Sameer Sahasrabuddhe 421557974a [AMDGPU] Use glue for convergence tokens at call-like operations (#86766) ...

The earlier implementation on AMDGPU used explicit token operands at
SI_CALL and SI_CALL_ISEL. This is now replaced with CONVERGENCECTRL_GLUE
operands, with the following effects:

- The treatment of tokens at call-like operations is now consistent with
the treatment at intrinsics.
- Support for tail calls using implicit tokens at SI_TCRETURN "just
works".
- The extra parameter at call-like instructions is eliminated, thus
restoring those instructions and their handling to the original state.

The new glue node is placed after the existing glue node for the
outgoing call parameters, which seems to not interfere with selection of
the call-like nodes.

2024-04-01 10:51:13 +05:30

75 KiB

Raw Blame History

View Raw