Update clang, llvm, lld, lldb, compiler-rt and libc++ to 4.0.0 release:

MFC r309142 (by emaste):

Add WITH_LLD_AS_LD build knob

If set it installs LLD as /usr/bin/ld.  LLD (as of version 3.9) is not
capable of linking the world and kernel, but can self-host and link many
substantial applications. GNU ld continues to be used for the world and
kernel build, regardless of how this knob is set.

It is on by default for arm64, and off for all other CPU architectures.

Sponsored by:	The FreeBSD Foundation

MFC r310840:

Reapply 310775, now it also builds correctly if lldb is disabled:

Move llvm-objdump from CLANG_EXTRAS to installed by default

We currently install three tools from binutils 2.17.50: as, ld, and
objdump. Work is underway to migrate to a permissively-licensed
tool-chain, with one goal being the retirement of binutils 2.17.50.

LLVM's llvm-objdump is intended to be compatible with GNU objdump
although it is currently missing some options and may have formatting
differences. Enable it by default for testing and further investigation.
It may later be changed to install as /usr/bin/objdump, it becomes a
fully viable replacement.

Reviewed by:	emaste
Differential Revision:	https://reviews.freebsd.org/D8879

MFC r312855 (by emaste):

Rename LLD_AS_LD to LLD_IS_LD, for consistency with CLANG_IS_CC

Reported by:	Dan McGregor <dan.mcgregor usask.ca>

MFC r313559 | glebius | 2017-02-10 18:34:48 +0100 (Fri, 10 Feb 2017) | 5 lines

Don't check struct rtentry on FreeBSD, it is an internal kernel structure.
On other systems it may be API structure for SIOCADDRT/SIOCDELRT.

Reviewed by:	emaste, dim

MFC r314152 (by jkim):

Remove an assembler flag, which is redundant since r309124.  The upstream
took care of it by introducing a macro NO_EXEC_STACK_DIRECTIVE.

http://llvm.org/viewvc/llvm-project?rev=273500&view=rev

Reviewed by:	dim

MFC r314564:

Upgrade our copies of clang, llvm, lld, lldb, compiler-rt and libc++ to
4.0.0 (branches/release_40 296509).  The release will follow soon.

Please note that from 3.5.0 onwards, clang, llvm and lldb require C++11
support to build; see UPDATING for more information.

Also note that as of 4.0.0, lld should be able to link the base system
on amd64 and aarch64.  See the WITH_LLD_IS_LLD setting in src.conf(5).
Though please be aware that this is work in progress.

Release notes for llvm, clang and lld will be available here:
<http://releases.llvm.org/4.0.0/docs/ReleaseNotes.html>
<http://releases.llvm.org/4.0.0/tools/clang/docs/ReleaseNotes.html>
<http://releases.llvm.org/4.0.0/tools/lld/docs/ReleaseNotes.html>

Thanks to Ed Maste, Jan Beich, Antoine Brodin and Eric Fiselier for
their help.

Relnotes:	yes
Exp-run:	antoine
PR:		215969, 216008

MFC r314708:

For now, revert r287232 from upstream llvm trunk (by Daniil Fukalov):

  [SCEV] limit recursion depth of CompareSCEVComplexity

  Summary:
  CompareSCEVComplexity goes too deep (50+ on a quite a big unrolled
  loop) and runs almost infinite time.

  Added cache of "equal" SCEV pairs to earlier cutoff of further
  estimation. Recursion depth limit was also introduced as a parameter.

  Reviewers: sanjoy

  Subscribers: mzolotukhin, tstellarAMD, llvm-commits

  Differential Revision: https://reviews.llvm.org/D26389

This commit is the cause of excessive compile times on skein_block.c
(and possibly other files) during kernel builds on amd64.

We never saw the problematic behavior described in this upstream commit,
so for now it is better to revert it.  An upstream bug has been filed
here: https://bugs.llvm.org/show_bug.cgi?id=32142

Reported by:	mjg

MFC r314795:

Reapply r287232 from upstream llvm trunk (by Daniil Fukalov):

  [SCEV] limit recursion depth of CompareSCEVComplexity

  Summary:
  CompareSCEVComplexity goes too deep (50+ on a quite a big unrolled
  loop) and runs almost infinite time.

  Added cache of "equal" SCEV pairs to earlier cutoff of further
  estimation. Recursion depth limit was also introduced as a parameter.

  Reviewers: sanjoy

  Subscribers: mzolotukhin, tstellarAMD, llvm-commits

  Differential Revision: https://reviews.llvm.org/D26389

Pull in r296992 from upstream llvm trunk (by Sanjoy Das):

  [SCEV] Decrease the recursion threshold for CompareValueComplexity

  Fixes PR32142.

  r287232 accidentally increased the recursion threshold for
  CompareValueComplexity from 2 to 32.  This change reverses that
  change by introducing a separate flag for CompareValueComplexity's
  threshold.

The latter revision fixes the excessive compile times for skein_block.c.

MFC r314907 | mmel | 2017-03-08 12:40:27 +0100 (Wed, 08 Mar 2017) | 7 lines

Unbreak ARMv6 world.

The new compiler_rt library imported with clang 4.0.0 have several fatal
issues (non-functional __udivsi3 for example) with ARM specific instrict
functions. As temporary workaround, until upstream solve these problems,
disable all thumb[1][2] related feature.

MFC r315016:

Update clang, llvm, lld, lldb, compiler-rt and libc++ to 4.0.0 release.
We were already very close to the last release candidate, so this is a
pretty minor update.

Relnotes:	yes

MFC r316005:

Revert r314907, and pull in r298713 from upstream compiler-rt trunk (by
Weiming Zhao):

  builtins: Select correct code fragments when compiling for Thumb1/Thum2/ARM ISA.

  Summary:
  Value of __ARM_ARCH_ISA_THUMB isn't based on the actual compilation
  mode (-mthumb, -marm), it reflect's capability of given CPU.

  Due to this:
   - use  __tbumb__ and __thumb2__ insteand of __ARM_ARCH_ISA_THUMB
   - use '.thumb' directive consistently  in all affected files
   - decorate all thumb functions using
     DEFINE_COMPILERRT_THUMB_FUNCTION()

  ---------
  Note: This patch doesn't fix broken Thumb1 variant of __udivsi3 !

  Reviewers: weimingz, rengolin, compnerd

  Subscribers: aemerson, dim

  Differential Revision: https://reviews.llvm.org/D30938

Discussed with:	mmel

1 files changed, 357 insertions, 121 deletions

diff --git a/contrib/llvm/lib/Analysis/ConstantFolding.cpp b/contrib/llvm/lib/Analysis/ConstantFolding.cpp
index c9adaa7..7386727 100644
--- a/contrib/llvm/lib/Analysis/ConstantFolding.cpp
+++ b/contrib/llvm/lib/Analysis/ConstantFolding.cpp
@@ -17,29 +17,38 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/Analysis/ConstantFolding.h"
+#include "llvm/ADT/APFloat.h"
+#include "llvm/ADT/APInt.h"
+#include "llvm/ADT/ArrayRef.h"
+#include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/STLExtras.h"
-#include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/StringMap.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/Config/config.h"
+#include "llvm/IR/Constant.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Function.h"
-#include "llvm/IR/GetElementPtrTypeIterator.h"
+#include "llvm/IR/GlobalValue.h"
 #include "llvm/IR/GlobalVariable.h"
+#include "llvm/IR/InstrTypes.h"
+#include "llvm/IR/Instruction.h"
 #include "llvm/IR/Instructions.h"
-#include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/Operator.h"
+#include "llvm/IR/Type.h"
+#include "llvm/IR/Value.h"
+#include "llvm/Support/Casting.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/MathExtras.h"
 #include <cassert>
 #include <cerrno>
 #include <cfenv>
 #include <cmath>
-#include <limits>
+#include <cstddef>
+#include <cstdint>
 
 using namespace llvm;
 
@@ -49,6 +58,36 @@ namespace {
 // Constant Folding internal helper functions
 //===----------------------------------------------------------------------===//
 
+static Constant *foldConstVectorToAPInt(APInt &Result, Type *DestTy,
+                                        Constant *C, Type *SrcEltTy,
+                                        unsigned NumSrcElts,
+                                        const DataLayout &DL) {
+  // Now that we know that the input value is a vector of integers, just shift
+  // and insert them into our result.
+  unsigned BitShift = DL.getTypeSizeInBits(SrcEltTy);
+  for (unsigned i = 0; i != NumSrcElts; ++i) {
+    Constant *Element;
+    if (DL.isLittleEndian())
+      Element = C->getAggregateElement(NumSrcElts - i - 1);
+    else
+      Element = C->getAggregateElement(i);
+
+    if (Element && isa<UndefValue>(Element)) {
+      Result <<= BitShift;
+      continue;
+    }
+
+    auto *ElementCI = dyn_cast_or_null<ConstantInt>(Element);
+    if (!ElementCI)
+      return ConstantExpr::getBitCast(C, DestTy);
+
+    Result <<= BitShift;
+    Result |= ElementCI->getValue().zextOrSelf(Result.getBitWidth());
+  }
+
+  return nullptr;
+}
+
 /// Constant fold bitcast, symbolically evaluating it with DataLayout.
 /// This always returns a non-null constant, but it may be a
 /// ConstantExpr if unfoldable.
@@ -60,45 +99,33 @@ Constant *FoldBitCast(Constant *C, Type *DestTy, const DataLayout &DL) {
       !DestTy->isPtrOrPtrVectorTy()) // Don't get ones for ptr types!
     return Constant::getAllOnesValue(DestTy);
 
-  // Handle a vector->integer cast.
-  if (auto *IT = dyn_cast<IntegerType>(DestTy)) {
-    auto *VTy = dyn_cast<VectorType>(C->getType());
-    if (!VTy)
-      return ConstantExpr::getBitCast(C, DestTy);
+  if (auto *VTy = dyn_cast<VectorType>(C->getType())) {
+    // Handle a vector->scalar integer/fp cast.
+    if (isa<IntegerType>(DestTy) || DestTy->isFloatingPointTy()) {
+      unsigned NumSrcElts = VTy->getNumElements();
+      Type *SrcEltTy = VTy->getElementType();
+
+      // If the vector is a vector of floating point, convert it to vector of int
+      // to simplify things.
+      if (SrcEltTy->isFloatingPointTy()) {
+        unsigned FPWidth = SrcEltTy->getPrimitiveSizeInBits();
+        Type *SrcIVTy =
+          VectorType::get(IntegerType::get(C->getContext(), FPWidth), NumSrcElts);
+        // Ask IR to do the conversion now that #elts line up.
+        C = ConstantExpr::getBitCast(C, SrcIVTy);
+      }
 
-    unsigned NumSrcElts = VTy->getNumElements();
-    Type *SrcEltTy = VTy->getElementType();
-
-    // If the vector is a vector of floating point, convert it to vector of int
-    // to simplify things.
-    if (SrcEltTy->isFloatingPointTy()) {
-      unsigned FPWidth = SrcEltTy->getPrimitiveSizeInBits();
-      Type *SrcIVTy =
-        VectorType::get(IntegerType::get(C->getContext(), FPWidth), NumSrcElts);
-      // Ask IR to do the conversion now that #elts line up.
-      C = ConstantExpr::getBitCast(C, SrcIVTy);
-    }
+      APInt Result(DL.getTypeSizeInBits(DestTy), 0);
+      if (Constant *CE = foldConstVectorToAPInt(Result, DestTy, C,
+                                                SrcEltTy, NumSrcElts, DL))
+        return CE;
 
-    // Now that we know that the input value is a vector of integers, just shift
-    // and insert them into our result.
-    unsigned BitShift = DL.getTypeSizeInBits(SrcEltTy);
-    APInt Result(IT->getBitWidth(), 0);
-    for (unsigned i = 0; i != NumSrcElts; ++i) {
-      Constant *Element;
-      if (DL.isLittleEndian())
-        Element = C->getAggregateElement(NumSrcElts-i-1);
-      else
-        Element = C->getAggregateElement(i);
-
-      auto *ElementCI = dyn_cast_or_null<ConstantInt>(Element);
-      if (!ElementCI)
-        return ConstantExpr::getBitCast(C, DestTy);
+      if (isa<IntegerType>(DestTy))
+        return ConstantInt::get(DestTy, Result);
 
-      Result <<= BitShift;
-      Result |= ElementCI->getValue().zextOrSelf(IT->getBitWidth());
+      APFloat FP(DestTy->getFltSemantics(), Result);
+      return ConstantFP::get(DestTy->getContext(), FP);
     }
-
-    return ConstantInt::get(IT, Result);
   }
 
   // The code below only handles casts to vectors currently.
@@ -180,7 +207,11 @@ Constant *FoldBitCast(Constant *C, Type *DestTy, const DataLayout &DL) {
       Constant *Elt = Zero;
       unsigned ShiftAmt = isLittleEndian ? 0 : SrcBitSize*(Ratio-1);
       for (unsigned j = 0; j != Ratio; ++j) {
-        Constant *Src = dyn_cast<ConstantInt>(C->getAggregateElement(SrcElt++));
+        Constant *Src = C->getAggregateElement(SrcElt++);
+        if (Src && isa<UndefValue>(Src))
+          Src = Constant::getNullValue(C->getType()->getVectorElementType());
+        else
+          Src = dyn_cast_or_null<ConstantInt>(Src);
         if (!Src)  // Reject constantexpr elements.
           return ConstantExpr::getBitCast(C, DestTy);
 
@@ -206,8 +237,19 @@ Constant *FoldBitCast(Constant *C, Type *DestTy, const DataLayout &DL) {
 
   // Loop over each source value, expanding into multiple results.
   for (unsigned i = 0; i != NumSrcElt; ++i) {
-    auto *Src = dyn_cast<ConstantInt>(C->getAggregateElement(i));
-    if (!Src)  // Reject constantexpr elements.
+    auto *Element = C->getAggregateElement(i);
+
+    if (!Element) // Reject constantexpr elements.
+      return ConstantExpr::getBitCast(C, DestTy);
+
+    if (isa<UndefValue>(Element)) {
+      // Correctly Propagate undef values.
+      Result.append(Ratio, UndefValue::get(DstEltTy));
+      continue;
+    }
+
+    auto *Src = dyn_cast<ConstantInt>(Element);
+    if (!Src)
       return ConstantExpr::getBitCast(C, DestTy);
 
     unsigned ShiftAmt = isLittleEndian ? 0 : DstBitSize*(Ratio-1);
@@ -333,7 +375,7 @@ bool ReadDataFromGlobal(Constant *C, uint64_t ByteOffset, unsigned char *CurPtr,
     uint64_t CurEltOffset = SL->getElementOffset(Index);
     ByteOffset -= CurEltOffset;
 
-    while (1) {
+    while (true) {
       // If the element access is to the element itself and not to tail padding,
       // read the bytes from the element.
       uint64_t EltSize = DL.getTypeAllocSize(CS->getOperand(Index)->getType());
@@ -689,23 +731,27 @@ Constant *SymbolicallyEvaluateBinop(unsigned Opc, Constant *Op0, Constant *Op1,
 /// If array indices are not pointer-sized integers, explicitly cast them so
 /// that they aren't implicitly casted by the getelementptr.
 Constant *CastGEPIndices(Type *SrcElemTy, ArrayRef<Constant *> Ops,
-                         Type *ResultTy, const DataLayout &DL,
-                         const TargetLibraryInfo *TLI) {
+                         Type *ResultTy, Optional<unsigned> InRangeIndex,
+                         const DataLayout &DL, const TargetLibraryInfo *TLI) {
   Type *IntPtrTy = DL.getIntPtrType(ResultTy);
+  Type *IntPtrScalarTy = IntPtrTy->getScalarType();
 
   bool Any = false;
   SmallVector<Constant*, 32> NewIdxs;
   for (unsigned i = 1, e = Ops.size(); i != e; ++i) {
     if ((i == 1 ||
-         !isa<StructType>(GetElementPtrInst::getIndexedType(SrcElemTy,
-             Ops.slice(1, i - 1)))) &&
-        Ops[i]->getType() != IntPtrTy) {
+         !isa<StructType>(GetElementPtrInst::getIndexedType(
+             SrcElemTy, Ops.slice(1, i - 1)))) &&
+        Ops[i]->getType()->getScalarType() != IntPtrScalarTy) {
       Any = true;
+      Type *NewType = Ops[i]->getType()->isVectorTy()
+                          ? IntPtrTy
+                          : IntPtrTy->getScalarType();
       NewIdxs.push_back(ConstantExpr::getCast(CastInst::getCastOpcode(Ops[i],
                                                                       true,
-                                                                      IntPtrTy,
+                                                                      NewType,
                                                                       true),
-                                              Ops[i], IntPtrTy));
+                                              Ops[i], NewType));
     } else
       NewIdxs.push_back(Ops[i]);
   }
@@ -713,11 +759,10 @@ Constant *CastGEPIndices(Type *SrcElemTy, ArrayRef<Constant *> Ops,
   if (!Any)
     return nullptr;
 
-  Constant *C = ConstantExpr::getGetElementPtr(SrcElemTy, Ops[0], NewIdxs);
-  if (auto *CE = dyn_cast<ConstantExpr>(C)) {
-    if (Constant *Folded = ConstantFoldConstantExpression(CE, DL, TLI))
-      C = Folded;
-  }
+  Constant *C = ConstantExpr::getGetElementPtr(
+      SrcElemTy, Ops[0], NewIdxs, /*InBounds=*/false, InRangeIndex);
+  if (Constant *Folded = ConstantFoldConstant(C, DL, TLI))
+    C = Folded;
 
   return C;
 }
@@ -744,13 +789,17 @@ Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
                                   ArrayRef<Constant *> Ops,
                                   const DataLayout &DL,
                                   const TargetLibraryInfo *TLI) {
+  const GEPOperator *InnermostGEP = GEP;
+  bool InBounds = GEP->isInBounds();
+
   Type *SrcElemTy = GEP->getSourceElementType();
   Type *ResElemTy = GEP->getResultElementType();
   Type *ResTy = GEP->getType();
   if (!SrcElemTy->isSized())
     return nullptr;
 
-  if (Constant *C = CastGEPIndices(SrcElemTy, Ops, ResTy, DL, TLI))
+  if (Constant *C = CastGEPIndices(SrcElemTy, Ops, ResTy,
+                                   GEP->getInRangeIndex(), DL, TLI))
     return C;
 
   Constant *Ptr = Ops[0];
@@ -775,8 +824,8 @@ Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
           Constant *Res = ConstantExpr::getPtrToInt(Ptr, CE->getType());
           Res = ConstantExpr::getSub(Res, CE->getOperand(1));
           Res = ConstantExpr::getIntToPtr(Res, ResTy);
-          if (auto *ResCE = dyn_cast<ConstantExpr>(Res))
-            Res = ConstantFoldConstantExpression(ResCE, DL, TLI);
+          if (auto *FoldedRes = ConstantFoldConstant(Res, DL, TLI))
+            Res = FoldedRes;
           return Res;
         }
       }
@@ -793,6 +842,9 @@ Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
 
   // If this is a GEP of a GEP, fold it all into a single GEP.
   while (auto *GEP = dyn_cast<GEPOperator>(Ptr)) {
+    InnermostGEP = GEP;
+    InBounds &= GEP->isInBounds();
+
     SmallVector<Value *, 4> NestedOps(GEP->op_begin() + 1, GEP->op_end());
 
     // Do not try the incorporate the sub-GEP if some index is not a number.
@@ -821,7 +873,9 @@ Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
     }
   }
 
-  if (Ptr->isNullValue() || BasePtr != 0) {
+  auto *PTy = cast<PointerType>(Ptr->getType());
+  if ((Ptr->isNullValue() || BasePtr != 0) &&
+      !DL.isNonIntegralPointerType(PTy)) {
     Constant *C = ConstantInt::get(Ptr->getContext(), Offset + BasePtr);
     return ConstantExpr::getIntToPtr(C, ResTy);
   }
@@ -830,8 +884,7 @@ Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
   // we eliminate over-indexing of the notional static type array bounds.
   // This makes it easy to determine if the getelementptr is "inbounds".
   // Also, this helps GlobalOpt do SROA on GlobalVariables.
-  Type *Ty = Ptr->getType();
-  assert(Ty->isPointerTy() && "Forming regular GEP of non-pointer type");
+  Type *Ty = PTy;
   SmallVector<Constant *, 32> NewIdxs;
 
   do {
@@ -897,8 +950,23 @@ Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
   if (Offset != 0)
     return nullptr;
 
+  // Preserve the inrange index from the innermost GEP if possible. We must
+  // have calculated the same indices up to and including the inrange index.
+  Optional<unsigned> InRangeIndex;
+  if (Optional<unsigned> LastIRIndex = InnermostGEP->getInRangeIndex())
+    if (SrcElemTy == InnermostGEP->getSourceElementType() &&
+        NewIdxs.size() > *LastIRIndex) {
+      InRangeIndex = LastIRIndex;
+      for (unsigned I = 0; I <= *LastIRIndex; ++I)
+        if (NewIdxs[I] != InnermostGEP->getOperand(I + 1)) {
+          InRangeIndex = None;
+          break;
+        }
+    }
+
   // Create a GEP.
-  Constant *C = ConstantExpr::getGetElementPtr(SrcElemTy, Ptr, NewIdxs);
+  Constant *C = ConstantExpr::getGetElementPtr(SrcElemTy, Ptr, NewIdxs,
+                                               InBounds, InRangeIndex);
   assert(C->getType()->getPointerElementType() == Ty &&
          "Computed GetElementPtr has unexpected type!");
 
@@ -916,15 +984,16 @@ Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
 /// attempting to fold instructions like loads and stores, which have no
 /// constant expression form.
 ///
-/// TODO: This function neither utilizes nor preserves nsw/nuw/inbounds/etc
-/// information, due to only being passed an opcode and operands. Constant
+/// TODO: This function neither utilizes nor preserves nsw/nuw/inbounds/inrange
+/// etc information, due to only being passed an opcode and operands. Constant
 /// folding using this function strips this information.
 ///
-Constant *ConstantFoldInstOperandsImpl(const Value *InstOrCE, Type *DestTy,
-                                       unsigned Opcode,
+Constant *ConstantFoldInstOperandsImpl(const Value *InstOrCE, unsigned Opcode,
                                        ArrayRef<Constant *> Ops,
                                        const DataLayout &DL,
                                        const TargetLibraryInfo *TLI) {
+  Type *DestTy = InstOrCE->getType();
+
   // Handle easy binops first.
   if (Instruction::isBinaryOp(Opcode))
     return ConstantFoldBinaryOpOperands(Opcode, Ops[0], Ops[1], DL);
@@ -936,10 +1005,14 @@ Constant *ConstantFoldInstOperandsImpl(const Value *InstOrCE, Type *DestTy,
     if (Constant *C = SymbolicallyEvaluateGEP(GEP, Ops, DL, TLI))
       return C;
 
-    return ConstantExpr::getGetElementPtr(GEP->getSourceElementType(),
-                                          Ops[0], Ops.slice(1));
+    return ConstantExpr::getGetElementPtr(GEP->getSourceElementType(), Ops[0],
+                                          Ops.slice(1), GEP->isInBounds(),
+                                          GEP->getInRangeIndex());
   }
 
+  if (auto *CE = dyn_cast<ConstantExpr>(InstOrCE))
+    return CE->getWithOperands(Ops);
+
   switch (Opcode) {
   default: return nullptr;
   case Instruction::ICmp:
@@ -966,12 +1039,58 @@ Constant *ConstantFoldInstOperandsImpl(const Value *InstOrCE, Type *DestTy,
 // Constant Folding public APIs
 //===----------------------------------------------------------------------===//
 
+namespace {
+
+Constant *
+ConstantFoldConstantImpl(const Constant *C, const DataLayout &DL,
+                         const TargetLibraryInfo *TLI,
+                         SmallDenseMap<Constant *, Constant *> &FoldedOps) {
+  if (!isa<ConstantVector>(C) && !isa<ConstantExpr>(C))
+    return nullptr;
+
+  SmallVector<Constant *, 8> Ops;
+  for (const Use &NewU : C->operands()) {
+    auto *NewC = cast<Constant>(&NewU);
+    // Recursively fold the ConstantExpr's operands. If we have already folded
+    // a ConstantExpr, we don't have to process it again.
+    if (isa<ConstantVector>(NewC) || isa<ConstantExpr>(NewC)) {
+      auto It = FoldedOps.find(NewC);
+      if (It == FoldedOps.end()) {
+        if (auto *FoldedC =
+                ConstantFoldConstantImpl(NewC, DL, TLI, FoldedOps)) {
+          NewC = FoldedC;
+          FoldedOps.insert({NewC, FoldedC});
+        } else {
+          FoldedOps.insert({NewC, NewC});
+        }
+      } else {
+        NewC = It->second;
+      }
+    }
+    Ops.push_back(NewC);
+  }
+
+  if (auto *CE = dyn_cast<ConstantExpr>(C)) {
+    if (CE->isCompare())
+      return ConstantFoldCompareInstOperands(CE->getPredicate(), Ops[0], Ops[1],
+                                             DL, TLI);
+
+    return ConstantFoldInstOperandsImpl(CE, CE->getOpcode(), Ops, DL, TLI);
+  }
+
+  assert(isa<ConstantVector>(C));
+  return ConstantVector::get(Ops);
+}
+
+} // end anonymous namespace
+
 Constant *llvm::ConstantFoldInstruction(Instruction *I, const DataLayout &DL,
                                         const TargetLibraryInfo *TLI) {
   // Handle PHI nodes quickly here...
   if (auto *PN = dyn_cast<PHINode>(I)) {
     Constant *CommonValue = nullptr;
 
+    SmallDenseMap<Constant *, Constant *> FoldedOps;
     for (Value *Incoming : PN->incoming_values()) {
       // If the incoming value is undef then skip it.  Note that while we could
       // skip the value if it is equal to the phi node itself we choose not to
@@ -984,8 +1103,8 @@ Constant *llvm::ConstantFoldInstruction(Instruction *I, const DataLayout &DL,
       if (!C)
         return nullptr;
       // Fold the PHI's operands.
-      if (auto *NewC = dyn_cast<ConstantExpr>(C))
-        C = ConstantFoldConstantExpression(NewC, DL, TLI);
+      if (auto *FoldedC = ConstantFoldConstantImpl(C, DL, TLI, FoldedOps))
+        C = FoldedC;
       // If the incoming value is a different constant to
       // the one we saw previously, then give up.
       if (CommonValue && C != CommonValue)
@@ -993,7 +1112,6 @@ Constant *llvm::ConstantFoldInstruction(Instruction *I, const DataLayout &DL,
       CommonValue = C;
     }
 
-
     // If we reach here, all incoming values are the same constant or undef.
     return CommonValue ? CommonValue : UndefValue::get(PN->getType());
   }
@@ -1003,12 +1121,13 @@ Constant *llvm::ConstantFoldInstruction(Instruction *I, const DataLayout &DL,
   if (!all_of(I->operands(), [](Use &U) { return isa<Constant>(U); }))
     return nullptr;
 
+  SmallDenseMap<Constant *, Constant *> FoldedOps;
   SmallVector<Constant *, 8> Ops;
   for (const Use &OpU : I->operands()) {
     auto *Op = cast<Constant>(&OpU);
     // Fold the Instruction's operands.
-    if (auto *NewCE = dyn_cast<ConstantExpr>(Op))
-      Op = ConstantFoldConstantExpression(NewCE, DL, TLI);
+    if (auto *FoldedOp = ConstantFoldConstantImpl(Op, DL, TLI, FoldedOps))
+      Op = FoldedOp;
 
     Ops.push_back(Op);
   }
@@ -1036,55 +1155,17 @@ Constant *llvm::ConstantFoldInstruction(Instruction *I, const DataLayout &DL,
   return ConstantFoldInstOperands(I, Ops, DL, TLI);
 }
 
-namespace {
-
-Constant *
-ConstantFoldConstantExpressionImpl(const ConstantExpr *CE, const DataLayout &DL,
-                                   const TargetLibraryInfo *TLI,
-                                   SmallPtrSetImpl<ConstantExpr *> &FoldedOps) {
-  SmallVector<Constant *, 8> Ops;
-  for (const Use &NewU : CE->operands()) {
-    auto *NewC = cast<Constant>(&NewU);
-    // Recursively fold the ConstantExpr's operands. If we have already folded
-    // a ConstantExpr, we don't have to process it again.
-    if (auto *NewCE = dyn_cast<ConstantExpr>(NewC)) {
-      if (FoldedOps.insert(NewCE).second)
-        NewC = ConstantFoldConstantExpressionImpl(NewCE, DL, TLI, FoldedOps);
-    }
-    Ops.push_back(NewC);
-  }
-
-  if (CE->isCompare())
-    return ConstantFoldCompareInstOperands(CE->getPredicate(), Ops[0], Ops[1],
-                                           DL, TLI);
-
-  return ConstantFoldInstOperandsImpl(CE, CE->getType(), CE->getOpcode(), Ops,
-                                      DL, TLI);
-}
-
-} // end anonymous namespace
-
-Constant *llvm::ConstantFoldConstantExpression(const ConstantExpr *CE,
-                                               const DataLayout &DL,
-                                               const TargetLibraryInfo *TLI) {
-  SmallPtrSet<ConstantExpr *, 4> FoldedOps;
-  return ConstantFoldConstantExpressionImpl(CE, DL, TLI, FoldedOps);
+Constant *llvm::ConstantFoldConstant(const Constant *C, const DataLayout &DL,
+                                     const TargetLibraryInfo *TLI) {
+  SmallDenseMap<Constant *, Constant *> FoldedOps;
+  return ConstantFoldConstantImpl(C, DL, TLI, FoldedOps);
 }
 
 Constant *llvm::ConstantFoldInstOperands(Instruction *I,
                                          ArrayRef<Constant *> Ops,
                                          const DataLayout &DL,
                                          const TargetLibraryInfo *TLI) {
-  return ConstantFoldInstOperandsImpl(I, I->getType(), I->getOpcode(), Ops, DL,
-                                      TLI);
-}
-
-Constant *llvm::ConstantFoldInstOperands(unsigned Opcode, Type *DestTy,
-                                         ArrayRef<Constant *> Ops,
-                                         const DataLayout &DL,
-                                         const TargetLibraryInfo *TLI) {
-  assert(Opcode != Instruction::GetElementPtr && "Invalid for GEPs");
-  return ConstantFoldInstOperandsImpl(nullptr, DestTy, Opcode, Ops, DL, TLI);
+  return ConstantFoldInstOperandsImpl(I, I->getOpcode(), Ops, DL, TLI);
 }
 
 Constant *llvm::ConstantFoldCompareInstOperands(unsigned Predicate,
@@ -1350,6 +1431,8 @@ bool llvm::canConstantFoldCallTo(const Function *F) {
            Name == "log10f";
   case 'p':
     return Name == "pow" || Name == "powf";
+  case 'r':
+    return Name == "round" || Name == "roundf";
   case 's':
     return Name == "sin" || Name == "sinh" || Name == "sqrt" ||
            Name == "sinf" || Name == "sinhf" || Name == "sqrtf";
@@ -1364,7 +1447,7 @@ Constant *GetConstantFoldFPValue(double V, Type *Ty) {
   if (Ty->isHalfTy()) {
     APFloat APF(V);
     bool unused;
-    APF.convert(APFloat::IEEEhalf, APFloat::rmNearestTiesToEven, &unused);
+    APF.convert(APFloat::IEEEhalf(), APFloat::rmNearestTiesToEven, &unused);
     return ConstantFP::get(Ty->getContext(), APF);
   }
   if (Ty->isFloatTy())
@@ -1455,7 +1538,7 @@ double getValueAsDouble(ConstantFP *Op) {
 
   bool unused;
   APFloat APF = Op->getValueAPF();
-  APF.convert(APFloat::IEEEdouble, APFloat::rmNearestTiesToEven, &unused);
+  APF.convert(APFloat::IEEEdouble(), APFloat::rmNearestTiesToEven, &unused);
   return APF.convertToDouble();
 }
 
@@ -1473,7 +1556,7 @@ Constant *ConstantFoldScalarCall(StringRef Name, unsigned IntrinsicID, Type *Ty,
         APFloat Val(Op->getValueAPF());
 
         bool lost = false;
-        Val.convert(APFloat::IEEEhalf, APFloat::rmNearestTiesToEven, &lost);
+        Val.convert(APFloat::IEEEhalf(), APFloat::rmNearestTiesToEven, &lost);
 
         return ConstantInt::get(Ty->getContext(), Val.bitcastToAPInt());
       }
@@ -1614,6 +1697,10 @@ Constant *ConstantFoldScalarCall(StringRef Name, unsigned IntrinsicID, Type *Ty,
           }
         }
         break;
+      case 'r':
+        if ((Name == "round" && TLI->has(LibFunc::round)) ||
+            (Name == "roundf" && TLI->has(LibFunc::roundf)))
+          return ConstantFoldFP(round, V, Ty);
       case 's':
         if ((Name == "sin" && TLI->has(LibFunc::sin)) ||
             (Name == "sinf" && TLI->has(LibFunc::sinf)))
@@ -1648,7 +1735,7 @@ Constant *ConstantFoldScalarCall(StringRef Name, unsigned IntrinsicID, Type *Ty,
       case Intrinsic::bitreverse:
         return ConstantInt::get(Ty->getContext(), Op->getValue().reverseBits());
       case Intrinsic::convert_from_fp16: {
-        APFloat Val(APFloat::IEEEhalf, Op->getValue());
+        APFloat Val(APFloat::IEEEhalf(), Op->getValue());
 
         bool lost = false;
         APFloat::opStatus status = Val.convert(
@@ -1927,3 +2014,152 @@ llvm::ConstantFoldCall(Function *F, ArrayRef<Constant *> Operands,
 
   return ConstantFoldScalarCall(Name, F->getIntrinsicID(), Ty, Operands, TLI);
 }
+
+bool llvm::isMathLibCallNoop(CallSite CS, const TargetLibraryInfo *TLI) {
+  // FIXME: Refactor this code; this duplicates logic in LibCallsShrinkWrap
+  // (and to some extent ConstantFoldScalarCall).
+  Function *F = CS.getCalledFunction();
+  if (!F)
+    return false;
+
+  LibFunc::Func Func;
+  if (!TLI || !TLI->getLibFunc(*F, Func))
+    return false;
+
+  if (CS.getNumArgOperands() == 1) {
+    if (ConstantFP *OpC = dyn_cast<ConstantFP>(CS.getArgOperand(0))) {
+      const APFloat &Op = OpC->getValueAPF();
+      switch (Func) {
+      case LibFunc::logl:
+      case LibFunc::log:
+      case LibFunc::logf:
+      case LibFunc::log2l:
+      case LibFunc::log2:
+      case LibFunc::log2f:
+      case LibFunc::log10l:
+      case LibFunc::log10:
+      case LibFunc::log10f:
+        return Op.isNaN() || (!Op.isZero() && !Op.isNegative());
+
+      case LibFunc::expl:
+      case LibFunc::exp:
+      case LibFunc::expf:
+        // FIXME: These boundaries are slightly conservative.
+        if (OpC->getType()->isDoubleTy())
+          return Op.compare(APFloat(-745.0)) != APFloat::cmpLessThan &&
+                 Op.compare(APFloat(709.0)) != APFloat::cmpGreaterThan;
+        if (OpC->getType()->isFloatTy())
+          return Op.compare(APFloat(-103.0f)) != APFloat::cmpLessThan &&
+                 Op.compare(APFloat(88.0f)) != APFloat::cmpGreaterThan;
+        break;
+
+      case LibFunc::exp2l:
+      case LibFunc::exp2:
+      case LibFunc::exp2f:
+        // FIXME: These boundaries are slightly conservative.
+        if (OpC->getType()->isDoubleTy())
+          return Op.compare(APFloat(-1074.0)) != APFloat::cmpLessThan &&
+                 Op.compare(APFloat(1023.0)) != APFloat::cmpGreaterThan;
+        if (OpC->getType()->isFloatTy())
+          return Op.compare(APFloat(-149.0f)) != APFloat::cmpLessThan &&
+                 Op.compare(APFloat(127.0f)) != APFloat::cmpGreaterThan;
+        break;
+
+      case LibFunc::sinl:
+      case LibFunc::sin:
+      case LibFunc::sinf:
+      case LibFunc::cosl:
+      case LibFunc::cos:
+      case LibFunc::cosf:
+        return !Op.isInfinity();
+
+      case LibFunc::tanl:
+      case LibFunc::tan:
+      case LibFunc::tanf: {
+        // FIXME: Stop using the host math library.
+        // FIXME: The computation isn't done in the right precision.
+        Type *Ty = OpC->getType();
+        if (Ty->isDoubleTy() || Ty->isFloatTy() || Ty->isHalfTy()) {
+          double OpV = getValueAsDouble(OpC);
+          return ConstantFoldFP(tan, OpV, Ty) != nullptr;
+        }
+        break;
+      }
+
+      case LibFunc::asinl:
+      case LibFunc::asin:
+      case LibFunc::asinf:
+      case LibFunc::acosl:
+      case LibFunc::acos:
+      case LibFunc::acosf:
+        return Op.compare(APFloat(Op.getSemantics(), "-1")) !=
+                   APFloat::cmpLessThan &&
+               Op.compare(APFloat(Op.getSemantics(), "1")) !=
+                   APFloat::cmpGreaterThan;
+
+      case LibFunc::sinh:
+      case LibFunc::cosh:
+      case LibFunc::sinhf:
+      case LibFunc::coshf:
+      case LibFunc::sinhl:
+      case LibFunc::coshl:
+        // FIXME: These boundaries are slightly conservative.
+        if (OpC->getType()->isDoubleTy())
+          return Op.compare(APFloat(-710.0)) != APFloat::cmpLessThan &&
+                 Op.compare(APFloat(710.0)) != APFloat::cmpGreaterThan;
+        if (OpC->getType()->isFloatTy())
+          return Op.compare(APFloat(-89.0f)) != APFloat::cmpLessThan &&
+                 Op.compare(APFloat(89.0f)) != APFloat::cmpGreaterThan;
+        break;
+
+      case LibFunc::sqrtl:
+      case LibFunc::sqrt:
+      case LibFunc::sqrtf:
+        return Op.isNaN() || Op.isZero() || !Op.isNegative();
+
+      // FIXME: Add more functions: sqrt_finite, atanh, expm1, log1p,
+      // maybe others?
+      default:
+        break;
+      }
+    }
+  }
+
+  if (CS.getNumArgOperands() == 2) {
+    ConstantFP *Op0C = dyn_cast<ConstantFP>(CS.getArgOperand(0));
+    ConstantFP *Op1C = dyn_cast<ConstantFP>(CS.getArgOperand(1));
+    if (Op0C && Op1C) {
+      const APFloat &Op0 = Op0C->getValueAPF();
+      const APFloat &Op1 = Op1C->getValueAPF();
+
+      switch (Func) {
+      case LibFunc::powl:
+      case LibFunc::pow:
+      case LibFunc::powf: {
+        // FIXME: Stop using the host math library.
+        // FIXME: The computation isn't done in the right precision.
+        Type *Ty = Op0C->getType();
+        if (Ty->isDoubleTy() || Ty->isFloatTy() || Ty->isHalfTy()) {
+          if (Ty == Op1C->getType()) {
+            double Op0V = getValueAsDouble(Op0C);
+            double Op1V = getValueAsDouble(Op1C);
+            return ConstantFoldBinaryFP(pow, Op0V, Op1V, Ty) != nullptr;
+          }
+        }
+        break;
+      }
+
+      case LibFunc::fmodl:
+      case LibFunc::fmod:
+      case LibFunc::fmodf:
+        return Op0.isNaN() || Op1.isNaN() ||
+               (!Op0.isInfinity() && !Op1.isZero());
+
+      default:
+        break;
+      }
+    }
+  }
+
+  return false;
+}