re PR tree-optimization/55590 (SRA still produces unnecessarily unaligned memory accesses)

2012-12-07  Martin Jambor  <mjambor@suse.cz>

	PR tree-optimization/55590
	* tree-sra.c (build_ref_for_offset): Use get_object_alignment_1 to
	get base alignment.

	* testsuite/gcc.target/i386/pr55590-1.c: New test.
	* testsuite/gcc.target/i386/pr55590-2.c: Likewise.

From-SVN: r194300

gcc/ChangeLog

-2012-12-06  Jason Merrill  <jason@redhat.com>
+2012-12-07  Martin Jambor  <mjambor@suse.cz>
+
+	PR tree-optimization/55590
+	* tree-sra.c (build_ref_for_offset): Use get_object_alignment_1 to
+	get base alignment.
 
 2012-12-06  Uros Bizjak  <ubizjak@gmail.com>
 	    H.J. Lu  <hongjiu.lu@intel.com>

gcc/testsuite/ChangeLog

+2012-12-07  Martin Jambor  <mjambor@suse.cz>
+
+	PR tree-optimization/55590
+	* gcc.target/i386/pr55590-1.c: New test.
+	* gcc.target/i386/pr55590-2.c: Likewise.
+
 2012-12-07  Paolo Carlini  <paolo.carlini@oracle.com>
 
 	PR c++/54975

gcc/testsuite/gcc.target/i386/pr55590-1.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx" } */
+
+#include <immintrin.h>
+
+struct S
+{
+  __m128 a, b;
+};
+
+struct T
+{
+  int a;
+  struct S s;
+};
+
+
+void foo (struct T *p, __m128 v)
+{
+  struct S s;
+
+  s = p->s;
+  s.b = _mm_add_ps(s.b, v);
+  p->s = s;
+}
+
+/* { dg-final { scan-assembler-not "vmovups" } } */

gcc/testsuite/gcc.target/i386/pr55590-2.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx" } */
+
+#include <immintrin.h>
+
+struct S
+{
+  __m128 a, b;
+};
+
+struct T
+{
+  int a;
+  struct S s[8];
+};
+
+
+void foo (struct T *p, int i, __m128 v)
+{
+  struct S s;
+
+  s = p->s[i];
+  s.b = _mm_add_ps(s.b, v);
+  p->s[i] = s;
+}
+
+/* { dg-final { scan-assembler-not "vmovups" } } */

gcc/tree-sra.c

@@ -1423,7 +1423,10 @@ make_fancy_name (tree expr)
    EXP_TYPE at the given OFFSET.  If BASE is something for which
    get_addr_base_and_unit_offset returns NULL, gsi must be non-NULL and is used
    to insert new statements either before or below the current one as specified
-   by INSERT_AFTER.  This function is not capable of handling bitfields.  */
+   by INSERT_AFTER.  This function is not capable of handling bitfields.
+
+   BASE must be either a declaration or a memory reference that has correct
+   alignment ifformation embeded in it (e.g. a pre-existing one in SRA).  */
 
 tree
 build_ref_for_offset (location_t loc, tree base, HOST_WIDE_INT offset,
@@ -1437,7 +1440,7 @@ build_ref_for_offset (location_t loc, tree base, HOST_WIDE_INT offset,
   unsigned int align;
 
   gcc_checking_assert (offset % BITS_PER_UNIT == 0);
-
+  get_object_alignment_1 (base, &align, &misalign);
   base = get_addr_base_and_unit_offset (base, &base_offset);
 
   /* get_addr_base_and_unit_offset returns NULL for references with a variable
@@ -1476,22 +1479,7 @@ build_ref_for_offset (location_t loc, tree base, HOST_WIDE_INT offset,
       base = build_fold_addr_expr (unshare_expr (base));
     }
 
-  /* If prev_base were always an originally performed access
-     we can extract more optimistic alignment information
-     by looking at the access mode.  That would constrain the
-     alignment of base + base_offset which we would need to
-     adjust according to offset.  */
-  if (!get_pointer_alignment_1 (base, &align, &misalign))
-    {
-      gcc_assert (misalign == 0);
-      if (TREE_CODE (prev_base) == MEM_REF
-	  || TREE_CODE (prev_base) == TARGET_MEM_REF)
-	align = TYPE_ALIGN (TREE_TYPE (prev_base));
-    }
-  misalign += (tree_to_double_int (off)
-	       .sext (TYPE_PRECISION (TREE_TYPE (off))).low
-	       * BITS_PER_UNIT);
-  misalign = misalign & (align - 1);
+  misalign = (misalign + offset) & (align - 1);
   if (misalign != 0)
     align = (misalign & -misalign);
   if (align < TYPE_ALIGN (exp_type))