[PATCH] D62363: [X86] Enable intrinsics that convert float and bf16 data to each other

[Kan Shengchen via Phabricator via cfe-commits]

skan marked 3 inline comments as done.
skan added inline comments.


================
Comment at: lib/Headers/avx512bf16intrin.h:52
+///
+/// \headerfile<x86intrin.h>
+///
----------------
RKSimon wrote:
> \headerfile <x86intrin.h>
fixed in updated patch


================
Comment at: lib/Headers/avx512bf16intrin.h:66
+///
+/// \headerfile<x86intrin.h>
+///
----------------
RKSimon wrote:
> \headerfile <x86intrin.h>
fixed in updated patch


================
Comment at: lib/Headers/avx512bf16intrin.h:98
+  return (__m512bh)__builtin_ia32_selectw_512(
+      (__mmask32)__U, (__v32hi)_mm512_cvtne2ps_pbh(__A, __B), (__v32hi)__W);
 }
----------------
RKSimon wrote:
> style/clang-format changes like these should be separated into their own patch
style changes are removed in the updated patch


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D62363/new/

https://reviews.llvm.org/D62363