[all-commits] [llvm/llvm-project] 32a3f2: [AMDGPU] const-fold imm operands of amdgcn_update_...

[Pravin Jagtap via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 32a3f2afe6ea7ffb02a6a188b123ded6f4c89f6c
      https://github.com/llvm/llvm-project/commit/32a3f2afe6ea7ffb02a6a188b123ded6f4c89f6c
  Author: Pravin Jagtap <prjagtap at amd.com>
  Date:   2023-11-08 (Wed, 08 Nov 2023)

  Changed paths:
    M clang/lib/CodeGen/CGBuiltin.cpp
    M clang/lib/CodeGen/CodeGenFunction.h
    A clang/test/CodeGenHIP/dpp-const-fold.hip

  Log Message:
  -----------
  [AMDGPU] const-fold imm operands of amdgcn_update_dpp intrinsic (#71139)

Operands of `__builtin_amdgcn_update_dpp` need to evaluate to constant
to match the intrinsic requirements.

Fixes: SWDEV-426822, SWDEV-431138
---------

Authored-by: Pravin Jagtap <Pravin.Jagtap at amd.com>