tree-optimization/107212 - SLP reduction of reduction paths

The following fixes an issue with how we handle epilogue generation
for SLP reductions of reduction paths where the actual live lanes
are not "canonical".  We need to make sure to identify all live
lanes as reductions and thus have to iterate over all participating
SLP lanes when walking the reduction SSA use-def chain.  Also the
previous attempt likely to mitigate such issue in
vectorizable_live_operation is misguided and has to be removed.

	PR tree-optimization/107212
	* tree-vect-loop.cc (vectorizable_reduction): Make sure to
	set STMT_VINFO_REDUC_DEF for all live lanes in a SLP
	reduction.
	(vectorizable_live_operation): Do not pun to the SLP
	node representative for reduction epilogue generation.

	* gcc.dg/vect/pr107212-1.c: New testcase.
	* gcc.dg/vect/pr107212-2.c: Likewise.

3 files changed, 63 insertions, 7 deletions

diff --git a/gcc/testsuite/gcc.dg/vect/pr107212-1.c b/gcc/testsuite/gcc.dg/vect/pr107212-1.c
new file mode 100644
index 0000000..5343f9b
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr107212-1.c
@@ -0,0 +1,27 @@
+/* { dg-do run } */
+
+#include "tree-vect.h"
+
+int main()
+{
+  check_vect ();
+
+  unsigned int tab[6][2] = { {69, 73}, {36, 40}, {24, 16},
+        {16, 11}, {4, 5}, {3, 1} };
+
+  int sum_0 = 0;
+  int sum_1 = 0;
+
+  for(int t=0; t<6; t++) {
+      sum_0 += tab[t][0];
+      sum_1 += tab[t][1];
+  }
+
+  int x1 = (sum_0 < 100);
+  int x2 = (sum_0 > 200);
+
+  if (x1 || x2 || sum_1 != 146)
+    __builtin_abort ();
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.dg/vect/pr107212-2.c b/gcc/testsuite/gcc.dg/vect/pr107212-2.c
new file mode 100644
index 0000000..109c2b9
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr107212-2.c
@@ -0,0 +1,23 @@
+/* { dg-do run } */
+
+#include "tree-vect.h"
+
+int sum_1 = 0;
+
+int main()
+{
+  check_vect ();
+
+  unsigned int tab[6][2] = {{150, 0}, {0, 0}, {0, 0}, {0, 0}, {0, 0}, {0, 0}};
+  
+  int sum_0 = 0;
+  
+  for (int t = 0; t < 6; t++) {
+    sum_0 += tab[t][0];
+    sum_1 += tab[t][0];
+  }
+  
+  if (sum_0 < 100 || sum_0 > 200)
+    __builtin_abort();
+  return 0;
+}
diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
index 2536cc3..1996ecf 100644
--- a/gcc/tree-vect-loop.cc
+++ b/gcc/tree-vect-loop.cc
@@ -6822,10 +6822,20 @@ vectorizable_reduction (loop_vec_info loop_vinfo,
 	}
       if (!REDUC_GROUP_FIRST_ELEMENT (vdef))
 	only_slp_reduc_chain = false;
-      /* ???  For epilogue generation live members of the chain need
+      /* For epilogue generation live members of the chain need
          to point back to the PHI via their original stmt for
-	 info_for_reduction to work.  */
-      if (STMT_VINFO_LIVE_P (vdef))
+	 info_for_reduction to work.  For SLP we need to look at
+	 all lanes here - even though we only will vectorize from
+	 the SLP node with live lane zero the other live lanes also
+	 need to be identified as part of a reduction to be able
+	 to skip code generation for them.  */
+      if (slp_for_stmt_info)
+	{
+	  for (auto s : SLP_TREE_SCALAR_STMTS (slp_for_stmt_info))
+	    if (STMT_VINFO_LIVE_P (s))
+	      STMT_VINFO_REDUC_DEF (vect_orig_stmt (s)) = phi_info;
+	}
+      else if (STMT_VINFO_LIVE_P (vdef))
 	STMT_VINFO_REDUC_DEF (def) = phi_info;
       gimple_match_op op;
       if (!gimple_extract_op (vdef->stmt, &op))
@@ -9601,10 +9611,6 @@ vectorizable_live_operation (vec_info *vinfo,
 	     all involved stmts together.  */
 	  else if (slp_index != 0)
 	    return true;
-	  else
-	    /* For SLP reductions the meta-info is attached to
-	       the representative.  */
-	    stmt_info = SLP_TREE_REPRESENTATIVE (slp_node);
 	}
       stmt_vec_info reduc_info = info_for_reduction (loop_vinfo, stmt_info);
       gcc_assert (reduc_info->is_reduc_info);