[SimplifyLibCalls] Add dereferenceable bytes from known callsites

[xbolva00]

Summary

int mm(char *a, char *b) {

return memcmp(a,b,16);

}

Currently:
define dso_local i32 @mm(i8* nocapture readonly %a, i8* nocapture readonly %b) local_unnamed_addr #1 {
entry:

%call = tail call i32 @memcmp(i8* %a, i8* %b, i64 16)
ret i32 %call

}

After patch:
define dso_local i32 @mm(i8* nocapture readonly %a, i8* nocapture readonly %b) local_unnamed_addr #1 {
entry:

%call = tail call i32 @memcmp(i8* dereferenceable(16)  %a, i8* dereferenceable(16)  %b, i64 16)
ret i32 %call

}

[xbolva00]

Please @jdoerfert check it. I will add more tests when the code is OK.

[xbolva00]

lib/Transforms/Utils/SimplifyLibCalls.cpp

193

Copy paste from @spatel 's patch: https://reviews.llvm.org/D64258

We should find proper place for this.

[xbolva00]

Some ideas
1, + memchr
2, infer noalias as follow up

[jdoerfert]

I like the direction, first obstacle identified but solvable. We need tests.

lib/Transforms/Utils/SimplifyLibCalls.cpp

193

The Attributor has a similar, though more elaborate, utility which is not exposed yet. I would expect that to be usable but the interface is in flux right now. I'd go with this and a TODO note.

---

Edit: Reading through the use cases, maybe we should use the Attributor code which can handle more cases. What is happening here is not what we want, see my example below.

---

Proposal, do it here, sth like:

static void annotateDereferenceableBytes(CallSite CS, unsigned ArgNo, uint64_t DerefBytes) {
  if (CS.getDereferenceableBytes(ArgNo) < DerefBytes) {
    CS.removeParamAttr(ArgNo, Attribute::Dereferenceable);
    CS.removeParamAttr(ArgNo, Attribute::DereferenceableOrNull);
    // TODO: CallSite does not have an `addParamAttr` for integer attributes.
    CS.addAttribute(ArgNo + AttributeList::FirstArgIndex, Attribute::getWithDereferenceableBytes(CS->getContext(), DerefBytes));
  }
}

(I did not try to compile this!)

947

LHS and RHS are call site operands for which we deduced dereferenceability. Thus we want to annotate the call site. Now with this code, if I'm not mistaken, there are two possibilities for LHS, RHS is the same:

1. LHS is anything but an argument -> no annotation -> not what we want
2. LHS is an argument -> annotation at the argument -> not necessarily correct, see below:

We should not derive deref for the arguments a or b from the memcmp call. We can and should derive deref for their usage in the memcmp call.

void foo(int *a, int *b) {
  if (a && b)
    memcmp(a, b, 4);
}

986

What does the return value here mean? I'm also confused by the Op0 which was there already.

[xbolva00]

memchr support.

[xbolva00]

lib/Transforms/Utils/SimplifyLibCalls.cpp

947

Right. I also wanted to annotate callsite arguments but I didnt find a nice API.

I will try your code above.

986

nullptr means that nothing was simplified.

below, for memcpy, we can just turn memcpy libcall to memcpy intrinsic.

[xbolva00]

Thanks for review, I am going to address your notes now + tests.

[jdoerfert]

lib/Transforms/Utils/SimplifyLibCalls.cpp

986

but why is the pointer operand returned?

[xbolva00]

lib/Transforms/Utils/SimplifyLibCalls.cpp

986

llvm memcpy intrinsic "returns" void so in order to fix return value, we return dst pointer.

return memcpy(dst, ...)

to

llvm.memcpy(dst, ....)
return dst;

I dont know why this was designed this way :)

[xbolva00]

lib/Transforms/Utils/SimplifyLibCalls.cpp

986

https://llvm.org/docs/LangRef.html#llvm-memcpy-intrinsic

[xbolva00]

Addressed review tips.
Added tests. (extensive tests for memcmp, light tests for others)

[xbolva00]

(I havent run test suite yet, I expect many test files need to be updated.. I will do it tommorow)

lib/Transforms/Utils/SimplifyLibCalls.cpp

193

if (CI->getDereferenceableBytes(ArgNo + 1) < DerefBytes) {

quite surprising :) spent some time on find this :D

[jdoerfert]

One minor request, a few nits, LGTM.

lib/Transforms/Utils/SimplifyLibCalls.cpp

193

My bad, I added AttributeList::FirstArgIndex (= 1) below but forgot it above.
Can you replace 1 with AttributeList::FirstArgIndex please.

785

Maybe call annotateDereferenceableBytes after the zero check.

949

Again, I guess if the inner condition hits the annotations are lost (are they?). We could annotate afterwards.

988

I don't mind but you don't even need the Op0 .. changes anymore.

[xbolva00]

Fixed nits

[xbolva00]

Hello @jdoerfert.

I found another opportunity

char *d;

char * xmain(unsigned long n) {

char *s = malloc(32);
__builtin_memcpy(s, d, n);
return s;

}

define dso_local noalias i8* @xmain(i64 %n) local_unnamed_addr #0 {
entry:

%call = tail call i8* @malloc(i64 32)
%0 = load i8*, i8** @d, align 8, !tbaa !2
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 %call, i8* align 1 %0, i64 %n, i1 false)
ret i8* %call

}

from malloc-like functions we can infer e.g. tail call void @llvm.memcpy.p0i8.p0i8.i64(i8*dereferenceable_or_null(32) align 1 %call, i8* align 1 %0, i64 %n, i1 false)

@spatel not sure what is best approach here.. in SLC's optimizeMalloc walk thru all malloc's users (+ sane threshold?) and annotate them?

[xbolva00]

Or by conservative (dont make IC much slower) and check only str(n)cpy, memcpy, memmove, memset buffers if they come from malloc/realloc/calloc?

Edit: maybe we can just add deref or null (C) to malloc ret value and it would do the right thing easily.

[jdoerfert]

In D66079#1630512, @xbolva00 wrote:

Edit: maybe we can just add deref or null (C) to malloc ret value and it would do the right thing easily.

Yes! That is what we should do.

include/llvm/Transforms/Utils/SimplifyLibCalls.h

private:
   Value *optimizeStrTo(CallInst *CI, IRBuilder<> &B);
   Value *optimizeStrSpn(CallInst *CI, IRBuilder<> &B);
   Value *optimizeStrCSpn(CallInst *CI, IRBuilder<> &B);
   Value *optimizeStrStr(CallInst *CI, IRBuilder<> &B);
   Value *optimizeMemChr(CallInst *CI, IRBuilder<> &B);
   Value *optimizeMemCmp(CallInst *CI, IRBuilder<> &B);
   Value *optimizeBCmp(CallInst *CI, IRBuilder<> &B);
   Value *optimizeMemCmpBCmpCommon(CallInst *CI, IRBuilder<> &B);
-  Value *optimizeMemCpy(CallInst *CI, IRBuilder<> &B);
-  Value *optimizeMemMove(CallInst *CI, IRBuilder<> &B);
-  Value *optimizeMemSet(CallInst *CI, IRBuilder<> &B);
+  Value *optimizeMemCpy(CallInst *CI, IRBuilder<> &B, bool isIntrinsic = false);
+  Value *optimizeMemMove(CallInst *CI, IRBuilder<> &B, bool isIntrinsic = false);
+  Value *optimizeMemSet(CallInst *CI, IRBuilder<> &B, bool isIntrinsic = false);
   Value *optimizeRealloc(CallInst *CI, IRBuilder<> &B);
   Value *optimizeWcslen(CallInst *CI, IRBuilder<> &B);
   // Wrapper for all String/Memory Library Call Optimizations
   Value *optimizeStringMemoryLibCall(CallInst *CI, IRBuilder<> &B);
 
   // Math Library Optimizations
   Value *optimizeCAbs(CallInst *CI, IRBuilder<> &B);
   Value *optimizePow(CallInst *CI, IRBuilder<> &B);

lib/Transforms/Utils/SimplifyLibCalls.cpp

if (!isDereferenceableAndAlignedPointer(Str, 1, APInt(64, Len), DL))
     return false;
 
   if (CI->getFunction()->hasFnAttribute(Attribute::SanitizeMemory))
     return false;
 
   return true;
 }
 
+static void annotateDereferenceableBytes(CallInst *CI,
+                                         ArrayRef<unsigned> ArgNos,
+                                         uint64_t DerefBytes) {
+  for (unsigned ArgNo : ArgNos) {
+    if (CI->getDereferenceableBytes(ArgNo + AttributeList::FirstArgIndex) <
+        DerefBytes) {
+      CI->removeParamAttr(ArgNo, Attribute::Dereferenceable);
+      CI->removeParamAttr(ArgNo, Attribute::DereferenceableOrNull);
+      CI->addParamAttr(ArgNo, Attribute::getWithDereferenceableBytes(
+                                  CI->getContext(), DerefBytes));
+    }
+  }
+}
+
 //===----------------------------------------------------------------------===//
 // String and Memory Library Call Optimizations
 //===----------------------------------------------------------------------===//
 
 Value *LibCallSimplifier::optimizeStrCat(CallInst *CI, IRBuilder<> &B) {
   // Extract some information from the instruction
   Value *Dst = CI->getArgOperand(0);
   Value *Src = CI->getArgOperand(1);

 }
 
 Value *LibCallSimplifier::optimizeMemChr(CallInst *CI, IRBuilder<> &B) {
   Value *SrcStr = CI->getArgOperand(0);
   ConstantInt *CharC = dyn_cast<ConstantInt>(CI->getArgOperand(1));
   ConstantInt *LenC = dyn_cast<ConstantInt>(CI->getArgOperand(2));
 
   // memchr(x, y, 0) -> null
-  if (LenC && LenC->isZero())
+  if (LenC) {
+    if (LenC->isZero())
       return Constant::getNullValue(CI->getType());
-
+    annotateDereferenceableBytes(CI, {0}, LenC->getZExtValue());
+  }
   // From now on we need at least constant length and string.
   StringRef Str;
   if (!LenC || !getConstantStringInfo(SrcStr, Str, 0, /*TrimAtNul=*/false))
     return nullptr;
 
   // Truncate the string to LenC. If Str is smaller than LenC we will still only
   // scan the string, as reading past the end of it is undefined and we can just
   // return null if we don't find the char.
Value *LibCallSimplifier::optimizeMemCmpBCmpCommon(CallInst *CI,
                                                    IRBuilder<> &B) {
   Value *LHS = CI->getArgOperand(0), *RHS = CI->getArgOperand(1);
   Value *Size = CI->getArgOperand(2);
 
   if (LHS == RHS) // memcmp(s,s,x) -> 0
     return Constant::getNullValue(CI->getType());
 
   // Handle constant lengths.
-  if (ConstantInt *LenC = dyn_cast<ConstantInt>(Size))
+  if (ConstantInt *LenC = dyn_cast<ConstantInt>(Size)) {
     if (Value *Res = optimizeMemCmpConstantSize(CI, LHS, RHS,
                                                 LenC->getZExtValue(), B, DL))
       return Res;
+    annotateDereferenceableBytes(CI, {0, 1}, LenC->getZExtValue());
+  }
 
   return nullptr;
 }
 
 Value *LibCallSimplifier::optimizeMemCmp(CallInst *CI, IRBuilder<> &B) {
   if (Value *V = optimizeMemCmpBCmpCommon(CI, B))
     return V;
 
Value *LibCallSimplifier::optimizeMemCmp(CallInst *CI, IRBuilder<> &B) {
 
   return nullptr;
 }
 
 Value *LibCallSimplifier::optimizeBCmp(CallInst *CI, IRBuilder<> &B) {
   return optimizeMemCmpBCmpCommon(CI, B);
 }
 
-Value *LibCallSimplifier::optimizeMemCpy(CallInst *CI, IRBuilder<> &B) {
+Value *LibCallSimplifier::optimizeMemCpy(CallInst *CI, IRBuilder<> &B,
+                                         bool isIntrinsic) {
+  Value *Size = CI->getArgOperand(2);
+  if (ConstantInt *LenC = dyn_cast<ConstantInt>(Size))
+    annotateDereferenceableBytes(CI, {0, 1}, LenC->getZExtValue());
+
+  if (isIntrinsic)
+    return nullptr;
+
   // memcpy(x, y, n) -> llvm.memcpy(align 1 x, align 1 y, n)
-  B.CreateMemCpy(CI->getArgOperand(0), 1, CI->getArgOperand(1), 1,
-                 CI->getArgOperand(2));
+  B.CreateMemCpy(CI->getArgOperand(0), 1, CI->getArgOperand(1), 1, Size);
   return CI->getArgOperand(0);
 }
 
-Value *LibCallSimplifier::optimizeMemMove(CallInst *CI, IRBuilder<> &B) {
+Value *LibCallSimplifier::optimizeMemMove(CallInst *CI, IRBuilder<> &B, bool isIntrinsic) {
+  Value *Size = CI->getArgOperand(2);
+  if (ConstantInt *LenC = dyn_cast<ConstantInt>(Size))
+    annotateDereferenceableBytes(CI, {0, 1}, LenC->getZExtValue());
+
+  if (isIntrinsic)
+    return nullptr;
+
   // memmove(x, y, n) -> llvm.memmove(align 1 x, align 1 y, n)
-  B.CreateMemMove(CI->getArgOperand(0), 1, CI->getArgOperand(1), 1,
-                  CI->getArgOperand(2));
-  return CI->getArgOperand(0);
+  B.CreateMemMove( CI->getArgOperand(0), 1, CI->getArgOperand(1), 1, Size);
+  return  CI->getArgOperand(0);
 }
 
 /// Fold memset[_chk](malloc(n), 0, n) --> calloc(1, n).
 Value *LibCallSimplifier::foldMallocMemset(CallInst *Memset, IRBuilder<> &B) {
   // This has to be a memset of zeros (bzero).
   auto *FillValue = dyn_cast<ConstantInt>(Memset->getArgOperand(1));
   if (!FillValue || FillValue->getZExtValue() != 0)
     return nullptr;
if (!Calloc)
     return nullptr;
 
   Malloc->replaceAllUsesWith(Calloc);
   eraseFromParent(Malloc);
 
   return Calloc;
 }
 
-Value *LibCallSimplifier::optimizeMemSet(CallInst *CI, IRBuilder<> &B) {
+Value *LibCallSimplifier::optimizeMemSet(CallInst *CI, IRBuilder<> &B,
+                                         bool isIntrinsic) {
+  Value *Size = CI->getArgOperand(2);
+  if (ConstantInt *LenC = dyn_cast<ConstantInt>(Size))
+    annotateDereferenceableBytes(CI, {0}, LenC->getZExtValue());
+
+  if (isIntrinsic)
+    return nullptr;
+
   if (auto *Calloc = foldMallocMemset(CI, B))
     return Calloc;
 
   // memset(p, v, n) -> llvm.memset(align 1 p, v, n)
   Value *Val = B.CreateIntCast(CI->getArgOperand(1), B.getInt8Ty(), false);
-  B.CreateMemSet(CI->getArgOperand(0), Val, CI->getArgOperand(2), 1);
+  B.CreateMemSet(CI->getArgOperand(0), Val, Size, 1);
   return CI->getArgOperand(0);
 }
 
 Value *LibCallSimplifier::optimizeRealloc(CallInst *CI, IRBuilder<> &B) {
   if (isa<ConstantPointerNull>(CI->getArgOperand(0)))
     return emitMalloc(CI->getArgOperand(1), B, DL, TLI);
 
   return nullptr;
case Intrinsic::pow:
       return optimizePow(CI, Builder);
     case Intrinsic::exp2:
       return optimizeExp2(CI, Builder);
     case Intrinsic::log:
       return optimizeLog(CI, Builder);
     case Intrinsic::sqrt:
       return optimizeSqrt(CI, Builder);
     // TODO: Use foldMallocMemset() with memset intrinsic.
+    case Intrinsic::memset:
+      return optimizeMemSet(CI, Builder, true);
+    case Intrinsic::memcpy:
+      return optimizeMemCpy(CI, Builder, true);
+    case Intrinsic::memmove:
+      return optimizeMemMove(CI, Builder, true);
     default:
       return nullptr;
     }
   }
 
   // Also try to simplify calls to fortified library functions.
   if (Value *SimplifiedFortifiedCI = FortifiedSimplifier.optimizeCall(CI)) {
     // Try to further simplify the result.

test/Analysis/TypeBasedAliasAnalysis/memcpyopt.ll

 ; RUN: opt -S -tbaa -basicaa -memcpyopt -instcombine < %s | FileCheck %s
 
 target datalayout = "e-p:64:64:64"
 
 ; The second memcpy is redundant and can be deleted. There's an intervening store, but
 ; it has a TBAA tag which declares that it is unrelated.
 
 ; CHECK: @foo
-; CHECK-NEXT: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 %p, i8* align 1 %q, i64 16, i1 false), !tbaa !0
+; CHECK-NEXT: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 dereferenceable(16) %p, i8* align 1 dereferenceable(16) %q, i64 16, i1 false), !tbaa !0
 ; CHECK-NEXT: store i8 2, i8* %s, align 1, !tbaa [[TAGA:!.*]]
 ; CHECK-NEXT: ret void
 define void @foo(i8* nocapture %p, i8* nocapture %q, i8* nocapture %s) nounwind {
   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %p, i8* %q, i64 16, i1 false), !tbaa !2
   store i8 2, i8* %s, align 1, !tbaa !1
   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %q, i8* %p, i64 16, i1 false), !tbaa !2
   ret void
 }

test/Transforms/InstCombine/ARM/strcmp.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; Test that the strcmp library call simplifier works correctly.
 ; RUN: opt < %s -instcombine -S | FileCheck %s
 
 target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
 
 @hello = constant [6 x i8] c"hello\00"
 @hell = constant [5 x i8] c"hell\00"
 @bell = constant [5 x i8] c"bell\00"
 @null = constant [1 x i8] zeroinitializer
 
 declare i32 @strcmp(i8*, i8*)
 
 ; strcmp("", x) -> -*x
 define arm_aapcscc i32 @test1(i8* %str2) {
 ; CHECK-LABEL: @test1(
-; CHECK: %strcmpload = load i8, i8* %str
-; CHECK: %1 = zext i8 %strcmpload to i32
-; CHECK: %2 = sub nsw i32 0, %1
-; CHECK: ret i32 %2
+; CHECK-NEXT:    [[STRCMPLOAD:%.*]] = load i8, i8* [[STR2:%.*]], align 1
+; CHECK-NEXT:    [[TMP1:%.*]] = zext i8 [[STRCMPLOAD]] to i32
+; CHECK-NEXT:    [[TMP2:%.*]] = sub nsw i32 0, [[TMP1]]
+; CHECK-NEXT:    ret i32 [[TMP2]]
+;
 
   %str1 = getelementptr inbounds [1 x i8], [1 x i8]* @null, i32 0, i32 0
   %temp1 = call arm_apcscc i32 @strcmp(i8* %str1, i8* %str2)
   ret i32 %temp1
 
 }
 
 ; strcmp(x, "") -> *x
 define arm_aapcscc i32 @test2(i8* %str1) {
 ; CHECK-LABEL: @test2(
-; CHECK: %strcmpload = load i8, i8* %str
-; CHECK: %1 = zext i8 %strcmpload to i32
-; CHECK: ret i32 %1
+; CHECK-NEXT:    [[STRCMPLOAD:%.*]] = load i8, i8* [[STR1:%.*]], align 1
+; CHECK-NEXT:    [[TMP1:%.*]] = zext i8 [[STRCMPLOAD]] to i32
+; CHECK-NEXT:    ret i32 [[TMP1]]
+;
 
   %str2 = getelementptr inbounds [1 x i8], [1 x i8]* @null, i32 0, i32 0
   %temp1 = call arm_aapcscc i32 @strcmp(i8* %str1, i8* %str2)
   ret i32 %temp1
 }
 
 ; strcmp(x, y)  -> cnst
 define arm_aapcscc i32 @test3() {
 ; CHECK-LABEL: @test3(
-; CHECK: ret i32 -1
+; CHECK-NEXT:    ret i32 -1
+;
 
   %str1 = getelementptr inbounds [5 x i8], [5 x i8]* @hell, i32 0, i32 0
   %str2 = getelementptr inbounds [6 x i8], [6 x i8]* @hello, i32 0, i32 0
   %temp1 = call arm_aapcscc i32 @strcmp(i8* %str1, i8* %str2)
   ret i32 %temp1
 }
 
 define arm_aapcscc i32 @test4() {
 ; CHECK-LABEL: @test4(
-; CHECK: ret i32 1
+; CHECK-NEXT:    ret i32 1
+;
 
   %str1 = getelementptr inbounds [5 x i8], [5 x i8]* @hell, i32 0, i32 0
   %str2 = getelementptr inbounds [1 x i8], [1 x i8]* @null, i32 0, i32 0
   %temp1 = call arm_aapcscc i32 @strcmp(i8* %str1, i8* %str2)
   ret i32 %temp1
 }
 
 ; strcmp(x, y)   -> memcmp(x, y, <known length>)
 ; (This transform is rather difficult to trigger in a useful manner)
 define arm_aapcscc i32 @test5(i1 %b) {
 ; CHECK-LABEL: @test5(
-; CHECK: %memcmp = call i32 @memcmp(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @hello, i32 0, i32 0), i8* %str2, i32 5)
-; CHECK: ret i32 %memcmp
+; CHECK-NEXT:    [[STR2:%.*]] = select i1 [[B:%.*]], i8* getelementptr inbounds ([5 x i8], [5 x i8]* @hell, i32 0, i32 0), i8* getelementptr inbounds ([5 x i8], [5 x i8]* @bell, i32 0, i32 0)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* dereferenceable(5) getelementptr inbounds ([6 x i8], [6 x i8]* @hello, i32 0, i32 0), i8* dereferenceable(5) [[STR2]], i32 5)
+; CHECK-NEXT:    ret i32 [[MEMCMP]]
+;
 
   %str1 = getelementptr inbounds [6 x i8], [6 x i8]* @hello, i32 0, i32 0
   %temp1 = getelementptr inbounds [5 x i8], [5 x i8]* @hell, i32 0, i32 0
   %temp2 = getelementptr inbounds [5 x i8], [5 x i8]* @bell, i32 0, i32 0
   %str2 = select i1 %b, i8* %temp1, i8* %temp2
   %temp3 = call arm_aapcscc i32 @strcmp(i8* %str1, i8* %str2)
   ret i32 %temp3
 }
 
 ; strcmp(x,x)  -> 0
 define arm_aapcscc i32 @test6(i8* %str) {
 ; CHECK-LABEL: @test6(
-; CHECK: ret i32 0
+; CHECK-NEXT:    ret i32 0
+;
 
   %temp1 = call arm_aapcscc i32 @strcmp(i8* %str, i8* %str)
   ret i32 %temp1
 }
 
 ; strcmp("", x) -> -*x
 define arm_aapcs_vfpcc i32 @test1_vfp(i8* %str2) {
 ; CHECK-LABEL: @test1_vfp(
-; CHECK: %strcmpload = load i8, i8* %str
-; CHECK: %1 = zext i8 %strcmpload to i32
-; CHECK: %2 = sub nsw i32 0, %1
-; CHECK: ret i32 %2
+; CHECK-NEXT:    [[STRCMPLOAD:%.*]] = load i8, i8* [[STR2:%.*]], align 1
+; CHECK-NEXT:    [[TMP1:%.*]] = zext i8 [[STRCMPLOAD]] to i32
+; CHECK-NEXT:    [[TMP2:%.*]] = sub nsw i32 0, [[TMP1]]
+; CHECK-NEXT:    ret i32 [[TMP2]]
+;
 
   %str1 = getelementptr inbounds [1 x i8], [1 x i8]* @null, i32 0, i32 0
   %temp1 = call arm_aapcs_vfpcc i32 @strcmp(i8* %str1, i8* %str2)
   ret i32 %temp1
 
 }
 
 ; strcmp(x, "") -> *x
 define arm_aapcs_vfpcc i32 @test2_vfp(i8* %str1) {
 ; CHECK-LABEL: @test2_vfp(
-; CHECK: %strcmpload = load i8, i8* %str
-; CHECK: %1 = zext i8 %strcmpload to i32
-; CHECK: ret i32 %1
+; CHECK-NEXT:    [[STRCMPLOAD:%.*]] = load i8, i8* [[STR1:%.*]], align 1
+; CHECK-NEXT:    [[TMP1:%.*]] = zext i8 [[STRCMPLOAD]] to i32
+; CHECK-NEXT:    ret i32 [[TMP1]]
+;
 
   %str2 = getelementptr inbounds [1 x i8], [1 x i8]* @null, i32 0, i32 0
   %temp1 = call arm_aapcs_vfpcc i32 @strcmp(i8* %str1, i8* %str2)
   ret i32 %temp1
 }
 
 ; strcmp(x, y)  -> cnst
 define arm_aapcs_vfpcc i32 @test3_vfp() {
 ; CHECK-LABEL: @test3_vfp(
-; CHECK: ret i32 -1
+; CHECK-NEXT:    ret i32 -1
+;
 
   %str1 = getelementptr inbounds [5 x i8], [5 x i8]* @hell, i32 0, i32 0
   %str2 = getelementptr inbounds [6 x i8], [6 x i8]* @hello, i32 0, i32 0
   %temp1 = call arm_aapcs_vfpcc i32 @strcmp(i8* %str1, i8* %str2)
   ret i32 %temp1
 }
 
 define arm_aapcs_vfpcc i32 @test4_vfp() {
 ; CHECK-LABEL: @test4_vfp(
-; CHECK: ret i32 1
+; CHECK-NEXT:    ret i32 1
+;
 
   %str1 = getelementptr inbounds [5 x i8], [5 x i8]* @hell, i32 0, i32 0
   %str2 = getelementptr inbounds [1 x i8], [1 x i8]* @null, i32 0, i32 0
   %temp1 = call arm_aapcs_vfpcc i32 @strcmp(i8* %str1, i8* %str2)
   ret i32 %temp1
 }
 
 ; strcmp(x, y)   -> memcmp(x, y, <known length>)
 ; (This transform is rather difficult to trigger in a useful manner)
 define arm_aapcs_vfpcc i32 @test5_vfp(i1 %b) {
 ; CHECK-LABEL: @test5_vfp(
-; CHECK: %memcmp = call i32 @memcmp(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @hello, i32 0, i32 0), i8* %str2, i32 5)
-; CHECK: ret i32 %memcmp
+; CHECK-NEXT:    [[STR2:%.*]] = select i1 [[B:%.*]], i8* getelementptr inbounds ([5 x i8], [5 x i8]* @hell, i32 0, i32 0), i8* getelementptr inbounds ([5 x i8], [5 x i8]* @bell, i32 0, i32 0)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* dereferenceable(5) getelementptr inbounds ([6 x i8], [6 x i8]* @hello, i32 0, i32 0), i8* dereferenceable(5) [[STR2]], i32 5)
+; CHECK-NEXT:    ret i32 [[MEMCMP]]
+;
 
   %str1 = getelementptr inbounds [6 x i8], [6 x i8]* @hello, i32 0, i32 0
   %temp1 = getelementptr inbounds [5 x i8], [5 x i8]* @hell, i32 0, i32 0
   %temp2 = getelementptr inbounds [5 x i8], [5 x i8]* @bell, i32 0, i32 0
   %str2 = select i1 %b, i8* %temp1, i8* %temp2
   %temp3 = call arm_aapcs_vfpcc i32 @strcmp(i8* %str1, i8* %str2)
   ret i32 %temp3
 }
 
 ; strcmp(x,x)  -> 0
 define arm_aapcs_vfpcc i32 @test6_vfp(i8* %str) {
 ; CHECK-LABEL: @test6_vfp(
-; CHECK: ret i32 0
+; CHECK-NEXT:    ret i32 0
+;
 
   %temp1 = call arm_aapcs_vfpcc i32 @strcmp(i8* %str, i8* %str)
   ret i32 %temp1
 }

test/Transforms/InstCombine/align-addr.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -instcombine -S | FileCheck %s
 target datalayout = "E-p:64:64:64-p1:32:32:32-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
 
 ; Instcombine should be able to prove vector alignment in the
 ; presence of a few mild address computation tricks.
 
-; CHECK-LABEL: @test0(
-; CHECK: align 16
-
 define void @test0(i8* %b, i64 %n, i64 %u, i64 %y) nounwind  {
+; CHECK-LABEL: @test0(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[C:%.*]] = ptrtoint i8* [[B:%.*]] to i64
+; CHECK-NEXT:    [[D:%.*]] = and i64 [[C]], -16
+; CHECK-NEXT:    [[E:%.*]] = inttoptr i64 [[D]] to double*
+; CHECK-NEXT:    [[V:%.*]] = shl i64 [[U:%.*]], 1
+; CHECK-NEXT:    [[Z:%.*]] = and i64 [[Y:%.*]], -2
+; CHECK-NEXT:    [[T1421:%.*]] = icmp eq i64 [[N:%.*]], 0
+; CHECK-NEXT:    br i1 [[T1421]], label [[RETURN:%.*]], label [[BB:%.*]]
+; CHECK:       bb:
+; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[INDVAR_NEXT:%.*]], [[BB]] ], [ 20, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[J:%.*]] = mul i64 [[I]], [[V]]
+; CHECK-NEXT:    [[H:%.*]] = add i64 [[J]], [[Z]]
+; CHECK-NEXT:    [[T8:%.*]] = getelementptr double, double* [[E]], i64 [[H]]
+; CHECK-NEXT:    [[P:%.*]] = bitcast double* [[T8]] to <2 x double>*
+; CHECK-NEXT:    store <2 x double> zeroinitializer, <2 x double>* [[P]], align 16
+; CHECK-NEXT:    [[INDVAR_NEXT]] = add i64 [[I]], 1
+; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVAR_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[RETURN]], label [[BB]]
+; CHECK:       return:
+; CHECK-NEXT:    ret void
+;
 entry:
   %c = ptrtoint i8* %b to i64
   %d = and i64 %c, -16
   %e = inttoptr i64 %d to double*
   %v = mul i64 %u, 2
   %z = and i64 %y, -2
   %t1421 = icmp eq i64 %n, 0
   br i1 %t1421, label %return, label %bb

 
 return:
   ret void
 }
 
 ; When we see a unaligned load from an insufficiently aligned global or
 ; alloca, increase the alignment of the load, turning it into an aligned load.
 
-; CHECK-LABEL: @test1(
-; CHECK: tmp = load
-; CHECK: GLOBAL{{.*}}align 16
-
 @GLOBAL = internal global [4 x i32] zeroinitializer
 
 define <16 x i8> @test1(<2 x i64> %x) {
+; CHECK-LABEL: @test1(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([4 x i32]* @GLOBAL to <16 x i8>*), align 16
+; CHECK-NEXT:    ret <16 x i8> [[TMP]]
+;
 entry:
-  %tmp = load <16 x i8>, <16 x i8>* bitcast ([4 x i32]* @GLOBAL to <16 x i8>*), align 1
-  ret <16 x i8> %tmp
+  %tmp = load <16 x i8>, <16 x i8>* bitcast ([4 x i32]* @GLOBAL to <16 x i8>*), align 1
+  ret <16 x i8> %tmp
 }
 
 @GLOBAL_as1 = internal addrspace(1) global [4 x i32] zeroinitializer
 
 define <16 x i8> @test1_as1(<2 x i64> %x) {
 ; CHECK-LABEL: @test1_as1(
-; CHECK: tmp = load
-; CHECK: GLOBAL_as1{{.*}}align 16
+; CHECK-NEXT:    [[TMP:%.*]] = load <16 x i8>, <16 x i8> addrspace(1)* bitcast ([4 x i32] addrspace(1)* @GLOBAL_as1 to <16 x i8> addrspace(1)*), align 16
+; CHECK-NEXT:    ret <16 x i8> [[TMP]]
+;
   %tmp = load <16 x i8>, <16 x i8> addrspace(1)* bitcast ([4 x i32] addrspace(1)* @GLOBAL_as1 to <16 x i8> addrspace(1)*), align 1
   ret <16 x i8> %tmp
 }
 
 @GLOBAL_as1_gep = internal addrspace(1) global [8 x i32] zeroinitializer
 
 define <16 x i8> @test1_as1_gep(<2 x i64> %x) {
 ; CHECK-LABEL: @test1_as1_gep(
-; CHECK: tmp = load
-; CHECK: GLOBAL_as1_gep{{.*}}align 16
+; CHECK-NEXT:    [[TMP:%.*]] = load <16 x i8>, <16 x i8> addrspace(1)* bitcast (i32 addrspace(1)* getelementptr inbounds ([8 x i32], [8 x i32] addrspace(1)* @GLOBAL_as1_gep, i32 0, i32 4) to <16 x i8> addrspace(1)*), align 16
+; CHECK-NEXT:    ret <16 x i8> [[TMP]]
+;
   %tmp = load <16 x i8>, <16 x i8> addrspace(1)* bitcast (i32 addrspace(1)* getelementptr ([8 x i32], [8 x i32] addrspace(1)* @GLOBAL_as1_gep, i16 0, i16 4) to <16 x i8> addrspace(1)*), align 1
   ret <16 x i8> %tmp
 }
 
 
 ; When a load or store lacks an explicit alignment, add one.
 
-; CHECK-LABEL: @test2(
-; CHECK: load double, double* %p, align 8
-; CHECK: store double %n, double* %p, align 8
-
 define double @test2(double* %p, double %n) nounwind {
+; CHECK-LABEL: @test2(
+; CHECK-NEXT:    [[T:%.*]] = load double, double* [[P:%.*]], align 8
+; CHECK-NEXT:    store double [[N:%.*]], double* [[P]], align 8
+; CHECK-NEXT:    ret double [[T]]
+;
   %t = load double, double* %p
   store double %n, double* %p
   ret double %t
 }
 
 declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
 
 declare void @use(i8*)
 
 %struct.s = type { i32, i32, i32, i32 }
 
 define void @test3(%struct.s* sret %a4) {
 ; Check that the alignment is bumped up the alignment of the sret type.
 ; CHECK-LABEL: @test3(
+; CHECK-NEXT:    [[A4_CAST:%.*]] = bitcast %struct.s* [[A4:%.*]] to i8*
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 dereferenceable(16) [[A4_CAST]], i8 0, i64 16, i1 false)
+; CHECK-NEXT:    call void @use(i8* [[A4_CAST]])
+; CHECK-NEXT:    ret void
+;
   %a4.cast = bitcast %struct.s* %a4 to i8*
   call void @llvm.memset.p0i8.i64(i8* %a4.cast, i8 0, i64 16, i1 false)
-; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %a4.cast, i8 0, i64 16, i1 false)
   call void @use(i8* %a4.cast)
   ret void
 }

test/Transforms/InstCombine/mem-deref-bytes.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -instcombine  -S < %s | FileCheck %s
+
+declare i32 @memcmp(i8* nocapture, i8* nocapture, i64)
+declare i8* @memcpy(i8* nocapture, i8* nocapture, i64)
+declare i8* @memmove(i8* nocapture, i8* nocapture, i64)
+declare i8* @memset(i8* nocapture, i8, i64)
+declare i8* @memchr(i8* nocapture, i32, i64)
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1)
+declare void @llvm.memmove.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1)
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1)
+
+define i32 @memcmp_const_size_set_deref(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @memcmp_const_size_set_deref(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* dereferenceable(16) [[D:%.*]], i8* dereferenceable(16) [[S:%.*]], i64 16)
+; CHECK-NEXT:    ret i32 [[CALL]]
+;
+  %call = tail call i32 @memcmp(i8* %d, i8* %s, i64 16)
+  ret i32 %call
+}
+
+define i32 @memcmp_const_size_update_deref(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @memcmp_const_size_update_deref(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* dereferenceable(16) [[D:%.*]], i8* dereferenceable(16) [[S:%.*]], i64 16)
+; CHECK-NEXT:    ret i32 [[CALL]]
+;
+  %call = tail call i32 @memcmp(i8* dereferenceable(4) %d, i8* dereferenceable(8) %s, i64 16)
+  ret i32 %call
+}
+
+define i32 @memcmp_const_size_update_deref2(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @memcmp_const_size_update_deref2(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* dereferenceable(16) [[D:%.*]], i8* dereferenceable(16) [[S:%.*]], i64 16)
+; CHECK-NEXT:    ret i32 [[CALL]]
+;
+  %call = tail call i32 @memcmp(i8* %d, i8* dereferenceable_or_null(8) %s, i64 16)
+  ret i32 %call
+}
+
+define i32 @memcmp_const_size_no_update_deref(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @memcmp_const_size_no_update_deref(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* dereferenceable(40) [[D:%.*]], i8* dereferenceable(16) [[S:%.*]], i64 16)
+; CHECK-NEXT:    ret i32 [[CALL]]
+;
+  %call = tail call i32 @memcmp(i8* dereferenceable(40) %d, i8* %s, i64 16)
+  ret i32 %call
+}
+
+define i32 @memcmp_const_size_no_update_deref2(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @memcmp_const_size_no_update_deref2(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* dereferenceable(16) [[D:%.*]], i8* dereferenceable(16) [[S:%.*]], i64 16)
+; CHECK-NEXT:    ret i32 [[CALL]]
+;
+  %call = tail call i32 @memcmp(i8* dereferenceable_or_null(40) %d, i8* %s, i64 16)
+  ret i32 %call
+}
+
+define i32 @memcmp_nonconst_size(i8* nocapture readonly %d, i8* nocapture readonly %s, i64 %n) {
+; CHECK-LABEL: @memcmp_nonconst_size(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* [[D:%.*]], i8* [[S:%.*]], i64 [[N:%.*]])
+; CHECK-NEXT:    ret i32 [[CALL]]
+;
+  %call = tail call i32 @memcmp(i8* %d, i8* %s, i64 %n)
+  ret i32 %call
+}
+
+define i8* @memcpy_const_size_set_deref(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @memcpy_const_size_set_deref(
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 dereferenceable(64) [[D:%.*]], i8* align 1 dereferenceable(64) [[S:%.*]], i64 64, i1 false)
+; CHECK-NEXT:    ret i8* [[D]]
+;
+  %call = tail call i8* @memcpy(i8* %d, i8* %s, i64 64)
+  ret i8* %call
+}
+
+define i8* @memmove_const_size_set_deref(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @memmove_const_size_set_deref(
+; CHECK-NEXT:    call void @llvm.memmove.p0i8.p0i8.i64(i8* align 1 dereferenceable(64) [[D:%.*]], i8* align 1 dereferenceable(64) [[S:%.*]], i64 64, i1 false)
+; CHECK-NEXT:    ret i8* [[D]]
+;
+  %call = tail call i8* @memmove(i8* %d, i8* %s, i64 64)
+  ret i8* %call
+}
+
+define i8* @memset_const_size_set_deref(i8* nocapture readonly %s, i8 %c) {
+; CHECK-LABEL: @memset_const_size_set_deref(
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 1 dereferenceable(64) [[S:%.*]], i8 [[C:%.*]], i64 64, i1 false)
+; CHECK-NEXT:    ret i8* [[S]]
+;
+  %call = tail call i8* @memset(i8* %s, i8 %c, i64 64)
+  ret i8* %call
+}
+
+define i8* @memchr_const_size_set_deref(i8* nocapture readonly %s, i32 %c) {
+; CHECK-LABEL: @memchr_const_size_set_deref(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i8* @memchr(i8* dereferenceable(64) [[S:%.*]], i32 [[C:%.*]], i64 64)
+; CHECK-NEXT:    ret i8* [[CALL]]
+;
+  %call = tail call i8* @memchr(i8* %s, i32 %c, i64 64)
+  ret i8* %call
+}
+
+define i8* @llvm_memcpy_const_size_set_deref(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @llvm_memcpy_const_size_set_deref(
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 dereferenceable(16) [[D:%.*]], i8* align 1 dereferenceable(16) [[S:%.*]], i64 16, i1 false)
+; CHECK-NEXT:    ret i8* [[D]]
+;
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 %d, i8* align 1 %s, i64 16, i1 false)
+  ret i8* %d
+}
+
+define i8* @llvm_memmove_const_size_set_deref(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @llvm_memmove_const_size_set_deref(
+; CHECK-NEXT:    call void @llvm.memmove.p0i8.p0i8.i64(i8* align 1 dereferenceable(16) [[D:%.*]], i8* align 1 dereferenceable(16) [[S:%.*]], i64 16, i1 false)
+; CHECK-NEXT:    ret i8* [[D]]
+;
+  call void @llvm.memmove.p0i8.p0i8.i64(i8* align 1 %d, i8* align 1 %s, i64 16, i1 false)
+  ret i8* %d
+}
+define i8* @llvm_memset_const_size_set_deref(i8* nocapture readonly %s, i8 %c) {
+; CHECK-LABEL: @llvm_memset_const_size_set_deref(
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 1 dereferenceable(16) [[S:%.*]], i8 [[C:%.*]], i64 16, i1 false)
+; CHECK-NEXT:    ret i8* [[S]]
+;
+  call void @llvm.memset.p0i8.i64(i8* align 1 %s, i8 %c, i64 16, i1 false)
+  ret i8* %s
+}

test/Transforms/InstCombine/memchr.ll

;
   %src = getelementptr [14 x i8], [14 x i8]* @hello, i32 0, i32 0
   %dst = call i8* @memchr(i8* %src, i32 0, i32 14)
   store i8* %dst, i8** @chp
   ret void
 }
 
 define void @test4(i32 %chr) {
 ; CHECK-LABEL: @test4(
-; CHECK-NEXT:    [[DST:%.*]] = call i8* @memchr(i8* getelementptr inbounds ([14 x i8], [14 x i8]* @hello, i32 0, i32 0), i32 [[CHR:%.*]], i32 14)
+; CHECK-NEXT:    [[DST:%.*]] = call i8* @memchr(i8* dereferenceable(14) getelementptr inbounds ([14 x i8], [14 x i8]* @hello, i32 0, i32 0), i32 [[CHR:%.*]], i32 14)
 ; CHECK-NEXT:    store i8* [[DST]], i8** @chp, align 4
 ; CHECK-NEXT:    ret void
 ;
   %src = getelementptr [14 x i8], [14 x i8]* @hello, i32 0, i32 0
   %dst = call i8* @memchr(i8* %src, i32 %chr, i32 14)
   store i8* %dst, i8** @chp
   ret void
 }
;
   %dst = call i8* @memchr(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @newlines, i64 0, i64 0), i32 %C, i32 2)
   %cmp = icmp ne i8* %dst, null
   ret i1 %cmp
 }
 
 ; No 64 bits here
 define i1 @test12(i32 %C) {
 ; CHECK-LABEL: @test12(
-; CHECK-NEXT:    [[DST:%.*]] = call i8* @memchr(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @spaces, i32 0, i32 0), i32 [[C:%.*]], i32 3)
+; CHECK-NEXT:    [[DST:%.*]] = call i8* @memchr(i8* dereferenceable(3) getelementptr inbounds ([4 x i8], [4 x i8]* @spaces, i32 0, i32 0), i32 [[C:%.*]], i32 3)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i8* [[DST]], null
 ; CHECK-NEXT:    ret i1 [[CMP]]
 ;
   %dst = call i8* @memchr(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @spaces, i64 0, i64 0), i32 %C, i32 3)
   %cmp = icmp ne i8* %dst, null
   ret i1 %cmp
 }
 

 ;
   %dst = call i8* @memchr(i8* getelementptr inbounds ([2 x i8], [2 x i8]* @single, i64 0, i64 0), i32 %C, i32 1)
   %cmp = icmp ne i8* %dst, null
   ret i1 %cmp
 }
 
 define i1 @test15(i32 %C) {
 ; CHECK-LABEL: @test15(
-; CHECK-NEXT:    [[DST:%.*]] = call i8* @memchr(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @negative, i32 0, i32 0), i32 [[C:%.*]], i32 3)
+; CHECK-NEXT:    [[DST:%.*]] = call i8* @memchr(i8* dereferenceable(3) getelementptr inbounds ([3 x i8], [3 x i8]* @negative, i32 0, i32 0), i32 [[C:%.*]], i32 3)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i8* [[DST]], null
 ; CHECK-NEXT:    ret i1 [[CMP]]
 ;
   %dst = call i8* @memchr(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @negative, i64 0, i64 0), i32 %C, i32 3)
   %cmp = icmp ne i8* %dst, null
   ret i1 %cmp
 }
 
 @s = internal constant [1 x i8] [i8 0], align 1
 define i8* @pr32124() {
 ; CHECK-LABEL: @pr32124(
 ; CHECK-NEXT:    ret i8* getelementptr inbounds ([1 x i8], [1 x i8]* @s, i32 0, i32 0)
 ;
   %res = tail call i8* @memchr(i8* getelementptr ([1 x i8], [1 x i8]* @s, i64 0, i64 0), i32 0, i32 1)
   ret i8* %res
 }

test/Transforms/InstCombine/memcmp-constant-fold.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -instcombine -S -data-layout=e-n32 | FileCheck %s --check-prefix=ALL --check-prefix=LE
 ; RUN: opt < %s -instcombine -S -data-layout=E-n32 | FileCheck %s --check-prefix=ALL --check-prefix=BE
 
 declare i32 @memcmp(i8*, i8*, i64)
 
 ; The alignment of this constant does not matter. We constant fold the load.
 
 @charbuf = private unnamed_addr constant [4 x i8] [i8 0, i8 0, i8 0, i8 1], align 1
 
 define i1 @memcmp_4bytes_unaligned_constant_i8(i8* align 4 %x) {
 ; LE-LABEL: @memcmp_4bytes_unaligned_constant_i8(
-; LE-NEXT:    [[TMP1:%.*]] = bitcast i8* %x to i32*
+; LE-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32*
 ; LE-NEXT:    [[LHSV:%.*]] = load i32, i32* [[TMP1]], align 4
 ; LE-NEXT:    [[TMP2:%.*]] = icmp eq i32 [[LHSV]], 16777216
 ; LE-NEXT:    ret i1 [[TMP2]]
 ;
 ; BE-LABEL: @memcmp_4bytes_unaligned_constant_i8(
-; BE-NEXT:    [[TMP1:%.*]] = bitcast i8* %x to i32*
+; BE-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32*
 ; BE-NEXT:    [[LHSV:%.*]] = load i32, i32* [[TMP1]], align 4
 ; BE-NEXT:    [[TMP2:%.*]] = icmp eq i32 [[LHSV]], 1
 ; BE-NEXT:    ret i1 [[TMP2]]
 ;
   %call = tail call i32 @memcmp(i8* %x, i8* getelementptr inbounds ([4 x i8], [4 x i8]* @charbuf, i64 0, i64 0), i64 4)
   %cmpeq0 = icmp eq i32 %call, 0
   ret i1 %cmpeq0
 }
 
 ; We still don't care about alignment of the constant. We are not limited to constant folding only i8 arrays.
 ; It doesn't matter if the constant operand is the first operand to the memcmp.
 
 @intbuf_unaligned = private unnamed_addr constant [4 x i16] [i16 1, i16 2, i16 3, i16 4], align 1
 
 define i1 @memcmp_4bytes_unaligned_constant_i16(i8* align 4 %x) {
 ; LE-LABEL: @memcmp_4bytes_unaligned_constant_i16(
-; LE-NEXT:    [[TMP1:%.*]] = bitcast i8* %x to i32*
+; LE-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32*
 ; LE-NEXT:    [[RHSV:%.*]] = load i32, i32* [[TMP1]], align 4
 ; LE-NEXT:    [[TMP2:%.*]] = icmp eq i32 [[RHSV]], 131073
 ; LE-NEXT:    ret i1 [[TMP2]]
 ;
 ; BE-LABEL: @memcmp_4bytes_unaligned_constant_i16(
-; BE-NEXT:    [[TMP1:%.*]] = bitcast i8* %x to i32*
+; BE-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32*
 ; BE-NEXT:    [[RHSV:%.*]] = load i32, i32* [[TMP1]], align 4
 ; BE-NEXT:    [[TMP2:%.*]] = icmp eq i32 [[RHSV]], 65538
 ; BE-NEXT:    ret i1 [[TMP2]]
 ;
   %call = tail call i32 @memcmp(i8* bitcast (i16* getelementptr inbounds ([4 x i16], [4 x i16]* @intbuf_unaligned, i64 0, i64 0) to i8*), i8* %x, i64 4)
   %cmpeq0 = icmp eq i32 %call, 0
   ret i1 %cmpeq0
 }
 
 ; TODO: Any memcmp where all arguments are constants should be constant folded. Currently, we only handle i8 array constants.
 
 @intbuf = private unnamed_addr constant [2 x i32] [i32 0, i32 1], align 4
 
 define i1 @memcmp_3bytes_aligned_constant_i32(i8* align 4 %x) {
 ; ALL-LABEL: @memcmp_3bytes_aligned_constant_i32(
-; ALL-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* bitcast (i32* getelementptr inbounds ([2 x i32], [2 x i32]* @intbuf, i64 0, i64 1) to i8*), i8* bitcast ([2 x i32]* @intbuf to i8*), i64 3)
+; ALL-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* dereferenceable(3) bitcast (i32* getelementptr inbounds ([2 x i32], [2 x i32]* @intbuf, i64 0, i64 1) to i8*), i8* dereferenceable(3) bitcast ([2 x i32]* @intbuf to i8*), i64 3)
 ; ALL-NEXT:    [[CMPEQ0:%.*]] = icmp eq i32 [[CALL]], 0
 ; ALL-NEXT:    ret i1 [[CMPEQ0]]
 ;
   %call = tail call i32 @memcmp(i8* bitcast (i32* getelementptr inbounds ([2 x i32], [2 x i32]* @intbuf, i64 0, i64 1) to i8*), i8* bitcast (i32* getelementptr inbounds ([2 x i32], [2 x i32]* @intbuf, i64 0, i64 0) to i8*), i64 3)
   %cmpeq0 = icmp eq i32 %call, 0
   ret i1 %cmpeq0
 }
 
 ; A sloppy implementation would infinite loop by recreating the unused instructions.
 
 define i1 @memcmp_4bytes_one_unaligned_i8(i8* align 4 %x, i8* align 1 %y) {
 ; ALL-LABEL: @memcmp_4bytes_one_unaligned_i8(
-; ALL-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* %x, i8* %y, i64 4)
+; ALL-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* dereferenceable(4) [[X:%.*]], i8* dereferenceable(4) [[Y:%.*]], i64 4)
 ; ALL-NEXT:    [[CMPEQ0:%.*]] = icmp eq i32 [[CALL]], 0
 ; ALL-NEXT:    ret i1 [[CMPEQ0]]
 ;
   %bc = bitcast i8* %x to i32*
   %lhsv = load i32, i32* %bc
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 4)
   %cmpeq0 = icmp eq i32 %call, 0
   ret i1 %cmpeq0
 }
 

test/Transforms/InstCombine/memcpy-from-global.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -instcombine -S | FileCheck %s
 target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64"
 @C.0.1248 = internal constant [128 x float] [ float -1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float -1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 0.000000e+00, float -1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 0.000000e+00, float -1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 1.000000e+00, float 0.000000e+00, float -1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 0.000000e+00, float 1.000000e+00, float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 1.000000e+00, float -1.000000e+00, float 0.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00 ], align 32    ; <[128 x float]*> [#uses=1]
 
 define float @test1(i32 %hash, float %x, float %y, float %z, float %w) {
+; CHECK-LABEL: @test1(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP3:%.*]] = shl i32 [[HASH:%.*]], 2
+; CHECK-NEXT:    [[TMP5:%.*]] = and i32 [[TMP3]], 124
+; CHECK-NEXT:    [[TMP0:%.*]] = zext i32 [[TMP5]] to i64
+; CHECK-NEXT:    [[TMP753:%.*]] = getelementptr [128 x float], [128 x float]* @C.0.1248, i64 0, i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP9:%.*]] = load float, float* [[TMP753]], align 16
+; CHECK-NEXT:    [[TMP11:%.*]] = fmul float [[TMP9]], [[X:%.*]]
+; CHECK-NEXT:    [[TMP13:%.*]] = fadd float [[TMP11]], 0.000000e+00
+; CHECK-NEXT:    [[TMP17_SUM52:%.*]] = or i32 [[TMP5]], 1
+; CHECK-NEXT:    [[TMP1:%.*]] = zext i32 [[TMP17_SUM52]] to i64
+; CHECK-NEXT:    [[TMP1851:%.*]] = getelementptr [128 x float], [128 x float]* @C.0.1248, i64 0, i64 [[TMP1]]
+; CHECK-NEXT:    [[TMP19:%.*]] = load float, float* [[TMP1851]], align 4
+; CHECK-NEXT:    [[TMP21:%.*]] = fmul float [[TMP19]], [[Y:%.*]]
+; CHECK-NEXT:    [[TMP23:%.*]] = fadd float [[TMP21]], [[TMP13]]
+; CHECK-NEXT:    [[TMP27_SUM50:%.*]] = or i32 [[TMP5]], 2
+; CHECK-NEXT:    [[TMP2:%.*]] = zext i32 [[TMP27_SUM50]] to i64
+; CHECK-NEXT:    [[TMP2849:%.*]] = getelementptr [128 x float], [128 x float]* @C.0.1248, i64 0, i64 [[TMP2]]
+; CHECK-NEXT:    [[TMP29:%.*]] = load float, float* [[TMP2849]], align 8
+; CHECK-NEXT:    [[TMP31:%.*]] = fmul float [[TMP29]], [[Z:%.*]]
+; CHECK-NEXT:    [[TMP33:%.*]] = fadd float [[TMP31]], [[TMP23]]
+; CHECK-NEXT:    [[TMP37_SUM48:%.*]] = or i32 [[TMP5]], 3
+; CHECK-NEXT:    [[TMP3:%.*]] = zext i32 [[TMP37_SUM48]] to i64
+; CHECK-NEXT:    [[TMP3847:%.*]] = getelementptr [128 x float], [128 x float]* @C.0.1248, i64 0, i64 [[TMP3]]
+; CHECK-NEXT:    [[TMP39:%.*]] = load float, float* [[TMP3847]], align 4
+; CHECK-NEXT:    [[TMP41:%.*]] = fmul float [[TMP39]], [[W:%.*]]
+; CHECK-NEXT:    [[TMP43:%.*]] = fadd float [[TMP41]], [[TMP33]]
+; CHECK-NEXT:    ret float [[TMP43]]
+;
 entry:
-  %lookupTable = alloca [128 x float], align 16    ; <[128 x float]*> [#uses=5]
-  %lookupTable1 = bitcast [128 x float]* %lookupTable to i8*    ; <i8*> [#uses=1]
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %lookupTable1, i8* align 16 bitcast ([128 x float]* @C.0.1248 to i8*), i64 512, i1 false)
+  %lookupTable = alloca [128 x float], align 16    ; <[128 x float]*> [#uses=5]
+  %lookupTable1 = bitcast [128 x float]* %lookupTable to i8*    ; <i8*> [#uses=1]
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %lookupTable1, i8* align 16 bitcast ([128 x float]* @C.0.1248 to i8*), i64 512, i1 false)
 
-; CHECK-LABEL: @test1(
-; CHECK-NOT: alloca
-; CHECK-NOT: call{{.*}}@llvm.memcpy
 
-  %tmp3 = shl i32 %hash, 2    ; <i32> [#uses=1]
-  %tmp5 = and i32 %tmp3, 124    ; <i32> [#uses=4]
-  %tmp753 = getelementptr [128 x float], [128 x float]* %lookupTable, i32 0, i32 %tmp5    ; <float*> [#uses=1]
-  %tmp9 = load float, float* %tmp753    ; <float> [#uses=1]
-  %tmp11 = fmul float %tmp9, %x    ; <float> [#uses=1]
-  %tmp13 = fadd float %tmp11, 0.000000e+00    ; <float> [#uses=1]
-  %tmp17.sum52 = or i32 %tmp5, 1    ; <i32> [#uses=1]
-  %tmp1851 = getelementptr [128 x float], [128 x float]* %lookupTable, i32 0, i32 %tmp17.sum52    ; <float*> [#uses=1]
-  %tmp19 = load float, float* %tmp1851    ; <float> [#uses=1]
-  %tmp21 = fmul float %tmp19, %y    ; <float> [#uses=1]
-  %tmp23 = fadd float %tmp21, %tmp13    ; <float> [#uses=1]
-  %tmp27.sum50 = or i32 %tmp5, 2    ; <i32> [#uses=1]
-  %tmp2849 = getelementptr [128 x float], [128 x float]* %lookupTable, i32 0, i32 %tmp27.sum50    ; <float*> [#uses=1]
-  %tmp29 = load float, float* %tmp2849    ; <float> [#uses=1]
-  %tmp31 = fmul float %tmp29, %z    ; <float> [#uses=1]
-  %tmp33 = fadd float %tmp31, %tmp23    ; <float> [#uses=1]
-  %tmp37.sum48 = or i32 %tmp5, 3    ; <i32> [#uses=1]
-  %tmp3847 = getelementptr [128 x float], [128 x float]* %lookupTable, i32 0, i32 %tmp37.sum48    ; <float*> [#uses=1]
-  %tmp39 = load float, float* %tmp3847    ; <float> [#uses=1]
-  %tmp41 = fmul float %tmp39, %w    ; <float> [#uses=1]
-  %tmp43 = fadd float %tmp41, %tmp33    ; <float> [#uses=1]
-  ret float %tmp43
+  %tmp3 = shl i32 %hash, 2    ; <i32> [#uses=1]
+  %tmp5 = and i32 %tmp3, 124    ; <i32> [#uses=4]
+  %tmp753 = getelementptr [128 x float], [128 x float]* %lookupTable, i32 0, i32 %tmp5    ; <float*> [#uses=1]
+  %tmp9 = load float, float* %tmp753    ; <float> [#uses=1]
+  %tmp11 = fmul float %tmp9, %x    ; <float> [#uses=1]
+  %tmp13 = fadd float %tmp11, 0.000000e+00    ; <float> [#uses=1]
+  %tmp17.sum52 = or i32 %tmp5, 1    ; <i32> [#uses=1]
+  %tmp1851 = getelementptr [128 x float], [128 x float]* %lookupTable, i32 0, i32 %tmp17.sum52    ; <float*> [#uses=1]
+  %tmp19 = load float, float* %tmp1851    ; <float> [#uses=1]
+  %tmp21 = fmul float %tmp19, %y    ; <float> [#uses=1]
+  %tmp23 = fadd float %tmp21, %tmp13    ; <float> [#uses=1]
+  %tmp27.sum50 = or i32 %tmp5, 2    ; <i32> [#uses=1]
+  %tmp2849 = getelementptr [128 x float], [128 x float]* %lookupTable, i32 0, i32 %tmp27.sum50    ; <float*> [#uses=1]
+  %tmp29 = load float, float* %tmp2849    ; <float> [#uses=1]
+  %tmp31 = fmul float %tmp29, %z    ; <float> [#uses=1]
+  %tmp33 = fadd float %tmp31, %tmp23    ; <float> [#uses=1]
+  %tmp37.sum48 = or i32 %tmp5, 3    ; <i32> [#uses=1]
+  %tmp3847 = getelementptr [128 x float], [128 x float]* %lookupTable, i32 0, i32 %tmp37.sum48    ; <float*> [#uses=1]
+  %tmp39 = load float, float* %tmp3847    ; <float> [#uses=1]
+  %tmp41 = fmul float %tmp39, %w    ; <float> [#uses=1]
+  %tmp43 = fadd float %tmp41, %tmp33    ; <float> [#uses=1]
+  ret float %tmp43
 }
 
 declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
 declare void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* nocapture, i8* nocapture, i64, i1) nounwind
 declare void @llvm.memcpy.p0i8.p1i8.i64(i8* nocapture, i8 addrspace(1)* nocapture, i64, i1) nounwind
 declare void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture, i64, i1) nounwind
 
 %T = type { i8, [123 x i8] }
 %U = type { i32, i32, i32, i32, i32 }
 
 @G = constant %T {i8 1, [123 x i8] zeroinitializer }
 @H = constant [2 x %U] zeroinitializer, align 16
 
 define void @test2() {
+; CHECK-LABEL: @test2(
+; CHECK-NEXT:    [[B1:%.*]] = alloca [124 x i8], align 8
+; CHECK-NEXT:    [[B1_SUB:%.*]] = getelementptr inbounds [124 x i8], [124 x i8]* [[B1]], i64 0, i64 0
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull align 8 dereferenceable(124) [[B1_SUB]], i8* align 16 dereferenceable(124) getelementptr inbounds (%T, %T* @G, i64 0, i32 0), i64 124, i1 false)
+; CHECK-NEXT:    call void @bar(i8* nonnull [[B1_SUB]])
+; CHECK-NEXT:    ret void
+;
   %A = alloca %T
   %B = alloca %T
   %a = bitcast %T* %A to i8*
   %b = bitcast %T* %B to i8*
 
-; CHECK-LABEL: @test2(
 
 ; %A alloca is deleted
-; CHECK-NEXT: alloca [124 x i8]
-; CHECK-NEXT: getelementptr inbounds [124 x i8], [124 x i8]*
 
 ; use @G instead of %A
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull align 8 %{{.*}}, i8* align 16 getelementptr inbounds (%T, %T* @G, i64 0, i32 0)
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 bitcast (%T* @G to i8*), i64 124, i1 false)
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %b, i8* align 4 %a, i64 124, i1 false)
   call void @bar(i8* %b)
   ret void
 }
 
 define void @test2_no_null_opt() #0 {
+; CHECK-LABEL: @test2_no_null_opt(
+; CHECK-NEXT:    [[B1:%.*]] = alloca [124 x i8], align 8
+; CHECK-NEXT:    [[B1_SUB:%.*]] = getelementptr inbounds [124 x i8], [124 x i8]* [[B1]], i64 0, i64 0
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 dereferenceable(124) [[B1_SUB]], i8* align 16 dereferenceable(124) getelementptr inbounds (%T, %T* @G, i64 0, i32 0), i64 124, i1 false)
+; CHECK-NEXT:    call void @bar(i8* [[B1_SUB]])
+; CHECK-NEXT:    ret void
+;
   %A = alloca %T
   %B = alloca %T
   %a = bitcast %T* %A to i8*
   %b = bitcast %T* %B to i8*
 
-; CHECK-LABEL: @test2_no_null_opt(
 
 ; %A alloca is deleted
-; CHECK-NEXT: alloca [124 x i8]
-; CHECK-NEXT: getelementptr inbounds [124 x i8], [124 x i8]*
 
 ; use @G instead of %A
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %{{.*}}, i8* align 16 getelementptr inbounds (%T, %T* @G, i64 0, i32 0)
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 bitcast (%T* @G to i8*), i64 124, i1 false)
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %b, i8* align 4 %a, i64 124, i1 false)
   call void @bar(i8* %b)
   ret void
 }
 
 define void @test2_addrspacecast() {
+; CHECK-LABEL: @test2_addrspacecast(
+; CHECK-NEXT:    [[B1:%.*]] = alloca [124 x i8], align 8
+; CHECK-NEXT:    [[B1_SUB:%.*]] = getelementptr inbounds [124 x i8], [124 x i8]* [[B1]], i64 0, i64 0
+; CHECK-NEXT:    [[B:%.*]] = addrspacecast i8* [[B1_SUB]] to i8 addrspace(1)*
+; CHECK-NEXT:    call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* align 4 dereferenceable(124) [[B]], i8 addrspace(1)* align 4 dereferenceable(124) addrspacecast (i8* getelementptr inbounds (%T, %T* @G, i64 0, i32 0) to i8 addrspace(1)*), i64 124, i1 false)
+; CHECK-NEXT:    call void @bar_as1(i8 addrspace(1)* [[B]])
+; CHECK-NEXT:    ret void
+;
   %A = alloca %T
   %B = alloca %T
   %a = addrspacecast %T* %A to i8 addrspace(1)*
   %b = addrspacecast %T* %B to i8 addrspace(1)*
 
-; CHECK-LABEL: @test2_addrspacecast(
 
 ; %A alloca is deleted
 ; This doesn't exactly match what test2 does, because folding the type
 ; cast into the alloca doesn't work for the addrspacecast yet.
-; CHECK-NEXT: alloca [124 x i8]
-; CHECK-NEXT: getelementptr
-; CHECK-NEXT: addrspacecast
 
 ; use @G instead of %A
-; CHECK-NEXT: call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* align 4 %{{.*}},
   call void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* align 4 %a, i8* align 4 bitcast (%T* @G to i8*), i64 124, i1 false)
   call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* align 4 %b, i8 addrspace(1)* align 4 %a, i64 124, i1 false)
   call void @bar_as1(i8 addrspace(1)* %b)
   ret void
 }
 
 declare void @bar(i8*)
 declare void @bar_as1(i8 addrspace(1)*)
 
 
 ;; Should be able to eliminate the alloca.
 define void @test3() {
+; CHECK-LABEL: @test3(
+; CHECK-NEXT:    call void @bar(i8* getelementptr inbounds (%T, %T* @G, i64 0, i32 0)) #2
+; CHECK-NEXT:    ret void
+;
   %A = alloca %T
   %a = bitcast %T* %A to i8*
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 bitcast (%T* @G to i8*), i64 124, i1 false)
   call void @bar(i8* %a) readonly
-; CHECK-LABEL: @test3(
-; CHECK-NEXT: call void @bar(i8* getelementptr inbounds (%T, %T* @G, i64 0, i32 0))
   ret void
 }
 
 define void @test3_addrspacecast() {
+; CHECK-LABEL: @test3_addrspacecast(
+; CHECK-NEXT:    call void @bar(i8* getelementptr inbounds (%T, %T* @G, i64 0, i32 0)) #2
+; CHECK-NEXT:    ret void
+;
   %A = alloca %T
   %a = bitcast %T* %A to i8*
   call void @llvm.memcpy.p0i8.p1i8.i64(i8* align 4 %a, i8 addrspace(1)* align 4 addrspacecast (%T* @G to i8 addrspace(1)*), i64 124, i1 false)
   call void @bar(i8* %a) readonly
-; CHECK-LABEL: @test3_addrspacecast(
-; CHECK-NEXT: call void @bar(i8* getelementptr inbounds (%T, %T* @G, i64 0, i32 0))
   ret void
 }
 
 
 define void @test4() {
+; CHECK-LABEL: @test4(
+; CHECK-NEXT:    call void @baz(i8* byval getelementptr inbounds (%T, %T* @G, i64 0, i32 0))
+; CHECK-NEXT:    ret void
+;
   %A = alloca %T
   %a = bitcast %T* %A to i8*
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 bitcast (%T* @G to i8*), i64 124, i1 false)
   call void @baz(i8* byval %a)
-; CHECK-LABEL: @test4(
-; CHECK-NEXT: call void @baz(i8* byval getelementptr inbounds (%T, %T* @G, i64 0, i32 0))
   ret void
 }
 
 declare void @llvm.lifetime.start.p0i8(i64, i8*)
 define void @test5() {
+; CHECK-LABEL: @test5(
+; CHECK-NEXT:    call void @baz(i8* byval getelementptr inbounds (%T, %T* @G, i64 0, i32 0))
+; CHECK-NEXT:    ret void
+;
   %A = alloca %T
   %a = bitcast %T* %A to i8*
   call void @llvm.lifetime.start.p0i8(i64 -1, i8* %a)
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 bitcast (%T* @G to i8*), i64 124, i1 false)
   call void @baz(i8* byval %a)
-; CHECK-LABEL: @test5(
-; CHECK-NEXT: call void @baz(i8* byval getelementptr inbounds (%T, %T* @G, i64 0, i32 0))
   ret void
 }
 
 
 declare void @baz(i8* byval)
 
 
 define void @test6() {
+; CHECK-LABEL: @test6(
+; CHECK-NEXT:    call void @bar(i8* bitcast ([2 x %U]* @H to i8*)) #2
+; CHECK-NEXT:    ret void
+;
   %A = alloca %U, align 16
   %a = bitcast %U* %A to i8*
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %a, i8* align 16 bitcast ([2 x %U]* @H to i8*), i64 20, i1 false)
   call void @bar(i8* %a) readonly
-; CHECK-LABEL: @test6(
-; CHECK-NEXT: call void @bar(i8* bitcast ([2 x %U]* @H to i8*))
   ret void
 }
 
 define void @test7() {
+; CHECK-LABEL: @test7(
+; CHECK-NEXT:    call void @bar(i8* bitcast ([2 x %U]* @H to i8*)) #2
+; CHECK-NEXT:    ret void
+;
   %A = alloca %U, align 16
   %a = bitcast %U* %A to i8*
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 bitcast (%U* getelementptr ([2 x %U], [2 x %U]* @H, i64 0, i32 0) to i8*), i64 20, i1 false)
   call void @bar(i8* %a) readonly
-; CHECK-LABEL: @test7(
-; CHECK-NEXT: call void @bar(i8* bitcast ([2 x %U]* @H to i8*))
   ret void
 }
 
 define void @test8() {
-  %A = alloca %U, align 16
-  %a = bitcast %U* %A to i8*
+; CHECK-LABEL: @test8(
+; CHECK-NEXT:    [[AL:%.*]] = alloca [[U:%.*]], align 16
+; CHECK-NEXT:    [[A:%.*]] = bitcast %U* [[AL]] to i8*
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull align 16 dereferenceable(20) [[A]], i8* align 4 dereferenceable(20) bitcast (%U* getelementptr inbounds ([2 x %U], [2 x %U]* @H, i64 0, i64 1) to i8*), i64 20, i1 false)
+; CHECK-NEXT:    call void @bar(i8* nonnull [[A]]) #2
+; CHECK-NEXT:    ret void
+;
+  %al = alloca %U, align 16
+  %a = bitcast %U* %al to i8*
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 bitcast (%U* getelementptr ([2 x %U], [2 x %U]* @H, i64 0, i32 1) to i8*), i64 20, i1 false)
   call void @bar(i8* %a) readonly
-; CHECK-LABEL: @test8(
-; CHECK: llvm.memcpy
-; CHECK: bar
   ret void
 }
 
 
 define void @test8_addrspacecast() {
-  %A = alloca %U, align 16
-  %a = bitcast %U* %A to i8*
+; CHECK-LABEL: @test8_addrspacecast(
+; CHECK-NEXT:    [[AL:%.*]] = alloca [[U:%.*]], align 16
+; CHECK-NEXT:    [[A:%.*]] = bitcast %U* [[AL]] to i8*
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p1i8.i64(i8* nonnull align 16 dereferenceable(20) [[A]], i8 addrspace(1)* align 4 dereferenceable(20) addrspacecast (i8* bitcast (%U* getelementptr inbounds ([2 x %U], [2 x %U]* @H, i64 0, i64 1) to i8*) to i8 addrspace(1)*), i64 20, i1 false)
+; CHECK-NEXT:    call void @bar(i8* nonnull [[A]]) #2
+; CHECK-NEXT:    ret void
+;
+  %Al = alloca %U, align 16
+  %a = bitcast %U* %Al to i8*
   call void @llvm.memcpy.p0i8.p1i8.i64(i8* align 4 %a, i8 addrspace(1)* align 4 addrspacecast (%U* getelementptr ([2 x %U], [2 x %U]* @H, i64 0, i32 1) to i8 addrspace(1)*), i64 20, i1 false)
   call void @bar(i8* %a) readonly
-; CHECK-LABEL: @test8_addrspacecast(
-; CHECK: llvm.memcpy
-; CHECK: bar
   ret void
 }
 
 define void @test9() {
+; CHECK-LABEL: @test9(
+; CHECK-NEXT:    call void @bar(i8* bitcast (%U* getelementptr inbounds ([2 x %U], [2 x %U]* @H, i64 0, i64 1) to i8*)) #2
+; CHECK-NEXT:    ret void
+;
   %A = alloca %U, align 4
   %a = bitcast %U* %A to i8*
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 bitcast (%U* getelementptr ([2 x %U], [2 x %U]* @H, i64 0, i32 1) to i8*), i64 20, i1 false)
   call void @bar(i8* %a) readonly
-; CHECK-LABEL: @test9(
-; CHECK-NEXT: call void @bar(i8* bitcast (%U* getelementptr inbounds ([2 x %U], [2 x %U]* @H, i64 0, i64 1) to i8*))
   ret void
 }
 
 define void @test9_addrspacecast() {
+; CHECK-LABEL: @test9_addrspacecast(
+; CHECK-NEXT:    call void @bar(i8* bitcast (%U* getelementptr inbounds ([2 x %U], [2 x %U]* @H, i64 0, i64 1) to i8*)) #2
+; CHECK-NEXT:    ret void
+;
   %A = alloca %U, align 4
   %a = bitcast %U* %A to i8*
   call void @llvm.memcpy.p0i8.p1i8.i64(i8* align 4 %a, i8 addrspace(1)* align 4 addrspacecast (%U* getelementptr ([2 x %U], [2 x %U]* @H, i64 0, i32 1) to i8 addrspace(1)*), i64 20, i1 false)
   call void @bar(i8* %a) readonly
-; CHECK-LABEL: @test9_addrspacecast(
-; CHECK-NEXT: call void @bar(i8* bitcast (%U* getelementptr inbounds ([2 x %U], [2 x %U]* @H, i64 0, i64 1) to i8*))
   ret void
 }
 
 @bbb = local_unnamed_addr global [1000000 x i8] zeroinitializer, align 16
 @_ZL3KKK = internal unnamed_addr constant [3 x i8] c"\01\01\02", align 1
 
 ; Should not replace alloca with global because of size mismatch.
 define void @test9_small_global() {
 ; CHECK-LABEL: @test9_small_global(
-; CHECK-NOT: call void @llvm.memcpy.p0i8.p0i8.i64({{.*}}@bbb,{{.*}}@_ZL3KKK, 
-; CHECK: alloca [1000000 x i8]
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[CC:%.*]] = alloca [1000000 x i8], align 16
+; CHECK-NEXT:    [[ARRAYDECAY:%.*]] = getelementptr inbounds [1000000 x i8], [1000000 x i8]* [[CC]], i64 0, i64 0
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull align 16 dereferenceable(3) [[ARRAYDECAY]], i8* align 16 dereferenceable(3) getelementptr inbounds ([3 x i8], [3 x i8]* @_ZL3KKK, i64 0, i64 0), i64 3, i1 false)
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 dereferenceable(1000000) getelementptr inbounds ([1000000 x i8], [1000000 x i8]* @bbb, i64 0, i64 0), i8* nonnull align 16 dereferenceable(1000000) [[ARRAYDECAY]], i64 1000000, i1 false)
+; CHECK-NEXT:    ret void
+;
 entry:
   %cc = alloca [1000000 x i8], align 16
   %cc.0..sroa_idx = getelementptr inbounds [1000000 x i8], [1000000 x i8]* %cc, i64 0, i64 0
   %arraydecay = getelementptr inbounds [1000000 x i8], [1000000 x i8]* %cc, i32 0, i32 0
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arraydecay, i8* getelementptr inbounds ([3 x i8], [3 x i8]* @_ZL3KKK, i32 0, i32 0), i64 3, i1 false)
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 getelementptr inbounds ([1000000 x i8], [1000000 x i8]* @bbb, i32 0, i32 0), i8* align 16 %arraydecay, i64 1000000, i1 false)
   ret void
 }
 
 ; Should replace alloca with global as they have exactly the same size.
 define void @test10_same_global() {
 ; CHECK-LABEL: @test10_same_global(
-; CHECK-NOT: alloca
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64({{.*}}@bbb,{{.*}}@_ZL3KKK,{{.*}}, i64 3,
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 dereferenceable(3) getelementptr inbounds ([1000000 x i8], [1000000 x i8]* @bbb, i64 0, i64 0), i8* align 16 dereferenceable(3) getelementptr inbounds ([3 x i8], [3 x i8]* @_ZL3KKK, i64 0, i64 0), i64 3, i1 false)
+; CHECK-NEXT:    ret void
+;
 entry:
   %cc = alloca [3 x i8], align 1
   %cc.0..sroa_idx = getelementptr inbounds [3 x i8], [3 x i8]* %cc, i64 0, i64 0
   %arraydecay = getelementptr inbounds [3 x i8], [3 x i8]* %cc, i32 0, i32 0
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arraydecay, i8* getelementptr inbounds ([3 x i8], [3 x i8]* @_ZL3KKK, i32 0, i32 0), i64 3, i1 false)
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* getelementptr inbounds ([1000000 x i8], [1000000 x i8]* @bbb, i32 0, i32 0), i8* %arraydecay, i64 3, i1 false)
   ret void
 }
 
 attributes #0 = { "null-pointer-is-valid"="true" }

test/Transforms/InstCombine/memcpy-to-load.ll

;
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 2, i1 false)
   ret void
 }
 
 ; We don't expand small non-power-of-2. Should we? Might be a target-dependent choice.
 
 define void @copy_3_bytes(i8* %d, i8* %s) {
 ; ALL-LABEL: @copy_3_bytes(
-; ALL-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[D:%.*]], i8* align 1 [[S:%.*]], i32 3, i1 false)
+; ALL-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 dereferenceable(3) [[D:%.*]], i8* align 1 dereferenceable(3) [[S:%.*]], i32 3, i1 false)
 ; ALL-NEXT:    ret void
 ;
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 3, i1 false)
   ret void
 }
 
 define void @copy_4_bytes(i8* %d, i8* %s) {
 ; ALL-LABEL: @copy_4_bytes(
 ; ALL-NEXT:    [[TMP1:%.*]] = bitcast i8* [[S:%.*]] to i32*
 ; ALL-NEXT:    [[TMP2:%.*]] = bitcast i8* [[D:%.*]] to i32*
 ; ALL-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1]], align 1
 ; ALL-NEXT:    store i32 [[TMP3]], i32* [[TMP2]], align 1
 ; ALL-NEXT:    ret void
 ;
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 4, i1 false)
   ret void
 }
 
 ; We don't expand small non-power-of-2. Should we? Might be a target-dependent choice.
 
 define void @copy_5_bytes(i8* %d, i8* %s) {
 ; ALL-LABEL: @copy_5_bytes(
-; ALL-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[D:%.*]], i8* align 1 [[S:%.*]], i32 5, i1 false)
+; ALL-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 dereferenceable(5) [[D:%.*]], i8* align 1 dereferenceable(5) [[S:%.*]], i32 5, i1 false)
 ; ALL-NEXT:    ret void
 ;
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 5, i1 false)
   ret void
 }
 
 define void @copy_8_bytes(i8* %d, i8* %s) {
 ; ALL-LABEL: @copy_8_bytes(
 ; ALL-NEXT:    [[TMP1:%.*]] = bitcast i8* [[S:%.*]] to i64*
 ; ALL-NEXT:    [[TMP2:%.*]] = bitcast i8* [[D:%.*]] to i64*
 ; ALL-NEXT:    [[TMP3:%.*]] = load i64, i64* [[TMP1]], align 1
 ; ALL-NEXT:    store i64 [[TMP3]], i64* [[TMP2]], align 1
 ; ALL-NEXT:    ret void
 ;
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 8, i1 false)
   ret void
 }
 
 define void @copy_16_bytes(i8* %d, i8* %s) {
 ; ALL-LABEL: @copy_16_bytes(
-; ALL-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[D:%.*]], i8* align 1 [[S:%.*]], i32 16, i1 false)
+; ALL-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 dereferenceable(16) [[D:%.*]], i8* align 1 dereferenceable(16) [[S:%.*]], i32 16, i1 false)
 ; ALL-NEXT:    ret void
 ;
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 16, i1 false)
   ret void
 }
 

test/Transforms/InstCombine/memcpy.ll

;
   tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %a, i32 100, i1 true)
   ret void
 }
 
 ; 17179869184 == 0x400000000 - make sure that doesn't get truncated to 32-bit.
 
 define void @test3(i8* %d, i8* %s) {
 ; CHECK-LABEL: @test3(
-; CHECK-NEXT:    tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[D:%.*]], i8* align 4 [[S:%.*]], i64 17179869184, i1 false)
+; CHECK-NEXT:    tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 dereferenceable(17179869184) [[D:%.*]], i8* align 4 dereferenceable(17179869184) [[S:%.*]], i64 17179869184, i1 false)
 ; CHECK-NEXT:    ret void
 ;
   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %d, i8* align 4 %s, i64 17179869184, i1 false)
   ret void
 }
 
 @UnknownConstant = external constant i128
 
 define void @memcpy_to_constant(i8* %src) {
 ; CHECK-LABEL: @memcpy_to_constant(
 ; CHECK-NEXT:    ret void
 ;
   %dest = bitcast i128* @UnknownConstant to i8*
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 16, i1 false)
   ret void
 }

test/Transforms/InstCombine/memcpy_chk-1.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; Test lib call simplification of __memcpy_chk calls with various values
 ; for dstlen and len.
 ;
 ; RUN: opt < %s -instcombine -S | FileCheck %s
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 
 %struct.T1 = type { [100 x i32], [100 x i32], [1024 x i8] }
 %struct.T2 = type { [100 x i32], [100 x i32], [1024 x i8] }
 %struct.T3 = type { [100 x i32], [100 x i32], [2048 x i8] }
 
 @t1 = common global %struct.T1 zeroinitializer
 @t2 = common global %struct.T2 zeroinitializer
 @t3 = common global %struct.T3 zeroinitializer
 
 ; Check cases where dstlen >= len.
 
 define i8* @test_simplify1() {
 ; CHECK-LABEL: @test_simplify1(
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 dereferenceable(1824) bitcast (%struct.T1* @t1 to i8*), i8* align 4 dereferenceable(1824) bitcast (%struct.T2* @t2 to i8*), i64 1824, i1 false)
+; CHECK-NEXT:    ret i8* bitcast (%struct.T1* @t1 to i8*)
+;
   %dst = bitcast %struct.T1* @t1 to i8*
   %src = bitcast %struct.T2* @t2 to i8*
-
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 bitcast (%struct.T1* @t1 to i8*), i8* align 4 bitcast (%struct.T2* @t2 to i8*), i64 1824, i1 false)
-; CHECK-NEXT: ret i8* bitcast (%struct.T1* @t1 to i8*)
   %ret = call i8* @__memcpy_chk(i8* %dst, i8* %src, i64 1824, i64 1824)
   ret i8* %ret
 }
 
 define i8* @test_simplify2() {
 ; CHECK-LABEL: @test_simplify2(
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 dereferenceable(1824) bitcast (%struct.T1* @t1 to i8*), i8* align 4 dereferenceable(1824) bitcast (%struct.T3* @t3 to i8*), i64 1824, i1 false)
+; CHECK-NEXT:    ret i8* bitcast (%struct.T1* @t1 to i8*)
+;
   %dst = bitcast %struct.T1* @t1 to i8*
   %src = bitcast %struct.T3* @t3 to i8*
-
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 bitcast (%struct.T1* @t1 to i8*), i8* align 4 bitcast (%struct.T3* @t3 to i8*), i64 1824, i1 false)
-; CHECK-NEXT: ret i8* bitcast (%struct.T1* @t1 to i8*)
   %ret = call i8* @__memcpy_chk(i8* %dst, i8* %src, i64 1824, i64 2848)
   ret i8* %ret
 }
 
 ; Check cases where dstlen < len.
 
 define i8* @test_no_simplify1() {
 ; CHECK-LABEL: @test_no_simplify1(
+; CHECK-NEXT:    [[RET:%.*]] = call i8* @__memcpy_chk(i8* bitcast (%struct.T3* @t3 to i8*), i8* bitcast (%struct.T1* @t1 to i8*), i64 2848, i64 1824)
+; CHECK-NEXT:    ret i8* [[RET]]
+;
   %dst = bitcast %struct.T3* @t3 to i8*
   %src = bitcast %struct.T1* @t1 to i8*
-
-; CHECK-NEXT: %ret = call i8* @__memcpy_chk(i8* bitcast (%struct.T3* @t3 to i8*), i8* bitcast (%struct.T1* @t1 to i8*), i64 2848, i64 1824)
-; CHECK-NEXT: ret i8* %ret
   %ret = call i8* @__memcpy_chk(i8* %dst, i8* %src, i64 2848, i64 1824)
   ret i8* %ret
 }
 
 define i8* @test_no_simplify2() {
 ; CHECK-LABEL: @test_no_simplify2(
+; CHECK-NEXT:    [[RET:%.*]] = call i8* @__memcpy_chk(i8* bitcast (%struct.T1* @t1 to i8*), i8* bitcast (%struct.T2* @t2 to i8*), i64 1024, i64 0)
+; CHECK-NEXT:    ret i8* [[RET]]
+;
   %dst = bitcast %struct.T1* @t1 to i8*
   %src = bitcast %struct.T2* @t2 to i8*
-
-; CHECK-NEXT: %ret = call i8* @__memcpy_chk(i8* bitcast (%struct.T1* @t1 to i8*), i8* bitcast (%struct.T2* @t2 to i8*), i64 1024, i64 0)
-; CHECK-NEXT: ret i8* %ret
   %ret = call i8* @__memcpy_chk(i8* %dst, i8* %src, i64 1024, i64 0)
   ret i8* %ret
 }
 
 define i8* @test_simplify_return_indcall(i8* ()* %alloc) {
 ; CHECK-LABEL: @test_simplify_return_indcall(
+; CHECK-NEXT:    [[DST:%.*]] = call i8* [[ALLOC:%.*]]()
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 dereferenceable(1824) [[DST]], i8* align 4 dereferenceable(1824) bitcast (%struct.T2* @t2 to i8*), i64 1824, i1 false)
+; CHECK-NEXT:    ret i8* [[DST]]
+;
   %src = bitcast %struct.T2* @t2 to i8*
-
-; CHECK-NEXT: %dst = call i8* %alloc()
   %dst = call i8* %alloc()
-
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64
   %ret = call i8* @__memcpy_chk(i8* %dst, i8* %src, i64 1824, i64 1824)
-; CHECK-NEXT: ret i8* %dst
   ret i8* %ret
 }
 
 declare i8* @__memcpy_chk(i8*, i8*, i64, i64)

test/Transforms/InstCombine/memmove_chk-1.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; Test lib call simplification of __memmove_chk calls with various values
 ; for dstlen and len.
 ;
 ; RUN: opt < %s -instcombine -S | FileCheck %s
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 
 %struct.T1 = type { [100 x i32], [100 x i32], [1024 x i8] }
 %struct.T2 = type { [100 x i32], [100 x i32], [1024 x i8] }
 %struct.T3 = type { [100 x i32], [100 x i32], [2048 x i8] }
 
 @t1 = common global %struct.T1 zeroinitializer
 @t2 = common global %struct.T2 zeroinitializer
 @t3 = common global %struct.T3 zeroinitializer
 
 ; Check cases where dstlen >= len.
 
 define i8* @test_simplify1() {
 ; CHECK-LABEL: @test_simplify1(
+; CHECK-NEXT:    call void @llvm.memmove.p0i8.p0i8.i64(i8* align 4 dereferenceable(1824) bitcast (%struct.T1* @t1 to i8*), i8* align 4 dereferenceable(1824) bitcast (%struct.T2* @t2 to i8*), i64 1824, i1 false)
+; CHECK-NEXT:    ret i8* bitcast (%struct.T1* @t1 to i8*)
+;
   %dst = bitcast %struct.T1* @t1 to i8*
   %src = bitcast %struct.T2* @t2 to i8*
 
-; CHECK-NEXT: call void @llvm.memmove.p0i8.p0i8.i64(i8* align 4 bitcast (%struct.T1* @t1 to i8*), i8* align 4 bitcast (%struct.T2* @t2 to i8*), i64 1824, i1 false)
-; CHECK-NEXT: ret i8* bitcast (%struct.T1* @t1 to i8*)
   %ret = call i8* @__memmove_chk(i8* %dst, i8* %src, i64 1824, i64 1824)
   ret i8* %ret
 }
 
 define i8* @test_simplify2() {
 ; CHECK-LABEL: @test_simplify2(
+; CHECK-NEXT:    call void @llvm.memmove.p0i8.p0i8.i64(i8* align 4 dereferenceable(1824) bitcast (%struct.T1* @t1 to i8*), i8* align 4 dereferenceable(1824) bitcast (%struct.T3* @t3 to i8*), i64 1824, i1 false)
+; CHECK-NEXT:    ret i8* bitcast (%struct.T1* @t1 to i8*)
+;
   %dst = bitcast %struct.T1* @t1 to i8*
   %src = bitcast %struct.T3* @t3 to i8*
 
-; CHECK-NEXT: call void @llvm.memmove.p0i8.p0i8.i64(i8* align 4 bitcast (%struct.T1* @t1 to i8*), i8* align 4 bitcast (%struct.T3* @t3 to i8*), i64 1824, i1 false)
-; CHECK-NEXT: ret i8* bitcast (%struct.T1* @t1 to i8*)
   %ret = call i8* @__memmove_chk(i8* %dst, i8* %src, i64 1824, i64 2848)
   ret i8* %ret
 }
 
 ; Check cases where dstlen < len.
 
 define i8* @test_no_simplify1() {
 ; CHECK-LABEL: @test_no_simplify1(
+; CHECK-NEXT:    [[RET:%.*]] = call i8* @__memmove_chk(i8* bitcast (%struct.T3* @t3 to i8*), i8* bitcast (%struct.T1* @t1 to i8*), i64 2848, i64 1824)
+; CHECK-NEXT:    ret i8* [[RET]]
+;
   %dst = bitcast %struct.T3* @t3 to i8*
   %src = bitcast %struct.T1* @t1 to i8*
 
-; CHECK-NEXT: %ret = call i8* @__memmove_chk(i8* bitcast (%struct.T3* @t3 to i8*), i8* bitcast (%struct.T1* @t1 to i8*), i64 2848, i64 1824)
-; CHECK-NEXT: ret i8* %ret
   %ret = call i8* @__memmove_chk(i8* %dst, i8* %src, i64 2848, i64 1824)
   ret i8* %ret
 }
 
 define i8* @test_no_simplify2() {
 ; CHECK-LABEL: @test_no_simplify2(
+; CHECK-NEXT:    [[RET:%.*]] = call i8* @__memmove_chk(i8* bitcast (%struct.T1* @t1 to i8*), i8* bitcast (%struct.T2* @t2 to i8*), i64 1024, i64 0)
+; CHECK-NEXT:    ret i8* [[RET]]
+;
   %dst = bitcast %struct.T1* @t1 to i8*
   %src = bitcast %struct.T2* @t2 to i8*
 
-; CHECK-NEXT: %ret = call i8* @__memmove_chk(i8* bitcast (%struct.T1* @t1 to i8*), i8* bitcast (%struct.T2* @t2 to i8*), i64 1024, i64 0)
-; CHECK-NEXT: ret i8* %ret
   %ret = call i8* @__memmove_chk(i8* %dst, i8* %src, i64 1024, i64 0)
   ret i8* %ret
 }
 
 declare i8* @__memmove_chk(i8*, i8*, i64, i64)

test/Transforms/InstCombine/memset_chk-1.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; Test lib call simplification of __memset_chk calls with various values
 ; for dstlen and len.
 ;
 ; RUN: opt < %s -instcombine -S | FileCheck %s
 ; rdar://7719085
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 
 %struct.T = type { [100 x i32], [100 x i32], [1024 x i8] }
 @t = common global %struct.T zeroinitializer
 
 ; Check cases where dstlen >= len.
 
 define i8* @test_simplify1() {
 ; CHECK-LABEL: @test_simplify1(
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 dereferenceable(1824) bitcast (%struct.T* @t to i8*), i8 0, i64 1824, i1 false)
+; CHECK-NEXT:    ret i8* bitcast (%struct.T* @t to i8*)
+;
   %dst = bitcast %struct.T* @t to i8*
 
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 4 bitcast (%struct.T* @t to i8*), i8 0, i64 1824, i1 false)
-; CHECK-NEXT: ret i8* bitcast (%struct.T* @t to i8*)
   %ret = call i8* @__memset_chk(i8* %dst, i32 0, i64 1824, i64 1824)
   ret i8* %ret
 }
 
 define i8* @test_simplify2() {
 ; CHECK-LABEL: @test_simplify2(
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 dereferenceable(1824) bitcast (%struct.T* @t to i8*), i8 0, i64 1824, i1 false)
+; CHECK-NEXT:    ret i8* bitcast (%struct.T* @t to i8*)
+;
   %dst = bitcast %struct.T* @t to i8*
 
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 4 bitcast (%struct.T* @t to i8*), i8 0, i64 1824, i1 false)
-; CHECK-NEXT: ret i8* bitcast (%struct.T* @t to i8*)
   %ret = call i8* @__memset_chk(i8* %dst, i32 0, i64 1824, i64 3648)
   ret i8* %ret
 }
 
 define i8* @test_simplify3() {
 ; CHECK-LABEL: @test_simplify3(
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 dereferenceable(1824) bitcast (%struct.T* @t to i8*), i8 0, i64 1824, i1 false)
+; CHECK-NEXT:    ret i8* bitcast (%struct.T* @t to i8*)
+;
   %dst = bitcast %struct.T* @t to i8*
 
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 4 bitcast (%struct.T* @t to i8*), i8 0, i64 1824, i1 false)
-; CHECK-NEXT: ret i8* bitcast (%struct.T* @t to i8*)
   %ret = call i8* @__memset_chk(i8* %dst, i32 0, i64 1824, i64 -1)
   ret i8* %ret
 }
 
 ; Check cases where dstlen < len.
 
 define i8* @test_no_simplify1() {
 ; CHECK-LABEL: @test_no_simplify1(
+; CHECK-NEXT:    [[RET:%.*]] = call i8* @__memset_chk(i8* bitcast (%struct.T* @t to i8*), i32 0, i64 1824, i64 400)
+; CHECK-NEXT:    ret i8* [[RET]]
+;
   %dst = bitcast %struct.T* @t to i8*
 
-; CHECK-NEXT: %ret = call i8* @__memset_chk(i8* bitcast (%struct.T* @t to i8*), i32 0, i64 1824, i64 400)
-; CHECK-NEXT: ret i8* %ret
   %ret = call i8* @__memset_chk(i8* %dst, i32 0, i64 1824, i64 400)
   ret i8* %ret
 }
 
 define i8* @test_no_simplify2() {
 ; CHECK-LABEL: @test_no_simplify2(
+; CHECK-NEXT:    [[RET:%.*]] = call i8* @__memset_chk(i8* bitcast (%struct.T* @t to i8*), i32 0, i64 1824, i64 0)
+; CHECK-NEXT:    ret i8* [[RET]]
+;
   %dst = bitcast %struct.T* @t to i8*
 
-; CHECK-NEXT: %ret = call i8* @__memset_chk(i8* bitcast (%struct.T* @t to i8*), i32 0, i64 1824, i64 0)
-; CHECK-NEXT: ret i8* %ret
   %ret = call i8* @__memset_chk(i8* %dst, i32 0, i64 1824, i64 0)
   ret i8* %ret
 }
 
 ; Test that RAUW in SimplifyLibCalls for __memset_chk generates valid IR
 define i32 @test_rauw(i8* %a, i8* %b, i8** %c) {
-; CHECK-LABEL: test_rauw
+; CHECK-LABEL: @test_rauw(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[CALL49:%.*]] = call i64 @strlen(i8* [[A:%.*]])
+; CHECK-NEXT:    [[ADD180:%.*]] = add i64 [[CALL49]], 1
+; CHECK-NEXT:    [[YO107:%.*]] = call i64 @llvm.objectsize.i64.p0i8(i8* [[B:%.*]], i1 false, i1 false, i1 false)
+; CHECK-NEXT:    [[CALL50:%.*]] = call i8* @__memmove_chk(i8* [[B]], i8* [[A]], i64 [[ADD180]], i64 [[YO107]])
+; CHECK-NEXT:    [[STRLEN:%.*]] = call i64 @strlen(i8* [[B]])
+; CHECK-NEXT:    [[STRCHR2:%.*]] = getelementptr i8, i8* [[B]], i64 [[STRLEN]]
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i8** [[C:%.*]] to i64*
+; CHECK-NEXT:    [[D1:%.*]] = load i64, i64* [[TMP0]], align 8
+; CHECK-NEXT:    [[SUB183:%.*]] = ptrtoint i8* [[B]] to i64
+; CHECK-NEXT:    [[SUB184:%.*]] = sub i64 [[D1]], [[SUB183]]
+; CHECK-NEXT:    [[ADD52_I_I:%.*]] = add nsw i64 [[SUB184]], 1
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 1 [[STRCHR2]], i8 0, i64 [[ADD52_I_I]], i1 false)
+; CHECK-NEXT:    ret i32 4
+;
 entry:
   %call49 = call i64 @strlen(i8* %a)
   %add180 = add i64 %call49, 1
   %yo107 = call i64 @llvm.objectsize.i64.p0i8(i8* %b, i1 false, i1 false, i1 false)
   %call50 = call i8* @__memmove_chk(i8* %b, i8* %a, i64 %add180, i64 %yo107)
-; CHECK: %strlen = call i64 @strlen(i8* %b)
-; CHECK-NEXT: %strchr2 = getelementptr i8, i8* %b, i64 %strlen
   %call51i = call i8* @strrchr(i8* %b, i32 0)
   %d = load i8*, i8** %c, align 8
   %sub182 = ptrtoint i8* %d to i64
   %sub183 = ptrtoint i8* %b to i64
   %sub184 = sub i64 %sub182, %sub183
   %add52.i.i = add nsw i64 %sub184, 1
-; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %strchr2
   %call185 = call i8* @__memset_chk(i8* %call51i, i32 0, i64 %add52.i.i, i64 -1)
   ret i32 4
 }
 
 declare i8* @__memmove_chk(i8*, i8*, i64, i64)
 declare i8* @strrchr(i8*, i32)
 declare i64 @strlen(i8* nocapture)
 declare i64 @llvm.objectsize.i64.p0i8(i8*, i1, i1, i1)
 
 declare i8* @__memset_chk(i8*, i32, i64, i64)
 
 ; FIXME: memset(malloc(x), 0, x) -> calloc(1, x)
 
 define float* @pr25892(i64 %size) #0 {
+; CHECK-LABEL: @pr25892(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i8* @malloc(i64 [[SIZE:%.*]]) #3
+; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i8* [[CALL]], null
+; CHECK-NEXT:    br i1 [[CMP]], label [[CLEANUP:%.*]], label [[IF_END:%.*]]
+; CHECK:       if.end:
+; CHECK-NEXT:    [[BC:%.*]] = bitcast i8* [[CALL]] to float*
+; CHECK-NEXT:    [[CALL2:%.*]] = tail call i64 @llvm.objectsize.i64.p0i8(i8* nonnull [[CALL]], i1 false, i1 false, i1 false)
+; CHECK-NEXT:    [[CALL3:%.*]] = tail call i8* @__memset_chk(i8* nonnull [[CALL]], i32 0, i64 [[SIZE]], i64 [[CALL2]]) #3
+; CHECK-NEXT:    br label [[CLEANUP]]
+; CHECK:       cleanup:
+; CHECK-NEXT:    [[RETVAL_0:%.*]] = phi float* [ [[BC]], [[IF_END]] ], [ null, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    ret float* [[RETVAL_0]]
+;
 entry:
   %call = tail call i8* @malloc(i64 %size) #1
   %cmp = icmp eq i8* %call, null
   br i1 %cmp, label %cleanup, label %if.end
 if.end:
   %bc = bitcast i8* %call to float*
   %call2 = tail call i64 @llvm.objectsize.i64.p0i8(i8* nonnull %call, i1 false, i1 false, i1 false)
   %call3 = tail call i8* @__memset_chk(i8* nonnull %call, i32 0, i64 %size, i64 %call2) #1
   br label %cleanup
 cleanup:
   %retval.0 = phi float* [ %bc, %if.end ], [ null, %entry ]
   ret float* %retval.0
 
-; CHECK-LABEL: @pr25892(
-; CHECK:       entry:
-; CHECK-NEXT:    %call = tail call i8* @malloc(i64 %size)
-; CHECK-NEXT:    %cmp = icmp eq i8* %call, null
-; CHECK-NEXT:    br i1 %cmp, label %cleanup, label %if.end
-; CHECK:       if.end:
-; CHECK-NEXT:    %bc = bitcast i8* %call to float*
-; CHECK-NEXT:    %call2 = tail call i64 @llvm.objectsize.i64.p0i8(i8* nonnull %call, i1 false, i1 false, i1 false)
-; CHECK-NEXT:    %call3 = tail call i8* @__memset_chk(i8* nonnull %call, i32 0, i64 %size, i64 %call2)
-; CHECK-NEXT:    br label %cleanup
-; CHECK:       cleanup:
-; CHECK-NEXT:    %retval.0 = phi float* [ %bc, %if.end ], [ null, %entry ]
-; CHECK-NEXT:    ret float* %retval.0
 }
 
 declare noalias i8* @malloc(i64) #1
 
 attributes #0 = { nounwind ssp uwtable }
 attributes #1 = { nounwind }
 attributes #2 = { nounwind readnone }
 

test/Transforms/InstCombine/objsize.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; Test a pile of objectsize bounds checking.
 ; RUN: opt < %s -instcombine -S | FileCheck %s
 ; We need target data to get the sizes of the arrays and structures.
 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
 
 @a = private global [60 x i8] zeroinitializer, align 1 ; <[60 x i8]*>
 @.str = private constant [8 x i8] c"abcdefg\00"   ; <[8 x i8]*>
 define i32 @foo() nounwind {
 ; CHECK-LABEL: @foo(
-; CHECK-NEXT: ret i32 60
+; CHECK-NEXT:    ret i32 60
+;
   %1 = call i32 @llvm.objectsize.i32.p0i8(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i1 false, i1 false, i1 false)
   ret i32 %1
 }
 
 define i8* @bar() nounwind {
 ; CHECK-LABEL: @bar(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[RETVAL:%.*]] = alloca i8*, align 4
+; CHECK-NEXT:    br i1 true, label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
+; CHECK:       cond.true:
+; CHECK-NEXT:    [[TMP0:%.*]] = load i8*, i8** [[RETVAL]], align 4
+; CHECK-NEXT:    ret i8* [[TMP0]]
+; CHECK:       cond.false:
+; CHECK-NEXT:    ret i8* undef
+;
 entry:
   %retval = alloca i8*
   %0 = call i32 @llvm.objectsize.i32.p0i8(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i1 false, i1 false, i1 false)
   %cmp = icmp ne i32 %0, -1
-; CHECK: br i1 true
   br i1 %cmp, label %cond.true, label %cond.false
 
 cond.true:
   %1 = load i8*, i8** %retval
   ret i8* %1
 
 cond.false:
   %2 = load i8*, i8** %retval
   ret i8* %2
 }
 
 define i32 @f() nounwind {
 ; CHECK-LABEL: @f(
-; CHECK-NEXT: ret i32 0
+; CHECK-NEXT:    ret i32 0
+;
   %1 = call i32 @llvm.objectsize.i32.p0i8(i8* getelementptr ([60 x i8], [60 x i8]* @a, i32 1, i32 0), i1 false, i1 false, i1 false)
   ret i32 %1
 }
 
 @window = external global [0 x i8]
 
 define i1 @baz() nounwind {
 ; CHECK-LABEL: @baz(
-; CHECK-NEXT: objectsize
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call i32 @llvm.objectsize.i32.p0i8(i8* getelementptr inbounds ([0 x i8], [0 x i8]* @window, i32 0, i32 0), i1 false, i1 false, i1 false)
+; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i32 [[TMP1]], -1
+; CHECK-NEXT:    ret i1 [[TMP2]]
+;
   %1 = tail call i32 @llvm.objectsize.i32.p0i8(i8* getelementptr inbounds ([0 x i8], [0 x i8]* @window, i32 0, i32 0), i1 false, i1 false, i1 false)
   %2 = icmp eq i32 %1, -1
   ret i1 %2
 }
 
 define void @test1(i8* %q, i32 %x) nounwind noinline {
 ; CHECK-LABEL: @test1(
-; CHECK: objectsize.i32.p0i8
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.objectsize.i32.p0i8(i8* getelementptr inbounds ([0 x i8], [0 x i8]* @window, i32 0, i32 10), i1 false, i1 false, i1 false)
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq i32 [[TMP0]], -1
+; CHECK-NEXT:    br i1 [[TMP1]], label %"47", label %"46"
+; CHECK:       "46":
+; CHECK-NEXT:    unreachable
+; CHECK:       "47":
+; CHECK-NEXT:    unreachable
+;
 entry:
   %0 = call i32 @llvm.objectsize.i32.p0i8(i8* getelementptr inbounds ([0 x i8], [0 x i8]* @window, i32 0, i32 10), i1 false, i1 false, i1 false) ; <i64> [#uses=1]
   %1 = icmp eq i32 %0, -1                         ; <i1> [#uses=1]
   br i1 %1, label %"47", label %"46"
 
 "46":                                             ; preds = %entry
   unreachable
 
 "47":                                             ; preds = %entry
   unreachable
 }
 
 @.str5 = private constant [9 x i32] [i32 97, i32 98, i32 99, i32 100, i32 0, i32
  101, i32 102, i32 103, i32 0], align 4
 define i32 @test2() nounwind {
 ; CHECK-LABEL: @test2(
-; CHECK-NEXT: ret i32 34
+; CHECK-NEXT:    ret i32 34
+;
   %1 = call i32 @llvm.objectsize.i32.p0i8(i8* getelementptr (i8, i8* bitcast ([9 x i32]* @.str5 to i8*), i32 2), i1 false, i1 false, i1 false)
   ret i32 %1
 }
 
 ; rdar://7674946
 @array = internal global [480 x float] zeroinitializer ; <[480 x float]*> [#uses=1]
 
 declare i8* @__memcpy_chk(i8*, i8*, i32, i32) nounwind
 
 declare i32 @llvm.objectsize.i32.p0i8(i8*, i1, i1, i1) nounwind readonly
 
 declare i32 @llvm.objectsize.i32.p1i8(i8 addrspace(1)*, i1, i1, i1) nounwind readonly
 
 declare i8* @__inline_memcpy_chk(i8*, i8*, i32) nounwind inlinehint
 
 define void @test3() nounwind {
 ; CHECK-LABEL: @test3(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br i1 undef, label [[BB11:%.*]], label [[BB12:%.*]]
+; CHECK:       bb11:
+; CHECK-NEXT:    unreachable
+; CHECK:       bb12:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i8* @__inline_memcpy_chk(i8* bitcast (float* getelementptr inbounds ([480 x float], [480 x float]* @array, i32 0, i32 1) to i8*), i8* undef, i32 512) #3
+; CHECK-NEXT:    unreachable
+;
 entry:
   br i1 undef, label %bb11, label %bb12
 
 bb11:
   %0 = getelementptr inbounds float, float* getelementptr inbounds ([480 x float], [480 x float]* @array, i32 0, i32 128), i32 -127 ; <float*> [#uses=1]
   %1 = bitcast float* %0 to i8*                   ; <i8*> [#uses=1]
   %2 = call i32 @llvm.objectsize.i32.p0i8(i8* %1, i1 false, i1 false, i1 false) ; <i32> [#uses=1]
   %3 = call i8* @__memcpy_chk(i8* undef, i8* undef, i32 512, i32 %2) nounwind ; <i8*> [#uses=0]
-; CHECK: unreachable
   unreachable
 
 bb12:
   %4 = getelementptr inbounds float, float* getelementptr inbounds ([480 x float], [480 x float]* @array, i32 0, i32 128), i32 -127 ; <float*> [#uses=1]
   %5 = bitcast float* %4 to i8*                   ; <i8*> [#uses=1]
   %6 = call i8* @__inline_memcpy_chk(i8* %5, i8* undef, i32 512) nounwind inlinehint ; <i8*> [#uses=0]
-; CHECK: @__inline_memcpy_chk
   unreachable
 }
 
 ; rdar://7718857
 
 %struct.data = type { [100 x i32], [100 x i32], [1024 x i8] }
 
 define i32 @test4(i8** %esc) nounwind ssp {
 ; CHECK-LABEL: @test4(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = alloca [[STRUCT_DATA:%.*]], align 8
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast %struct.data* [[TMP0]] to i8*
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i32(i8* nonnull align 8 dereferenceable(1824) [[TMP1]], i8 0, i32 1824, i1 false)
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8** [[ESC:%.*]] to %struct.data**
+; CHECK-NEXT:    store %struct.data* [[TMP0]], %struct.data** [[TMP2]], align 4
+; CHECK-NEXT:    ret i32 0
+;
 entry:
   %0 = alloca %struct.data, align 8
   %1 = bitcast %struct.data* %0 to i8*
   %2 = call i32 @llvm.objectsize.i32.p0i8(i8* %1, i1 false, i1 false, i1 false) nounwind
-; CHECK-NOT: @llvm.objectsize
-; CHECK: @llvm.memset.p0i8.i32(i8* nonnull align 8 %1, i8 0, i32 1824, i1 false)
   %3 = call i8* @__memset_chk(i8* %1, i32 0, i32 1824, i32 %2) nounwind
   store i8* %1, i8** %esc
   ret i32 0
 }
 
 ; rdar://7782496
 @s = external global i8*
 
 define i8* @test5(i32 %n) nounwind ssp {
 ; CHECK-LABEL: @test5(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = tail call noalias i8* @malloc(i32 20) #0
+; CHECK-NEXT:    [[TMP1:%.*]] = load i8*, i8** @s, align 8
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 dereferenceable(10) [[TMP0]], i8* align 1 dereferenceable(10) [[TMP1]], i32 10, i1 false)
+; CHECK-NEXT:    ret i8* [[TMP0]]
+;
 entry:
   %0 = tail call noalias i8* @malloc(i32 20) nounwind
   %1 = tail call i32 @llvm.objectsize.i32.p0i8(i8* %0, i1 false, i1 false, i1 false)
   %2 = load i8*, i8** @s, align 8
-; CHECK-NOT: @llvm.objectsize
-; CHECK: @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %0, i8* align 1 %1, i32 10, i1 false)
   %3 = tail call i8* @__memcpy_chk(i8* %0, i8* %2, i32 10, i32 %1) nounwind
   ret i8* %0
 }
 
 define void @test6(i32 %n) nounwind ssp {
 ; CHECK-LABEL: @test6(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = tail call noalias i8* @malloc(i32 20) #0
+; CHECK-NEXT:    [[TMP1:%.*]] = load i8*, i8** @s, align 8
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call i8* @__memcpy_chk(i8* [[TMP0]], i8* [[TMP1]], i32 30, i32 20) #0
+; CHECK-NEXT:    ret void
+;
 entry:
   %0 = tail call noalias i8* @malloc(i32 20) nounwind
   %1 = tail call i32 @llvm.objectsize.i32.p0i8(i8* %0, i1 false, i1 false, i1 false)
   %2 = load i8*, i8** @s, align 8
-; CHECK-NOT: @llvm.objectsize
-; CHECK: @__memcpy_chk(i8* %0, i8* %1, i32 30, i32 20)
   %3 = tail call i8* @__memcpy_chk(i8* %0, i8* %2, i32 30, i32 %1) nounwind
   ret void
 }
 
 declare i8* @__memset_chk(i8*, i32, i32, i32) nounwind
 
 declare noalias i8* @malloc(i32) nounwind
 
 define i32 @test7(i8** %esc) {
 ; CHECK-LABEL: @test7(
+; CHECK-NEXT:    [[ALLOC:%.*]] = call noalias i8* @malloc(i32 48) #0
+; CHECK-NEXT:    store i8* [[ALLOC]], i8** [[ESC:%.*]], align 4
+; CHECK-NEXT:    ret i32 32
+;
   %alloc = call noalias i8* @malloc(i32 48) nounwind
   store i8* %alloc, i8** %esc
   %gep = getelementptr inbounds i8, i8* %alloc, i32 16
   %objsize = call i32 @llvm.objectsize.i32.p0i8(i8* %gep, i1 false, i1 false, i1 false) nounwind readonly
-; CHECK: ret i32 32
   ret i32 %objsize
 }
 
 declare noalias i8* @calloc(i32, i32) nounwind
 
 define i32 @test8(i8** %esc) {
 ; CHECK-LABEL: @test8(
+; CHECK-NEXT:    [[ALLOC:%.*]] = call noalias i8* @calloc(i32 5, i32 7) #0
+; CHECK-NEXT:    store i8* [[ALLOC]], i8** [[ESC:%.*]], align 4
+; CHECK-NEXT:    ret i32 30
+;
   %alloc = call noalias i8* @calloc(i32 5, i32 7) nounwind
   store i8* %alloc, i8** %esc
   %gep = getelementptr inbounds i8, i8* %alloc, i32 5
   %objsize = call i32 @llvm.objectsize.i32.p0i8(i8* %gep, i1 false, i1 false, i1 false) nounwind readonly
-; CHECK: ret i32 30
   ret i32 %objsize
 }
 
 declare noalias i8* @strdup(i8* nocapture) nounwind
 declare noalias i8* @strndup(i8* nocapture, i32) nounwind
 
-; CHECK-LABEL: @test9(
 define i32 @test9(i8** %esc) {
+; CHECK-LABEL: @test9(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i8* @strdup(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i32 0, i32 0)) #0
+; CHECK-NEXT:    store i8* [[CALL]], i8** [[ESC:%.*]], align 8
+; CHECK-NEXT:    ret i32 8
+;
   %call = tail call i8* @strdup(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0)) nounwind
   store i8* %call, i8** %esc, align 8
   %1 = tail call i32 @llvm.objectsize.i32.p0i8(i8* %call, i1 true, i1 false, i1 false)
-; CHECK: ret i32 8
   ret i32 %1
 }
 
-; CHECK-LABEL: @test10(
 define i32 @test10(i8** %esc) {
+; CHECK-LABEL: @test10(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i8* @strndup(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i32 0, i32 0), i32 3) #0
+; CHECK-NEXT:    store i8* [[CALL]], i8** [[ESC:%.*]], align 8
+; CHECK-NEXT:    ret i32 4
+;
   %call = tail call i8* @strndup(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0), i32 3) nounwind
   store i8* %call, i8** %esc, align 8
   %1 = tail call i32 @llvm.objectsize.i32.p0i8(i8* %call, i1 true, i1 false, i1 false)
-; CHECK: ret i32 4
   ret i32 %1
 }
 
-; CHECK-LABEL: @test11(
 define i32 @test11(i8** %esc) {
+; CHECK-LABEL: @test11(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i8* @strndup(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i32 0, i32 0), i32 7) #0
+; CHECK-NEXT:    store i8* [[CALL]], i8** [[ESC:%.*]], align 8
+; CHECK-NEXT:    ret i32 8
+;
   %call = tail call i8* @strndup(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0), i32 7) nounwind
   store i8* %call, i8** %esc, align 8
   %1 = tail call i32 @llvm.objectsize.i32.p0i8(i8* %call, i1 true, i1 false, i1 false)
-; CHECK: ret i32 8
   ret i32 %1
 }
 
-; CHECK-LABEL: @test12(
 define i32 @test12(i8** %esc) {
+; CHECK-LABEL: @test12(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i8* @strndup(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i32 0, i32 0), i32 8) #0
+; CHECK-NEXT:    store i8* [[CALL]], i8** [[ESC:%.*]], align 8
+; CHECK-NEXT:    ret i32 8
+;
   %call = tail call i8* @strndup(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0), i32 8) nounwind
   store i8* %call, i8** %esc, align 8
   %1 = tail call i32 @llvm.objectsize.i32.p0i8(i8* %call, i1 true, i1 false, i1 false)
-; CHECK: ret i32 8
   ret i32 %1
 }
 
-; CHECK-LABEL: @test13(
 define i32 @test13(i8** %esc) {
+; CHECK-LABEL: @test13(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i8* @strndup(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i32 0, i32 0), i32 57) #0
+; CHECK-NEXT:    store i8* [[CALL]], i8** [[ESC:%.*]], align 8
+; CHECK-NEXT:    ret i32 8
+;
   %call = tail call i8* @strndup(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0), i32 57) nounwind
   store i8* %call, i8** %esc, align 8
   %1 = tail call i32 @llvm.objectsize.i32.p0i8(i8* %call, i1 true, i1 false, i1 false)
-; CHECK: ret i32 8
   ret i32 %1
 }
 
 @globalalias = internal alias [60 x i8], [60 x i8]* @a
 
+define i32 @test18() {
 ; CHECK-LABEL: @test18(
-; CHECK-NEXT: ret i32 60
-define i32 @test18() {
+; CHECK-NEXT:    ret i32 60
+;
   %bc = bitcast [60 x i8]* @globalalias to i8*
   %1 = call i32 @llvm.objectsize.i32.p0i8(i8* %bc, i1 false, i1 false, i1 false)
   ret i32 %1
 }
 
 @globalalias2 = weak alias [60 x i8], [60 x i8]* @a
 
-; CHECK-LABEL: @test19(
-; CHECK: llvm.objectsize
 define i32 @test19() {
+; CHECK-LABEL: @test19(
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.objectsize.i32.p0i8(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @globalalias2, i32 0, i32 0), i1 false, i1 false, i1 false)
+; CHECK-NEXT:    ret i32 [[TMP1]]
+;
   %bc = bitcast [60 x i8]* @globalalias2 to i8*
   %1 = call i32 @llvm.objectsize.i32.p0i8(i8* %bc, i1 false, i1 false, i1 false)
   ret i32 %1
 }
 
-; CHECK-LABEL: @test20(
-; CHECK: ret i32 0
 define i32 @test20() {
+; CHECK-LABEL: @test20(
+; CHECK-NEXT:    ret i32 0
+;
   %1 = call i32 @llvm.objectsize.i32.p0i8(i8* null, i1 false, i1 false, i1 false)
   ret i32 %1
 }
 
-; CHECK-LABEL: @test21(
-; CHECK: ret i32 0
 define i32 @test21() {
+; CHECK-LABEL: @test21(
+; CHECK-NEXT:    ret i32 0
+;
   %1 = call i32 @llvm.objectsize.i32.p0i8(i8* null, i1 true, i1 false, i1 false)
   ret i32 %1
 }
 
-; CHECK-LABEL: @test22(
-; CHECK: llvm.objectsize
 define i32 @test22() {
+; CHECK-LABEL: @test22(
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.objectsize.i32.p0i8(i8* null, i1 false, i1 true, i1 false)
+; CHECK-NEXT:    ret i32 [[TMP1]]
+;
   %1 = call i32 @llvm.objectsize.i32.p0i8(i8* null, i1 false, i1 true, i1 false)
   ret i32 %1
 }
 
-; CHECK-LABEL: @test23(
-; CHECK: llvm.objectsize
 define i32 @test23() {
+; CHECK-LABEL: @test23(
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.objectsize.i32.p0i8(i8* null, i1 true, i1 true, i1 false)
+; CHECK-NEXT:    ret i32 [[TMP1]]
+;
   %1 = call i32 @llvm.objectsize.i32.p0i8(i8* null, i1 true, i1 true, i1 false)
   ret i32 %1
 }
 
 ; 1 is an arbitrary non-zero address space.
-; CHECK-LABEL: @test24(
-; CHECK: llvm.objectsize
 define i32 @test24() {
+; CHECK-LABEL: @test24(
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.objectsize.i32.p1i8(i8 addrspace(1)* null, i1 false, i1 false, i1 false)
+; CHECK-NEXT:    ret i32 [[TMP1]]
+;
   %1 = call i32 @llvm.objectsize.i32.p1i8(i8 addrspace(1)* null, i1 false,
-                                          i1 false, i1 false)
   ret i32 %1
 }
 
-; CHECK-LABEL: @test25(
-; CHECK: llvm.objectsize
 define i32 @test25() {
+; CHECK-LABEL: @test25(
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.objectsize.i32.p1i8(i8 addrspace(1)* null, i1 true, i1 false, i1 false)
+; CHECK-NEXT:    ret i32 [[TMP1]]
+;
   %1 = call i32 @llvm.objectsize.i32.p1i8(i8 addrspace(1)* null, i1 true,
-                                          i1 false, i1 false)
   ret i32 %1
 }
 
-; CHECK-LABEL: @test26(
-; CHECK: llvm.objectsize
 define i32 @test26() {
+; CHECK-LABEL: @test26(
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.objectsize.i32.p1i8(i8 addrspace(1)* null, i1 false, i1 true, i1 false)
+; CHECK-NEXT:    ret i32 [[TMP1]]
+;
   %1 = call i32 @llvm.objectsize.i32.p1i8(i8 addrspace(1)* null, i1 false,
-                                          i1 true, i1 false)
   ret i32 %1
 }
 
-; CHECK-LABEL: @test27(
-; CHECK: llvm.objectsize
 define i32 @test27() {
+; CHECK-LABEL: @test27(
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.objectsize.i32.p1i8(i8 addrspace(1)* null, i1 true, i1 true, i1 false)
+; CHECK-NEXT:    ret i32 [[TMP1]]
+;
   %1 = call i32 @llvm.objectsize.i32.p1i8(i8 addrspace(1)* null, i1 true,
-                                          i1 true, i1 false)
   ret i32 %1
 }

test/Transforms/InstCombine/sprintf-1.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; Test that the sprintf library call simplifier works correctly.
 ;
 ; RUN: opt < %s -instcombine -S | FileCheck %s
 ; RUN: opt < %s -mtriple xcore-xmos-elf -instcombine -S | FileCheck %s -check-prefix=CHECK-IPRINTF
 
 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
 
 @hello_world = constant [13 x i8] c"hello world\0A\00"
 @null = constant [1 x i8] zeroinitializer
 @null_hello = constant [7 x i8] c"\00hello\00"
 @h = constant [2 x i8] c"h\00"
 @percent_c = constant [3 x i8] c"%c\00"
 @percent_d = constant [3 x i8] c"%d\00"
 @percent_f = constant [3 x i8] c"%f\00"
 @percent_s = constant [3 x i8] c"%s\00"
 
 declare i32 @sprintf(i8*, i8*, ...)
 
 ; Check sprintf(dst, fmt) -> llvm.memcpy(str, fmt, strlen(fmt) + 1, 1).
 
 define void @test_simplify1(i8* %dst) {
 ; CHECK-LABEL: @test_simplify1(
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 dereferenceable(13) [[DST:%.*]], i8* align 1 dereferenceable(13) getelementptr inbounds ([13 x i8], [13 x i8]* @hello_world, i32 0, i32 0), i32 13, i1 false)
+; CHECK-NEXT:    ret void
+;
+; CHECK-IPRINTF-LABEL: @test_simplify1(
+; CHECK-IPRINTF-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 dereferenceable(13) [[DST:%.*]], i8* align 1 dereferenceable(13) getelementptr inbounds ([13 x i8], [13 x i8]* @hello_world, i32 0, i32 0), i32 13, i1 false)
+; CHECK-IPRINTF-NEXT:    ret void
+;
   %fmt = getelementptr [13 x i8], [13 x i8]* @hello_world, i32 0, i32 0
   call i32 (i8*, i8*, ...) @sprintf(i8* %dst, i8* %fmt)
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %dst, i8* align 1 getelementptr inbounds ([13 x i8], [13 x i8]* @hello_world, i32 0, i32 0), i32 13, i1 false)
   ret void
-; CHECK-NEXT: ret void
 }
 
 define void @test_simplify2(i8* %dst) {
 ; CHECK-LABEL: @test_simplify2(
+; CHECK-NEXT:    store i8 0, i8* [[DST:%.*]], align 1
+; CHECK-NEXT:    ret void
+;
+; CHECK-IPRINTF-LABEL: @test_simplify2(
+; CHECK-IPRINTF-NEXT:    store i8 0, i8* [[DST:%.*]], align 1
+; CHECK-IPRINTF-NEXT:    ret void
+;
   %fmt = getelementptr [1 x i8], [1 x i8]* @null, i32 0, i32 0
   call i32 (i8*, i8*, ...) @sprintf(i8* %dst, i8* %fmt)
-; CHECK-NEXT: store i8 0, i8* %dst, align 1
   ret void
-; CHECK-NEXT: ret void
 }
 
 define void @test_simplify3(i8* %dst) {
 ; CHECK-LABEL: @test_simplify3(
+; CHECK-NEXT:    store i8 0, i8* [[DST:%.*]], align 1
+; CHECK-NEXT:    ret void
+;
+; CHECK-IPRINTF-LABEL: @test_simplify3(
+; CHECK-IPRINTF-NEXT:    store i8 0, i8* [[DST:%.*]], align 1
+; CHECK-IPRINTF-NEXT:    ret void
+;
   %fmt = getelementptr [7 x i8], [7 x i8]* @null_hello, i32 0, i32 0
   call i32 (i8*, i8*, ...) @sprintf(i8* %dst, i8* %fmt)
-; CHECK-NEXT: store i8 0, i8* %dst, align 1
   ret void
-; CHECK-NEXT: ret void
 }
 
 ; Check sprintf(dst, "%c", chr) -> *(i8*)dst = chr; *((i8*)dst + 1) = 0.
 
 define void @test_simplify4(i8* %dst) {
 ; CHECK-LABEL: @test_simplify4(
+; CHECK-NEXT:    store i8 104, i8* [[DST:%.*]], align 1
+; CHECK-NEXT:    [[NUL:%.*]] = getelementptr i8, i8* [[DST]], i32 1
+; CHECK-NEXT:    store i8 0, i8* [[NUL]], align 1
+; CHECK-NEXT:    ret void
+;
+; CHECK-IPRINTF-LABEL: @test_simplify4(
+; CHECK-IPRINTF-NEXT:    store i8 104, i8* [[DST:%.*]], align 1
+; CHECK-IPRINTF-NEXT:    [[NUL:%.*]] = getelementptr i8, i8* [[DST]], i32 1
+; CHECK-IPRINTF-NEXT:    store i8 0, i8* [[NUL]], align 1
+; CHECK-IPRINTF-NEXT:    ret void
+;
   %fmt = getelementptr [3 x i8], [3 x i8]* @percent_c, i32 0, i32 0
   call i32 (i8*, i8*, ...) @sprintf(i8* %dst, i8* %fmt, i8 104)
-; CHECK-NEXT: store i8 104, i8* %dst, align 1
-; CHECK-NEXT: [[NUL:%[a-z0-9]+]] = getelementptr i8, i8* %dst, i32 1
-; CHECK-NEXT: store i8 0, i8* [[NUL]], align 1
   ret void
-; CHECK-NEXT: ret void
 }
 
 ; Check sprintf(dst, "%s", str) -> llvm.memcpy(dest, str, strlen(str) + 1, 1).
 
 define void @test_simplify5(i8* %dst, i8* %str) {
 ; CHECK-LABEL: @test_simplify5(
+; CHECK-NEXT:    [[STRLEN:%.*]] = call i32 @strlen(i8* [[STR:%.*]])
+; CHECK-NEXT:    [[LENINC:%.*]] = add i32 [[STRLEN]], 1
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[DST:%.*]], i8* align 1 [[STR]], i32 [[LENINC]], i1 false)
+; CHECK-NEXT:    ret void
+;
+; CHECK-IPRINTF-LABEL: @test_simplify5(
+; CHECK-IPRINTF-NEXT:    [[STRLEN:%.*]] = call i32 @strlen(i8* [[STR:%.*]])
+; CHECK-IPRINTF-NEXT:    [[LENINC:%.*]] = add i32 [[STRLEN]], 1
+; CHECK-IPRINTF-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[DST:%.*]], i8* align 1 [[STR]], i32 [[LENINC]], i1 false)
+; CHECK-IPRINTF-NEXT:    ret void
+;
   %fmt = getelementptr [3 x i8], [3 x i8]* @percent_s, i32 0, i32 0
   call i32 (i8*, i8*, ...) @sprintf(i8* %dst, i8* %fmt, i8* %str)
-; CHECK-NEXT: [[STRLEN:%[a-z0-9]+]] = call i32 @strlen(i8* %str)
-; CHECK-NEXT: [[LENINC:%[a-z0-9]+]] = add i32 [[STRLEN]], 1
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %dst, i8* align 1 %str, i32 [[LENINC]], i1 false)
   ret void
-; CHECK-NEXT: ret void
 }
 
 ; Check sprintf(dst, format, ...) -> siprintf(str, format, ...) if no floating.
 
 define void @test_simplify6(i8* %dst) {
+; CHECK-LABEL: @test_simplify6(
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 (i8*, i8*, ...) @sprintf(i8* [[DST:%.*]], i8* getelementptr inbounds ([3 x i8], [3 x i8]* @percent_d, i32 0, i32 0), i32 187)
+; CHECK-NEXT:    ret void
+;
 ; CHECK-IPRINTF-LABEL: @test_simplify6(
+; CHECK-IPRINTF-NEXT:    [[TMP1:%.*]] = call i32 (i8*, i8*, ...) @siprintf(i8* [[DST:%.*]], i8* getelementptr inbounds ([3 x i8], [3 x i8]* @percent_d, i32 0, i32 0), i32 187)
+; CHECK-IPRINTF-NEXT:    ret void
+;
   %fmt = getelementptr [3 x i8], [3 x i8]* @percent_d, i32 0, i32 0
   call i32 (i8*, i8*, ...) @sprintf(i8* %dst, i8* %fmt, i32 187)
-; CHECK-IPRINTF-NEXT: call i32 (i8*, i8*, ...) @siprintf(i8* %dst, i8* getelementptr inbounds ([3 x i8], [3 x i8]* @percent_d, i32 0, i32 0), i32 187)
   ret void
-; CHECK-IPRINTF-NEXT: ret void
 }
 
 define void @test_no_simplify1(i8* %dst) {
+; CHECK-LABEL: @test_no_simplify1(
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 (i8*, i8*, ...) @sprintf(i8* [[DST:%.*]], i8* getelementptr inbounds ([3 x i8], [3 x i8]* @percent_f, i32 0, i32 0), double 1.870000e+00)
+; CHECK-NEXT:    ret void
+;
 ; CHECK-IPRINTF-LABEL: @test_no_simplify1(
+; CHECK-IPRINTF-NEXT:    [[TMP1:%.*]] = call i32 (i8*, i8*, ...) @sprintf(i8* [[DST:%.*]], i8* getelementptr inbounds ([3 x i8], [3 x i8]* @percent_f, i32 0, i32 0), double 1.870000e+00)
+; CHECK-IPRINTF-NEXT:    ret void
+;
   %fmt = getelementptr [3 x i8], [3 x i8]* @percent_f, i32 0, i32 0
   call i32 (i8*, i8*, ...) @sprintf(i8* %dst, i8* %fmt, double 1.87)
-; CHECK-IPRINTF-NEXT: call i32 (i8*, i8*, ...) @sprintf(i8* %dst, i8* getelementptr inbounds ([3 x i8], [3 x i8]* @percent_f, i32 0, i32 0), double 1.870000e+00)
   ret void
-; CHECK-IPRINTF-NEXT: ret void
 }
 
 define void @test_no_simplify2(i8* %dst, i8* %fmt, double %d) {
 ; CHECK-LABEL: @test_no_simplify2(
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 (i8*, i8*, ...) @sprintf(i8* [[DST:%.*]], i8* [[FMT:%.*]], double [[D:%.*]])
+; CHECK-NEXT:    ret void
+;
+; CHECK-IPRINTF-LABEL: @test_no_simplify2(
+; CHECK-IPRINTF-NEXT:    [[TMP1:%.*]] = call i32 (i8*, i8*, ...) @sprintf(i8* [[DST:%.*]], i8* [[FMT:%.*]], double [[D:%.*]])
+; CHECK-IPRINTF-NEXT:    ret void
+;
   call i32 (i8*, i8*, ...) @sprintf(i8* %dst, i8* %fmt, double %d)
-; CHECK-NEXT: call i32 (i8*, i8*, ...) @sprintf(i8* %dst, i8* %fmt, double %d)
   ret void
-; CHECK-NEXT: ret void
 }

test/Transforms/InstCombine/stpcpy_chk-1.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; Test lib call simplification of __stpcpy_chk calls with various values
 ; for src, dst, and slen.
 ;
 ; RUN: opt < %s -instcombine -S | FileCheck %s
 
 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
 
 @a = common global [60 x i8] zeroinitializer, align 1
 @b = common global [60 x i8] zeroinitializer, align 1
 @.str = private constant [12 x i8] c"abcdefghijk\00"
 
 ; Check cases where slen >= strlen (src).
 
 define i8* @test_simplify1() {
 ; CHECK-LABEL: @test_simplify1(
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 dereferenceable(12) getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 dereferenceable(12) getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
+; CHECK-NEXT:    ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 11)
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0
 
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
-; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 11)
   %ret = call i8* @__stpcpy_chk(i8* %dst, i8* %src, i32 60)
   ret i8* %ret
 }
 
 define i8* @test_simplify2() {
 ; CHECK-LABEL: @test_simplify2(
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 dereferenceable(12) getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 dereferenceable(12) getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
+; CHECK-NEXT:    ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 11)
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0
 
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
-; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 11)
   %ret = call i8* @__stpcpy_chk(i8* %dst, i8* %src, i32 12)
   ret i8* %ret
 }
 
 define i8* @test_simplify3() {
 ; CHECK-LABEL: @test_simplify3(
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 dereferenceable(12) getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 dereferenceable(12) getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
+; CHECK-NEXT:    ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 11)
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0
 
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
-; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 11)
   %ret = call i8* @__stpcpy_chk(i8* %dst, i8* %src, i32 -1)
   ret i8* %ret
 }
 
 ; Check cases where there are no string constants.
 
 define i8* @test_simplify4() {
 ; CHECK-LABEL: @test_simplify4(
+; CHECK-NEXT:    [[STPCPY:%.*]] = call i8* @stpcpy(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i32 0, i32 0))
+; CHECK-NEXT:    ret i8* [[STPCPY]]
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [60 x i8], [60 x i8]* @b, i32 0, i32 0
 
-; CHECK-NEXT: %stpcpy = call i8* @stpcpy(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i32 0, i32 0))
-; CHECK-NEXT: ret i8* %stpcpy
   %ret = call i8* @__stpcpy_chk(i8* %dst, i8* %src, i32 -1)
   ret i8* %ret
 }
 
 ; Check case where the string length is not constant.
 
 define i8* @test_simplify5() {
 ; CHECK-LABEL: @test_simplify5(
+; CHECK-NEXT:    [[LEN:%.*]] = call i32 @llvm.objectsize.i32.p0i8(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i1 false, i1 false, i1 false)
+; CHECK-NEXT:    [[TMP1:%.*]] = call i8* @__memcpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i32 [[LEN]])
+; CHECK-NEXT:    ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 11)
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0
 
-; CHECK-NEXT: %len = call i32 @llvm.objectsize.i32.p0i8(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i1 false, i1 false, i1 false)
-; CHECK-NEXT: %1 = call i8* @__memcpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i32 %len)
-; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 11)
   %len = call i32 @llvm.objectsize.i32.p0i8(i8* %dst, i1 false, i1 false, i1 false)
   %ret = call i8* @__stpcpy_chk(i8* %dst, i8* %src, i32 %len)
   ret i8* %ret
 }
 
 ; Check case where the source and destination are the same.
 
 define i8* @test_simplify6() {
 ; CHECK-LABEL: @test_simplify6(
+; CHECK-NEXT:    [[STRLEN:%.*]] = call i32 @strlen(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0))
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 [[STRLEN]]
+; CHECK-NEXT:    ret i8* [[TMP1]]
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
 
-; CHECK-NEXT: %strlen = call i32 @strlen(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0))
-; CHECK-NEXT: %1 = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 %strlen
-; CHECK-NEXT: ret i8* %1
   %len = call i32 @llvm.objectsize.i32.p0i8(i8* %dst, i1 false, i1 false, i1 false)
   %ret = call i8* @__stpcpy_chk(i8* %dst, i8* %dst, i32 %len)
   ret i8* %ret
 }
 
 ; Check case where slen < strlen (src).
 
 define i8* @test_no_simplify1() {
 ; CHECK-LABEL: @test_no_simplify1(
+; CHECK-NEXT:    [[RET:%.*]] = call i8* @__stpcpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i32 0, i32 0), i32 8)
+; CHECK-NEXT:    ret i8* [[RET]]
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [60 x i8], [60 x i8]* @b, i32 0, i32 0
 
-; CHECK-NEXT: %ret = call i8* @__stpcpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i32 0, i32 0), i32 8)
-; CHECK-NEXT: ret i8* %ret
   %ret = call i8* @__stpcpy_chk(i8* %dst, i8* %src, i32 8)
   ret i8* %ret
 }
 
 declare i8* @__stpcpy_chk(i8*, i8*, i32) nounwind
 declare i32 @llvm.objectsize.i32.p0i8(i8*, i1, i1, i1) nounwind readonly

test/Transforms/InstCombine/strcmp-1.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; Test that the strcmp library call simplifier works correctly.
 ; RUN: opt < %s -instcombine -S | FileCheck %s --check-prefix=NOBCMP
 ; RUN: opt < %s -instcombine -mtriple=unknown-unknown-linux-gnu -S | FileCheck %s --check-prefix=BCMP
 
 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
 
 @hello = constant [6 x i8] c"hello\00"
 @hell = constant [5 x i8] c"hell\00"
 @bell = constant [5 x i8] c"bell\00"
 @null = constant [1 x i8] zeroinitializer
 
 declare i32 @strcmp(i8*, i8*)
 
 ; strcmp("", x) -> -*x
 define i32 @test1(i8* %str2) {
 ; CHECK-LABEL: @test1(
 ; CHECK: %strcmpload = load i8, i8* %str
 ; CHECK: %1 = zext i8 %strcmpload to i32
 ; CHECK: %2 = sub nsw i32 0, %1
 ; CHECK: ret i32 %2
-
+; NOBCMP-LABEL: @test1(
+; NOBCMP-NEXT:    [[STRCMPLOAD:%.*]] = load i8, i8* [[STR2:%.*]], align 1
+; NOBCMP-NEXT:    [[TMP1:%.*]] = zext i8 [[STRCMPLOAD]] to i32
+; NOBCMP-NEXT:    [[TMP2:%.*]] = sub nsw i32 0, [[TMP1]]
+; NOBCMP-NEXT:    ret i32 [[TMP2]]
+;
+; BCMP-LABEL: @test1(
+; BCMP-NEXT:    [[STRCMPLOAD:%.*]] = load i8, i8* [[STR2:%.*]], align 1
+; BCMP-NEXT:    [[TMP1:%.*]] = zext i8 [[STRCMPLOAD]] to i32
+; BCMP-NEXT:    [[TMP2:%.*]] = sub nsw i32 0, [[TMP1]]
+; BCMP-NEXT:    ret i32 [[TMP2]]
+;
   %str1 = getelementptr inbounds [1 x i8], [1 x i8]* @null, i32 0, i32 0
   %temp1 = call i32 @strcmp(i8* %str1, i8* %str2)
   ret i32 %temp1
 
 }
 
 ; strcmp(x, "") -> *x
 define i32 @test2(i8* %str1) {
 ; CHECK-LABEL: @test2(
 ; CHECK: %strcmpload = load i8, i8* %str
 ; CHECK: %1 = zext i8 %strcmpload to i32
 ; CHECK: ret i32 %1
-
+; NOBCMP-LABEL: @test2(
+; NOBCMP-NEXT:    [[STRCMPLOAD:%.*]] = load i8, i8* [[STR1:%.*]], align 1
+; NOBCMP-NEXT:    [[TMP1:%.*]] = zext i8 [[STRCMPLOAD]] to i32
+; NOBCMP-NEXT:    ret i32 [[TMP1]]
+;
+; BCMP-LABEL: @test2(
+; BCMP-NEXT:    [[STRCMPLOAD:%.*]] = load i8, i8* [[STR1:%.*]], align 1
+; BCMP-NEXT:    [[TMP1:%.*]] = zext i8 [[STRCMPLOAD]] to i32
+; BCMP-NEXT:    ret i32 [[TMP1]]
+;
   %str2 = getelementptr inbounds [1 x i8], [1 x i8]* @null, i32 0, i32 0
   %temp1 = call i32 @strcmp(i8* %str1, i8* %str2)
   ret i32 %temp1
 }
 
 ; strcmp(x, y)  -> cnst
 define i32 @test3() {
 ; CHECK-LABEL: @test3(
 ; CHECK: ret i32 -1
-
+; NOBCMP-LABEL: @test3(
+; NOBCMP-NEXT:    ret i32 -1
+;
+; BCMP-LABEL: @test3(
+; BCMP-NEXT:    ret i32 -1
+;
   %str1 = getelementptr inbounds [5 x i8], [5 x i8]* @hell, i32 0, i32 0
   %str2 = getelementptr inbounds [6 x i8], [6 x i8]* @hello, i32 0, i32 0
   %temp1 = call i32 @strcmp(i8* %str1, i8* %str2)
   ret i32 %temp1
 }
 
 define i32 @test4() {
 ; CHECK-LABEL: @test4(
 ; CHECK: ret i32 1
-
+; NOBCMP-LABEL: @test4(
+; NOBCMP-NEXT:    ret i32 1
+;
+; BCMP-LABEL: @test4(
+; BCMP-NEXT:    ret i32 1
+;
   %str1 = getelementptr inbounds [5 x i8], [5 x i8]* @hell, i32 0, i32 0
   %str2 = getelementptr inbounds [1 x i8], [1 x i8]* @null, i32 0, i32 0
   %temp1 = call i32 @strcmp(i8* %str1, i8* %str2)
   ret i32 %temp1
 }
 
 ; strcmp(x, y)   -> memcmp(x, y, <known length>)
 ; (This transform is rather difficult to trigger in a useful manner)
 define i32 @test5(i1 %b) {
 ; CHECK-LABEL: @test5(
 ; CHECK: %memcmp = call i32 @memcmp(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @hello, i32 0, i32 0), i8* %str2, i32 5)
 ; CHECK: ret i32 %memcmp
-
+; NOBCMP-LABEL: @test5(
+; NOBCMP-NEXT:    [[STR2:%.*]] = select i1 [[B:%.*]], i8* getelementptr inbounds ([5 x i8], [5 x i8]* @hell, i32 0, i32 0), i8* getelementptr inbounds ([5 x i8], [5 x i8]* @bell, i32 0, i32 0)
+; NOBCMP-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* dereferenceable(5) getelementptr inbounds ([6 x i8], [6 x i8]* @hello, i32 0, i32 0), i8* dereferenceable(5) [[STR2]], i32 5)
+; NOBCMP-NEXT:    ret i32 [[MEMCMP]]
+;
+; BCMP-LABEL: @test5(
+; BCMP-NEXT:    [[STR2:%.*]] = select i1 [[B:%.*]], i8* getelementptr inbounds ([5 x i8], [5 x i8]* @hell, i32 0, i32 0), i8* getelementptr inbounds ([5 x i8], [5 x i8]* @bell, i32 0, i32 0)
+; BCMP-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* dereferenceable(5) getelementptr inbounds ([6 x i8], [6 x i8]* @hello, i32 0, i32 0), i8* dereferenceable(5) [[STR2]], i32 5)
+; BCMP-NEXT:    ret i32 [[MEMCMP]]
+;
   %str1 = getelementptr inbounds [6 x i8], [6 x i8]* @hello, i32 0, i32 0
   %temp1 = getelementptr inbounds [5 x i8], [5 x i8]* @hell, i32 0, i32 0
   %temp2 = getelementptr inbounds [5 x i8], [5 x i8]* @bell, i32 0, i32 0
   %str2 = select i1 %b, i8* %temp1, i8* %temp2
   %temp3 = call i32 @strcmp(i8* %str1, i8* %str2)
   ret i32 %temp3
 }
 
 ; strcmp(x,x)  -> 0
 define i32 @test6(i8* %str) {
 ; CHECK-LABEL: @test6(
 ; CHECK: ret i32 0
-
+; NOBCMP-LABEL: @test6(
+; NOBCMP-NEXT:    ret i32 0
+;
+; BCMP-LABEL: @test6(
+; BCMP-NEXT:    ret i32 0
+;
   %temp1 = call i32 @strcmp(i8* %str, i8* %str)
   ret i32 %temp1
 }
 
 ; strcmp(x, y) == 0  -> bcmp(x, y, <known length>)
 define i1 @test7(i1 %b) {
+; NOBCMP-LABEL: @test7(
+; NOBCMP-NEXT:    [[STR2:%.*]] = select i1 [[B:%.*]], i8* getelementptr inbounds ([5 x i8], [5 x i8]* @hell, i32 0, i32 0), i8* getelementptr inbounds ([5 x i8], [5 x i8]* @bell, i32 0, i32 0)
+; NOBCMP-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* dereferenceable(5) getelementptr inbounds ([6 x i8], [6 x i8]* @hello, i32 0, i32 0), i8* dereferenceable(5) [[STR2]], i32 5)
+; NOBCMP-NEXT:    [[RES:%.*]] = icmp eq i32 [[MEMCMP]], 0
+; NOBCMP-NEXT:    ret i1 [[RES]]
+;
 ; BCMP-LABEL: @test7(
-; BCMP: %bcmp = call i32 @bcmp(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @hello, i32 0, i32 0), i8* %str2, i32 5)
-; BCMP: %res = icmp eq i32 %bcmp, 0
-; BCMP: ret i1 %res
+; BCMP-NEXT:    [[STR2:%.*]] = select i1 [[B:%.*]], i8* getelementptr inbounds ([5 x i8], [5 x i8]* @hell, i32 0, i32 0), i8* getelementptr inbounds ([5 x i8], [5 x i8]* @bell, i32 0, i32 0)
+; BCMP-NEXT:    [[BCMP:%.*]] = call i32 @bcmp(i8* dereferenceable(5) getelementptr inbounds ([6 x i8], [6 x i8]* @hello, i32 0, i32 0), i8* dereferenceable(5) [[STR2]], i32 5)
+; BCMP-NEXT:    [[RES:%.*]] = icmp eq i32 [[BCMP]], 0
+; BCMP-NEXT:    ret i1 [[RES]]
+;
 
-; NOBCMP-LABEL: @test7(
-; NOBCMP: %memcmp = call i32 @memcmp(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @hello, i32 0, i32 0), i8* %str2, i32 5)
-; NOBCMP: %res = icmp eq i32 %memcmp, 0
-; NOBCMP: ret i1 %res
 
   %str1 = getelementptr inbounds [6 x i8], [6 x i8]* @hello, i32 0, i32 0
   %temp1 = getelementptr inbounds [5 x i8], [5 x i8]* @hell, i32 0, i32 0
   %temp2 = getelementptr inbounds [5 x i8], [5 x i8]* @bell, i32 0, i32 0
   %str2 = select i1 %b, i8* %temp1, i8* %temp2
   %temp3 = call i32 @strcmp(i8* %str1, i8* %str2)
   %res = icmp eq i32 %temp3, 0
   ret i1 %res
 }

test/Transforms/InstCombine/strcmp-memcmp.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -instcombine -S | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 
 @key = constant [4 x i8] c"key\00", align 1
 @abc = constant [8 x i8] c"abc\00de\00\00", align 1
 
 declare void @use(i32)
 
 define i32 @strcmp_memcmp([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strcmp_memcmp(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull [[STRING]], i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull dereferenceable(4) [[STRING]], i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strcmp(i8* nonnull %string, i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0))
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 declare i32 @strcmp(i8* nocapture, i8* nocapture)
 
 define i32 @strcmp_memcmp2([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strcmp_memcmp2(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull [[STRING]], i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull dereferenceable(4) [[STRING]], i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strcmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull %string)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strcmp_memcmp3([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strcmp_memcmp3(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull [[STRING]], i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull dereferenceable(4) [[STRING]], i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strcmp(i8* nonnull %string, i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0))
   %cmp = icmp ne i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strcmp_memcmp4([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strcmp_memcmp4(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull [[STRING]], i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull dereferenceable(4) [[STRING]], i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strcmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull %string)
   %cmp = icmp ne i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strcmp_memcmp5([5 x i8]* dereferenceable (5) %buf) {
 ; CHECK-LABEL: @strcmp_memcmp5(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [5 x i8], [5 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull [[STRING]], i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull dereferenceable(4) [[STRING]], i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [5 x i8], [5 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strcmp(i8* nonnull align 1 %string, i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0))
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strcmp_memcmp6([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strcmp_memcmp6(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull [[STRING]], i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull dereferenceable(4) [[STRING]], i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strcmp(i8* nonnull %string, i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0))
   %cmp = icmp sgt i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strcmp_memcmp7([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strcmp_memcmp7(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull [[STRING]], i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull dereferenceable(4) [[STRING]], i64 4)
 ; CHECK-NEXT:    [[MEMCMP_LOBIT:%.*]] = lshr i32 [[MEMCMP]], 31
 ; CHECK-NEXT:    ret i32 [[MEMCMP_LOBIT]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strcmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull %string)
   %cmp = icmp slt i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strcmp_memcmp8([4 x i8]* dereferenceable (4) %buf) {
 ; CHECK-LABEL: @strcmp_memcmp8(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [4 x i8], [4 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull [[STRING]], i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull dereferenceable(4) [[STRING]], i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [4 x i8], [4 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strcmp(i8* nonnull %string, i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0))
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strcmp_memcmp9([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strcmp_memcmp9(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull [[STRING]], i8* getelementptr inbounds ([8 x i8], [8 x i8]* @abc, i64 0, i64 0), i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull dereferenceable(4) [[STRING]], i8* dereferenceable(4) getelementptr inbounds ([8 x i8], [8 x i8]* @abc, i64 0, i64 0), i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strcmp(i8* nonnull %string, i8* getelementptr inbounds ([8 x i8], [8 x i8]* @abc, i64 0, i64 0))
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 
 define i32 @strncmp_memcmp([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strncmp_memcmp(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull [[STRING]], i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 2)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull dereferenceable(2) [[STRING]], i8* dereferenceable(2) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 2)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strncmp(i8* nonnull %string, i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 2)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 declare i32 @strncmp(i8* nocapture, i8* nocapture, i64)
 
 define i32 @strncmp_memcmp2([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strncmp_memcmp2(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull [[STRING]], i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull dereferenceable(4) [[STRING]], i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strncmp(i8* nonnull %string, i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 11)
   %cmp = icmp ne i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strncmp_memcmp3([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strncmp_memcmp3(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull [[STRING]], i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull dereferenceable(4) [[STRING]], i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strncmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull %string, i64 11)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strncmp_memcmp4([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strncmp_memcmp4(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull [[STRING]], i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull dereferenceable(4) [[STRING]], i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strncmp(i8* nonnull %string, i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 5)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strncmp_memcmp5([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strncmp_memcmp5(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull [[STRING]], i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull dereferenceable(4) [[STRING]], i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strncmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull %string, i64 5)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 
 define i32 @strncmp_memcmp6([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strncmp_memcmp6(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull [[STRING]], i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull dereferenceable(4) [[STRING]], i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strncmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull %string, i64 5)
   %cmp = icmp ne i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strncmp_memcmp7([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strncmp_memcmp7(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull [[STRING]], i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull dereferenceable(4) [[STRING]], i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strncmp(i8* nonnull %string, i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 4)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strncmp_memcmp8([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strncmp_memcmp8(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull [[STRING]], i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 3)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull dereferenceable(3) [[STRING]], i8* dereferenceable(3) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 3)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strncmp(i8* nonnull %string, i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i64 3)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strncmp_memcmp9([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strncmp_memcmp9(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull [[STRING]], i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull dereferenceable(4) [[STRING]], i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strncmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull %string, i64 5)
   %cmp = icmp sgt i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strncmp_memcmp10([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strncmp_memcmp10(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull [[STRING]], i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull dereferenceable(4) [[STRING]], i64 4)
 ; CHECK-NEXT:    [[MEMCMP_LOBIT:%.*]] = lshr i32 [[MEMCMP]], 31
 ; CHECK-NEXT:    ret i32 [[MEMCMP_LOBIT]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strncmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull %string, i64 5)
   %cmp = icmp slt i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strncmp_memcmp11([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strncmp_memcmp11(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull [[STRING]], i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull dereferenceable(4) [[STRING]], i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strncmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull %string, i64 12)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strncmp_memcmp12([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strncmp_memcmp12(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull [[STRING]], i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* dereferenceable(4) getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull dereferenceable(4) [[STRING]], i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strncmp(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @key, i64 0, i64 0), i8* nonnull %string, i64 12)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strncmp_memcmp13([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strncmp_memcmp13(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull [[STRING]], i8* getelementptr inbounds ([8 x i8], [8 x i8]* @abc, i64 0, i64 0), i64 2)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull dereferenceable(2) [[STRING]], i8* dereferenceable(2) getelementptr inbounds ([8 x i8], [8 x i8]* @abc, i64 0, i64 0), i64 2)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strncmp(i8* nonnull %string, i8* getelementptr inbounds ([8 x i8], [8 x i8]* @abc, i64 0, i64 0), i64 2)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @strncmp_memcmp14([12 x i8]* dereferenceable (12) %buf) {
 ; CHECK-LABEL: @strncmp_memcmp14(
 ; CHECK-NEXT:    [[STRING:%.*]] = getelementptr inbounds [12 x i8], [12 x i8]* [[BUF:%.*]], i64 0, i64 0
-; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull [[STRING]], i8* getelementptr inbounds ([8 x i8], [8 x i8]* @abc, i64 0, i64 0), i64 4)
+; CHECK-NEXT:    [[MEMCMP:%.*]] = call i32 @memcmp(i8* nonnull dereferenceable(4) [[STRING]], i8* dereferenceable(4) getelementptr inbounds ([8 x i8], [8 x i8]* @abc, i64 0, i64 0), i64 4)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[MEMCMP]], 0
 ; CHECK-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; CHECK-NEXT:    ret i32 [[CONV]]
 ;
   %string = getelementptr inbounds [12 x i8], [12 x i8]* %buf, i64 0, i64 0
   %call = call i32 @strncmp(i8* nonnull %string, i8* getelementptr inbounds ([8 x i8], [8 x i8]* @abc, i64 0, i64 0), i64 12)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32

test/Transforms/InstCombine/strcpy_chk-1.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; Test lib call simplification of __strcpy_chk calls with various values
 ; for src, dst, and slen.
 ;
 ; RUN: opt < %s -instcombine -S | FileCheck %s
 
 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
 
 @a = common global [60 x i8] zeroinitializer, align 1
 @b = common global [60 x i8] zeroinitializer, align 1
 @.str = private constant [12 x i8] c"abcdefghijk\00"
 
 ; Check cases where slen >= strlen (src).
 
 define i8* @test_simplify1() {
 ; CHECK-LABEL: @test_simplify1(
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 dereferenceable(12) getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 dereferenceable(12) getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
+; CHECK-NEXT:    ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0)
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0
 
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
-; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0)
   %ret = call i8* @__strcpy_chk(i8* %dst, i8* %src, i32 60)
   ret i8* %ret
 }
 
 define i8* @test_simplify2() {
 ; CHECK-LABEL: @test_simplify2(
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 dereferenceable(12) getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 dereferenceable(12) getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
+; CHECK-NEXT:    ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0)
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0
 
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
-; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0)
   %ret = call i8* @__strcpy_chk(i8* %dst, i8* %src, i32 12)
   ret i8* %ret
 }
 
 define i8* @test_simplify3() {
 ; CHECK-LABEL: @test_simplify3(
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 dereferenceable(12) getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 dereferenceable(12) getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
+; CHECK-NEXT:    ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0)
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0
 
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
-; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0)
   %ret = call i8* @__strcpy_chk(i8* %dst, i8* %src, i32 -1)
   ret i8* %ret
 }
 
 ; Check cases where there are no string constants.
 
 define i8* @test_simplify4() {
 ; CHECK-LABEL: @test_simplify4(
+; CHECK-NEXT:    [[STRCPY:%.*]] = call i8* @strcpy(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i32 0, i32 0))
+; CHECK-NEXT:    ret i8* [[STRCPY]]
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [60 x i8], [60 x i8]* @b, i32 0, i32 0
 
-; CHECK-NEXT: %strcpy = call i8* @strcpy(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i32 0, i32 0))
-; CHECK-NEXT: ret i8* %strcpy
   %ret = call i8* @__strcpy_chk(i8* %dst, i8* %src, i32 -1)
   ret i8* %ret
 }
 
 ; Check case where the string length is not constant.
 
 define i8* @test_simplify5() {
 ; CHECK-LABEL: @test_simplify5(
+; CHECK-NEXT:    [[LEN:%.*]] = call i32 @llvm.objectsize.i32.p0i8(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i1 false, i1 false, i1 false)
+; CHECK-NEXT:    [[TMP1:%.*]] = call i8* @__memcpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i32 [[LEN]])
+; CHECK-NEXT:    ret i8* [[TMP1]]
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0
 
-; CHECK-NEXT: %len = call i32 @llvm.objectsize.i32.p0i8(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i1 false, i1 false, i1 false)
-; CHECK-NEXT: %1 = call i8* @__memcpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i32 %len)
-; CHECK-NEXT: ret i8* %1
   %len = call i32 @llvm.objectsize.i32.p0i8(i8* %dst, i1 false, i1 false, i1 false)
   %ret = call i8* @__strcpy_chk(i8* %dst, i8* %src, i32 %len)
   ret i8* %ret
 }
 
 ; Check case where the source and destination are the same.
 
 define i8* @test_simplify6() {
 ; CHECK-LABEL: @test_simplify6(
+; CHECK-NEXT:    [[LEN:%.*]] = call i32 @llvm.objectsize.i32.p0i8(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i1 false, i1 false, i1 false)
+; CHECK-NEXT:    [[RET:%.*]] = call i8* @__strcpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i32 [[LEN]])
+; CHECK-NEXT:    ret i8* [[RET]]
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
 
-; CHECK-NEXT: %len = call i32 @llvm.objectsize.i32.p0i8(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i1 false, i1 false, i1 false)
-; CHECK-NEXT: %ret = call i8* @__strcpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i32 %len)
-; CHECK-NEXT: ret i8* %ret
   %len = call i32 @llvm.objectsize.i32.p0i8(i8* %dst, i1 false, i1 false, i1 false)
   %ret = call i8* @__strcpy_chk(i8* %dst, i8* %dst, i32 %len)
   ret i8* %ret
 }
 
 ; Check case where slen < strlen (src).
 
 define i8* @test_no_simplify1() {
 ; CHECK-LABEL: @test_no_simplify1(
+; CHECK-NEXT:    [[RET:%.*]] = call i8* @__strcpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i32 0, i32 0), i32 8)
+; CHECK-NEXT:    ret i8* [[RET]]
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [60 x i8], [60 x i8]* @b, i32 0, i32 0
 
-; CHECK-NEXT: %ret = call i8* @__strcpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i32 0, i32 0), i32 8)
-; CHECK-NEXT: ret i8* %ret
   %ret = call i8* @__strcpy_chk(i8* %dst, i8* %src, i32 8)
   ret i8* %ret
 }
 
 declare i8* @__strcpy_chk(i8*, i8*, i32) nounwind
 declare i32 @llvm.objectsize.i32.p0i8(i8*, i1, i1, i1) nounwind readonly

test/Transforms/InstCombine/strncpy_chk-1.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; Test lib call simplification of __strncpy_chk calls with various values
 ; for len and dstlen.
 ;
 ; RUN: opt < %s -instcombine -S | FileCheck %s
 
 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
 
 @a = common global [60 x i8] zeroinitializer, align 1
 @b = common global [60 x i8] zeroinitializer, align 1
 @.str = private constant [12 x i8] c"abcdefghijk\00"
 
 ; Check cases where dstlen >= len
 
 define i8* @test_simplify1() {
 ; CHECK-LABEL: @test_simplify1(
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 dereferenceable(12) getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 dereferenceable(12) getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
+; CHECK-NEXT:    ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0)
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0
 
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
-; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0)
   %ret = call i8* @__strncpy_chk(i8* %dst, i8* %src, i32 12, i32 60)
   ret i8* %ret
 }
 
 define i8* @test_simplify2() {
 ; CHECK-LABEL: @test_simplify2(
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 dereferenceable(12) getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 dereferenceable(12) getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
+; CHECK-NEXT:    ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0)
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0
 
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false)
-; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0)
   %ret = call i8* @__strncpy_chk(i8* %dst, i8* %src, i32 12, i32 12)
   ret i8* %ret
 }
 
 define i8* @test_simplify3() {
 ; CHECK-LABEL: @test_simplify3(
+; CHECK-NEXT:    [[STRNCPY:%.*]] = call i8* @strncpy(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i32 0, i32 0), i32 12)
+; CHECK-NEXT:    ret i8* [[STRNCPY]]
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [60 x i8], [60 x i8]* @b, i32 0, i32 0
 
-; CHECK-NEXT: %strncpy = call i8* @strncpy(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i32 0, i32 0), i32 12)
-; CHECK-NEXT: ret i8* %strncpy
   %ret = call i8* @__strncpy_chk(i8* %dst, i8* %src, i32 12, i32 60)
   ret i8* %ret
 }
 
 ; Check cases where dstlen < len
 
 define i8* @test_no_simplify1() {
 ; CHECK-LABEL: @test_no_simplify1(
+; CHECK-NEXT:    [[RET:%.*]] = call i8* @__strncpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 8, i32 4)
+; CHECK-NEXT:    ret i8* [[RET]]
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0
 
-; CHECK-NEXT: %ret = call i8* @__strncpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 8, i32 4)
-; CHECK-NEXT: ret i8* %ret
   %ret = call i8* @__strncpy_chk(i8* %dst, i8* %src, i32 8, i32 4)
   ret i8* %ret
 }
 
 define i8* @test_no_simplify2() {
 ; CHECK-LABEL: @test_no_simplify2(
+; CHECK-NEXT:    [[RET:%.*]] = call i8* @__strncpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i32 0, i32 0), i32 8, i32 0)
+; CHECK-NEXT:    ret i8* [[RET]]
+;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [60 x i8], [60 x i8]* @b, i32 0, i32 0
 
-; CHECK-NEXT: %ret = call i8* @__strncpy_chk(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i32 0, i32 0), i32 8, i32 0)
-; CHECK-NEXT: ret i8* %ret
   %ret = call i8* @__strncpy_chk(i8* %dst, i8* %src, i32 8, i32 0)
   ret i8* %ret
 }
 
 declare i8* @__strncpy_chk(i8*, i8*, i32, i32)

test/Transforms/MemCpyOpt/memcpy-to-memset-with-lifetimes.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -basicaa -memcpyopt -instcombine -S < %s | FileCheck %s
 
 target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 define void @foo([8 x i64]* noalias nocapture sret dereferenceable(64) %sret) {
+; CHECK-LABEL: @foo(
+; CHECK-NEXT:  entry-block:
+; CHECK-NEXT:    [[SRET1:%.*]] = bitcast [8 x i64]* [[SRET:%.*]] to i8*
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* nonnull align 8 dereferenceable(64) [[SRET1]], i8 0, i64 64, i1 false)
+; CHECK-NEXT:    ret void
+;
 entry-block:
   %a = alloca [8 x i64], align 8
   %a.cast = bitcast [8 x i64]* %a to i8*
   call void @llvm.lifetime.start.p0i8(i64 64, i8* %a.cast)
   call void @llvm.memset.p0i8.i64(i8* align 8 %a.cast, i8 0, i64 64, i1 false)
   %sret.cast = bitcast [8 x i64]* %sret to i8*
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %sret.cast, i8* align 8 %a.cast, i64 64, i1 false)
   call void @llvm.lifetime.end.p0i8(i64 64, i8* %a.cast)
   ret void
 
-; CHECK-LABEL: @foo(
-; CHECK:         %[[sret_cast:[^=]+]] = bitcast [8 x i64]* %sret to i8*
-; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* nonnull align 8 %[[sret_cast]], i8 0, i64 64
-; CHECK-NOT: call void @llvm.memcpy
-; CHECK: ret void
 }
 
 define void @bar([8 x i64]* noalias nocapture sret dereferenceable(64) %sret, [8 x i64]* noalias nocapture dereferenceable(64) %out) {
+; CHECK-LABEL: @bar(
+; CHECK-NEXT:  entry-block:
+; CHECK-NEXT:    [[A:%.*]] = alloca [8 x i64], align 8
+; CHECK-NEXT:    [[A_CAST:%.*]] = bitcast [8 x i64]* [[A]] to i8*
+; CHECK-NEXT:    call void @llvm.lifetime.start.p0i8(i64 64, i8* nonnull [[A_CAST]])
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* nonnull align 8 dereferenceable(64) [[A_CAST]], i8 0, i64 64, i1 false)
+; CHECK-NEXT:    [[SRET_CAST:%.*]] = bitcast [8 x i64]* [[SRET:%.*]] to i8*
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* nonnull align 8 dereferenceable(64) [[SRET_CAST]], i8 0, i64 64, i1 false)
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* nonnull align 8 dereferenceable(32) [[A_CAST]], i8 42, i64 32, i1 false)
+; CHECK-NEXT:    [[OUT_CAST:%.*]] = bitcast [8 x i64]* [[OUT:%.*]] to i8*
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull align 8 dereferenceable(64) [[OUT_CAST]], i8* nonnull align 8 dereferenceable(64) [[A_CAST]], i64 64, i1 false)
+; CHECK-NEXT:    call void @llvm.lifetime.end.p0i8(i64 64, i8* nonnull [[A_CAST]])
+; CHECK-NEXT:    ret void
+;
 entry-block:
   %a = alloca [8 x i64], align 8
   %a.cast = bitcast [8 x i64]* %a to i8*
   call void @llvm.lifetime.start.p0i8(i64 64, i8* %a.cast)
   call void @llvm.memset.p0i8.i64(i8* align 8 %a.cast, i8 0, i64 64, i1 false)
   %sret.cast = bitcast [8 x i64]* %sret to i8*
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %sret.cast, i8* align 8 %a.cast, i64 64, i1 false)
   call void @llvm.memset.p0i8.i64(i8* align 8 %a.cast, i8 42, i64 32, i1 false)
   %out.cast = bitcast [8 x i64]* %out to i8*
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %out.cast, i8* align 8 %a.cast, i64 64, i1 false)
   call void @llvm.lifetime.end.p0i8(i64 64, i8* %a.cast)
   ret void
 
-; CHECK-LABEL: @bar(
-; CHECK:         %[[a:[^=]+]] = alloca [8 x i64]
-; CHECK:         %[[a_cast:[^=]+]] = bitcast [8 x i64]* %[[a]] to i8*
-; CHECK:         call void @llvm.memset.p0i8.i64(i8* nonnull align 8 %[[a_cast]], i8 0, i64 64
-; CHECK:         %[[sret_cast:[^=]+]] = bitcast [8 x i64]* %sret to i8*
-; CHECK:         call void @llvm.memset.p0i8.i64(i8* nonnull align 8 %[[sret_cast]], i8 0, i64 64
-; CHECK:         call void @llvm.memset.p0i8.i64(i8* nonnull align 8 %[[a_cast]], i8 42, i64 32
-; CHECK:         %[[out_cast:[^=]+]] = bitcast [8 x i64]* %out to i8*
-; CHECK:         call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull align 8 %[[out_cast]], i8* nonnull align 8 %[[a_cast]], i64 64
-; CHECK-NOT: call void @llvm.memcpy
-; CHECK: ret void
 }
 
 declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) nounwind
 declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) nounwind
 
 declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) nounwind
 declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind