[all-commits] [llvm/llvm-project] d9a6fc: [AMDGPU] Run unmerge combines post regbankselect

[Pierre van Houtryve via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: d9a6fc82f56f1e4ebb6ba053a57a5839c3907a7e
      https://github.com/llvm/llvm-project/commit/d9a6fc82f56f1e4ebb6ba053a57a5839c3907a7e
  Author: Pierre van Houtryve <pierre.vanhoutryve at amd.com>
  Date:   2023-02-10 (Fri, 10 Feb 2023)

  Changed paths:
    M llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUCombine.td
    M llvm/lib/Target/AMDGPU/SIInstructions.td
    M llvm/test/CodeGen/AMDGPU/GlobalISel/extractelement.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/fshl.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/fshr.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/image-waterfall-loop-O0.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/insertelement.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.atomic.add.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.atomic.cmpswap.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.atomic.fadd.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.load.format.f16.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.load.format.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.load.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.store.format.f16.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.store.format.f32.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.store.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.tbuffer.load.f16.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.tbuffer.load.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.tbuffer.store.f16.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.tbuffer.store.i8.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.tbuffer.store.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.s.buffer.load.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.atomic.add.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.atomic.cmpswap.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.atomic.fadd.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.load.format.f16.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.load.format.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.load.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.store.format.f16.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.store.format.f32.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.store.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.tbuffer.load.f16.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.tbuffer.load.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/saddsat.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/sext_inreg.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/srem.i64.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/ssubsat.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/urem.i64.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/xnor.ll
    M llvm/test/CodeGen/AMDGPU/bfi_int.ll
    M llvm/test/CodeGen/AMDGPU/constrained-shift.ll
    M llvm/test/CodeGen/AMDGPU/cttz_zero_undef.ll

  Log Message:
  -----------
  [AMDGPU] Run unmerge combines post regbankselect

RegBankSelect can insert G_UNMERGE_VALUES in a lot of places which
left us with a lot of unmerge/merge pairs that could be simplified.
These often got in the way of pattern matching and made codegen
worse.

This patch:
  - Makes the necessary changes to the merge/unmerge combines so they can run post RegBankSelect
  - Adds relevant unmerge combines to the list of RegBankSelect combines for AMDGPU
  - Updates some tablegen patterns that were missing explicit cross-regbank copies (V_BFI patterns were causing constant bus violations with this change).

This seems to be mostly beneficial for code quality.

Reviewed By: arsenm

Differential Revision: https://reviews.llvm.org/D142192