extend.texi: Add fvect-cost-model flag.

gcc/ChangeLog:
2007-06-08  Harsha Jagasia <harsha.jagasia@amd.com>
            Tony Linthicum <tony.linthicum@amd.com>

	* doc/extend.texi: Add fvect-cost-model flag.
	* common.opt (fvect-cost-model): New flag.
	* tree-vectorizer.c (new_stmt_vec_info): Initialize inside and outside
	cost fields in stmt_vec_info struct for STMT.
	* tree-vectorizer.h (stmt_vec_info): Define inside and outside cost
	fields in stmt_vec_info struct and access functions for the same.
	(TARG_COND_BRANCH_COST): Define cost of conditional branch.
	(TARG_VEC_STMT_COST): Define cost of any vector operation, excluding
	load, store and vector to scalar operation.
	(TARG_VEC_TO_SCALAR_COST): Define cost of vector to scalar operation.
	(TARG_VEC_LOAD_COST): Define cost of aligned vector load.
	(TARG_VEC_UNALIGNED_LOAD_COST): Define cost of misasligned vector load.
	(TARG_VEC_STORE_COST): Define cost of vector store.
	(vect_estimate_min_profitable_iters): Define new function.
	* tree-vect-analyze.c (vect_analyze_operations): Add a compile-time
	check to evaluate if loop iterations are less than minimum profitable
	iterations determined by cost model or minimum vect loop bound defined
	by user, whichever is more conservative.
	* tree-vect-transform.c (vect_do_peeling_for_loop_bound): Add a
	run-time check to evaluate if loop iterations are less than minimum
	profitable iterations determined by cost model or minimum vect loop
	bound defined by user, whichever is more conservative.
	(vect_estimate_min_profitable_iterations): New function to estimate
	mimimimum iterartions required for vector version of loop to be
	profitable over scalar version.
        (vect_model_reduction_cost): New function.
	(vect_model_induction_cost): New function.
	(vect_model_simple_cost): New function.
	(vect_cost_strided_group_size): New function.
	(vect_model_store_cost): New function.
	(vect_model_load_cost): New function.
	(vectorizable_reduction): Call vect_model_reduction_cost during
	analysis phase.
	(vectorizable_induction): Call vect_model_induction_cost during
	analysis phase.
	(vectorizable_load): Call vect_model_load_cost during analysis phase.
	(vectorizable_store): Call vect_model_store_cost during analysis phase.
	(vectorizable_call, vectorizable_assignment, vectorizable_operation,
	vectorizable_promotion, vectorizable_demotion): Call 
	vect_model_simple_cost during analysis phase.

gcc/testsuite/ChangeLog:
2007-06-08  Harsha Jagasia <harsha.jagasia@amd.com>

	* gcc.dg/vect/costmodel: New directory.
	* gcc.dg/vect/costmodel/i386: New directory.
	* gcc.dg/vect/costmodel/i386/i386-costmodel-vect.exp: New testsuite.
	* gcc.dg/vect/costmodel/i386/costmodel-fast-math-vect-pr29925.c:
	New test.
	* gcc.dg/vect/costmodel/i386/costmodel-vect-31.c: New test.
	* gcc.dg/vect/costmodel/i386/costmodel-vect-33.c: New test.
	* gcc.dg/vect/costmodel/i386/costmodel-vect-68.c: New test.
	* gcc.dg/vect/costmodel/i386/costmodel-vect-reduc-1char.c: New test.
	* gcc.dg/vect/costmodel/x86_64: New directory.
	* gcc.dg/vect/costmodel/x86_64/x86_64-costmodel-vect.exp:
	New testsuite.	
	* gcc.dg/vect/costmodel/x86_64/costmodel-fast-math-vect-pr29925.c:
	New test.
	* gcc.dg/vect/costmodel/x86_64/costmodel-vect-31.c: New test.
	* gcc.dg/vect/costmodel/x86_64/costmodel-vect-33.c: New test.
	* gcc.dg/vect/costmodel/x86_64/costmodel-vect-68.c: New test.
	* gcc.dg/vect/costmodel/x86_64/costmodel-vect-reduc-1char.c: New test.
	* gcc.dg/vect/costmodel/x86_64/costmodel-pr30843.c: New test.

Co-Authored-By: Tony Linthicum <tony.linthicum@amd.com>

From-SVN: r125575

1 files changed, 48 insertions, 8 deletions

diff --git a/gcc/tree-vect-analyze.c b/gcc/tree-vect-analyze.c
index 454cae6..b4cd79d 100644
--- a/gcc/tree-vect-analyze.c
+++ b/gcc/tree-vect-analyze.c
@@ -1,5 +1,5 @@
 /* Analysis Utilities for Loop Vectorization.
-   Copyright (C) 2003,2004,2005,2006 Free Software Foundation, Inc.
+   Copyright (C) 2003, 2004, 2005, 2006, 2007 Free Software Foundation, Inc.
    Contributed by Dorit Naishlos <dorit@il.ibm.com>
 
 This file is part of GCC.
@@ -300,6 +300,9 @@ vect_analyze_operations (loop_vec_info loop_vinfo)
   tree phi;
   stmt_vec_info stmt_info;
   bool need_to_vectorize = false;
+  int min_profitable_iters;
+  int min_scalar_loop_bound;
+  unsigned int th;
 
   if (vect_print_dump_info (REPORT_DETAILS))
     fprintf (vect_dump, "=== vect_analyze_operations ===");
@@ -443,8 +446,6 @@ vect_analyze_operations (loop_vec_info loop_vinfo)
 	} /* stmts in bb */
     } /* bbs */
 
-  /* TODO: Analyze cost. Decide if worth while to vectorize.  */
-
   /* All operations in the loop are either irrelevant (deal with loop
      control, or dead), or only used outside the loop and can be moved
      out of the loop (e.g. invariants, inductions).  The loop can be 
@@ -468,16 +469,55 @@ vect_analyze_operations (loop_vec_info loop_vinfo)
         vectorization_factor, LOOP_VINFO_INT_NITERS (loop_vinfo));
 
   if (LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)
-      && ((LOOP_VINFO_INT_NITERS (loop_vinfo) < vectorization_factor)
-	  || (LOOP_VINFO_INT_NITERS (loop_vinfo) <=
-		((unsigned) (PARAM_VALUE (PARAM_MIN_VECT_LOOP_BOUND)) 
-					   * vectorization_factor))))
+      && (LOOP_VINFO_INT_NITERS (loop_vinfo) < vectorization_factor))
     {
       if (vect_print_dump_info (REPORT_UNVECTORIZED_LOOPS))
-	fprintf (vect_dump, "not vectorized: iteration count too small.");
+        fprintf (vect_dump, "not vectorized: iteration count too small.");
+      if (vect_print_dump_info (REPORT_DETAILS))
+        fprintf (vect_dump,"not vectorized: iteration count smaller than "
+                 "vectorization factor.");
       return false;
     }
 
+  /* Analyze cost. Decide if worth while to vectorize.  */
+
+  min_profitable_iters = vect_estimate_min_profitable_iters (loop_vinfo);
+
+  if (min_profitable_iters < 0)
+    {
+      if (vect_print_dump_info (REPORT_UNVECTORIZED_LOOPS))
+        fprintf (vect_dump, "not vectorized: vectorization not profitable.");
+      if (vect_print_dump_info (REPORT_DETAILS))
+        fprintf (vect_dump, "not vectorized: vector version will never be "
+                 "profitable.");
+      return false;
+    }
+
+  min_scalar_loop_bound = (PARAM_VALUE (PARAM_MIN_VECT_LOOP_BOUND))
+                          * vectorization_factor;
+
+  /* Use the cost model only if it is more conservative than user specified
+     threshold.  */
+
+  th = (unsigned) min_scalar_loop_bound;
+  if (min_profitable_iters 
+      && (!min_scalar_loop_bound
+          || min_profitable_iters > min_scalar_loop_bound))
+    th = (unsigned) min_profitable_iters;
+
+  if (LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)
+      && LOOP_VINFO_INT_NITERS (loop_vinfo) < th)
+    {
+      if (vect_print_dump_info (REPORT_UNVECTORIZED_LOOPS))	      
+        fprintf (vect_dump, "not vectorized: vectorization not "
+                 "profitable.");
+      if (vect_print_dump_info (REPORT_DETAILS))	      
+        fprintf (vect_dump, "not vectorized: iteration count smaller than "
+                 "user specified loop bound parameter or minimum "
+                 "profitable iterations (whichever is more conservative).");
+      return false;
+    }  
+
   if (!LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)
       || LOOP_VINFO_INT_NITERS (loop_vinfo) % vectorization_factor != 0
       || LOOP_PEELING_FOR_ALIGNMENT (loop_vinfo))