[PATCH] D96822: AMDGPU: Add regression testcase for bundle pressure issue

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added a reviewer: rampitec.
Herald added subscribers: kerbowa, t-tye, tpr, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl.
arsenm requested review of this revision.
Herald added a subscriber: wdng.
Herald added a project: LLVM.

This is a somewhat reduced testcase that regressed, causing the revert
in 477e3fe4f874b1c4d5896f3bfaf7b3b8a6d38103 <https://reviews.llvm.org/rG477e3fe4f874b1c4d5896f3bfaf7b3b8a6d38103>.

      

This was producing a bundle that could not be allocated. This is a
tricky one to reduce/reproduce, but I do like having some sanity check
for this. I could make this less fragile by converting to a MIR test,
but it would still be pretty big.


https://reviews.llvm.org/D96822

Files:
  llvm/test/CodeGen/AMDGPU/unallocatable-bundle-regression.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D96822.324134.patch
Type: text/x-patch
Size: 10282 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210217/9c9c4a5b/attachment.bin>