[all-commits] [llvm/llvm-project] 13c031: [AMDGPU] Restrict immediate scratch offsets

[Sebastian Neubauer via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 13c0316239dc31a34262f2270d0952aa152a9a76
      https://github.com/llvm/llvm-project/commit/13c0316239dc31a34262f2270d0952aa152a9a76
  Author: Sebastian Neubauer <sebastian.neubauer at amd.com>
  Date:   2021-05-07 (Fri, 07 May 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPU.td
    M llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
    M llvm/lib/Target/AMDGPU/GCNSubtarget.h
    M llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
    M llvm/test/CodeGen/AMDGPU/flat-scratch.ll
    M llvm/test/CodeGen/AMDGPU/local-stack-alloc-block-sp-reference.ll

  Log Message:
  -----------
  [AMDGPU] Restrict immediate scratch offsets

gfx9 does not work with negative offsets, gfx10 works only with
aligned negative offsets, but not with unaligned negative offsets.

This is slightly more conservative than needed, gfx9 does support
negative offsets when a VGPR address is used and gfx10 supports
negative, unaligned offsets when an SGPR address is used, but we
do not make use of that with this patch.

Differential Revision: https://reviews.llvm.org/D101292