[all-commits] [llvm/llvm-project] a1ed39: [AMDGPU] Select V_CVT_*16_F16 more often

[Julien Pagès via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: a1ed39df96bc5b98bd5a83c7d2c1a385c03133e5
      https://github.com/llvm/llvm-project/commit/a1ed39df96bc5b98bd5a83c7d2c1a385c03133e5
  Author: Julien Pagès <julien.pages at amd.com>
  Date:   2021-05-05 (Wed, 05 May 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/fp_to_uint.ll
    M llvm/test/CodeGen/AMDGPU/fptosi.f16.ll
    M llvm/test/CodeGen/AMDGPU/fptoui.f16.ll

  Log Message:
  -----------
  [AMDGPU] Select V_CVT_*16_F16 more often

Improve the code generation of fp_to_sint
and fp_to_uint for integer on 16-bits.

Differential Revision: https://reviews.llvm.org/D101481

Patch by Julien Pagès!