[all-commits] [llvm/llvm-project] fef54d: AMDGPU/GlobalISel: Add skeletons for new register ...

[Petar Avramovic via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: fef54d0393fda144a23d764f96d42f5e1d17ab3e
      https://github.com/llvm/llvm-project/commit/fef54d0393fda144a23d764f96d42f5e1d17ab3e
  Author: Petar Avramovic <Petar.Avramovic at amd.com>
  Date:   2024-12-03 (Tue, 03 Dec 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPU.h
    A llvm/lib/Target/AMDGPU/AMDGPURegBankLegalize.cpp
    A llvm/lib/Target/AMDGPU/AMDGPURegBankSelect.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
    M llvm/lib/Target/AMDGPU/CMakeLists.txt
    A llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui-regbanklegalize.mir
    A llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui-regbankselect.mir
    A llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui-salu-float.ll
    A llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui-salu-float.mir
    A llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui.ll
    A llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui.mir

  Log Message:
  -----------
  AMDGPU/GlobalISel: Add skeletons for new register bank select passes (#112862)

New register bank select for AMDGPU will be split in two passes:
- AMDGPURegBankSelect: select banks based on machine uniformity analysis
- AMDGPURegBankLegalize: lower instructions that can't be inst-selected
  with register banks assigned by AMDGPURegBankSelect.
AMDGPURegBankLegalize is similar to legalizer but with context of
uniformity analysis. Does not change already assigned banks.
Main goal of AMDGPURegBankLegalize is to provide high level table-like
overview of how to lower generic instructions based on available target
features and uniformity info (uniform vs divergent).
See RegBankLegalizeRules.

Summary of new features:
At the moment register bank select assigns register bank to output
register using simple algorithm:
- one of the inputs is vgpr output is vgpr
- all inputs are sgpr output is sgpr.
When function does not contain divergent control flow propagating
register banks like this works. In general, first point is still correct
but second is not when function contains divergent control flow.
Examples:
- Phi with uniform inputs that go through divergent branch
- Instruction with temporal divergent use.
To fix this AMDGPURegBankSelect will use machine uniformity analysis
to assign vgpr to each divergent and sgpr to each uniform instruction.
But some instructions are only available on VALU (for example floating
point instructions before gfx1150) and we need to assign vgpr to them.
Since we are no longer propagating register banks we need to ensure that
uniform instructions get their inputs in sgpr in some way.
In AMDGPURegBankLegalize uniform instructions that are only available on
VALU will be reassigned to vgpr on all operands and read-any-lane vgpr
output to original sgpr output.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications