diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index c751ea7ed6c..9ba7b943efc 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,9 @@
+2015-05-04  Richard Biener  <rguenther@suse.de>
+
+	PR tree-optimization/65935
+	* tree-vect-slp.c (vect_build_slp_tree): If we swapped operands
+	then make sure to apply that swapping to the IL.
+
 2015-05-04  Jakub Jelinek  <jakub@redhat.com>
 
 	* Makefile.in (PATCHLEVEL_c): New variable.
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index eaff1ab5d76..719e013cbcc 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2015-05-04  Richard Biener  <rguenther@suse.de>
+
+	PR tree-optimization/65935
+	* gcc.dg/vect/bb-slp-pr65935.c: New testcase.
+
 2015-05-03  Christophe Lyon  <christophe.lyon@linaro.org>
 
 	* gcc.target/aarch64/advsimd-intrinsics/binary_op.inc: Call CHECK
diff --git a/gcc/testsuite/gcc.dg/vect/bb-slp-pr65935.c b/gcc/testsuite/gcc.dg/vect/bb-slp-pr65935.c
new file mode 100644
index 00000000000..057dc20544d
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/bb-slp-pr65935.c
@@ -0,0 +1,63 @@
+/* { dg-do run } */
+/* { dg-additional-options "-O3" } */
+/* { dg-require-effective-target vect_double } */
+
+#include "tree-vect.h"
+
+extern void abort (void);
+extern void *malloc (__SIZE_TYPE__);
+
+struct site {
+    struct {
+	struct {
+	    double real;
+	    double imag;
+	} e[3][3];
+    } link[32];
+    double phase[32];
+} *lattice;
+int sites_on_node;
+
+void rephase (void)
+{
+  int i,j,k,dir;
+  struct site *s;
+  for(i=0,s=lattice;i<sites_on_node;i++,s++)
+    for(dir=0;dir<32;dir++)
+      for(j=0;j<3;j++)for(k=0;k<3;k++)
+	{
+	  s->link[dir].e[j][k].real *= s->phase[dir];
+	  s->link[dir].e[j][k].imag *= s->phase[dir];
+	}
+}
+
+int main()
+{
+  int i,j,k;
+  check_vect ();
+  sites_on_node = 1;
+  lattice = malloc (sizeof (struct site) * sites_on_node);
+  for (i = 0; i < 32; ++i)
+    {
+      lattice->phase[i] = i;
+      for (j = 0; j < 3; ++j)
+	for (k = 0; k < 3; ++k)
+	  {
+	    lattice->link[i].e[j][k].real = 1.0;
+	    lattice->link[i].e[j][k].imag = 1.0;
+	    __asm__ volatile ("" : : : "memory");
+	  }
+    }
+  rephase ();
+  for (i = 0; i < 32; ++i)
+    for (j = 0; j < 3; ++j)
+      for (k = 0; k < 3; ++k)
+	if (lattice->link[i].e[j][k].real != i
+	    || lattice->link[i].e[j][k].imag != i)
+	  abort ();
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "basic block vectorized" 1 "slp1" } } */
+/* { dg-final { cleanup-tree-dump "slp1" } } */
+/* { dg-final { cleanup-tree-dump "slp2" } } */
diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c
index 60f257b4da9..2b8f9bde5ae 100644
--- a/gcc/tree-vect-slp.c
+++ b/gcc/tree-vect-slp.c
@@ -1081,13 +1081,25 @@ vect_build_slp_tree (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo,
 		dump_printf (MSG_NOTE, "%d ", j);
 	      }
 	  dump_printf (MSG_NOTE, "\n");
-	  /* And try again ... */
+	  /* And try again with scratch 'matches' ... */
+	  bool *tem = XALLOCAVEC (bool, group_size);
 	  if (vect_build_slp_tree (loop_vinfo, bb_vinfo, &child,
 				   group_size, max_nunits, loads,
 				   vectorization_factor,
-				   matches, npermutes, &this_tree_size,
+				   tem, npermutes, &this_tree_size,
 				   max_tree_size))
 	    {
+	      /* ... so if successful we can apply the operand swapping
+		 to the GIMPLE IL.  This is necessary because for example
+		 vect_get_slp_defs uses operand indexes and thus expects
+		 canonical operand order.  */
+	      for (j = 0; j < group_size; ++j)
+		if (!matches[j])
+		  {
+		    gimple stmt = SLP_TREE_SCALAR_STMTS (*node)[j];
+		    swap_ssa_operands (stmt, gimple_assign_rhs1_ptr (stmt),
+				       gimple_assign_rhs2_ptr (stmt));
+		  }
 	      oprnd_info->def_stmts = vNULL;
 	      SLP_TREE_CHILDREN (*node).quick_push (child);
 	      continue;