[Bug target/30778] [4.3 Regression] invalid code generation for memset() with -mtune=k8

["ubizjak at gmail dot com" <gcc-bugzilla@gcc.gnu.org>]

------- Comment #3 from ubizjak at gmail dot com  2007-02-24 10:59 -------
I'm currently testing this patch:

2007-02-24  Uros Bizjak  <ubizjak@gmail.com>

        * config/i386/i386.md (expand_set_or_movmem_via_loop): Return if
        GET_MODE_SIZE (mode) * unroll is less than expected_size.

testsuite/ChangeLog:

2007-02-24  Uros Bizjak  <ubizjak@gmail.com>

        * gcc.target/i386/pr30778.c: New test.

Index: config/i386/i386.c
===================================================================
--- config/i386/i386.c  (revision 122286)
+++ config/i386/i386.c  (working copy)
@@ -13315,13 +13315,19 @@
 {
   rtx out_label, top_label, iter, tmp;
   enum machine_mode iter_mode;
-  rtx piece_size = GEN_INT (GET_MODE_SIZE (mode) * unroll);
-  rtx piece_size_mask = GEN_INT (~((GET_MODE_SIZE (mode) * unroll) - 1));
+  HOST_WIDE_INT min_size = GET_MODE_SIZE (mode) * unroll;
+  rtx piece_size = GEN_INT (min_size);
+  rtx piece_size_mask = GEN_INT (~min_size - 1);
   rtx size;
   rtx x_addr;
   rtx y_addr;
   int i;

+  /* Bail out if expected size is less than minimum size
+     that can be emitted.  */
+  if (expected_size < min_size)
+    return;
+
   iter_mode = GET_MODE (count);
   if (iter_mode == VOIDmode)
     iter_mode = word_mode;

There is also an optimization opportunity. When compiling testcase to 32bit
code (with -m32 -O2 -mtune=k8), following is generated:

init_reg_last:
        pushl   %ebp
        movl    reg_stat, %edx
        xorl    %eax, %eax
        movl    %esp, %ebp
.L2:
        movl    $0, (%edx,%eax)
        movl    $0, 4(%edx,%eax)
        movl    $0, 8(%edx,%eax)
        movl    $0, 12(%edx,%eax)
        addl    $16, %eax
        cmpl    $16, %eax    <<< not needed
        jb      .L2          <<< not needed
        addl    %eax, %edx
        movw    $0, (%edx)
        movb    $0, 2(%edx)
        leave
        ret

We don't need to create loop in this case, as this loop will be executed only
once.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=30778