[all-commits] [llvm/llvm-project] 864a2b: [AMDGPU] Reserve extra SGPR blocks wth XNACK "any"...

[Austin Kerbow via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 864a2b25beac507cc76b50030757283aae434c0c
      https://github.com/llvm/llvm-project/commit/864a2b25beac507cc76b50030757283aae434c0c
  Author: Austin Kerbow <Austin.Kerbow at amd.com>
  Date:   2023-03-17 (Fri, 17 Mar 2023)

  Changed paths:
    M clang/test/Frontend/amdgcn-machine-analysis-remarks.cl
    M llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
    M llvm/test/CodeGen/AMDGPU/GlobalISel/extractelement.ll
    M llvm/test/CodeGen/AMDGPU/amdpal-callable.ll
    M llvm/test/CodeGen/AMDGPU/occupancy-levels.ll
    M llvm/test/CodeGen/AMDGPU/resource-optimization-remarks.ll
    A llvm/test/CodeGen/AMDGPU/tid-kd-xnack-any.ll
    A llvm/test/CodeGen/AMDGPU/tid-kd-xnack-off.ll
    A llvm/test/CodeGen/AMDGPU/tid-kd-xnack-on.ll
    M llvm/test/CodeGen/AMDGPU/trap-abis.ll

  Log Message:
  -----------
  [AMDGPU] Reserve extra SGPR blocks wth XNACK "any" TID Setting

ASMPrinter was relying on feature bits to setup extra SGRPs in the knerel
descriptor for the xnack_mask. This was broken for the dynamic XNACK "any" TID
setting which could cause user SGPRs to be clobbered if the number of SGPRs
reserved was near a granulated block boundary.

When XNACK was enabled this worked correctly in the ASMParser which meant some
kernels were only failing without "-save-temps".

Fixes: SWDEV-382764

Reviewed By: kzhuravl

Differential Revision: https://reviews.llvm.org/D145401