[all-commits] [llvm/llvm-project] 0f20a3: AMDGPU: Set up User SGPRs for queue_ptr only when ...

[Changpeng Fang via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 0f20a35b9e4bf4fdc4fb5ff2b5f9beee48081e9c
      https://github.com/llvm/llvm-project/commit/0f20a35b9e4bf4fdc4fb5ff2b5f9beee48081e9c
  Author: Changpeng Fang <Changpeng.Fang at amd.com>
  Date:   2022-03-09 (Wed, 09 Mar 2022)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
    M llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.is.private.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.is.shared.ll
    M llvm/test/CodeGen/AMDGPU/hsa-metadata-hidden-args-v5.ll
    M llvm/test/CodeGen/AMDGPU/hsa-metadata-queue-ptr-v5.ll
    A llvm/test/CodeGen/AMDGPU/hsa-metadata-queueptr-v5.ll
    M llvm/test/CodeGen/AMDGPU/kernarg-size.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.is.private.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.is.shared.ll
    M llvm/test/CodeGen/AMDGPU/trap-abis.ll
    M llvm/test/CodeGen/AMDGPU/trap.ll

  Log Message:
  -----------
  AMDGPU: Set up User SGPRs for queue_ptr only when necessary

Summary:
  In general, we need queue_ptr for aperture bases and trap handling,
and user SGPRs have to be set up to hold queue_ptr. In current implementation,
user SGPRs are set up unnecessarily for some cases. If the target has aperture
registers, queue_ptr is not needed to reference aperture bases. For trap
handling, if target suppots getDoorbellID, queue_ptr is also not necessary.
Futher, code object version 5 introduces new kernel ABI which passes queue_ptr
as an implicit kernel argument, so user SGPRs are no longer necessary for
queue_ptr. Based on the trap handling document:
https://llvm.org/docs/AMDGPUUsage.html#amdgpu-trap-handler-for-amdhsa-os-v4-onwards-table,
llvm.debugtrap does not need queue_ptr, we remove queue_ptr suport for llvm.debugtrap
in the backend.

Reviewers: sameerds, arsenm

Fixes: SWDEV-307189

Differential Revision: https://reviews.llvm.org/D119762