Index: llvm/lib/Passes/PassBuilder.cpp
===================================================================
--- llvm/lib/Passes/PassBuilder.cpp
+++ llvm/lib/Passes/PassBuilder.cpp
@@ -1839,6 +1839,17 @@
   MainFPM.addPass(InstCombinePass());
   invokePeepholeEPCallbacks(MainFPM, Level);
   MainFPM.addPass(JumpThreadingPass(/*InsertFreezeWhenUnfoldingSelect*/ true));
+
+  LoopPassManager LateLPM(DebugLogging);
+  LateLPM.addPass(
+      LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap));
+
+  // LICM should always be run after the final InstCombine because InstCombine
+  // sinks instructions without regard to loop-invariance.
+  MainFPM.addPass(createFunctionToLoopPassAdaptor(
+      std::move(LateLPM), /*UseMemorySSA=*/false,
+      /*UseBlockFrequencyInfo=*/true, DebugLogging));
+
   MPM.addPass(createModuleToFunctionPassAdaptor(std::move(MainFPM)));
 
   // Create a function that performs CFI checks for cross-DSO calls with
Index: llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
===================================================================
--- llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -1189,6 +1189,10 @@
     PM.add(createWholeProgramDevirtPass(ExportSummary, nullptr));
   }
 
+  // LICM should always be run after the final InstCombine because InstCombine
+  // sinks instructions without regard to loop-invariance.
+  PM.add(createLICMPass(LicmMssaOptCap, LicmMssaNoAccForPromotionCap));
+
   // Create a function that performs CFI checks for cross-DSO calls with targets
   // in the current module.
   PM.add(createCrossDSOCFIPass());
Index: llvm/test/Other/new-pm-lto-defaults.ll
===================================================================
--- llvm/test/Other/new-pm-lto-defaults.ll
+++ llvm/test/Other/new-pm-lto-defaults.ll
@@ -133,6 +133,13 @@
 ; CHECK-O23SZ-NEXT: Running pass: InstCombinePass on foo
 ; CHECK-EP-Peephole-NEXT: Running pass: NoOpFunctionPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: JumpThreadingPass on foo
+; CHECK-O23SZ-NEXT: Starting llvm::Function pass manager run.
+; CHECK-O23SZ-NEXT: Running pass: LoopSimplifyPass on foo
+; CHECK-O23SZ-NEXT: Running pass: LCSSAPass on foo
+; CHECK-O23SZ-NEXT: Finished llvm::Function pass manager run.
+; CHECK-O23SZ-NEXT: Starting Loop pass manager run.
+; CHECK-O23SZ-NEXT: Running pass: LICMPass on Loop
+; CHECK-O23SZ-NEXT: Finished Loop pass manager run.
 ; CHECK-O23SZ-NEXT: Running pass: CrossDSOCFIPass
 ; CHECK-O23SZ-NEXT: Running pass: LowerTypeTestsPass
 ; CHECK-O-NEXT: Running pass: LowerTypeTestsPass
Index: llvm/test/Other/opt-LTO-pipeline.ll
===================================================================
--- llvm/test/Other/opt-LTO-pipeline.ll
+++ llvm/test/Other/opt-LTO-pipeline.ll
@@ -176,6 +176,18 @@
 ; CHECK-NEXT:       Combine redundant instructions
 ; CHECK-NEXT:       Lazy Value Information Analysis
 ; CHECK-NEXT:       Jump Threading
+; CHECK-NEXT:     Basic Alias Analysis (stateless AA impl)
+; CHECK-NEXT:     Function Alias Analysis Results
+; CHECK-NEXT:     Memory SSA
+; CHECK-NEXT:     Natural Loop Information
+; CHECK-NEXT:     Canonicalize natural loops
+; CHECK-NEXT:     LCSSA Verifier
+; CHECK-NEXT:     Loop-Closed SSA Form Pass
+; CHECK-NEXT:     Scalar Evolution Analysis
+; CHECK-NEXT:     Lazy Branch Probability Analysis
+; CHECK-NEXT:     Lazy Block Frequency Analysis
+; CHECK-NEXT:     Loop Pass Manager
+; CHECK-NEXT:       Loop Invariant Code Motion
 ; CHECK-NEXT:     Cross-DSO CFI
 ; CHECK-NEXT:     Lower type metadata
 ; CHECK-NEXT:     Lower type metadata
Index: llvm/test/Transforms/PhaseOrdering/lto-licm.ll
===================================================================
--- llvm/test/Transforms/PhaseOrdering/lto-licm.ll
+++ llvm/test/Transforms/PhaseOrdering/lto-licm.ll
@@ -5,6 +5,7 @@
 define void @hoist_fdiv(float* %a, float %b) {
 ; CHECK-LABEL: @hoist_fdiv(
 ; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = fdiv fast float 1.000000e+00, [[B:%.*]]
 ; CHECK-NEXT:    br label [[FOR_COND:%.*]]
 ; CHECK:       for.cond:
 ; CHECK-NEXT:    [[I_0:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ]
@@ -13,9 +14,9 @@
 ; CHECK:       for.inc:
 ; CHECK-NEXT:    [[IDXPROM:%.*]] = zext i32 [[I_0]] to i64
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i64 [[IDXPROM]]
-; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[ARRAYIDX]], align 4
-; CHECK-NEXT:    [[TMP1:%.*]] = fdiv fast float [[TMP0]], [[B:%.*]]
-; CHECK-NEXT:    store float [[TMP1]], float* [[ARRAYIDX]], align 4
+; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[ARRAYIDX]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = fmul fast float [[TMP1]], [[TMP0]]
+; CHECK-NEXT:    store float [[TMP2]], float* [[ARRAYIDX]], align 4
 ; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_0]], 1
 ; CHECK-NEXT:    br label [[FOR_COND]]
 ; CHECK:       for.end: