[LLVM][Uniformity] Fix error causing assert on some irreducible control flow

As the test case demonstrates, it is possible for a block to be identified as a
join point while not being the header of a reducible cycle. To address this,
when searching for the outermost cycle made divergent by branch outside it, we
first check for an irreducible outermost cycle before checking if the parent is
reducible.

Reviewed By: sameerds

Differential Revision: https://reviews.llvm.org/D158014

Change-Id: If510748029b9e4cc06d43a57cccc86cd0cea232d

Author: AlexMaclean

llvm/include/llvm/ADT/GenericUniformityImpl.h

@@ -947,11 +947,6 @@ static const CycleT *getExtDivCycle(const CycleT *Cycle,
   if (Cycle->contains(DivTermBlock))
     return nullptr;
 
-  if (Cycle->isReducible()) {
-    assert(Cycle->getHeader() == JoinBlock);
-    return nullptr;
-  }
-
   const auto *Parent = Cycle->getParentCycle();
   while (Parent && !Parent->contains(DivTermBlock)) {
     // If the join is inside a child, then the parent must be
@@ -962,6 +957,11 @@ static const CycleT *getExtDivCycle(const CycleT *Cycle,
     Parent = Cycle->getParentCycle();
   }
 
+  if (Cycle->isReducible()) {
+    assert(Cycle->getHeader() == JoinBlock);
+    return nullptr;
+  }
+
   LLVM_DEBUG(dbgs() << "cycle made divergent by external branch\n");
   return Cycle;
 }

llvm/test/Analysis/UniformityAnalysis/NVPTX/non-header-join.ll

@@ -0,0 +1,24 @@
+; RUN: opt %s -passes='print<uniformity>' -disable-output 2>&1 | FileCheck %s
+
+target datalayout = "e-i64:64-v16:16-v32:32-n16:32:64"
+target triple = "nvptx64-nvidia-cuda"
+
+; CHECK: CYCLES ASSSUMED DIVERGENT:
+; CHECK-NEXT: depth=1: entries(if.end16 for.cond1) for.body4
+
+define void @foo(i1 %b) {
+entry:
+  br i1 %b, label %if.then, label %if.end16
+
+if.then:                                          ; preds = %entry
+  br label %for.cond1
+
+for.cond1:                                        ; preds = %if.end16, %for.body4, %if.then
+  br i1 false, label %for.body4, label %if.end16
+
+for.body4:                                        ; preds = %for.cond1
+  br label %for.cond1
+
+if.end16:                                         ; preds = %for.cond1, %entry
+  br label %for.cond1
+}