Index: llvm/lib/CodeGen/CodeGenPrepare.cpp
===================================================================
--- llvm/lib/CodeGen/CodeGenPrepare.cpp
+++ llvm/lib/CodeGen/CodeGenPrepare.cpp
@@ -6962,6 +6962,13 @@
   Instruction *InsertPoint = I;
   for (Use *U : ToReplace) {
     auto *UI = cast<Instruction>(U->get());
+    for (auto *U1 : UI->users()) {
+      auto *UI1 = cast<Instruction>(U1);
+      if (UI1->getParent() == TargetBB) {
+        InsertPoint = UI1;
+        break;
+      }
+    }
     Instruction *NI = UI->clone();
     NewInstructions[UI] = NI;
     MaybeDead.insert(UI);
Index: llvm/test/Transforms/CodeGenPrepare/AArch64/sink-free-instructions-1.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/CodeGenPrepare/AArch64/sink-free-instructions-1.ll
@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -S -codegenprepare -mtriple=aarch64-unknown-linux-gnu < %s -o - | FileCheck %s
+
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64-unknown-linux-gnu"
+
+define void @c(i16 %e, i8 %f) {
+; CHECK-LABEL: @c(
+; CHECK-NEXT:  for.cond4.preheader.lr.ph:
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i8 [[F:%.*]], 0
+; CHECK-NEXT:    [[CONV25:%.*]] = sext i16 [[E:%.*]] to i32
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_COND4_PREHEADER_US_PREHEADER:%.*]], label [[FOR_COND4_PREHEADER_PREHEADER:%.*]]
+; CHECK:       for.cond4.preheader.us.preheader:
+; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[CONV25]], i32 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT144:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP1:%.*]] = mul <4 x i32> zeroinitializer, [[BROADCAST_SPLAT144]]
+; CHECK-NEXT:    ret void
+; CHECK:       for.cond4.preheader.preheader:
+; CHECK-NEXT:    ret void
+;
+for.cond4.preheader.lr.ph:
+  %cmp = icmp slt i8 %f, 0
+  %conv25 = sext i16 %e to i32
+  %broadcast.splatinsert143 = insertelement <4 x i32> poison, i32 %conv25, i32 0
+  br i1 %cmp, label %for.cond4.preheader.us.preheader, label %for.cond4.preheader.preheader
+
+for.cond4.preheader.us.preheader:                 ; preds = %for.cond4.preheader.lr.ph
+  %broadcast.splat144 = shufflevector <4 x i32> %broadcast.splatinsert143, <4 x i32> poison, <4 x i32> zeroinitializer
+  %0 = mul <4 x i32> zeroinitializer, %broadcast.splat144
+  ret void
+
+for.cond4.preheader.preheader:                    ; preds = %for.cond4.preheader.lr.ph
+  ret void
+}