLOCAVEC (unsigned char, nelt);
   stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
   loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_info);
 
+  auto_vec_perm_indices sel (nelt);
+  sel.quick_grow (nelt);
+
   result_chain->quick_grow (length);
   memcpy (result_chain->address (), dr_chain.address (),
 	  length * sizeof (tree));
@@ -5501,7 +5509,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
 	sel[i] = i * 2;
       for (i = 0; i < nelt / 2; ++i)
 	sel[nelt / 2 + i] = i * 2 + 1;
-      if (!can_vec_perm_p (TYPE_MODE (vectype), false, sel))
+      if (!can_vec_perm_p (TYPE_MODE (vectype), false, &sel))
 	{
 	  if (dump_enabled_p ())
 	    dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
@@ -5515,7 +5523,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
 	sel[i] = i * 2 + 1;
       for (i = 0; i < nelt / 2; ++i)
 	sel[nelt / 2 + i] = i * 2;
-      if (!can_vec_perm_p (TYPE_MODE (vectype), false, sel))
+      if (!can_vec_perm_p (TYPE_MODE (vectype), false, &sel))
 	{
 	  if (dump_enabled_p ())
 	    dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
@@ -5529,7 +5537,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
 	 For vector length 8 it is {4 5 6 7 8 9 10 11}.  */
       for (i = 0; i < nelt; i++)
 	sel[i] = nelt / 2 + i;
-      if (!can_vec_perm_p (TYPE_MODE (vectype), false, sel))
+      if (!can_vec_perm_p (TYPE_MODE (vectype), false, &sel))
 	{
 	  if (dump_enabled_p ())
 	    dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
@@ -5544,7 +5552,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
 	sel[i] = i;
       for (i = nelt / 2; i < nelt; i++)
 	sel[i] = nelt + i;
-      if (!can_vec_perm_p (TYPE_MODE (vectype), false, sel))
+      if (!can_vec_perm_p (TYPE_MODE (vectype), false, &sel))
 	{
 	  if (dump_enabled_p ())
 	    dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
@@ -5607,7 +5615,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
 	  sel[i] = 3 * k + (l % 3);
 	  k++;
 	}
-      if (!can_vec_perm_p (TYPE_MODE (vectype), false, sel))
+      if (!can_vec_perm_p (TYPE_MODE (vectype), false, &sel))
 	{
 	  if (dump_enabled_p ())
 	    dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
@@ -5621,7 +5629,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
 	 For vector length 8 it is {6 7 8 9 10 11 12 13}.  */
       for (i = 0; i < nelt; i++)
 	sel[i] = 2 * (nelt / 3) + (nelt % 3) + i;
-      if (!can_vec_perm_p (TYPE_MODE (vectype), false, sel))
+      if (!can_vec_perm_p (TYPE_MODE (vectype), false, &sel))
 	{
 	  if (dump_enabled_p ())
 	    dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
@@ -5634,7 +5642,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
 	 For vector length 8 it is {5 6 7 8 9 10 11 12}.  */
       for (i = 0; i < nelt; i++)
 	sel[i] = 2 * (nelt / 3) + 1 + i;
-      if (!can_vec_perm_p (TYPE_MODE (vectype), false, sel))
+      if (!can_vec_perm_p (TYPE_MODE (vectype), false, &sel))
 	{
 	  if (dump_enabled_p ())
 	    dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
@@ -5647,7 +5655,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
 	 For vector length 8 it is {3 4 5 6 7 8 9 10}.  */
       for (i = 0; i < nelt; i++)
 	sel[i] = (nelt / 3) + (nelt % 3) / 2 + i;
-      if (!can_vec_perm_p (TYPE_MODE (vectype), false, sel))
+      if (!can_vec_perm_p (TYPE_MODE (vectype), false, &sel))
 	{
 	  if (dump_enabled_p ())
 	    dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
@@ -5660,7 +5668,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
 	 For vector length 8 it is {5 6 7 8 9 10 11 12}.  */
       for (i = 0; i < nelt; i++)
 	sel[i] = 2 * (nelt / 3) + (nelt % 3) / 2 + i;
-      if (!can_vec_perm_p (TYPE_MODE (vectype), false, sel))
+      if (!can_vec_perm_p (TYPE_MODE (vectype), false, &sel))
 	{
 	  if (dump_enabled_p ())
 	    dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,