diff --git a/llvm/lib/MCA/Stages/InOrderIssueStage.cpp b/llvm/lib/MCA/Stages/InOrderIssueStage.cpp
--- a/llvm/lib/MCA/Stages/InOrderIssueStage.cpp
+++ b/llvm/lib/MCA/Stages/InOrderIssueStage.cpp
@@ -241,6 +241,18 @@
     Bandwidth = Desc.EndGroup ? 0 : Bandwidth - NumMicroOps;
   }
 
+  // If the instruction has a latency of 0, we need to handle
+  // the execution and retirement now.
+  if (IS.isExecuted()) {
+    PRF.onInstructionExecuted(&IS);
+    notifyEvent<HWInstructionEvent>(
+        HWInstructionEvent(HWInstructionEvent::Executed, IR));
+    LLVM_DEBUG(dbgs() << "[E] Instruction #" << IR << " is executed\n");
+
+    retireInstruction(IR);
+    return llvm::ErrorSuccess();
+  }
+
   IssuedInst.push_back(IR);
 
   if (!IR.getInstruction()->getDesc().RetireOOO)
diff --git a/llvm/tools/llvm-mca/Views/TimelineView.cpp b/llvm/tools/llvm-mca/Views/TimelineView.cpp
--- a/llvm/tools/llvm-mca/Views/TimelineView.cpp
+++ b/llvm/tools/llvm-mca/Views/TimelineView.cpp
@@ -288,8 +288,6 @@
   for (unsigned Iteration = 0; Iteration < Iterations; ++Iteration) {
     for (const MCInst &Inst : Source) {
       const TimelineViewEntry &Entry = Timeline[IID];
-      if (Entry.CycleRetired == 0)
-        return;
 
       unsigned SourceIndex = IID % Source.size();
       printTimelineViewEntry(FOS, Entry, Iteration, SourceIndex);