[LLVMbugs] [Bug 6417] inefficient code for inserting i8 into i32

[bugzilla-daemon at llvm.org]

http://llvm.org/bugs/show_bug.cgi?id=6417

Dan Gohman <gohman at apple.com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|NEW                         |RESOLVED
                 CC|                            |gohman at apple.com
         Resolution|                            |INVALID

--- Comment #3 from Dan Gohman <gohman at apple.com> 2010-02-24 16:48:22 CST ---
The IR has a 4-byte store; a single byte store wouldn't produce the same
effect.

For the vector code, the -disable-mmx option is highly recommended.  Beyond
that, theoretically LLVM could convert that vector code back to scalar code,
but that's not very interesting unless you plan to write a lot of code like
that.

-- 
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.