[PATCH] D99038: AMDGPU/GlobalISel: Implement tail calls

[Sebastian Neubauer via Phabricator via llvm-commits]

Flakebi added a comment.

I left a nit inline. Apart from that, LGTM.



================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp:1165-1167
+    // The callee will pop the argument stack as a tail call. Thus, we must
+    // keep it 16-byte aligned.
+    NumBytes = alignTo(OutInfo.getNextStackOffset(), 16);
----------------
Can this and the assert below use getStackAlignment() instead of hardcoding 16?
Or does this have a different meaning?


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D99038/new/

https://reviews.llvm.org/D99038