[PATCH] D71717: [MachineScheduler] Ignore artificial edges when forming store chains

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec accepted this revision.
rampitec added a comment.
This revision is now accepted and ready to land.

I have realized that BaseMemOpClusterMutation::apply() in fact does not check all control dependencies and just breaks at the first one. I.e. this change just skips some SDeps preferring another one. More or less we are lucky to find a correct SDep which may form a useful chain. We may be not that lucky if order of the SDeps is different and we would somehow use another register (for example data register). We probably need a callback to check if that register belongs to pointer operand and skip it otherwise. Alternatively we may need a full search to find a best SDep in the list.

This is LGTM, but can you please add cluster_load_valu_cluster_store function from the testcase in D73509 <https://reviews.llvm.org/D73509>? At the moment stores are not properly clustered:

  flat_store_dword v[2:3], v4
  v_add_u32_e32 v1, 1, v5
  flat_store_dword v[2:3], v6 offset:16
  flat_store_dword v[2:3], v1 offset:8
  flat_store_dword v[2:3], v0 offset:24


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D71717/new/

https://reviews.llvm.org/D71717