[Bug middle-end/24929] long long shift/mask operations should be better optimized

["tkho at ucla dot edu" <gcc-bugzilla at gcc dot gnu dot org>]

------- Comment #1 from tkho at ucla dot edu  2005-11-18 02:35 -------
Created an attachment (id=10273)
 --> (http://gcc.gnu.org/bugzilla/attachment.cgi?id=10273&action=view)
shift/mask long long testcase

Here is a rough instruction-count comparison for f() compiled at -O2,
march=pentiumpro between icc9 and gcc head 20051108 with the patch in PR 17886,
comment #16:

icc: 11
gcc: 23

`icc -O2 -march=pentiumpro -S test3.c` gives:
        movl      4(%esp), %eax
        movl      8(%esp), %ecx
        movl      %eax, %edx
        shrl      $24, %edx
        shll      $8, %eax
        shll      $8, %ecx
        orl       %ecx, %edx
        movzwl    18(%esp), %ecx
        movzbl    %cl, %ecx
        orl       %ecx, %eax
        ret

`gcc -c test3.c -save-temps -O2 -march=pentiumpro -momit-leaf-frame-pointer`
gives:
        subl    $12, %esp
        movl    %edi, 8(%esp)
        movl    28(%esp), %edi
        movl    16(%esp), %eax
        movl    20(%esp), %edx
        movl    %esi, 4(%esp)
        movl    24(%esp), %esi
        movl    %edi, %esi
        xorl    %edi, %edi
        movl    8(%esp), %edi
        movl    %ebx, (%esp)
        shrl    $16, %esi
        xorl    %ebx, %ebx
        shldl   $8, %eax, %edx
        movl    %esi, %ecx
        movl    4(%esp), %esi
        orl     %ebx, %edx
        movl    (%esp), %ebx
        andl    $255, %ecx
        sall    $8, %eax
        addl    $12, %esp
        orl     %ecx, %eax
        ret

For comparison, here's the code from gcc 2.95.3. It generates the same 18
instructions for both march=i386 and march=pentiumpro.
`gcc -c test3.c -save-temps -O2 -momit-leaf-frame-pointer -march=pentiumpro`:
        pushl %ebx
        movl 8(%esp),%ecx
        movl 12(%esp),%ebx
        movl 16(%esp),%eax
        movl 20(%esp),%edx
        shldl $8,%ecx,%ebx
        sall $8,%ecx
        movl %edx,%eax
        xorl %edx,%edx
        shrl $16,%eax
        andl $255,%eax
        andl $0,%edx
        orl %eax,%ecx
        orl %edx,%ebx
        movl %ecx,%eax
        movl %ebx,%edx
        popl %ebx
        ret


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=24929