diff --git a/llvm/lib/Passes/PassBuilder.cpp b/llvm/lib/Passes/PassBuilder.cpp
--- a/llvm/lib/Passes/PassBuilder.cpp
+++ b/llvm/lib/Passes/PassBuilder.cpp
@@ -535,6 +535,9 @@
   // TODO: Investigate promotion cap for O1.
   LPM1.addPass(LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap));
   LPM1.addPass(SimpleLoopUnswitchPass());
+
+  if (EnableLoopFlatten)
+    FPM.addPass(LoopFlattenPass());
   LPM2.addPass(IndVarSimplifyPass());
   LPM2.addPass(LoopIdiomRecognizePass());
 
@@ -542,8 +545,6 @@
     C(LPM2, Level);
 
   LPM2.addPass(LoopDeletionPass());
-  if (EnableLoopFlatten)
-    FPM.addPass(LoopFlattenPass());
   // Do not enable unrolling in PreLinkThinLTO phase during sample PGO
   // because it changes IR to makes profile annotation in back compile
   // inaccurate. The normal unroller doesn't pay attention to forced full unroll
diff --git a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
--- a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -441,6 +441,10 @@
   MPM.add(createCFGSimplificationPass());
   MPM.add(createInstructionCombiningPass());
   // We resume loop passes creating a second loop pipeline here.
+  if (EnableLoopFlatten) {
+    MPM.add(createLoopFlattenPass()); // Flatten loops
+    MPM.add(createLoopSimplifyCFGPass());
+  }
   MPM.add(createIndVarSimplifyPass());        // Canonicalize indvars
   MPM.add(createLoopIdiomPass());             // Recognize idioms like memset.
   addExtensionsToPM(EP_LateLoopOptimizations, MPM);
@@ -448,10 +452,6 @@
 
   if (EnableLoopInterchange)
     MPM.add(createLoopInterchangePass()); // Interchange loops
-  if (EnableLoopFlatten) {
-    MPM.add(createLoopFlattenPass()); // Flatten loops
-    MPM.add(createLoopSimplifyCFGPass());
-  }
 
   // Unroll small loops
   MPM.add(createSimpleLoopUnrollPass(OptLevel, DisableUnrollLoops,
@@ -1045,12 +1045,12 @@
   PM.add(createMergedLoadStoreMotionPass()); // Merge ld/st in diamonds.
 
   // More loops are countable; try to optimize them.
+  if (EnableLoopFlatten)
+    PM.add(createLoopFlattenPass());
   PM.add(createIndVarSimplifyPass());
   PM.add(createLoopDeletionPass());
   if (EnableLoopInterchange)
     PM.add(createLoopInterchangePass());
-  if (EnableLoopFlatten)
-    PM.add(createLoopFlattenPass());
 
   // Unroll small loops
   PM.add(createSimpleLoopUnrollPass(OptLevel, DisableUnrollLoops,