re PR tree-optimization/37194 (Autovectorization of small constant iteration…

re PR tree-optimization/37194 (Autovectorization of small constant iteration loop degrades performance)

	PR tree-optimization/37194
	* tree-vect-transform.c (vect_estimate_min_profitable_iters):
	Don't add the cost of cost model guard in prologue to scalar 
	outside cost in case of known number of iterations.

From-SVN: r143183

gcc/ChangeLog

+2009-01-08  Ira Rosen  <irar@il.ibm.com>
+
+	PR tree-optimization/37194
+	* tree-vect-transform.c (vect_estimate_min_profitable_iters):
+	Don't add the cost of cost model guard in prologue to scalar 
+	outside cost in case of known number of iterations.
+
 2009-01-07  Nathan Froyd  <froydnj@codesourcery.com>
 	    Alan Modra  <amodra@bigpond.net.au>
 

gcc/testsuite/ChangeLog

+2009-01-08  Ira Rosen  <irar@il.ibm.com>
+
+	PR tree-optimization/37194
+	* gcc.dg/vect/costmodel/ppc/costmodel-pr37194.c: New test.
+
 2009-01-07  Jakub Jelinek  <jakub@redhat.com>
 
 	PR c++/38725

gcc/testsuite/gcc.dg/vect/costmodel/ppc/costmodel-pr37194.c

+/* { dg-require-effective-target vect_float } */
+/* { dg-do compile } */
+
+#include <stdlib.h>
+#include "../../tree-vect.h"
+
+__attribute__ ((noinline)) void 
+ggSpectrum_Set8(float * data, float d) 
+{
+   int i;
+
+   for (i = 0; i < 8; i++)
+      data[i] = d;
+}
+
+__attribute__ ((noinline)) void 
+ggSpectrum_Set20(float * data, float d) 
+{
+   int i;
+
+   for (i = 0; i < 20; i++)
+      data[i] = d;
+}
+
+/* { dg-final { scan-tree-dump-times "vectorization not profitable" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
+/* { dg-final { cleanup-tree-dump "vect" } } */
+

gcc/tree-vect-transform.c

@@ -122,7 +122,6 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo)
   int vec_outside_cost = 0;
   int scalar_single_iter_cost = 0;
   int scalar_outside_cost = 0;
-  bool runtime_test = false;
   int vf = LOOP_VINFO_VECT_FACTOR (loop_vinfo);
   struct loop *loop = LOOP_VINFO_LOOP (loop_vinfo);
   basic_block *bbs = LOOP_VINFO_BBS (loop_vinfo);
@@ -141,15 +140,7 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo)
       return 0;
     }
 
-  /* If the number of iterations is unknown, or the
-     peeling-for-misalignment amount is unknown, we will have to generate
-     a runtime test to test the loop count against the threshold.    */
-  if (!LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)
-      || (byte_misalign < 0))
-    runtime_test = true;
-
   /* Requires loop versioning tests to handle misalignment.  */
-
   if (VEC_length (gimple, LOOP_VINFO_MAY_MISALIGN_STMTS (loop_vinfo)))
     {
       /*  FIXME: Make cost depend on complexity of individual check.  */
@@ -245,7 +236,6 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo)
          not known. Hence guards remain the same.  */
       peel_guard_costs +=  2 * (TARG_COND_TAKEN_BRANCH_COST
                               + TARG_COND_NOT_TAKEN_BRANCH_COST);
-
     }
   else 
     {
@@ -337,7 +327,12 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo)
      conditions/branch directions.  Change the estimates below to
      something more reasonable.  */
 
-  if (runtime_test)
+  /* If the number of iterations is known and we do not do versioning, we can
+     decide whether to vectorize at compile time. Hence the scalar version
+     do not carry cost model guard costs.  */
+  if (!LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)
+      || VEC_length (gimple, LOOP_VINFO_MAY_MISALIGN_STMTS (loop_vinfo))
+      || VEC_length (ddr_p, LOOP_VINFO_MAY_ALIAS_DDRS (loop_vinfo)))
     {
       /* Cost model check occurs at versioning.  */
       if (VEC_length (gimple, LOOP_VINFO_MAY_MISALIGN_STMTS (loop_vinfo))
@@ -345,8 +340,8 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo)
 	scalar_outside_cost += TARG_COND_NOT_TAKEN_BRANCH_COST;
       else
 	{
-	  /* Cost model occurs at prologue generation.  */
-	  if (LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo))
+	  /* Cost model check occurs at prologue generation.  */
+	  if (LOOP_PEELING_FOR_ALIGNMENT (loop_vinfo) < 0)
 	    scalar_outside_cost += 2 * TARG_COND_TAKEN_BRANCH_COST
 	      + TARG_COND_NOT_TAKEN_BRANCH_COST;
 	  /* Cost model check occurs at epilogue generation.  */