[LoopUtils] Better accuracy for getLoopEstimatedTripCount.

Summary: Current implementation of getLoopEstimatedTripCount returns 1 iteration less than it should. The reason is that in bottom tested loop first iteration is executed before first back branch is taken. For example for loop with !{!"branch_weights", i32 1 // taken, i32 1 // exit} metadata getLoopEstimatedTripCount gives 1 while actual number of iterations is 2.

Reviewers: Ayal, fhahn

Reviewed By: Ayal

Subscribers: mgorny, hiraditya, zzheng, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D71990

1 files changed, 8 insertions, 5 deletions

diff --git a/llvm/lib/Transforms/Utils/LoopUtils.cpp b/llvm/lib/Transforms/Utils/LoopUtils.cpp
index 054ef17..98e4ca5 100644
--- a/llvm/lib/Transforms/Utils/LoopUtils.cpp
+++ b/llvm/lib/Transforms/Utils/LoopUtils.cpp
@@ -723,12 +723,15 @@ Optional<unsigned> llvm::getLoopEstimatedTripCount(Loop *L) {
   if (LatchBR->getSuccessor(0) != L->getHeader())
     std::swap(BackedgeTakenWeight, LatchExitWeight);
 
-  if (!BackedgeTakenWeight || !LatchExitWeight)
-    return 0;
+  if (!LatchExitWeight)
+    return None;
 
-  // Divide the count of the backedge by the count of the edge exiting the loop,
-  // rounding to nearest.
-  return llvm::divideNearest(BackedgeTakenWeight, LatchExitWeight);
+  // Estimated backedge taken count is a ratio of the backedge taken weight by
+  // the the edge exiting weight, rounded to nearest.
+  uint64_t BackedgeTakenCount =
+      llvm::divideNearest(BackedgeTakenWeight, LatchExitWeight);
+  // Estimated trip count is one plus estimated backedge taken count.
+  return BackedgeTakenCount + 1;
 }
 
 bool llvm::hasIterationCountInvariantInParent(Loop *InnerLoop,