[PATCH] D36396: [AArch64] Do not promote f16 when subtarget HasFullFP16

[Sjoerd Meijer via Phabricator via llvm-commits]

SjoerdMeijer created this revision.
Herald added subscribers: kristof.beyls, javed.absar, aemerson.

ARMv8.2a adds FP16 support , i.e. f16 is not only a storage-only type, but it also supports performing data processing on 16-bit floating-point quantities.
To take advantage of this, we do not want to promote f16 to f32 when the subtarget supports FullFP16.


https://reviews.llvm.org/D36396

Files:
  lib/Target/AArch64/AArch64ISelLowering.cpp
  test/CodeGen/AArch64/f16-instructions.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D36396.109992.patch
Type: text/x-patch
Size: 56895 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170807/d8e886b7/attachment.bin>