[all-commits] [llvm/llvm-project] da35db: AMDGPU/GlobalISel: AMDGPURegBankLegalize

[Petar Avramovic via All-commits]

  Branch: refs/heads/users/petar-avramovic/new-rbs-rb-legalize
  Home:   https://github.com/llvm/llvm-project
  Commit: da35db7ad34dd55da0a073f5eca8dae828682585
      https://github.com/llvm/llvm-project/commit/da35db7ad34dd55da0a073f5eca8dae828682585
  Author: Petar Avramovic <Petar.Avramovic at amd.com>
  Date:   2024-11-27 (Wed, 27 Nov 2024)

  Changed paths:
    M llvm/include/llvm/CodeGen/GlobalISel/MachineIRBuilder.h
    M llvm/include/llvm/CodeGen/MachineRegisterInfo.h
    M llvm/lib/CodeGen/GlobalISel/MachineIRBuilder.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUGlobalISelUtils.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUGlobalISelUtils.h
    M llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.h
    M llvm/lib/Target/AMDGPU/AMDGPURegBankLegalize.cpp
    A llvm/lib/Target/AMDGPU/AMDGPURegBankLegalizeHelper.cpp
    A llvm/lib/Target/AMDGPU/AMDGPURegBankLegalizeHelper.h
    A llvm/lib/Target/AMDGPU/AMDGPURegBankLegalizeRules.cpp
    A llvm/lib/Target/AMDGPU/AMDGPURegBankLegalizeRules.h
    M llvm/lib/Target/AMDGPU/CMakeLists.txt
    M llvm/lib/Target/AMDGPU/SIInstructions.td
    M llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui-regbanklegalize.mir
    M llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui-salu-float.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui-salu-float.mir
    M llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui.mir

  Log Message:
  -----------
  AMDGPU/GlobalISel: AMDGPURegBankLegalize

Lower G_ instructions that can't be inst-selected with register bank
assignment from AMDGPURegBankSelect based on uniformity analysis.
- Lower instruction to perform it on assigned register bank
- Put uniform value in vgpr because SALU instruction is not available
- Execute divergent instruction in SALU - "waterfall loop"

Given LLTs on all operands after legalizer, some register bank
assignments require lowering while other do not.
Note: cases where all register bank assignments would require lowering
are lowered in legalizer.

AMDGPURegBankLegalize goals:
- Define Rules: when and how to perform lowering
- Goal of defining Rules it to provide high level table-like brief
  overview of how to lower generic instructions based on available
  target features and uniformity info (uniform vs divergent).
- Fast search of Rules, depends on how complicated Rule.Predicate is
- For some opcodes there would be too many Rules that are essentially
  all the same just for different combinations of types and banks.
  Write custom function that handles all cases.
- Rules are made from enum IDs that correspond to each operand.
  Names of IDs are meant to give brief description what lowering does
  for each operand or the whole instruction.
- AMDGPURegBankLegalizeHelper implements lowering algorithms

Since this is the first patch that actually enables -new-reg-bank-select
here is the summary of regression tests that were added earlier:
- if instruction is uniform always select SALU instruction if available
- eliminate back to back vgpr to sgpr to vgpr copies of uniform values
- fast rules: small differences for standard and vector instruction
- enabling Rule based on target feature - salu_float
- how to specify lowering algorithm - vgpr S64 AND to S32
- on G_TRUNC in reg, it is up to user to deal with truncated bits
  G_TRUNC in reg is treated as no-op.
- dealing with truncated high bits - ABS S16 to S32
- sgpr S1 phi lowering
- new opcodes for vcc-to-scc and scc-to-vcc copies
- lowering for vgprS1-to-vcc copy (formally this is vgpr-to-vcc G_TRUNC)
- S1 zext and sext lowering to select
- uniform and divergent S1 AND(OR and XOR) lowering - inst-selected into
  SALU instruction
- divergent phi with uniform inputs
- divergent instruction with temporal divergent use, source instruction
  is defined as uniform(AMDGPURegBankSelect) - missing temporal
  divergence lowering
- uniform phi, because of undef incoming, is assigned to vgpr. Will be
  fixed in AMDGPURegBankSelect via another fix in machine uniformity
  analysis.



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