[all-commits] [llvm/llvm-project] c985b1: [AMDGPU] Examine instructions in pending queues du...

[Austin Kerbow via All-commits]

  Branch: refs/heads/users/kerbowa/reserved-resource-hazard
  Home:   https://github.com/llvm/llvm-project
  Commit: c985b177b6273250ec685fa19f607492e0d23c38
      https://github.com/llvm/llvm-project/commit/c985b177b6273250ec685fa19f607492e0d23c38
  Author: Austin Kerbow <Austin.Kerbow at amd.com>
  Date:   2025-08-24 (Sun, 24 Aug 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
    M llvm/lib/Target/AMDGPU/GCNSchedStrategy.h
    M llvm/test/CodeGen/AMDGPU/gfx-callable-return-types.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.iglp.opt.exp.large.mir
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.iglp.opt.exp.small.mir
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.iglp.opt.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.iglp.opt.single.2b.mir
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.iglp.opt.single.2c.mir
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.sched.group.barrier.ll
    M llvm/test/CodeGen/AMDGPU/machine-scheduler-sink-trivial-remats-attr.mir
    M llvm/test/CodeGen/AMDGPU/memintrinsic-unroll.ll
    M llvm/test/CodeGen/AMDGPU/mfma-no-register-aliasing.ll
    M llvm/test/CodeGen/AMDGPU/rewrite-vgpr-mfma-to-agpr.ll
    M llvm/test/CodeGen/AMDGPU/sched-barrier-pre-RA.mir
    M llvm/test/CodeGen/AMDGPU/sched-group-barrier-pipeline-solver.mir
    M llvm/test/CodeGen/AMDGPU/sched-group-barrier-pre-RA.mir

  Log Message:
  -----------
  [AMDGPU] Examine instructions in pending queues during scheduling

Examine instructions in the pending queue when scheduling. This makes
instructions visible to scheduling heuristics even when they aren't
immediately issuable due to hardware resource constraints.

The scheduler has two hardware resource modeling modes: an in-order mode
where instructions must be ready to issue before scheduling, and
out-of-order models where instructions are always visible to heuristics.
Special handling exists for unbuffered processor resources in
out-of-order models. These resources can cause pipeline stalls when used
back-to-back, so they're typically avoided. However, for AMDGPU targets,
managing register pressure and reducing spilling is critical enough to
justify exceptions to this approach.

This change enables examination of instructions that can't be
immediately issued because they use an already occupied unbuffered
resource. By making these instructions visible to scheduling heuristics
anyway, we gain more flexibility in scheduling decisions, potentially
allowing better register pressure and hardware resouce management.


  Commit: 31327a4d143572d1b922a90ed9cffee963d5f480
      https://github.com/llvm/llvm-project/commit/31327a4d143572d1b922a90ed9cffee963d5f480
  Author: Austin Kerbow <Austin.Kerbow at amd.com>
  Date:   2025-08-25 (Mon, 25 Aug 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.iglp.opt.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.iglp.opt.single.2b.mir
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.iglp.opt.single.2c.mir
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.sched.group.barrier.ll
    M llvm/test/CodeGen/AMDGPU/machine-scheduler-sink-trivial-remats-attr.mir
    M llvm/test/CodeGen/AMDGPU/memintrinsic-unroll.ll
    M llvm/test/CodeGen/AMDGPU/mfma-no-register-aliasing.ll
    M llvm/test/CodeGen/AMDGPU/rewrite-vgpr-mfma-to-agpr.ll
    M llvm/test/CodeGen/AMDGPU/sched-barrier-pre-RA.mir
    M llvm/test/CodeGen/AMDGPU/sched-group-barrier-pipeline-solver.mir
    M llvm/test/CodeGen/AMDGPU/sched-group-barrier-pre-RA.mir

  Log Message:
  -----------
  Address review comments.


Compare: https://github.com/llvm/llvm-project/compare/b67a6dddb7cc...31327a4d1435

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