re PR target/25413 (wrong alignment or incorrect address computation in vectorized code on Pentium 4 SSE)

2007-07-12  Dorit Nuzman  <dorit@il.ibm.com>
            Devang Patel  <dpatel@apple.com>

        PR tree-optimization/25413
        * targhooks.c (default_builtin_vector_alignment_reachable): New.
        * targhooks.h (default_builtin_vector_alignment_reachable): New.
        * tree.h (contains_packed_reference): New.
        * expr.c (contains_packed_reference): New.
        * tree-vect-analyze.c (vector_alignment_reachable_p): New.
        (vect_enhance_data_refs_alignment): Call
        vector_alignment_reachable_p.
        * target.h (vector_alignment_reachable): New builtin.
        * target-def.h (TARGET_VECTOR_ALIGNMENT_REACHABLE): New.
        * config/rs6000/rs6000.c (rs6000_vector_alignment_reachable): New.
        (TARGET_VECTOR_ALIGNMENT_REACHABLE): Define.


Co-Authored-By: Devang Patel <dpatel@apple.com>

From-SVN: r126591

1 files changed, 76 insertions, 27 deletions

diff --git a/gcc/tree-vect-analyze.c b/gcc/tree-vect-analyze.c
index 2b8f318..317e334 100644
--- a/gcc/tree-vect-analyze.c
+++ b/gcc/tree-vect-analyze.c
@@ -25,6 +25,7 @@ Software Foundation, 51 Franklin Street, Fifth Floor, Boston, MA
 #include "tm.h"
 #include "ggc.h"
 #include "tree.h"
+#include "target.h"
 #include "basic-block.h"
 #include "diagnostic.h"
 #include "tree-flow.h"
@@ -1379,6 +1380,76 @@ vect_verify_datarefs_alignment (loop_vec_info loop_vinfo)
 }
 
 
+/* Function vector_alignment_reachable_p
+
+   Return true if vector alignment for DR is reachable by peeling
+   a few loop iterations.  Return false otherwise.  */
+
+static bool
+vector_alignment_reachable_p (struct data_reference *dr)
+{
+  tree stmt = DR_STMT (dr);
+  stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
+  tree vectype = STMT_VINFO_VECTYPE (stmt_info);
+
+  if (DR_GROUP_FIRST_DR (stmt_info))
+    {
+      /* For interleaved access we peel only if number of iterations in
+	 the prolog loop ({VF - misalignment}), is a multiple of the
+	 number of the interleaved accesses.  */
+      int elem_size, mis_in_elements;
+      int nelements = TYPE_VECTOR_SUBPARTS (vectype);
+
+      /* FORNOW: handle only known alignment.  */
+      if (!known_alignment_for_access_p (dr))
+	return false;
+
+      elem_size = UNITS_PER_SIMD_WORD / nelements;
+      mis_in_elements = DR_MISALIGNMENT (dr) / elem_size;
+
+      if ((nelements - mis_in_elements) % DR_GROUP_SIZE (stmt_info))
+	return false;
+    }
+
+  /* If misalignment is known at the compile time then allow peeling
+     only if natural alignment is reachable through peeling.  */
+  if (known_alignment_for_access_p (dr) && !aligned_access_p (dr))
+    {
+      HOST_WIDE_INT elmsize = 
+		int_cst_value (TYPE_SIZE_UNIT (TREE_TYPE (vectype)));
+      if (vect_print_dump_info (REPORT_DETAILS))
+	{
+	  fprintf (vect_dump, "data size =" HOST_WIDE_INT_PRINT_DEC, elmsize);
+	  fprintf (vect_dump, ". misalignment = %d. ", DR_MISALIGNMENT (dr));
+	}
+      if (DR_MISALIGNMENT (dr) % elmsize)
+	{
+	  if (vect_print_dump_info (REPORT_DETAILS))
+	    fprintf (vect_dump, "data size does not divide the misalignment.\n");
+	  return false;
+	}
+    }
+
+  if (!known_alignment_for_access_p (dr))
+    {
+      tree type = (TREE_TYPE (DR_REF (dr)));
+      tree ba = DR_BASE_OBJECT (dr);
+      bool is_packed = false;
+
+      if (ba)
+	is_packed = contains_packed_reference (ba);
+
+      if (vect_print_dump_info (REPORT_DETAILS))
+	fprintf (vect_dump, "Unknown misalignment, is_packed = %d",is_packed);
+      if (targetm.vectorize.vector_alignment_reachable (type, is_packed))
+	return true;
+      else
+	return false;
+    }
+
+  return true;
+}
+
 /* Function vect_enhance_data_refs_alignment
 
    This pass will use loop versioning and loop peeling in order to enhance
@@ -1540,33 +1611,11 @@ vect_enhance_data_refs_alignment (loop_vec_info loop_vinfo)
 
       if (!DR_IS_READ (dr) && !aligned_access_p (dr))
         {
-	  if (DR_GROUP_FIRST_DR (stmt_info))
-	    {
-	      /* For interleaved access we peel only if number of iterations in
-		 the prolog loop ({VF - misalignment}), is a multiple of the
-		 number of the interleaved accesses.  */
-	      int elem_size, mis_in_elements;
-	      tree vectype = STMT_VINFO_VECTYPE (stmt_info);
-	      int nelements = TYPE_VECTOR_SUBPARTS (vectype);
-
-	      /* FORNOW: handle only known alignment.  */
-	      if (!known_alignment_for_access_p (dr))
-		{
-		  do_peeling = false;
-		  break;
-		}
-
-	      elem_size = UNITS_PER_SIMD_WORD / nelements;
-	      mis_in_elements = DR_MISALIGNMENT (dr) / elem_size;
-
-	      if ((nelements - mis_in_elements) % DR_GROUP_SIZE (stmt_info))
-		{
-		  do_peeling = false;
-		  break;
-		}
-	    }
-	  dr0 = dr;
-	  do_peeling = true;
+	  do_peeling = vector_alignment_reachable_p (dr);
+	  if (do_peeling)
+	    dr0 = dr;
+	  if (!do_peeling && vect_print_dump_info (REPORT_DETAILS))
+            fprintf (vect_dump, "vector alignment may not be reachable");
 	  break;
 	}
     }