re PR tree-optimization/69297 (Performance regression after r230020)

2016-01-18  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/69297
	* tree-vect-slp.c (vect_bb_slp_scalar_cost): Count each scalar
	stmt at most once.
	(vect_bb_vectorization_profitable_p): Clear visited flag again.

	* gcc.dg/vect/costmodel/x86_64/costmodel-pr69297.c: New testcase.

From-SVN: r232519

gcc/ChangeLog

+2016-01-18  Richard Biener  <rguenther@suse.de>
+
+	PR tree-optimization/69297
+	* tree-vect-slp.c (vect_bb_slp_scalar_cost): Count each scalar
+	stmt at most once.
+	(vect_bb_vectorization_profitable_p): Clear visited flag again.
+
 2016-01-18  Yuri Rumyantsev  <ysrumyan@gmail.com>
 
 	PR middle-end/68542

gcc/testsuite/ChangeLog

+2016-01-18  Richard Biener  <rguenther@suse.de>
+
+	PR tree-optimization/69297
+	* gcc.dg/vect/costmodel/x86_64/costmodel-pr69297.c: New testcase.
+
 2016-01-18  Joseph Myers  <joseph@codesourcery.com>
 
 	* gcc.target/mips/mips-3d-1.c: Use forbid_cpu=octeon.* in

gcc/testsuite/gcc.dg/vect/costmodel/x86_64/costmodel-pr69297.c

+/* { dg-do compile } */
+/* { dg-additional-options "-march=core-avx2 -fdump-tree-slp-details" } */
+
+#define abs(x) (x) < 0 ? -(x) : (x)
+int
+foo (int* diff)
+{
+  int k, satd = 0, m[16], d[16];
+  
+    m[ 0] = diff[ 0] + diff[12];
+    m[ 4] = diff[ 4] + diff[ 8];
+    m[ 8] = diff[ 4] - diff[ 8];
+    m[12] = diff[ 0] - diff[12];
+    m[ 1] = diff[ 1] + diff[13];
+    m[ 5] = diff[ 5] + diff[ 9];
+    m[ 9] = diff[ 5] - diff[ 9];
+    m[13] = diff[ 1] - diff[13];
+    m[ 2] = diff[ 2] + diff[14];
+    m[ 6] = diff[ 6] + diff[10];
+    m[10] = diff[ 6] - diff[10];
+    m[14] = diff[ 2] - diff[14];
+    m[ 3] = diff[ 3] + diff[15];
+    m[ 7] = diff[ 7] + diff[11];
+    m[11] = diff[ 7] - diff[11];
+    m[15] = diff[ 3] - diff[15];
+    
+    d[ 0] = m[ 0] + m[ 4];
+    d[ 8] = m[ 0] - m[ 4];
+    d[ 4] = m[ 8] + m[12];
+    d[12] = m[12] - m[ 8];
+    d[ 1] = m[ 1] + m[ 5];
+    d[ 9] = m[ 1] - m[ 5];
+    d[ 5] = m[ 9] + m[13];
+    d[13] = m[13] - m[ 9];
+    d[ 2] = m[ 2] + m[ 6];
+    d[10] = m[ 2] - m[ 6];
+    d[ 6] = m[10] + m[14];
+    d[14] = m[14] - m[10];
+    d[ 3] = m[ 3] + m[ 7];
+    d[11] = m[ 3] - m[ 7];
+    d[ 7] = m[11] + m[15];
+    d[15] = m[15] - m[11];
+    
+    m[ 0] = d[ 0] + d[ 3];
+    m[ 1] = d[ 1] + d[ 2];
+    m[ 2] = d[ 1] - d[ 2];
+    m[ 3] = d[ 0] - d[ 3];
+    m[ 4] = d[ 4] + d[ 7];
+    m[ 5] = d[ 5] + d[ 6];
+    m[ 6] = d[ 5] - d[ 6];
+    m[ 7] = d[ 4] - d[ 7];
+    m[ 8] = d[ 8] + d[11];
+    m[ 9] = d[ 9] + d[10];
+    m[10] = d[ 9] - d[10];
+    m[11] = d[ 8] - d[11];
+    m[12] = d[12] + d[15];
+    m[13] = d[13] + d[14];
+    m[14] = d[13] - d[14];
+    m[15] = d[12] - d[15];
+    
+    d[ 0] = m[ 0] + m[ 1];
+    d[ 1] = m[ 0] - m[ 1];
+    d[ 2] = m[ 2] + m[ 3];
+    d[ 3] = m[ 3] - m[ 2];
+    d[ 4] = m[ 4] + m[ 5];
+    d[ 5] = m[ 4] - m[ 5];
+    d[ 6] = m[ 6] + m[ 7];
+    d[ 7] = m[ 7] - m[ 6];
+    d[ 8] = m[ 8] + m[ 9];
+    d[ 9] = m[ 8] - m[ 9];
+    d[10] = m[10] + m[11];
+    d[11] = m[11] - m[10];
+    d[12] = m[12] + m[13];
+    d[13] = m[12] - m[13];
+    d[14] = m[14] + m[15];
+    d[15] = m[15] - m[14];
+    for (k=0; k<16; k++)
+      satd += abs(d[k]);
+  return satd;
+}
+
+/* { dg-final { scan-tree-dump "vectorization is not profitable" "slp1" } } */
+/* { dg-final { scan-tree-dump-not "basic block vectorized" "slp1" } } */

gcc/tree-vect-slp.c

@@ -2409,6 +2409,11 @@ vect_bb_slp_scalar_cost (basic_block bb,
       if ((*life)[i])
 	continue;
 
+      /* Count scalar stmts only once.  */
+      if (gimple_visited_p (stmt))
+	continue;
+      gimple_set_visited (stmt, true);
+
       stmt_info = vinfo_for_stmt (stmt);
       if (STMT_VINFO_DATA_REF (stmt_info))
         {
@@ -2451,6 +2456,11 @@ vect_bb_vectorization_profitable_p (bb_vec_info bb_vinfo)
 					      &life);
     }
 
+  /* Unset visited flag.  */
+  for (gimple_stmt_iterator gsi = bb_vinfo->region_begin;
+       gsi_stmt (gsi) != gsi_stmt (bb_vinfo->region_end); gsi_next (&gsi))
+    gimple_set_visited  (gsi_stmt (gsi), false);
+
   /* Complete the target-specific cost calculation.  */
   finish_cost (BB_VINFO_TARGET_COST_DATA (bb_vinfo), &vec_prologue_cost,
 	       &vec_inside_cost, &vec_epilogue_cost);