tree-optimization/107254 - check and support live lanes from permutes

The following fixes an omission from adding SLP permute nodes which
is live lanes originating from those.  We have to check that we
can extract the lane and have to actually code generate them.

	PR tree-optimization/107254
	* tree-vect-slp.cc (vect_slp_analyze_node_operations_1):
	For permutes also analyze live lanes.
	(vect_schedule_slp_node): For permutes also code generate
	live lane extracts.

	* gfortran.dg/vect/pr107254.f90: New testcase.

(cherry picked from commit 9ed4a849afb5b18b462bea311e7eee454c2c9f68)

2 files changed, 77 insertions, 5 deletions

diff --git a/gcc/testsuite/gfortran.dg/vect/pr107254.f90 b/gcc/testsuite/gfortran.dg/vect/pr107254.f90
new file mode 100644
index 0000000..85bcb5f
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/vect/pr107254.f90
@@ -0,0 +1,49 @@
+! { dg-do run }
+
+subroutine dlartg( f, g, s, r )
+  implicit none
+  double precision :: f, g, r, s
+  double precision :: d, p
+
+  d = sqrt( f*f + g*g )
+  p = 1.d0 / d
+  if( abs( f ) > 1 ) then
+     s = g*sign( p, f )
+     r = sign( d, f )
+  else
+     s = g*sign( p, f )
+     r = sign( d, f )
+  end if
+end subroutine
+
+subroutine dhgeqz( n, h, t )
+  implicit none
+  integer            n
+  double precision   h( n, * ), t( n, * )
+  integer            jc
+  double precision   c, s, temp, temp2, tempr
+  temp2 = 10d0
+  call dlartg( 10d0, temp2, s, tempr )
+  c = 0.9d0
+  s = 1.d0
+  do jc = 1, n
+     temp = c*h( 1, jc ) + s*h( 2, jc )
+     h( 2, jc ) = -s*h( 1, jc ) + c*h( 2, jc )
+     h( 1, jc ) = temp
+     temp2 = c*t( 1, jc ) + s*t( 2, jc )
+     t( 2, jc ) = -s*t( 1, jc ) + c*t( 2, jc )
+     t( 1, jc ) = temp2
+  enddo
+end subroutine dhgeqz
+
+program test
+  implicit none
+  double precision h(2,2), t(2,2)  
+  h = 0
+  t(1,1) = 1
+  t(2,1) = 0
+  t(1,2) = 0
+  t(2,2) = 0
+  call dhgeqz( 2, h, t )
+  if (t(2,2).ne.0) STOP 1
+end program test
diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
index 0223056..ec9c10a 100644
--- a/gcc/tree-vect-slp.cc
+++ b/gcc/tree-vect-slp.cc
@@ -4504,7 +4504,23 @@ vect_slp_analyze_node_operations_1 (vec_info *vinfo, slp_tree node,
 
   /* Handle purely internal nodes.  */
   if (SLP_TREE_CODE (node) == VEC_PERM_EXPR)
-    return vectorizable_slp_permutation (vinfo, NULL, node, cost_vec);
+    {
+      if (!vectorizable_slp_permutation (vinfo, NULL, node, cost_vec))
+	return false;
+
+      stmt_vec_info slp_stmt_info;
+      unsigned int i;
+      FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (node), i, slp_stmt_info)
+	{
+	  if (STMT_VINFO_LIVE_P (slp_stmt_info)
+	      && !vectorizable_live_operation (vinfo,
+					       slp_stmt_info, NULL, node,
+					       node_instance, i,
+					       false, cost_vec))
+	    return false;
+	}
+      return true;
+    }
 
   gcc_assert (STMT_SLP_TYPE (stmt_info) != loop_vect);
 
@@ -7344,8 +7360,6 @@ vect_schedule_slp_node (vec_info *vinfo,
 	}
     }
 
-  bool done_p = false;
-
   /* Handle purely internal nodes.  */
   if (SLP_TREE_CODE (node) == VEC_PERM_EXPR)
     {
@@ -7356,9 +7370,18 @@ vect_schedule_slp_node (vec_info *vinfo,
 	 but open-code it here (partly).  */
       bool done = vectorizable_slp_permutation (vinfo, &si, node, NULL);
       gcc_assert (done);
-      done_p = true;
+      stmt_vec_info slp_stmt_info;
+      unsigned int i;
+      FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (node), i, slp_stmt_info)
+	if (STMT_VINFO_LIVE_P (slp_stmt_info))
+	  {
+	    done = vectorizable_live_operation (vinfo,
+						slp_stmt_info, &si, node,
+						instance, i, true, NULL);
+	    gcc_assert (done);
+	  }
     }
-  if (!done_p)
+  else
     vect_transform_stmt (vinfo, stmt_info, &si, node, instance);
 }