tree-optimization/114375 - disallow SLP discovery of permuted mask loads

We cannot currently handle permutations of mask loads in code generation
or permute optimization.  But we simply drop any permutation on the
floor, so the following instead rejects the SLP build rather than
producing wrong-code.  I've also made sure to reject them in
vectorizable_load for completeness.

	PR tree-optimization/114375
	* tree-vect-slp.cc (vect_build_slp_tree_2): Compute the
	load permutation for masked loads but reject it when any
	such is necessary.
	* tree-vect-stmts.cc (vectorizable_load): Reject masked
	VMAT_ELEMENTWISE and VMAT_STRIDED_SLP as those are not
	supported.

	* gcc.dg/vect/vect-pr114375.c: New testcase.

3 files changed, 81 insertions, 10 deletions

diff --git a/gcc/testsuite/gcc.dg/vect/vect-pr114375.c b/gcc/testsuite/gcc.dg/vect/vect-pr114375.c
new file mode 100644
index 0000000..1e1cb01
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-pr114375.c
@@ -0,0 +1,44 @@
+/* { dg-additional-options "-mavx2" { target avx2_runtime } } */
+
+#include "tree-vect.h"
+
+int a[512];
+int b[512];
+int c[512];
+
+void __attribute__((noipa))
+foo(int * __restrict p)
+{
+  for (int i = 0; i < 64; ++i)
+    {
+      int tem = 2, tem2 = 2;
+      if (a[4*i + 1])
+        tem = p[4*i];
+      if (a[4*i])
+        tem2 = p[4*i + 2];
+      b[2*i] = tem2;
+      b[2*i+1] = tem;
+      if (a[4*i + 2])
+        tem = p[4*i + 1];
+      if (a[4*i + 3])
+        tem2 = p[4*i + 3];
+      c[2*i] = tem2;
+      c[2*i+1] = tem;
+    }
+}
+int main()
+{
+  check_vect ();
+
+  for (int i = 0; i < 512; ++i)
+    a[i] = (i >> 1) & 1;
+
+  foo (a);
+
+  if (c[0] != 1 || c[1] != 0 || c[2] != 1 || c[3] != 0
+      || b[0] != 2 || b[1] != 2 || b[2] != 2 || b[3] != 2)
+    abort ();
+
+  return 0;
+}
+
diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
index 527b06c..23f9593 100644
--- a/gcc/tree-vect-slp.cc
+++ b/gcc/tree-vect-slp.cc
@@ -1921,12 +1921,7 @@ vect_build_slp_tree_2 (vec_info *vinfo, slp_tree node,
   if (STMT_VINFO_DATA_REF (stmt_info)
       && DR_IS_READ (STMT_VINFO_DATA_REF (stmt_info)))
     {
-      if (gcall *stmt = dyn_cast <gcall *> (stmt_info->stmt))
-	gcc_assert (gimple_call_internal_p (stmt, IFN_MASK_LOAD)
-		    || gimple_call_internal_p (stmt, IFN_GATHER_LOAD)
-		    || gimple_call_internal_p (stmt, IFN_MASK_GATHER_LOAD)
-		    || gimple_call_internal_p (stmt, IFN_MASK_LEN_GATHER_LOAD));
-      else if (STMT_VINFO_GATHER_SCATTER_P (stmt_info))
+      if (STMT_VINFO_GATHER_SCATTER_P (stmt_info))
 	gcc_assert (DR_IS_READ (STMT_VINFO_DATA_REF (stmt_info)));
       else
 	{
@@ -1943,19 +1938,43 @@ vect_build_slp_tree_2 (vec_info *vinfo, slp_tree node,
 	  load_permutation.create (group_size);
 	  stmt_vec_info first_stmt_info
 	    = DR_GROUP_FIRST_ELEMENT (SLP_TREE_SCALAR_STMTS (node)[0]);
+	  bool any_permute = false;
 	  FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (node), j, load_info)
 	    {
 	      int load_place;
 	      if (STMT_VINFO_GROUPED_ACCESS (stmt_info))
 		load_place = vect_get_place_in_interleaving_chain
-				(load_info, first_stmt_info);
+		    (load_info, first_stmt_info);
 	      else
 		load_place = 0;
 	      gcc_assert (load_place != -1);
-	      load_permutation.safe_push (load_place);
+	      any_permute |= load_place != j;
+	      load_permutation.quick_push (load_place);
+	    }
+
+	  if (gcall *stmt = dyn_cast <gcall *> (stmt_info->stmt))
+	    {
+	      gcc_assert (gimple_call_internal_p (stmt, IFN_MASK_LOAD)
+			  || gimple_call_internal_p (stmt, IFN_GATHER_LOAD)
+			  || gimple_call_internal_p (stmt, IFN_MASK_GATHER_LOAD)
+			  || gimple_call_internal_p (stmt,
+						     IFN_MASK_LEN_GATHER_LOAD));
+	      load_permutation.release ();
+	      /* We cannot handle permuted masked loads, see PR114375.  */
+	      if (any_permute
+		  || (STMT_VINFO_GROUPED_ACCESS (stmt_info)
+		      && DR_GROUP_SIZE (first_stmt_info) != group_size)
+		  || STMT_VINFO_STRIDED_P (stmt_info))
+		{
+		  matches[0] = false;
+		  return NULL;
+		}
+	    }
+	  else
+	    {
+	      SLP_TREE_LOAD_PERMUTATION (node) = load_permutation;
+	      return node;
 	    }
-	  SLP_TREE_LOAD_PERMUTATION (node) = load_permutation;
-	  return node;
 	}
     }
   else if (gimple_assign_single_p (stmt_info->stmt)
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index e861743..5a4eb13 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -10080,6 +10080,14 @@ vectorizable_load (vec_info *vinfo,
 			     "unsupported masked emulated gather.\n");
 	  return false;
 	}
+      else if (memory_access_type == VMAT_ELEMENTWISE
+	       || memory_access_type == VMAT_STRIDED_SLP)
+	{
+	  if (dump_enabled_p ())
+	    dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
+			     "unsupported masked strided access.\n");
+	  return false;
+	}
     }
 
   bool costing_p = !vec_stmt;