[all-commits] [llvm/llvm-project] 6d48d4: [AMDGPU][HWEvents] Refactor VMEM_ACCESS as VMEM_RE...

[Pierre van Houtryve via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 6d48d45c130293452e398cda29ea7d348f384034
      https://github.com/llvm/llvm-project/commit/6d48d45c130293452e398cda29ea7d348f384034
  Author: Pierre van Houtryve <pierre.vanhoutryve at amd.com>
  Date:   2026-06-26 (Fri, 26 Jun 2026)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUHWEvents.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUHWEvents.def
    M llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp

  Log Message:
  -----------
  [AMDGPU][HWEvents] Refactor VMEM_ACCESS as VMEM_READ_ACCESS (#204545)

Instead of having an HWEvent that can be either a read or a write
depending on the target, keep the events as straightforward as
possible and let InsertWaitCnt interpret it. Rename VMEM_ACCESS
to VMEM_READ_ACCESS and set VMEM_WRITE_ACCESS & similar events
even if the target does not have a VSCnt.

I think this conceptually makes more sense.
This separates concerns better so that HWEvents models events
objectively, and InsertWaitCnt handles them as necessary for the task
it is trying to achieve (insert wait instructions).

My end goal with this series of changes is to de-tangle InsertWaitCnt so
we can divide it into layers, and each layer worries about its own thing.  
This is only possible with proper separation of concerns.



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