[PATCH] D84168: AMDGPU: Account for the size of LDS globals used through constant expressions.

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added reviewers: rampitec, cfang, kerbowa, foad.
Herald added subscribers: mgrang, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, jvesely, kzhuravl.
Herald added a project: LLVM.

Also "fix" the longstanding bug where the computed size depends on the
order of the visitation. We could try to predict the allocation order
used by legalization, but it would never be 100% perfect. Until we
start fixing the addresses somehow (or have a more reliable allocation
scheme later), just try to compute the size based on the worst case
padding.


https://reviews.llvm.org/D84168

Files:
  llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
  llvm/test/CodeGen/AMDGPU/promote-alloca-padding-size-estimate.ll
  llvm/test/CodeGen/AMDGPU/promote-alloca-to-lds-constantexpr-use.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D84168.279212.patch
Type: text/x-patch
Size: 14224 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200720/5c4d66db/attachment.bin>