[llvm] r293259 - ARM: fix vectorized division on WoA

[Hans Wennborg via llvm-commits]

Merged to 4.0 in r293306.

On Thu, Jan 26, 2017 at 7:41 PM, Saleem Abdulrasool via llvm-commits
<llvm-commits at lists.llvm.org> wrote:
> Author: compnerd
> Date: Thu Jan 26 21:41:53 2017
> New Revision: 293259
>
> URL: http://llvm.org/viewvc/llvm-project?rev=293259&view=rev
> Log:
> ARM: fix vectorized division on WoA
>
> The Windows on ARM target uses custom division for normal division as
> the backend needs to insert division-by-zero checks.  However, it is
> designed to only handle non-vectorized division.  ARM has custom
> lowering for vectorized division as that can avoid loading registers
> with the values and invoke a division routine for each one, preferring
> to lower using NEON instructions.  Fall back to the custom lowering for
> the NEON instructions if we encounter a vectorized division.
>
> Resolves PR31778!
>
> Modified:
>     llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp
>     llvm/trunk/test/CodeGen/ARM/neon_div.ll