[PATCH] D77610: [AMDGPU] Limit endcf-collapase to simple if

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

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

We can only collapse adjacent SI_END_CF if outer statement
belongs to a simple SI_IF, otherwise correct mask is not in the
register we expect, but is an argument of an S_XOR instruction.

Even if SI_IF is simple it might be lowered using S_XOR because
lowering is dependent on a basic block layout. It is not
considered simple if instruction consuming its output is
not an SI_END_CF. Since that SI_END_CF might have already been
lowered to an S_OR isSimpleIf() check may return false.

This situation is an opportunity for a further optimization
of SI_IF lowering, but that is a separate optimization. In the
meanwhile move SI_END_CF post the lowering when we already know
how the rest of the CFG was lowered since a non-simple SI_IF
case still needs to be handled.


https://reviews.llvm.org/D77610

Files:
  llvm/lib/Target/AMDGPU/SILowerControlFlow.cpp
  llvm/test/CodeGen/AMDGPU/collapse-endcf.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D77610.255544.patch
Type: text/x-patch
Size: 6132 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200407/29c327bb/attachment-0001.bin>