[PATCH] D71192: AMDGPU: Fix AMDGPUUnifyDivergentExitNodes with no normal returns

[Connor Abbott via Phabricator via llvm-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rG323bfde20c5f: AMDGPU: Fix AMDGPUUnifyDivergentExitNodes with no normal returns (authored by cwabbott).
Herald added a subscriber: kerbowa.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D71192/new/

https://reviews.llvm.org/D71192

Files:
  llvm/lib/Target/AMDGPU/AMDGPUUnifyDivergentExitNodes.cpp
  llvm/test/CodeGen/AMDGPU/kill-infinite-loop.ll


Index: llvm/test/CodeGen/AMDGPU/kill-infinite-loop.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/kill-infinite-loop.ll
+++ llvm/test/CodeGen/AMDGPU/kill-infinite-loop.ll
@@ -45,6 +45,22 @@
   ret void
 }
 
+; test the case where there's only a kill in an infinite loop
+; CHECK-LABEL: only_kill
+; CHECK: exp null off, off, off, off done vm
+; CHECK-NEXT: s_endpgm
+; SIInsertSkips inserts an extra null export here, but it should be harmless.
+; CHECK: exp null off, off, off, off done vm
+; CHECK-NEXT: s_endpgm
+define amdgpu_ps void @only_kill() #0 {
+main_body:
+  br label %loop
+
+loop:
+  call void @llvm.amdgcn.kill(i1 false) #3
+  br label %loop
+}
+
 ; In case there's an epilog, we shouldn't have to do this.
 ; CHECK-LABEL: return_nonvoid
 ; CHECK-NOT: exp null off, off, off, off done vm
Index: llvm/lib/Target/AMDGPU/AMDGPUUnifyDivergentExitNodes.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPUUnifyDivergentExitNodes.cpp
+++ llvm/lib/Target/AMDGPU/AMDGPUUnifyDivergentExitNodes.cpp
@@ -195,8 +195,6 @@
 
 bool AMDGPUUnifyDivergentExitNodes::runOnFunction(Function &F) {
   auto &PDT = getAnalysis<PostDominatorTreeWrapperPass>().getPostDomTree();
-  if (PDT.getRoots().size() <= 1)
-    return false;
 
   LegacyDivergenceAnalysis &DA = getAnalysis<LegacyDivergenceAnalysis>();
 
@@ -321,7 +319,7 @@
   if (ReturningBlocks.empty())
     return false; // No blocks return
 
-  if (ReturningBlocks.size() == 1)
+  if (ReturningBlocks.size() == 1 && !InsertExport)
     return false; // Already has a single return block
 
   const TargetTransformInfo &TTI


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D71192.241138.patch
Type: text/x-patch
Size: 1682 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200129/dd3d7861/attachment.bin>