[LoopVectorize] Clear stale CycleAnalysis after loop simplification

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -8330,6 +8330,12 @@ LoopVectorizeResult LoopVectorizePass::runImpl(Function &F) {
     Changed |= CFGChanged |=
         simplifyLoop(L, DT, LI, SE, AC, nullptr, false /* PreserveLCSSA */);
 
+  // Loop simplification may change the CFG before processLoop() lazily requests
+  // BlockFrequencyAnalysis. Clear a cached CycleAnalysis so BFI recomputes it
+  // for the simplified CFG.
+  if (CFGChanged && FAM->getCachedResult<CycleAnalysis>(F))
+    FAM->clearAnalysis<CycleAnalysis>(F);
+
   // Build up a worklist of inner-loops to vectorize. This is necessary as
   // the act of vectorizing or partially unrolling a loop creates new loops
   // and can invalidate iterators across the loops.

llvm/test/Transforms/LoopVectorize/bfi-stale-after-loop-simplify.ll

@@ -0,0 +1,25 @@
+; RUN: opt < %s -passes='function(require<cycles>,loop-vectorize)' -disable-output
+
+; LoopVectorize simplifies loops before processing them. If CycleAnalysis was
+; cached before the pass, it must not be reused after loop simplification
+; changes the CFG when BlockFrequencyInfo is requested lazily.
+
+define i16 @f(i1 %c) {
+entry:
+  br label %header
+
+latch:
+  %iv.next = add i16 %iv, 1
+  %done = icmp eq i16 %iv.next, 0
+  br i1 %done, label %second, label %header
+
+header:
+  %iv = phi i16 [ 0, %entry ], [ %iv.next, %latch ]
+  br i1 %c, label %trap, label %latch
+
+trap:
+  unreachable
+
+second:
+  br i1 false, label %second, label %second
+}