[all-commits] [llvm/llvm-project] eb1b57: [LangRef] Specify that syncscopes can affect the m...

[Fabian Ritter via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: eb1b57c639947ad381d9dff6093c2b8085b99d0f
      https://github.com/llvm/llvm-project/commit/eb1b57c639947ad381d9dff6093c2b8085b99d0f
  Author: ritter-x2a <9519134+ritter-x2a at users.noreply.github.com>
  Date:   2026-05-28 (Thu, 28 May 2026)

  Changed paths:
    M llvm/docs/LangRef.rst

  Log Message:
  -----------
  [LangRef] Specify that syncscopes can affect the monotonic modification order (#189017)

If a target specifies that atomics with mismatching syncscopes appear
non-atomic to each other, there is no point in requiring them to be ordered in
the monotonic modification order. Notably, the [AMDGPU target user
guide](https://llvm.org/docs/AMDGPUUsage.html#memory-scopes) has specified
syncscopes to relax the modification order for years.

So far, I haven't found an example where this less constrained ordering would
be observable (at least with the AMDGPU inclusive scope rules). Whenever a load
would be able to see two monotonic stores with non-inclusive scope, that's
considered a data race (i.e., the load would return `undef`), so it cannot be
used to observe the order of the stores.

Related RFC: https://discourse.llvm.org/t/rfc-clarifying-llvm-irs-concurrent-memory-model/90480



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