[all-commits] [llvm/llvm-project] 106959: [AMDGPU] Inline non-kernel functions using extern lds

[vangthao95 via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 106959acc15c4b98e252af0c43406aa9342a2e05
      https://github.com/llvm/llvm-project/commit/106959acc15c4b98e252af0c43406aa9342a2e05
  Author: Vang Thao <Vang.Thao at amd.com>
  Date:   2021-09-16 (Thu, 16 Sep 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUAlwaysInlinePass.cpp
    M llvm/test/CodeGen/AMDGPU/hip.extern.shared.array.ll

  Log Message:
  -----------
  [AMDGPU] Inline non-kernel functions using extern lds

In https://reviews.llvm.org/D100481, forceful inline of all non-kernel
functions using lds was disabled since AMDGPULowerModuleLDS pass now handles
static lds. However that pass does not handle extern lds so non-kernel
functions using extern lds must sill be inline.

Reviewed By: hsmhsm, arsenm

Differential Revision: https://reviews.llvm.org/D109773