diff --git a/llvm/lib/Passes/PassBuilderPipelines.cpp b/llvm/lib/Passes/PassBuilderPipelines.cpp
--- a/llvm/lib/Passes/PassBuilderPipelines.cpp
+++ b/llvm/lib/Passes/PassBuilderPipelines.cpp
@@ -1836,10 +1836,24 @@
     MPM.addPass(HotColdSplittingPass());
 
   // Add late LTO optimization passes.
+  FunctionPassManager LateFPM;
+
+  // LoopSink pass sinks instructions hoisted by LICM, which serves as a
+  // canonicalization pass that enables other optimizations. As a result,
+  // LoopSink pass needs to be a very late IR pass to avoid undoing LICM
+  // result too early.
+  LateFPM.addPass(LoopSinkPass());
+
+  // This hoists/decomposes div/rem ops. It should run after other sink/hoist
+  // passes to avoid re-sinking, but before SimplifyCFG because it can allow
+  // flattening of blocks.
+  LateFPM.addPass(DivRemPairsPass());
+
   // Delete basic blocks, which optimization passes may have killed.
-  MPM.addPass(createModuleToFunctionPassAdaptor(SimplifyCFGPass(
+  LateFPM.addPass(SimplifyCFGPass(
       SimplifyCFGOptions().convertSwitchRangeToICmp(true).hoistCommonInsts(
-          true))));
+          true)));
+  MPM.addPass(createModuleToFunctionPassAdaptor(std::move(LateFPM)));
 
   // Drop bodies of available eternally objects to improve GlobalDCE.
   MPM.addPass(EliminateAvailableExternallyPass());
diff --git a/llvm/test/Other/new-pm-lto-defaults.ll b/llvm/test/Other/new-pm-lto-defaults.ll
--- a/llvm/test/Other/new-pm-lto-defaults.ll
+++ b/llvm/test/Other/new-pm-lto-defaults.ll
@@ -135,6 +135,8 @@
 ; CHECK-O23SZ-NEXT: Running pass: JumpThreadingPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: LowerTypeTestsPass
 ; CHECK-O-NEXT: Running pass: LowerTypeTestsPass
+; CHECK-O23SZ-NEXT: Running pass: LoopSink
+; CHECK-O23SZ-NEXT: Running pass: DivRemPairs
 ; CHECK-O23SZ-NEXT: Running pass: SimplifyCFGPass
 ; CHECK-O23SZ-NEXT: Running pass: EliminateAvailableExternallyPass
 ; CHECK-O23SZ-NEXT: Running pass: GlobalDCEPass