1 files changed, 41 insertions, 7 deletions

diff --git a/contrib/llvm/lib/Target/ARM/ARMTargetTransformInfo.h b/contrib/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
index 3c83cd9..0695a4e 100644
--- a/contrib/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
+++ b/contrib/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
@@ -33,9 +33,38 @@ class ARMTTIImpl : public BasicTTIImplBase<ARMTTIImpl> {
   const ARMSubtarget *ST;
   const ARMTargetLowering *TLI;
 
-  /// Estimate the overhead of scalarizing an instruction. Insert and Extract
-  /// are set if the result needs to be inserted and/or extracted from vectors.
-  unsigned getScalarizationOverhead(Type *Ty, bool Insert, bool Extract);
+  // Currently the following features are excluded from InlineFeatureWhitelist.
+  // ModeThumb, FeatureNoARM, ModeSoftFloat, FeatureVFPOnlySP, FeatureD16
+  // Depending on whether they are set or unset, different
+  // instructions/registers are available. For example, inlining a callee with
+  // -thumb-mode in a caller with +thumb-mode, may cause the assembler to
+  // fail if the callee uses ARM only instructions, e.g. in inline asm.
+  const FeatureBitset InlineFeatureWhitelist = {
+      ARM::FeatureVFP2, ARM::FeatureVFP3, ARM::FeatureNEON, ARM::FeatureThumb2,
+      ARM::FeatureFP16, ARM::FeatureVFP4, ARM::FeatureFPARMv8,
+      ARM::FeatureFullFP16, ARM::FeatureHWDivThumb,
+      ARM::FeatureHWDivARM, ARM::FeatureDB, ARM::FeatureV7Clrex,
+      ARM::FeatureAcquireRelease, ARM::FeatureSlowFPBrcc,
+      ARM::FeaturePerfMon, ARM::FeatureTrustZone, ARM::Feature8MSecExt,
+      ARM::FeatureCrypto, ARM::FeatureCRC, ARM::FeatureRAS,
+      ARM::FeatureFPAO, ARM::FeatureFuseAES, ARM::FeatureZCZeroing,
+      ARM::FeatureProfUnpredicate, ARM::FeatureSlowVGETLNi32,
+      ARM::FeatureSlowVDUP32, ARM::FeaturePreferVMOVSR,
+      ARM::FeaturePrefISHSTBarrier, ARM::FeatureMuxedUnits,
+      ARM::FeatureSlowOddRegister, ARM::FeatureSlowLoadDSubreg,
+      ARM::FeatureDontWidenVMOVS, ARM::FeatureExpandMLx,
+      ARM::FeatureHasVMLxHazards, ARM::FeatureNEONForFPMovs,
+      ARM::FeatureNEONForFP, ARM::FeatureCheckVLDnAlign,
+      ARM::FeatureHasSlowFPVMLx, ARM::FeatureVMLxForwarding,
+      ARM::FeaturePref32BitThumb, ARM::FeatureAvoidPartialCPSR,
+      ARM::FeatureCheapPredicableCPSR, ARM::FeatureAvoidMOVsShOp,
+      ARM::FeatureHasRetAddrStack, ARM::FeatureHasNoBranchPredictor,
+      ARM::FeatureDSP, ARM::FeatureMP, ARM::FeatureVirtualization,
+      ARM::FeatureMClass, ARM::FeatureRClass, ARM::FeatureAClass,
+      ARM::FeatureNaClTrap, ARM::FeatureStrictAlign, ARM::FeatureLongCalls,
+      ARM::FeatureExecuteOnly, ARM::FeatureReserveR9, ARM::FeatureNoMovt,
+      ARM::FeatureNoNegativeImmediates
+  };
 
   const ARMSubtarget *getST() const { return ST; }
   const ARMTargetLowering *getTLI() const { return TLI; }
@@ -45,6 +74,9 @@ public:
       : BaseT(TM, F.getParent()->getDataLayout()), ST(TM->getSubtargetImpl(F)),
         TLI(ST->getTargetLowering()) {}
 
+  bool areInlineCompatible(const Function *Caller,
+                           const Function *Callee) const;
+
   bool enableInterleavedAccessVectorization() { return true; }
 
   /// Floating-point computation using ARMv8 AArch32 Advanced
@@ -82,7 +114,7 @@ public:
     return 13;
   }
 
-  unsigned getRegisterBitWidth(bool Vector) {
+  unsigned getRegisterBitWidth(bool Vector) const {
     if (Vector) {
       if (ST->hasNEON())
         return 128;
@@ -98,9 +130,11 @@ public:
 
   int getShuffleCost(TTI::ShuffleKind Kind, Type *Tp, int Index, Type *SubTp);
 
-  int getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src);
+  int getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
+                       const Instruction *I = nullptr);
 
-  int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy);
+  int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
+                         const Instruction *I = nullptr);
 
   int getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index);
 
@@ -118,7 +152,7 @@ public:
       ArrayRef<const Value *> Args = ArrayRef<const Value *>());
 
   int getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
-                      unsigned AddressSpace);
+                      unsigned AddressSpace, const Instruction *I = nullptr);
 
   int getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy, unsigned Factor,
                                  ArrayRef<unsigned> Indices, unsigned Alignment,