Merge commit '03da07996884' from llvm.org/main into next

Author: git apple-llvm automerger

llvm/include/llvm/Transforms/Utils/LoopUtils.h

@@ -318,9 +318,8 @@ void addStringMetadataToLoop(Loop *TheLoop, const char *MDString,
 /// Returns a loop's estimated trip count based on branch weight metadata.
 /// In addition if \p EstimatedLoopInvocationWeight is not null it is
 /// initialized with weight of loop's latch leading to the exit.
-/// Returns a valid positive trip count, or std::nullopt when a meaningful
-/// estimate cannot be made (including when the trip count wouldn't fit in the
-/// result type).
+/// Returns a valid positive trip count, saturated at UINT_MAX, or std::nullopt
+/// when a meaningful estimate cannot be made.
 std::optional<unsigned>
 getLoopEstimatedTripCount(Loop *L,
                           unsigned *EstimatedLoopInvocationWeight = nullptr);

llvm/lib/Transforms/Utils/LoopUtils.cpp

@@ -843,9 +843,9 @@ static std::optional<unsigned> getEstimatedTripCount(BranchInst *ExitingBranch,
   // edge exiting the loop, rounded to nearest.
   uint64_t ExitCount = llvm::divideNearest(LoopWeight, ExitWeight);
 
-  // When ExitCount + 1 would wrap in unsigned, return std::nullopt instead.
+  // When ExitCount + 1 would wrap in unsigned, saturate at UINT_MAX.
   if (ExitCount >= std::numeric_limits<unsigned>::max())
-    return std::nullopt;
+    return std::numeric_limits<unsigned>::max();
 
   // Estimated trip count is one plus estimated exit count.
   return ExitCount + 1;

llvm/test/Transforms/LoopVectorize/AArch64/low_trip_memcheck_cost.ll

@@ -180,8 +180,8 @@ outer.exit:
 define void @outer_pgo_minus1(ptr nocapture noundef %a, ptr nocapture noundef readonly %b, i64 noundef %m, i64 noundef %n) {
 ; CHECK-LABEL: LV: Checking a loop in 'outer_pgo_minus1'
 ; CHECK:      Calculating cost of runtime checks:
-; CHECK:      We expect runtime memory checks to be hoisted out of the outer loop. Cost reduced from 6 to 3
-; CHECK:      Total cost of runtime checks: 3
+; CHECK:      We expect runtime memory checks to be hoisted out of the outer loop. Cost reduced from 6 to 1
+; CHECK:      Total cost of runtime checks: 1
 ; CHECK-NEXT: LV: Minimum required TC for runtime checks to be profitable:16
 entry:
   br label %outer.loop