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
@@ -635,7 +635,7 @@
 
     FunctionPassManager FPM;
     FPM.addPass(SROAPass());
-    FPM.addPass(EarlyCSEPass());    // Catch trivial redundancies.
+    FPM.addPass(EarlyCSEPass()); // Catch trivial redundancies.
     FPM.addPass(SimplifyCFGPass(SimplifyCFGOptions().convertSwitchRangeToICmp(
         true)));                    // Merge & remove basic blocks.
     FPM.addPass(InstCombinePass()); // Combine silly sequences.
@@ -728,10 +728,9 @@
   if (PGOOpt)
     IP.EnableDeferral = EnablePGOInlineDeferral;
 
-  ModuleInlinerWrapperPass MIWP(
-      IP, PerformMandatoryInliningsFirst,
-      InlineContext{Phase, InlinePass::CGSCCInliner},
-      UseInlineAdvisor, MaxDevirtIterations);
+  ModuleInlinerWrapperPass MIWP(IP, PerformMandatoryInliningsFirst,
+                                InlineContext{Phase, InlinePass::CGSCCInliner},
+                                UseInlineAdvisor, MaxDevirtIterations);
 
   // Require the GlobalsAA analysis for the module so we can query it within
   // the CGSCC pipeline.
@@ -767,6 +766,14 @@
   if (Level == OptimizationLevel::O3)
     MainCGPipeline.addPass(ArgumentPromotionPass());
 
+  // The ArgumentPromotion pass runs Mem2Reg promotion at the end and this can
+  // make some arguments unused in the callee. Any unused arguments must be
+  // removed.
+  // FIXME: If ArgumentPromotionPass wouldn't be limited to O3, this also
+  // shouldn't.
+  if (Level == OptimizationLevel::O3)
+    MIWP.addLateModulePass(DeadArgumentEliminationPass());
+
   // Try to perform OpenMP specific optimizations. This is a (quick!) no-op if
   // there are no OpenMP runtime calls present in the module.
   if (Level == OptimizationLevel::O2 || Level == OptimizationLevel::O3)
@@ -1612,7 +1619,7 @@
       getInlineParamsFromOptLevel(Level),
       /* MandatoryFirst */ true,
       InlineContext{ThinOrFullLTOPhase::FullLTOPostLink,
-                          InlinePass::CGSCCInliner}));
+                    InlinePass::CGSCCInliner}));
 
   // Optimize globals again after we ran the inliner.
   MPM.addPass(GlobalOptPass());
@@ -1624,6 +1631,11 @@
   // transform it to pass arguments by value instead of by reference.
   MPM.addPass(createModuleToPostOrderCGSCCPassAdaptor(ArgumentPromotionPass()));
 
+  // The ArgumentPromotion pass runs Mem2Reg promotion at the end and this
+  // can make some arguments unused in the callee. Any unused arguments must be
+  // removed.
+  MPM.addPass(DeadArgumentEliminationPass());
+
   FunctionPassManager FPM;
   // The IPO Passes may leave cruft around. Clean up after them.
   FPM.addPass(InstCombinePass());
@@ -1686,7 +1698,6 @@
   MainFPM.addPass(DSEPass());
   MainFPM.addPass(MergedLoadStoreMotionPass());
 
-
   if (EnableConstraintElimination)
     MainFPM.addPass(ConstraintEliminationPass());
 
@@ -1711,8 +1722,7 @@
   addVectorPasses(Level, MainFPM, /* IsFullLTO */ true);
 
   // Run the OpenMPOpt CGSCC pass again late.
-  MPM.addPass(
-      createModuleToPostOrderCGSCCPassAdaptor(OpenMPOptCGSCCPass()));
+  MPM.addPass(createModuleToPostOrderCGSCCPassAdaptor(OpenMPOptCGSCCPass()));
 
   invokePeepholeEPCallbacks(MainFPM, Level);
   MainFPM.addPass(JumpThreadingPass());
diff --git a/llvm/test/Transforms/PhaseOrdering/dce-after-argument-promotion.ll b/llvm/test/Transforms/PhaseOrdering/dce-after-argument-promotion.ll
--- a/llvm/test/Transforms/PhaseOrdering/dce-after-argument-promotion.ll
+++ b/llvm/test/Transforms/PhaseOrdering/dce-after-argument-promotion.ll
@@ -9,7 +9,7 @@
 
 define internal void @f(%struct.ss* byval(%struct.ss) align 8 %b, i32* byval(i32) align 4 %X) noinline nounwind  {
 ; CHECK-LABEL: define {{[^@]+}}@f
-; CHECK-SAME: (i32 [[B_0:%.*]], i32 [[X:%.*]]){{[^#]*}} #[[ATTR0:[0-9]+]] {
+; CHECK-SAME: (i32 [[B_0:%.*]]){{[^#]*}} #[[ATTR0:[0-9]+]] {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TEMP:%.*]] = add i32 [[B_0]], 1
 ; CHECK-NEXT:    store i32 [[TEMP]], i32* [[DUMMY]], align 4
@@ -28,8 +28,7 @@
 ; CHECK-LABEL: define {{[^@]+}}@test
 ; CHECK-SAME: (i32* {{[^%]*}} [[X:%.*]]){{[^#]*}} #[[ATTR1:[0-9]+]] {
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[X_VAL:%.*]] = load i32, i32* [[X]], align 4
-; CHECK-NEXT:    tail call {{.*}}void @f(i32 1, i32 [[X_VAL]])
+; CHECK-NEXT:    tail call {{.*}}void @f(i32 1)
 ; CHECK-NEXT:    ret i32 0
 ;
 entry: