Hi,
this patch is very similar to the one I posted before
(http://gcc.gnu.org/ml/gcc-patches/2012-02/msg01377.html) except that
it is now adjusted to sit on top of the new one before this and does
not ignore complex numbers.
There are more movmisalign_optab generations in this function. There
is the TARGET_MEM_REF case which I intend to piggy-back on in the same
way like MEM_REF is handled in this patch once it leaves the RFC
stage. Finally, movmisalign_optab is also generated in
VIEW_CONVERT_EXPR case but as far as I understand the code, misaligned
loads are already handled there (only perhaps we should use
SLOW_UNALIGNED_ACCESS instead of STRICT_ALIGNMENT there?).
The three patches passed bootstrap and testing on x86_64-linux,
i686-linux, usparc64-linux (without Java) and ia64-linux (without
Ada). I propose to commit it after the previous patch passes review.
Thanks,
Martin
2012-03-09 Martin Jambor <mjam...@suse.cz>
* expr.c (expand_expr_real_1): handle misaligned scalar reads from
memory through MEM_REFs by calling extract_bit_field.
* testsuite/gcc.dg/misaligned-expand-1.c: New test.
Index: src/gcc/expr.c
===================================================================
--- src.orig/gcc/expr.c
+++ src/gcc/expr.c
@@ -9404,21 +9404,27 @@ expand_expr_real_1 (tree exp, rtx target
set_mem_addr_space (temp, as);
align = get_object_or_type_alignment (exp);
if (mode != BLKmode
- && align < GET_MODE_ALIGNMENT (mode)
- /* If the target does not have special handling for unaligned
- loads of mode then it can use regular moves for them. */
- && ((icode = optab_handler (movmisalign_optab, mode))
- != CODE_FOR_nothing))
+ && align < GET_MODE_ALIGNMENT (mode))
{
- struct expand_operand ops[2];
+ if ((icode = optab_handler (movmisalign_optab, mode))
+ != CODE_FOR_nothing)
+ {
+ struct expand_operand ops[2];
- /* We've already validated the memory, and we're creating a
- new pseudo destination. The predicates really can't fail,
- nor can the generator. */
- create_output_operand (&ops[0], NULL_RTX, mode);
- create_fixed_operand (&ops[1], temp);
- expand_insn (icode, 2, ops);
- return ops[0].value;
+ /* We've already validated the memory, and we're creating a
+ new pseudo destination. The predicates really can't fail,
+ nor can the generator. */
+ create_output_operand (&ops[0], NULL_RTX, mode);
+ create_fixed_operand (&ops[1], temp);
+ expand_insn (icode, 2, ops);
+ return ops[0].value;
+ }
+ else if (SLOW_UNALIGNED_ACCESS (mode, align))
+ temp = extract_bit_field (temp, GET_MODE_BITSIZE (mode),
+ 0, TYPE_UNSIGNED (TREE_TYPE (exp)),
+ true, (modifier == EXPAND_STACK_PARM
+ ? NULL_RTX : target),
+ mode, mode);
}
return temp;
}
Index: src/gcc/testsuite/gcc.dg/misaligned-expand-1.c
===================================================================
--- /dev/null
+++ src/gcc/testsuite/gcc.dg/misaligned-expand-1.c
@@ -0,0 +1,41 @@
+/* Test that expand can generate correct loads of misaligned data even on
+ strict alignment platforms. */
+
+/* { dg-do run } */
+/* { dg-options "-O0" } */
+
+extern void abort ();
+
+typedef unsigned int myint __attribute__((aligned(1)));
+
+unsigned int
+foo (myint *p)
+{
+ return *p;
+}
+
+#define cst 0xdeadbeef
+#define NUM 8
+
+struct blah
+{
+ char c;
+ myint i[NUM];
+};
+
+struct blah g;
+
+int
+main (int argc, char **argv)
+{
+ int i, k;
+ for (k = 0; k < NUM; k++)
+ {
+ g.i[k] = cst;
+ i = foo (&g.i[k]);
+
+ if (i != cst)
+ abort ();
+ }
+ return 0;
+}
Index: src/gcc/testsuite/gcc.dg/misaligned-expand-3.c
===================================================================
--- /dev/null
+++ src/gcc/testsuite/gcc.dg/misaligned-expand-3.c
@@ -0,0 +1,43 @@
+/* Test that expand can generate correct stores to misaligned data of complex
+ type even on strict alignment platforms. */
+
+/* { dg-do run } */
+/* { dg-options "-O0" } */
+
+extern void abort ();
+
+typedef _Complex float mycmplx __attribute__((aligned(1)));
+
+void
+foo (mycmplx *p, float r, float i)
+{
+ __real__ *p = r;
+ __imag__ *p = i;
+}
+
+#define cvr 3.2f
+#define cvi 2.5f
+#define NUM 8
+
+struct blah
+{
+ char c;
+ mycmplx x[NUM];
+} __attribute__((packed));
+
+struct blah g;
+
+int
+main (int argc, char **argv)
+{
+ int k;
+
+ for (k = 0; k < NUM; k++)
+ {
+ foo (&g.x[k], cvr, cvi);
+ if (__real__ g.x[k] != cvr
+ || __imag__ g.x[k] != cvi)
+ abort ();
+ }
+ return 0;
+}
