[LLVMbugs] [Bug 4216] Consecutive small memory accesses not merged in a bigger access

[bugzilla-daemon at cs.uiuc.edu]

http://llvm.org/bugs/show_bug.cgi?id=4216


Chris Lattner <clattner at apple.com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|NEW                         |RESOLVED
         Resolution|                            |FIXED




--- Comment #7 from Chris Lattner <clattner at apple.com>  2009-09-21 00:59:36 ---
The rest of the loads eliminated with this patch:
http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20090921/087571.html

We now compile this down to one load on x86-32, which is much much better than
GCC at least:

_test_bitfield:
        movl    4(%esp), %eax
        movl    %eax, %ecx
        andl    $-65536, %ecx
        orl     $32962, %eax
        andl    $40186, %eax
        orl     %ecx, %eax
        ret

This should be only one and and one or, but hey, it's still progress :)


-- 
Configure bugmail: http://llvm.org/bugs/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are on the CC list for the bug.