Merge commit '7dfcb84fc16b3bf6b2379713b53090757f0a45f9'

Conflicts:
	docs/LangRef.rst
	include/llvm/CodeGen/CallingConvLower.h
	include/llvm/IRReader/IRReader.h
	include/llvm/Target/TargetMachine.h
	lib/CodeGen/CallingConvLower.cpp
	lib/IRReader/IRReader.cpp
	lib/IRReader/LLVMBuild.txt
	lib/IRReader/Makefile
	lib/LLVMBuild.txt
	lib/Makefile
	lib/Support/MemoryBuffer.cpp
	lib/Support/Unix/PathV2.inc
	lib/Target/ARM/ARMBaseInstrInfo.cpp
	lib/Target/ARM/ARMISelLowering.cpp
	lib/Target/ARM/ARMInstrInfo.td
	lib/Target/ARM/ARMSubtarget.cpp
	lib/Target/ARM/ARMTargetMachine.cpp
	lib/Target/Mips/CMakeLists.txt
	lib/Target/Mips/MipsDelaySlotFiller.cpp
	lib/Target/Mips/MipsISelLowering.cpp
	lib/Target/Mips/MipsInstrInfo.td
	lib/Target/Mips/MipsSubtarget.cpp
	lib/Target/Mips/MipsSubtarget.h
	lib/Target/X86/X86FastISel.cpp
	lib/Target/X86/X86ISelDAGToDAG.cpp
	lib/Target/X86/X86ISelLowering.cpp
	lib/Target/X86/X86InstrControl.td
	lib/Target/X86/X86InstrFormats.td
	lib/Transforms/IPO/ExtractGV.cpp
	lib/Transforms/InstCombine/InstCombineCompares.cpp
	lib/Transforms/Utils/SimplifyLibCalls.cpp
	test/CodeGen/X86/fast-isel-divrem.ll
	test/MC/ARM/data-in-code.ll
	tools/Makefile
	tools/llvm-extract/llvm-extract.cpp
	tools/llvm-link/CMakeLists.txt
	tools/opt/CMakeLists.txt
	tools/opt/LLVMBuild.txt
	tools/opt/Makefile
	tools/opt/opt.cpp

1 files changed, 83 insertions, 19 deletions

diff --git a/lib/CodeGen/BasicTargetTransformInfo.cpp b/lib/CodeGen/BasicTargetTransformInfo.cpp
index e8b5b4fe8d..4a99184f5e 100644
--- a/lib/CodeGen/BasicTargetTransformInfo.cpp
+++ b/lib/CodeGen/BasicTargetTransformInfo.cpp
@@ -85,7 +85,9 @@ public:
   virtual unsigned getNumberOfRegisters(bool Vector) const;
   virtual unsigned getMaximumUnrollFactor() const;
   virtual unsigned getRegisterBitWidth(bool Vector) const;
-  virtual unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty) const;
+  virtual unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty,
+                                          OperandValueKind,
+                                          OperandValueKind) const;
   virtual unsigned getShuffleCost(ShuffleKind Kind, Type *Tp,
                                   int Index, Type *SubTp) const;
   virtual unsigned getCastInstrCost(unsigned Opcode, Type *Dst,
@@ -193,27 +195,34 @@ unsigned BasicTTI::getMaximumUnrollFactor() const {
   return 1;
 }
 
-unsigned BasicTTI::getArithmeticInstrCost(unsigned Opcode, Type *Ty) const {
+unsigned BasicTTI::getArithmeticInstrCost(unsigned Opcode, Type *Ty,
+                                          OperandValueKind,
+                                          OperandValueKind) const {
   // Check if any of the operands are vector operands.
   int ISD = TLI->InstructionOpcodeToISD(Opcode);
   assert(ISD && "Invalid opcode");
 
   std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(Ty);
 
+  bool IsFloat = Ty->getScalarType()->isFloatingPointTy();
+  // Assume that floating point arithmetic operations cost twice as much as
+  // integer operations.
+  unsigned OpCost = (IsFloat ? 2 : 1);
+
   if (TLI->isOperationLegalOrPromote(ISD, LT.second)) {
     // The operation is legal. Assume it costs 1.
-    // If the type is split to multiple registers, assume that thre is some
+    // If the type is split to multiple registers, assume that there is some
     // overhead to this.
     // TODO: Once we have extract/insert subvector cost we need to use them.
     if (LT.first > 1)
-      return LT.first * 2;
-    return LT.first * 1;
+      return LT.first * 2 * OpCost;
+    return LT.first * 1 * OpCost;
   }
 
   if (!TLI->isOperationExpand(ISD, LT.second)) {
     // If the operation is custom lowered then assume
     // thare the code is twice as expensive.
-    return LT.first * 2;
+    return LT.first * 2 * OpCost;
   }
 
   // Else, assume that we need to scalarize this op.
@@ -226,7 +235,7 @@ unsigned BasicTTI::getArithmeticInstrCost(unsigned Opcode, Type *Ty) const {
   }
 
   // We don't know anything about this scalar instruction.
-  return 1;
+  return OpCost;
 }
 
 unsigned BasicTTI::getShuffleCost(ShuffleKind Kind, Type *Tp, int Index,
@@ -379,22 +388,77 @@ unsigned BasicTTI::getMemoryOpCost(unsigned Opcode, Type *Src,
   return LT.first;
 }
 
-unsigned BasicTTI::getIntrinsicInstrCost(Intrinsic::ID, Type *RetTy,
+unsigned BasicTTI::getIntrinsicInstrCost(Intrinsic::ID IID, Type *RetTy,
                                          ArrayRef<Type *> Tys) const {
-  // assume that we need to scalarize this intrinsic.
-  unsigned ScalarizationCost = 0;
-  unsigned ScalarCalls = 1;
-  if (RetTy->isVectorTy()) {
-    ScalarizationCost = getScalarizationOverhead(RetTy, true, false);
-    ScalarCalls = std::max(ScalarCalls, RetTy->getVectorNumElements());
-  }
-  for (unsigned i = 0, ie = Tys.size(); i != ie; ++i) {
-    if (Tys[i]->isVectorTy()) {
-      ScalarizationCost += getScalarizationOverhead(Tys[i], false, true);
+  unsigned ISD = 0;
+  switch (IID) {
+  default: {
+    // Assume that we need to scalarize this intrinsic.
+    unsigned ScalarizationCost = 0;
+    unsigned ScalarCalls = 1;
+    if (RetTy->isVectorTy()) {
+      ScalarizationCost = getScalarizationOverhead(RetTy, true, false);
       ScalarCalls = std::max(ScalarCalls, RetTy->getVectorNumElements());
     }
+    for (unsigned i = 0, ie = Tys.size(); i != ie; ++i) {
+      if (Tys[i]->isVectorTy()) {
+        ScalarizationCost += getScalarizationOverhead(Tys[i], false, true);
+        ScalarCalls = std::max(ScalarCalls, RetTy->getVectorNumElements());
+      }
+    }
+
+    return ScalarCalls + ScalarizationCost;
+  }
+  // Look for intrinsics that can be lowered directly or turned into a scalar
+  // intrinsic call.
+  case Intrinsic::sqrt:    ISD = ISD::FSQRT;  break;
+  case Intrinsic::sin:     ISD = ISD::FSIN;   break;
+  case Intrinsic::cos:     ISD = ISD::FCOS;   break;
+  case Intrinsic::exp:     ISD = ISD::FEXP;   break;
+  case Intrinsic::exp2:    ISD = ISD::FEXP2;  break;
+  case Intrinsic::log:     ISD = ISD::FLOG;   break;
+  case Intrinsic::log10:   ISD = ISD::FLOG10; break;
+  case Intrinsic::log2:    ISD = ISD::FLOG2;  break;
+  case Intrinsic::fabs:    ISD = ISD::FABS;   break;
+  case Intrinsic::floor:   ISD = ISD::FFLOOR; break;
+  case Intrinsic::ceil:    ISD = ISD::FCEIL;  break;
+  case Intrinsic::trunc:   ISD = ISD::FTRUNC; break;
+  case Intrinsic::rint:    ISD = ISD::FRINT;  break;
+  case Intrinsic::pow:     ISD = ISD::FPOW;   break;
+  case Intrinsic::fma:     ISD = ISD::FMA;    break;
+  case Intrinsic::fmuladd: ISD = ISD::FMA;    break; // FIXME: mul + add?
+  }
+
+  std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(RetTy);
+
+  if (TLI->isOperationLegalOrPromote(ISD, LT.second)) {
+    // The operation is legal. Assume it costs 1.
+    // If the type is split to multiple registers, assume that thre is some
+    // overhead to this.
+    // TODO: Once we have extract/insert subvector cost we need to use them.
+    if (LT.first > 1)
+      return LT.first * 2;
+    return LT.first * 1;
+  }
+
+  if (!TLI->isOperationExpand(ISD, LT.second)) {
+    // If the operation is custom lowered then assume
+    // thare the code is twice as expensive.
+    return LT.first * 2;
   }
-  return ScalarCalls + ScalarizationCost;
+
+  // Else, assume that we need to scalarize this intrinsic. For math builtins
+  // this will emit a costly libcall, adding call overhead and spills. Make it
+  // very expensive.
+  if (RetTy->isVectorTy()) {
+    unsigned Num = RetTy->getVectorNumElements();
+    unsigned Cost = TopTTI->getIntrinsicInstrCost(IID, RetTy->getScalarType(),
+                                                  Tys);
+    return 10 * Cost * Num;
+  }
+
+  // This is going to be turned into a library call, make it expensive.
+  return 10;
 }
 
 unsigned BasicTTI::getNumberOfParts(Type *Tp) const {