[all-commits] [llvm/llvm-project] fc0c72: [X86] Add AVX512 support to the fast isel code for...

[topperc via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: fc0c72b2dfc1f6209f9d5a401730219727e166cc
      https://github.com/llvm/llvm-project/commit/fc0c72b2dfc1f6209f9d5a401730219727e166cc
  Author: Craig Topper <craig.topper at intel.com>
  Date:   2020-02-14 (Fri, 14 Feb 2020)

  Changed paths:
    M llvm/lib/Target/X86/X86FastISel.cpp
    M llvm/test/CodeGen/X86/fast-isel-float-half-convertion.ll

  Log Message:
  -----------
  [X86] Add AVX512 support to the fast isel code for Intrinsic::convert_from_fp16/convert_to_fp16.


  Commit: 391cc4dd41db934081c37ee523cb2149bf0e3a41
      https://github.com/llvm/llvm-project/commit/391cc4dd41db934081c37ee523cb2149bf0e3a41
  Author: Craig Topper <craig.topper at intel.com>
  Date:   2020-02-14 (Fri, 14 Feb 2020)

  Changed paths:
    M llvm/lib/Target/X86/X86FastISel.cpp
    M llvm/test/CodeGen/X86/fast-isel-float-half-convertion.ll

  Log Message:
  -----------
  [X86] Use ZERO_EXTEND instead of SIGN_EXTEND in the fast isel handling of convert_from_fp16.


Compare: https://github.com/llvm/llvm-project/compare/1326a5a4cfe0...391cc4dd41db