Index: llvm/lib/Transforms/IPO/IROutliner.cpp
===================================================================
--- llvm/lib/Transforms/IPO/IROutliner.cpp
+++ llvm/lib/Transforms/IPO/IROutliner.cpp
@@ -133,9 +133,18 @@
 void OutlinableRegion::splitCandidate() {
   assert(!CandidateSplit && "Candidate already split!");
 
-  Instruction *StartInst = (*Candidate->begin()).Inst;
   Instruction *EndInst = (*Candidate->end()).Inst;
-  assert(StartInst && EndInst && "Expected a start and end instruction?");
+  assert(EndInst && "Expected an end instruction?");
+
+  // We check if the current instruction following the last instruction in the
+  // region is the same as the recorded instruction following the last
+  // instruction, if they do not match, there could be problems in rewriting
+  // the program after outlining, so we ignore it.
+  if (EndInst != Candidate->backInstruction()->getNextNonDebugInstruction())
+    return;
+
+  Instruction *StartInst = (*Candidate->begin()).Inst;
+  assert(StartInst && EndInst && "Expected a start instruction?");
   StartBB = StartInst->getParent();
   PrevBB = StartBB;
 
@@ -1687,6 +1696,13 @@
       // Break the outlinable region out of its parent BasicBlock into its own
       // BasicBlocks (see function implementation).
       OS->splitCandidate();
+
+      // There's a chance that when the region is split, extra instructions are
+      // added changing the possibility of outlining, and it is no longer viable
+      // to be split, so we ignore it.
+      if (!OS->CandidateSplit)
+        continue;
+
       std::vector<BasicBlock *> BE = {OS->StartBB};
       OS->CE = new (ExtractorAllocator.Allocate())
           CodeExtractor(BE, nullptr, false, nullptr, nullptr, nullptr, false,
Index: llvm/test/Transforms/IROutliner/outlining-bitcasts.ll
===================================================================
--- llvm/test/Transforms/IROutliner/outlining-bitcasts.ll
+++ llvm/test/Transforms/IROutliner/outlining-bitcasts.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --include-generated-funcs
 ; RUN: opt -S -verify -iroutliner -ir-outlining-no-cost < %s | FileCheck %s
 
 ; This test ensures that an extra output is not added when there is a bitcast
@@ -12,15 +12,6 @@
 declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture)
 
 define void @outline_bitcast_base() {
-; CHECK-LABEL: @outline_bitcast_base(
-; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[A:%.*]] = alloca i32, align 4
-; CHECK-NEXT:    [[B:%.*]] = alloca i32, align 4
-; CHECK-NEXT:    [[C:%.*]] = alloca i32, align 4
-; CHECK-NEXT:    [[D:%.*]] = alloca i32, align 4
-; CHECK-NEXT:    call void @[[FUNCTION_0:.*]](i32* [[A]], i32* [[B]], i32* [[C]], i32* [[D]])
-; CHECK-NEXT:    ret void
-;
 entry:
   %a = alloca i32, align 4
   %b = alloca i32, align 4
@@ -37,25 +28,6 @@
 }
 
 define void @outline_bitcast_removed() {
-; CHECK-LABEL: @outline_bitcast_removed(
-; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[A:%.*]] = alloca i32, align 4
-; CHECK-NEXT:    [[B:%.*]] = alloca i32, align 4
-; CHECK-NEXT:    [[C:%.*]] = alloca i32, align 4
-; CHECK-NEXT:    [[D:%.*]] = alloca i32, align 4
-; CHECK-NEXT:    call void @[[FUNCTION_0:.*]](i32* [[A]], i32* [[B]], i32* [[C]], i32* [[D]])
-; CHECK-NEXT:    [[LT_CAST1:%.*]] = bitcast i32* [[D]] to i8*
-; CHECK-NEXT:    call void @llvm.lifetime.start.p0i8(i64 -1, i8* [[LT_CAST1]])
-; CHECK-NEXT:    [[AM:%.*]] = load i32, i32* [[B]], align 4
-; CHECK-NEXT:    [[BM:%.*]] = load i32, i32* [[A]], align 4
-; CHECK-NEXT:    [[CM:%.*]] = load i32, i32* [[C]], align 4
-; CHECK-NEXT:    [[AS:%.*]] = add i32 [[AM]], [[BM]]
-; CHECK-NEXT:    [[BS:%.*]] = add i32 [[BM]], [[AM]]
-; CHECK-NEXT:    [[CS:%.*]] = add i32 [[BM]], [[CM]]
-; CHECK-NEXT:    [[LT_CAST:%.*]] = bitcast i32* [[D]] to i8*
-; CHECK-NEXT:    call void @llvm.lifetime.end.p0i8(i64 -1, i8* [[LT_CAST]])
-; CHECK-NEXT:    ret void
-;
 entry:
   %a = alloca i32, align 4
   %b = alloca i32, align 4
@@ -72,34 +44,92 @@
   %am = load i32, i32* %b
   %bm = load i32, i32* %a
   %cm = load i32, i32* %c
-  %as = add i32 %am, %bm
-  %bs = add i32 %bm, %am
-  %cs = add i32 %bm, %cm
   call void @llvm.lifetime.end.p0i8(i64 -1, i8* %X)
   ret void
 }
 
+; The first bitcast is moved down to lifetime start, and, since the original
+; endpoint does not match the new endpoint, we cannot extract and outline the
+; second bitcast and set of ads.  Outlining only occurs in this case due to
+; the lack of a cost model, as denoted by the debug command line argument.
+
 define void @outline_bitcast_base2(i32 %a, i32 %b, i32 %c) {
-; CHECK-LABEL: @outline_bitcast_base2(
-; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[AL:%.*]] = add i32 [[A:%.*]], [[B:%.*]]
-; CHECK-NEXT:    [[BL:%.*]] = add i32 [[B]], [[A]]
-; CHECK-NEXT:    [[CL:%.*]] = add i32 [[B]], [[C:%.*]]
-; CHECK-NEXT:    ret void
-;
 entry:
+  %d = alloca i32, align 4
+  %X = bitcast i32* %d to i8*
   %al = add i32 %a, %b
   %bl = add i32 %b, %a
   %cl = add i32 %b, %c
+  %buffer = mul i32 %a, %b
+  %Y = bitcast i32* %d to i8*
+  %am = add i32 %a, %b
+  %bm = add i32 %b, %a
+  %cm = add i32 %b, %c
+  call void @llvm.lifetime.start.p0i8(i64 -1, i8* %X)
+  call void @llvm.lifetime.end.p0i8(i64 -1, i8* %X)
   ret void
 }
 
-; CHECK: define internal void @[[FUNCTION_0]](i32* [[ARG0:%.*]], i32* [[ARG1:%.*]], i32* [[ARG2:%.*]], i32* [[ARG3:%.*]])
-; CHECK: entry_to_outline:
-; CHECK-NEXT:    store i32 2, i32* [[ARG0]], align 4
-; CHECK-NEXT:    store i32 3, i32* [[ARG1]], align 4
-; CHECK-NEXT:    store i32 4, i32* [[ARG2]], align 4
-; CHECK-NEXT:    [[X:%.*]] = bitcast i32* [[ARG3]] to i8*
-; CHECK-NEXT:    [[AL:%.*]] = load i32, i32* [[ARG0]], align 4
-; CHECK-NEXT:    [[BL:%.*]] = load i32, i32* [[ARG1]], align 4
-; CHECK-NEXT:    [[CL:%.*]] = load i32, i32* [[ARG2]], align 4
+; CHECK-LABEL: @outline_bitcast_base(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[A:%.*]] = alloca i32, align 4
+; CHECK-NEXT:    [[B:%.*]] = alloca i32, align 4
+; CHECK-NEXT:    [[C:%.*]] = alloca i32, align 4
+; CHECK-NEXT:    [[D:%.*]] = alloca i32, align 4
+; CHECK-NEXT:    call void @outlined_ir_func_0(i32* [[A]], i32* [[B]], i32* [[C]], i32* [[D]])
+; CHECK-NEXT:    ret void
+;
+;
+; CHECK-LABEL: @outline_bitcast_removed(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[A:%.*]] = alloca i32, align 4
+; CHECK-NEXT:    [[B:%.*]] = alloca i32, align 4
+; CHECK-NEXT:    [[C:%.*]] = alloca i32, align 4
+; CHECK-NEXT:    [[D:%.*]] = alloca i32, align 4
+; CHECK-NEXT:    call void @outlined_ir_func_0(i32* [[A]], i32* [[B]], i32* [[C]], i32* [[D]])
+; CHECK-NEXT:    [[LT_CAST1:%.*]] = bitcast i32* [[D]] to i8*
+; CHECK-NEXT:    call void @llvm.lifetime.start.p0i8(i64 -1, i8* [[LT_CAST1]])
+; CHECK-NEXT:    [[AM:%.*]] = load i32, i32* [[B]], align 4
+; CHECK-NEXT:    [[BM:%.*]] = load i32, i32* [[A]], align 4
+; CHECK-NEXT:    [[CM:%.*]] = load i32, i32* [[C]], align 4
+; CHECK-NEXT:    [[LT_CAST:%.*]] = bitcast i32* [[D]] to i8*
+; CHECK-NEXT:    call void @llvm.lifetime.end.p0i8(i64 -1, i8* [[LT_CAST]])
+; CHECK-NEXT:    ret void
+;
+;
+; CHECK-LABEL: @outline_bitcast_base2(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[D:%.*]] = alloca i32, align 4
+; CHECK-NEXT:    call void @outlined_ir_func_1(i32* [[D]], i32 [[A:%.*]], i32 [[B:%.*]], i32 [[C:%.*]])
+; CHECK-NEXT:    [[BUFFER:%.*]] = mul i32 [[A]], [[B]]
+; CHECK-NEXT:    [[Y:%.*]] = bitcast i32* [[D]] to i8*
+; CHECK-NEXT:    [[AM:%.*]] = add i32 [[A]], [[B]]
+; CHECK-NEXT:    [[BM:%.*]] = add i32 [[B]], [[A]]
+; CHECK-NEXT:    [[CM:%.*]] = add i32 [[B]], [[C]]
+; CHECK-NEXT:    [[LT_CAST1:%.*]] = bitcast i32* [[D]] to i8*
+; CHECK-NEXT:    call void @llvm.lifetime.start.p0i8(i64 -1, i8* [[LT_CAST1]])
+; CHECK-NEXT:    [[LT_CAST:%.*]] = bitcast i32* [[D]] to i8*
+; CHECK-NEXT:    call void @llvm.lifetime.end.p0i8(i64 -1, i8* [[LT_CAST]])
+; CHECK-NEXT:    ret void
+;
+;
+; CHECK: @outlined_ir_func_0(i32* [[TMP0:%.*]], i32* [[TMP1:%.*]], i32* [[TMP2:%.*]], i32* [[TMP3:%.*]])
+; CHECK:       entry_to_outline:
+; CHECK-NEXT:    store i32 2, i32* [[TMP0:%.*]], align 4
+; CHECK-NEXT:    store i32 3, i32* [[TMP1:%.*]], align 4
+; CHECK-NEXT:    store i32 4, i32* [[TMP2:%.*]], align 4
+; CHECK-NEXT:    [[X:%.*]] = bitcast i32* [[TMP3:%.*]] to i8*
+; CHECK-NEXT:    [[AL:%.*]] = load i32, i32* [[TMP0]], align 4
+; CHECK-NEXT:    [[BL:%.*]] = load i32, i32* [[TMP1]], align 4
+; CHECK-NEXT:    [[CL:%.*]] = load i32, i32* [[TMP2]], align 4
+; CHECK-NEXT:    br label [[ENTRY_AFTER_OUTLINE_EXITSTUB:%.*]]
+;
+;
+; CHECK: @outlined_ir_func_1(i32* [[TMP0:%.*]], i32 [[TMP1:%.*]], i32 [[TMP2:%.*]], i32 [[TMP3:%.*]])
+; CHECK:       entry_to_outline:
+; CHECK-NEXT:    [[X:%.*]] = bitcast i32* [[TMP0]] to i8*
+; CHECK-NEXT:    [[AL:%.*]] = add i32 [[TMP1]], [[TMP2]]
+; CHECK-NEXT:    [[BL:%.*]] = add i32 [[TMP2]], [[TMP1]]
+; CHECK-NEXT:    [[CL:%.*]] = add i32 [[TMP2]], [[TMP3]]
+; CHECK-NEXT:    br label [[ENTRY_AFTER_OUTLINE_EXITSTUB:%.*]]
+;