Compiling the function below with -Os -march=i686 -mtune=pentiumpro
generates bigger code for 4.2 than for 4.0. 
The reason seems to be that 4.2 peels off one loop iteration.

typedef unsigned Tabs [10];

void
TabZonk(Tabs tabs)
{
    int i;

    for (i = 0; i < 10; ++i)
 tabs[i] = 0;
}

sdiff gcc-4.0.s gcc-4.2.s

TabZonk:                              TabZonk:
        pushl   %ebp                          pushl   %ebp
        movl    $1, %eax            |         movl    $2, %eax
        movl    %esp, %ebp                    movl    %esp, %ebp
        movl    8(%ebp), %edx                 movl    8(%ebp), %edx
                                    >         movl    $0, (%edx)
                                    >         .p2align 4,,15
.L2:                                  .L2:
        movl    $0, -4(%edx,%eax,4) |         xorl    %ecx, %ecx
                                    >         movl    %ecx, -4(%edx,%eax,4)
        incl    %eax                          incl    %eax
        cmpl    $11, %eax                     cmpl    $11, %eax
        jne     .L2                           jne     .L2
        popl    %ebp                          popl    %ebp
        ret                                   ret


-- 
           Summary: code size increase with -Os
           Product: gcc
           Version: 4.2.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: tree-optimization
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: dann at godzilla dot ics dot uci dot edu
  GCC host triplet: i686-pc-linux-gnu


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=26251

Reply via email to