[CodeGen] Print RegClasses on MI in verbose mode

[thegameg]

Summary

r322086 removed the trailing information describing reg classes for each register.

This patch adds printing reg classes next to every register when individual operands/instructions/basic blocks are printed. In the case of dumping MIR or printing a full function, by default don't print it.

[dsanders]

LGTM with a couple comment nits

include/llvm/CodeGen/MachineOperand.h

275 ↗

(On Diff #130398)

I'd go with 'but not when a fragment of the function is printed' or something to that effect to make it clear that the information is not available when you aren't looking at the whole function

lib/CodeGen/MachineFunction.cpp

525 ↗

(On Diff #130398)

... since that information is already present.

[MatzeB]

LGTM, thanks.

include/llvm/CodeGen/MachineBasicBlock.h

729 ↗

(On Diff #130398)

How about calling the parameter IsStandalone instead? (similar for the other functions)

[thegameg]

Sorry, I missed your comment @MatzeB. IsStandalone sounds better indeed, I fixed it in r322867.

llvm/trunk/include/llvm/CodeGen/MachineBasicBlock.h

#endif
   /// \p Reg must be a physical register.
   LivenessQueryResult computeRegisterLiveness(const TargetRegisterInfo *TRI,
                                               unsigned Reg,
                                               const_iterator Before,
                                               unsigned Neighborhood = 10) const;
 
   // Debugging methods.
   void dump() const;
-  void print(raw_ostream &OS, const SlotIndexes* = nullptr) const;
+  void print(raw_ostream &OS, const SlotIndexes * = nullptr,
+             bool IsVerbose = true) const;
   void print(raw_ostream &OS, ModuleSlotTracker &MST,
-             const SlotIndexes* = nullptr) const;
+             const SlotIndexes * = nullptr, bool IsVerbose = true) const;
 
   // Printing method used by LoopInfo.
   void printAsOperand(raw_ostream &OS, bool PrintType = true) const;
 
   /// MachineBasicBlocks are uniquely numbered at the function level, unless
   /// they're not in a MachineFunction yet, in which case this will return -1.
   int getNumber() const { return Number; }
   void setNumber(int N) { Number = N; }

llvm/trunk/include/llvm/CodeGen/MachineInstr.h

LLT getTypeToPrint(unsigned OpIdx, SmallBitVector &PrintedTypes,
                      const MachineRegisterInfo &MRI) const;
 
   /// Return true when an instruction has tied register that can't be determined
   /// by the instruction's descriptor. This is useful for MIR printing, to
   /// determine whether we need to print the ties or not.
   bool hasComplexRegisterTies() const;
 
   /// Print this MI to \p OS.
+  /// Don't print information that can be inferred from other instructions if
+  /// \p IsVerbose is false. It is usually true when only a fragment of the
+  /// function is printed.
   /// Only print the defs and the opcode if \p SkipOpers is true.
   /// Otherwise, also print operands if \p SkipDebugLoc is true.
   /// Otherwise, also print the debug loc, with a terminating newline.
   /// \p TII is used to print the opcode name.  If it's not present, but the
   /// MI is in a function, the opcode will be printed using the function's TII.
-  void print(raw_ostream &OS, bool SkipOpers = false, bool SkipDebugLoc = false,
-             const TargetInstrInfo *TII = nullptr) const;
-  void print(raw_ostream &OS, ModuleSlotTracker &MST, bool SkipOpers = false,
+  void print(raw_ostream &OS, bool IsVerbose = true, bool SkipOpers = false,
              bool SkipDebugLoc = false,
              const TargetInstrInfo *TII = nullptr) const;
+  void print(raw_ostream &OS, ModuleSlotTracker &MST, bool IsVerbose = true,
+             bool SkipOpers = false, bool SkipDebugLoc = false,
+             const TargetInstrInfo *TII = nullptr) const;
   void dump() const;
   /// @}
 
   //===--------------------------------------------------------------------===//
   // Accessors used to build up machine instructions.
 
   /// Add the specified operand to the instruction.  If it is an implicit
   /// operand, it is added to the end of the operand list.  If it is an

llvm/trunk/include/llvm/CodeGen/MachineOperand.h

void print(raw_ostream &os, const TargetRegisterInfo *TRI = nullptr,
              const TargetIntrinsicInfo *IntrinsicInfo = nullptr) const;
 
   /// More complex way of printing a MachineOperand.
   /// \param TypeToPrint specifies the generic type to be printed on uses and
   /// defs. It can be determined using MachineInstr::getTypeToPrint.
   /// \param PrintDef - whether we want to print `def` on an operand which
   /// isDef. Sometimes, if the operand is printed before '=', we don't print
   /// `def`.
+  /// \param IsVerbose - whether we want a verbose output of the MO. This
+  /// prints extra information that can be easily inferred when printing the
+  /// whole function, but not when printing only a fragment of it.
   /// \param ShouldPrintRegisterTies - whether we want to print register ties.
   /// Sometimes they are easily determined by the instruction's descriptor
   /// (MachineInstr::hasComplexRegiterTies can determine if it's needed).
   /// \param TiedOperandIdx - if we need to print register ties this needs to
   /// provide the index of the tied register. If not, it will be ignored.
   /// \param TRI - provide more target-specific information to the printer.
   /// Unlike the previous function, this one will not try and get the
   /// information from it's parent.
   /// \param IntrinsicInfo - same as \p TRI.
   void print(raw_ostream &os, ModuleSlotTracker &MST, LLT TypeToPrint,
-             bool PrintDef, bool ShouldPrintRegisterTies,
+             bool PrintDef, bool IsVerbose, bool ShouldPrintRegisterTies,
              unsigned TiedOperandIdx, const TargetRegisterInfo *TRI,
              const TargetIntrinsicInfo *IntrinsicInfo) const;
 
   void dump() const;
 
   //===--------------------------------------------------------------------===//
   // Accessors that tell you what kind of MachineOperand you're looking at.
   //===--------------------------------------------------------------------===//

llvm/trunk/lib/CodeGen/MIRPrinter.cpp

void MIPrinter::print(const MachineInstr &MI, unsigned OpIdx,
   case MachineOperand::MO_CFIIndex:
   case MachineOperand::MO_IntrinsicID:
   case MachineOperand::MO_Predicate:
   case MachineOperand::MO_BlockAddress: {
     unsigned TiedOperandIdx = 0;
     if (ShouldPrintRegisterTies && Op.isReg() && Op.isTied() && !Op.isDef())
       TiedOperandIdx = Op.getParent()->findTiedOperandIdx(OpIdx);
     const TargetIntrinsicInfo *TII = MI.getMF()->getTarget().getIntrinsicInfo();
-    Op.print(OS, MST, TypeToPrint, PrintDef, ShouldPrintRegisterTies,
-             TiedOperandIdx, TRI, TII);
+    Op.print(OS, MST, TypeToPrint, PrintDef, /*IsVerbose=*/false,
+             ShouldPrintRegisterTies, TiedOperandIdx, TRI, TII);
     break;
   }
   case MachineOperand::MO_FrameIndex:
     printStackObjectReference(Op.getIndex());
     break;
   case MachineOperand::MO_RegisterMask: {
     auto RegMaskInfo = RegisterMaskIds.find(Op.getRegMask());
     if (RegMaskInfo != RegisterMaskIds.end())

llvm/trunk/lib/CodeGen/MachineBasicBlock.cpp

if (getParent())
     Name = (getParent()->getName() + ":").str();
   if (getBasicBlock())
     Name += getBasicBlock()->getName();
   else
     Name += ("BB" + Twine(getNumber())).str();
   return Name;
 }
 
-void MachineBasicBlock::print(raw_ostream &OS, const SlotIndexes *Indexes)
-    const {
+void MachineBasicBlock::print(raw_ostream &OS, const SlotIndexes *Indexes,
+                              bool IsVerbose) const {
   const MachineFunction *MF = getParent();
   if (!MF) {
     OS << "Can't print out MachineBasicBlock because parent MachineFunction"
        << " is null\n";
     return;
   }
   const Function &F = MF->getFunction();
   const Module *M = F.getParent();
   ModuleSlotTracker MST(M);
-  print(OS, MST, Indexes);
+  print(OS, MST, Indexes, IsVerbose);
 }
 
 void MachineBasicBlock::print(raw_ostream &OS, ModuleSlotTracker &MST,
-                              const SlotIndexes *Indexes) const {
+                              const SlotIndexes *Indexes,
+                              bool IsVerbose) const {
   const MachineFunction *MF = getParent();
   if (!MF) {
     OS << "Can't print out MachineBasicBlock because parent MachineFunction"
        << " is null\n";
     return;
   }
 
   if (Indexes)
for (auto &I : instrs()) {
     if (Indexes) {
       if (Indexes->hasIndex(I))
         OS << Indexes->getInstructionIndex(I);
       OS << '\t';
     }
     OS << '\t';
     if (I.isInsideBundle())
       OS << "  * ";
-    I.print(OS, MST);
+    I.print(OS, MST, IsVerbose);
   }
 
   // Print the successors of this block according to the CFG.
   if (!succ_empty()) {
     if (Indexes) OS << '\t';
     OS << "    Successors according to CFG:";
     for (const_succ_iterator SI = succ_begin(), E = succ_end(); SI != E; ++SI) {
       OS << " " << printMBBReference(*(*SI));

llvm/trunk/lib/CodeGen/MachineFunction.cpp

if (RegInfo && !RegInfo->livein_empty()) {
     }
     OS << '\n';
   }
 
   ModuleSlotTracker MST(getFunction().getParent());
   MST.incorporateFunction(getFunction());
   for (const auto &BB : *this) {
     OS << '\n';
-    BB.print(OS, MST, Indexes);
+    // If we print the whole function, don't print any verbose information,
+    // since that information is already present.
+    BB.print(OS, MST, Indexes, /*IsVerbose=*/false);
   }
 
   OS << "\n# End machine code for function " << getName() << ".\n\n";
 }
 
 namespace llvm {
 
   template<>

llvm/trunk/lib/CodeGen/MachineInstr.cpp

 
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
 LLVM_DUMP_METHOD void MachineInstr::dump() const {
   dbgs() << "  ";
   print(dbgs());
 }
 #endif
 
-void MachineInstr::print(raw_ostream &OS, bool SkipOpers, bool SkipDebugLoc,
-                         const TargetInstrInfo *TII) const {
+void MachineInstr::print(raw_ostream &OS, bool IsVerbose, bool SkipOpers,
+                         bool SkipDebugLoc, const TargetInstrInfo *TII) const {
   const Module *M = nullptr;
   const Function *F = nullptr;
   if (const MachineFunction *MF = getMFIfAvailable(*this)) {
     F = &MF->getFunction();
     M = F->getParent();
   }
 
   ModuleSlotTracker MST(M);
   if (F)
     MST.incorporateFunction(*F);
-  print(OS, MST, SkipOpers, SkipDebugLoc, TII);
+  print(OS, MST, IsVerbose, SkipOpers, SkipDebugLoc, TII);
 }
 
 void MachineInstr::print(raw_ostream &OS, ModuleSlotTracker &MST,
-                         bool SkipOpers, bool SkipDebugLoc,
+                         bool IsVerbose, bool SkipOpers, bool SkipDebugLoc,
                          const TargetInstrInfo *TII) const {
   // We can be a bit tidier if we know the MachineFunction.
   const MachineFunction *MF = nullptr;
   const TargetRegisterInfo *TRI = nullptr;
   const MachineRegisterInfo *MRI = nullptr;
   const TargetIntrinsicInfo *IntrinsicInfo = nullptr;
   tryToGetTargetInfo(*this, TRI, MRI, IntrinsicInfo, TII);
 
while (StartOp < e) {
     if (!MO.isReg() || !MO.isDef() || MO.isImplicit())
       break;
 
     if (StartOp != 0)
       OS << ", ";
 
     LLT TypeToPrint = MRI ? getTypeToPrint(StartOp, PrintedTypes, *MRI) : LLT{};
     unsigned TiedOperandIdx = getTiedOperandIdx(StartOp);
-    MO.print(OS, MST, TypeToPrint, /*PrintDef=*/false, ShouldPrintRegisterTies,
-             TiedOperandIdx, TRI, IntrinsicInfo);
+    MO.print(OS, MST, TypeToPrint, /*PrintDef=*/false, IsVerbose,
+             ShouldPrintRegisterTies, TiedOperandIdx, TRI, IntrinsicInfo);
     ++StartOp;
   }
 
   if (StartOp != 0)
     OS << " = ";
 
   if (getFlag(MachineInstr::FrameSetup))
     OS << "frame-setup ";
void MachineInstr::print(raw_ostream &OS, ModuleSlotTracker &MST,
   unsigned AsmOpCount = 0;
 
   if (isInlineAsm() && e >= InlineAsm::MIOp_FirstOperand) {
     // Print asm string.
     OS << " ";
     const unsigned OpIdx = InlineAsm::MIOp_AsmString;
     LLT TypeToPrint = MRI ? getTypeToPrint(OpIdx, PrintedTypes, *MRI) : LLT{};
     unsigned TiedOperandIdx = getTiedOperandIdx(OpIdx);
-    getOperand(OpIdx).print(OS, MST, TypeToPrint, /*PrintDef=*/true,
+    getOperand(OpIdx).print(OS, MST, TypeToPrint, /*PrintDef=*/true, IsVerbose,
                             ShouldPrintRegisterTies, TiedOperandIdx, TRI,
                             IntrinsicInfo);
 
     // Print HasSideEffects, MayLoad, MayStore, IsAlignStack
     unsigned ExtraInfo = getOperand(InlineAsm::MIOp_ExtraInfo).getImm();
     if (ExtraInfo & InlineAsm::Extra_HasSideEffects)
       OS << " [sideeffect]";
     if (ExtraInfo & InlineAsm::Extra_MayLoad)
for (unsigned i = StartOp, e = getNumOperands(); i != e; ++i) {
     if (isDebugValue() && MO.isMetadata()) {
       // Pretty print DBG_VALUE instructions.
       auto *DIV = dyn_cast<DILocalVariable>(MO.getMetadata());
       if (DIV && !DIV->getName().empty())
         OS << "!\"" << DIV->getName() << '\"';
       else {
         LLT TypeToPrint = MRI ? getTypeToPrint(i, PrintedTypes, *MRI) : LLT{};
         unsigned TiedOperandIdx = getTiedOperandIdx(i);
-        MO.print(OS, MST, TypeToPrint, /*PrintDef=*/true,
+        MO.print(OS, MST, TypeToPrint, /*PrintDef=*/true, IsVerbose,
                  ShouldPrintRegisterTies, TiedOperandIdx, TRI, IntrinsicInfo);
       }
     } else if (i == AsmDescOp && MO.isImm()) {
       // Pretty print the inline asm operand descriptor.
       OS << '$' << AsmOpCount++;
       unsigned Flag = MO.getImm();
       switch (InlineAsm::getKind(Flag)) {
       case InlineAsm::Kind_RegUse:             OS << ":[reguse"; break;
if (isDebugValue() && MO.isMetadata()) {
       // Compute the index of the next operand descriptor.
       AsmDescOp += 1 + InlineAsm::getNumOperandRegisters(Flag);
     } else {
       LLT TypeToPrint = MRI ? getTypeToPrint(i, PrintedTypes, *MRI) : LLT{};
       unsigned TiedOperandIdx = getTiedOperandIdx(i);
       if (MO.isImm() && isOperandSubregIdx(i))
         MachineOperand::printSubRegIdx(OS, MO.getImm(), TRI);
       else
-        MO.print(OS, MST, TypeToPrint, /*PrintDef=*/true,
+        MO.print(OS, MST, TypeToPrint, /*PrintDef=*/true, IsVerbose,
                  ShouldPrintRegisterTies, TiedOperandIdx, TRI, IntrinsicInfo);
     }
   }
 
   bool HaveSemi = false;
   if (!memoperands_empty()) {
     if (!HaveSemi) {
       OS << ";";

llvm/trunk/lib/CodeGen/MachineOperand.cpp

default:
     break;
   }
 }
 
 void MachineOperand::print(raw_ostream &OS, const TargetRegisterInfo *TRI,
                            const TargetIntrinsicInfo *IntrinsicInfo) const {
   tryToGetTargetInfo(*this, TRI, IntrinsicInfo);
   ModuleSlotTracker DummyMST(nullptr);
-  print(OS, DummyMST, LLT{}, /*PrintDef=*/false,
+  print(OS, DummyMST, LLT{}, /*PrintDef=*/false, /*IsVerbose=*/true,
         /*ShouldPrintRegisterTies=*/true,
         /*TiedOperandIdx=*/0, TRI, IntrinsicInfo);
 }
 
 void MachineOperand::print(raw_ostream &OS, ModuleSlotTracker &MST,
-                           LLT TypeToPrint, bool PrintDef,
+                           LLT TypeToPrint, bool PrintDef, bool IsVerbose,
                            bool ShouldPrintRegisterTies,
                            unsigned TiedOperandIdx,
                            const TargetRegisterInfo *TRI,
                            const TargetIntrinsicInfo *IntrinsicInfo) const {
   printTargetFlags(OS, *this);
   switch (getType()) {
   case MachineOperand::MO_Register: {
     unsigned Reg = getReg();
if (unsigned SubReg = getSubReg()) {
         OS << '.' << TRI->getSubRegIndexName(SubReg);
       else
         OS << ".subreg" << SubReg;
     }
     // Print the register class / bank.
     if (TargetRegisterInfo::isVirtualRegister(Reg)) {
       if (const MachineFunction *MF = getMFIfAvailable(*this)) {
         const MachineRegisterInfo &MRI = MF->getRegInfo();
-        if (!PrintDef || MRI.def_empty(Reg)) {
+        if (IsVerbose || !PrintDef || MRI.def_empty(Reg)) {
           OS << ':';
           OS << printRegClassOrBank(Reg, MRI, TRI);
         }
       }
     }
     // Print ties.
     if (ShouldPrintRegisterTies && isTied() && !isDef())
       OS << "(tied-def " << TiedOperandIdx << ")";

llvm/trunk/lib/CodeGen/MachineOptimizationRemarkEmitter.cpp

 using namespace llvm;
 
 DiagnosticInfoMIROptimization::MachineArgument::MachineArgument(
     StringRef MKey, const MachineInstr &MI)
     : Argument() {
   Key = MKey;
 
   raw_string_ostream OS(Val);
-  MI.print(OS, /*SkipOpers=*/false, /*SkipDebugLoc=*/true);
+  MI.print(OS, /*IsVerbose=*/true, /*SkipOpers=*/false, /*SkipDebugLoc=*/true);
 }
 
 Optional<uint64_t>
 MachineOptimizationRemarkEmitter::computeHotness(const MachineBasicBlock &MBB) {
   if (!MBFI)
     return None;
 
   return MBFI->getBlockProfileCount(&MBB);

llvm/trunk/test/CodeGen/AArch64/GlobalISel/arm64-fallback.ll

 ; FALLBACK-WITH-REPORT-OUT: fmov d0, #1.0
 define [1 x double] @constant() {
   ret [1 x double] [double 1.0]
 }
 
   ; The key problem here is that we may fail to create an MBB referenced by a
   ; PHI. If so, we cannot complete the G_PHI and mustn't try or bad things
   ; happen.
-; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: cannot select: G_STORE %6(s32), %2(p0); mem:ST4[%addr] (in function: pending_phis)
+; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: cannot select: G_STORE %6:gpr(s32), %2:gpr(p0); mem:ST4[%addr] (in function: pending_phis)
 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for pending_phis
 ; FALLBACK-WITH-REPORT-OUT-LABEL: pending_phis:
 define i32 @pending_phis(i1 %tst, i32 %val, i32* %addr) {
   br i1 %tst, label %true, label %false
 
 end:
   %res = phi i32 [%val, %true], [42, %false]
   ret i32 %res
 
 true:
   store atomic i32 42, i32* %addr seq_cst, align 4
   br label %end
 
 false:
   br label %end
 
 }
 
   ; General legalizer inability to handle types whose size wasn't a power of 2.
-; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %1(s42), %0(p0); mem:ST6[%addr](align=8) (in function: odd_type)
+; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %1:_(s42), %0:_(p0); mem:ST6[%addr](align=8) (in function: odd_type)
 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for odd_type
 ; FALLBACK-WITH-REPORT-OUT-LABEL: odd_type:
 define void @odd_type(i42* %addr) {
   %val42 = load i42, i42* %addr
   store i42 %val42, i42* %addr
   ret void
 }
 
-; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %1(<7 x s32>), %0(p0); mem:ST28[%addr](align=32) (in function: odd_vector)
+; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %1:_(<7 x s32>), %0:_(p0); mem:ST28[%addr](align=32) (in function: odd_vector)
 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for odd_vector
 ; FALLBACK-WITH-REPORT-OUT-LABEL: odd_vector:
 define void @odd_vector(<7 x i32>* %addr) {
   %vec = load <7 x i32>, <7 x i32>* %addr
   store <7 x i32> %vec, <7 x i32>* %addr
   ret void
 }
 
   ; AArch64 was asserting instead of returning an invalid mapping for unknown
   ; sizes.
 ; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to translate instruction: ret: '  ret i128 undef' (in function: sequence_sizes)
 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for sequence_sizes
 ; FALLBACK-WITH-REPORT-LABEL: sequence_sizes:
 define i128 @sequence_sizes([8 x i8] %in) {
   ret i128 undef
 }
 
 ; Just to make sure we don't accidentally emit a normal load/store.
-; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: cannot select: %2:gpr(s64) = G_LOAD %0(p0); mem:LD8[%addr] (in function: atomic_ops)
+; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: cannot select: %2:gpr(s64) = G_LOAD %0:gpr(p0); mem:LD8[%addr] (in function: atomic_ops)
 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for atomic_ops
 ; FALLBACK-WITH-REPORT-LABEL: atomic_ops:
 define i64 @atomic_ops(i64* %addr) {
   store atomic i64 0, i64* %addr unordered, align 8
   %res = load atomic i64, i64* %addr seq_cst, align 8
   ret i64 %res
 }
 

 ; Check that we fallback on invoke translation failures.
 ; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: %0:_(s128) = G_FCONSTANT fp128 0xL00000000000000004000000000000000
 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for test_quad_dump
 ; FALLBACK-WITH-REPORT-OUT-LABEL: test_quad_dump:
 define fp128 @test_quad_dump() {
   ret fp128 0xL00000000000000004000000000000000
 }
 
-; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: %0:_(p0) = G_EXTRACT_VECTOR_ELT %1(<2 x p0>), %2(s32) (in function: vector_of_pointers_extractelement)
+; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: %0:_(p0) = G_EXTRACT_VECTOR_ELT %1:_(<2 x p0>), %2:_(s32) (in function: vector_of_pointers_extractelement)
 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for vector_of_pointers_extractelement
 ; FALLBACK-WITH-REPORT-OUT-LABEL: vector_of_pointers_extractelement:
 @var = global <2 x i16*> zeroinitializer
 define void @vector_of_pointers_extractelement() {
   br label %end
 
 block:
   %dummy = extractelement <2 x i16*> %vec, i32 0
   store i16* %dummy, i16** undef
   ret void
 
 end:
   %vec = load <2 x i16*>, <2 x i16*>* undef
   br label %block
 }
 
-; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %0(<2 x p0>), %4(p0); mem:ST16[undef] (in function: vector_of_pointers_insertelement)
+; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %0:_(<2 x p0>), %4:_(p0); mem:ST16[undef] (in function: vector_of_pointers_insertelement)
 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for vector_of_pointers_insertelement
 ; FALLBACK-WITH-REPORT-OUT-LABEL: vector_of_pointers_insertelement:
 define void @vector_of_pointers_insertelement() {
   br label %end
 
 block:
   %dummy = insertelement <2 x i16*> %vec, i16* null, i32 0
   store <2 x i16*> %dummy, <2 x i16*>* undef
   ret void
 
 end:
   %vec = load <2 x i16*>, <2 x i16*>* undef
   br label %block
 }
 
-; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %1(s96), %3(p0); mem:ST12[undef](align=4) (in function: nonpow2_insertvalue_narrowing)
+; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %1:_(s96), %3:_(p0); mem:ST12[undef](align=4) (in function: nonpow2_insertvalue_narrowing)
 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for nonpow2_insertvalue_narrowing
 ; FALLBACK-WITH-REPORT-OUT-LABEL: nonpow2_insertvalue_narrowing:
 %struct96 = type { float, float, float }
 define void @nonpow2_insertvalue_narrowing(float %a) {
   %dummy = insertvalue %struct96 undef, float %a, 0
   store %struct96 %dummy, %struct96* undef
   ret void
 }

 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for nonpow2_load_narrowing
 ; FALLBACK-WITH-REPORT-OUT-LABEL: nonpow2_load_narrowing:
 define void @nonpow2_load_narrowing() {
   %dummy = load i96, i96* undef
   store i96 %dummy, i96* undef
   ret void
 }
 
-; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %3(s96), %0(p0); mem:ST12[%c](align=16) (in function: nonpow2_store_narrowing
+; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %3:_(s96), %0:_(p0); mem:ST12[%c](align=16) (in function: nonpow2_store_narrowing
 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for nonpow2_store_narrowing
 ; FALLBACK-WITH-REPORT-OUT-LABEL: nonpow2_store_narrowing:
 define void @nonpow2_store_narrowing(i96* %c) {
   %a = add i128 undef, undef
   %b = trunc i128 %a to i96
   store i96 %b, i96* %c
   ret void
 }
 
-; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %0(s96), %1(p0); mem:ST12[undef](align=16) (in function: nonpow2_constant_narrowing)
+; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %0:_(s96), %1:_(p0); mem:ST12[undef](align=16) (in function: nonpow2_constant_narrowing)
 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for nonpow2_constant_narrowing
 ; FALLBACK-WITH-REPORT-OUT-LABEL: nonpow2_constant_narrowing:
 define void @nonpow2_constant_narrowing() {
   store i96 0, i96* undef
   ret void
 }
 
 ; Currently can't handle vector lengths that aren't an exact multiple of
 ; natively supported vector lengths. Test that the fall-back works for those.
-; FALLBACK-WITH-REPORT-ERR-G_IMPLICIT_DEF-LEGALIZABLE: (FIXME: this is what is expected once we can legalize non-pow-of-2 G_IMPLICIT_DEF) remark: <unknown>:0:0: unable to legalize instruction: %1(<7 x s64>) = G_ADD %0, %0; (in function: nonpow2_vector_add_fewerelements
-; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: %2:_(s64) = G_EXTRACT_VECTOR_ELT %1(<7 x s64>), %3(s64) (in function: nonpow2_vector_add_fewerelements)
+; FALLBACK-WITH-REPORT-ERR-G_IMPLICIT_DEF-LEGALIZABLE: (FIXME: this is what is expected once we can legalize non-pow-of-2 G_IMPLICIT_DEF) remark: <unknown>:0:0: unable to legalize instruction: %1:_(<7 x s64>) = G_ADD %0, %0; (in function: nonpow2_vector_add_fewerelements
+; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: %2:_(s64) = G_EXTRACT_VECTOR_ELT %1:_(<7 x s64>), %3:_(s64) (in function: nonpow2_vector_add_fewerelements)
 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for nonpow2_vector_add_fewerelements
 ; FALLBACK-WITH-REPORT-OUT-LABEL: nonpow2_vector_add_fewerelements:
 define void @nonpow2_vector_add_fewerelements() {
   %dummy = add <7 x i64> undef, undef
   %ex = extractelement <7 x i64> %dummy, i64 0
   store i64 %ex, i64* undef
   ret void
 }

llvm/trunk/test/CodeGen/AArch64/aarch64-stp-cluster.ll

 ; REQUIRES: asserts
 ; RUN: llc < %s -mtriple=arm64-linux-gnu -mcpu=cortex-a57 -verify-misched -debug-only=machine-scheduler -aarch64-enable-stp-suppress=false -o - 2>&1 > /dev/null | FileCheck %s
 
 ; CHECK: ********** MI Scheduling **********
 ; CHECK-LABEL: stp_i64_scale:%bb.0
 ; CHECK:Cluster ld/st SU(4) - SU(3)
 ; CHECK:Cluster ld/st SU(2) - SU(5)
-; CHECK:SU(4):   STRXui %1, %0, 1
-; CHECK:SU(3):   STRXui %1, %0, 2
-; CHECK:SU(2):   STRXui %1, %0, 3
-; CHECK:SU(5):   STRXui %1, %0, 4
+; CHECK:SU(4):   STRXui %1:gpr64, %0:gpr64common, 1
+; CHECK:SU(3):   STRXui %1:gpr64, %0:gpr64common, 2
+; CHECK:SU(2):   STRXui %1:gpr64, %0:gpr64common, 3
+; CHECK:SU(5):   STRXui %1:gpr64, %0:gpr64common, 4
 define i64 @stp_i64_scale(i64* nocapture %P, i64 %v) {
 entry:
   %arrayidx = getelementptr inbounds i64, i64* %P, i64 3
   store i64 %v, i64* %arrayidx
   %arrayidx1 = getelementptr inbounds i64, i64* %P, i64 2
   store i64 %v, i64* %arrayidx1
   %arrayidx2 = getelementptr inbounds i64, i64* %P, i64 1
   store i64 %v, i64* %arrayidx2
   %arrayidx3 = getelementptr inbounds i64, i64* %P, i64 4
   store i64 %v, i64* %arrayidx3
   ret i64 %v
 }
 
 ; CHECK: ********** MI Scheduling **********
 ; CHECK-LABEL: stp_i32_scale:%bb.0
 ; CHECK:Cluster ld/st SU(4) - SU(3)
 ; CHECK:Cluster ld/st SU(2) - SU(5)
-; CHECK:SU(4):   STRWui %1, %0, 1
-; CHECK:SU(3):   STRWui %1, %0, 2
-; CHECK:SU(2):   STRWui %1, %0, 3
-; CHECK:SU(5):   STRWui %1, %0, 4
+; CHECK:SU(4):   STRWui %1:gpr32, %0:gpr64common, 1
+; CHECK:SU(3):   STRWui %1:gpr32, %0:gpr64common, 2
+; CHECK:SU(2):   STRWui %1:gpr32, %0:gpr64common, 3
+; CHECK:SU(5):   STRWui %1:gpr32, %0:gpr64common, 4
 define i32 @stp_i32_scale(i32* nocapture %P, i32 %v) {
 entry:
   %arrayidx = getelementptr inbounds i32, i32* %P, i32 3
   store i32 %v, i32* %arrayidx
   %arrayidx1 = getelementptr inbounds i32, i32* %P, i32 2
   store i32 %v, i32* %arrayidx1
   %arrayidx2 = getelementptr inbounds i32, i32* %P, i32 1
   store i32 %v, i32* %arrayidx2
   %arrayidx3 = getelementptr inbounds i32, i32* %P, i32 4
   store i32 %v, i32* %arrayidx3
   ret i32 %v
 }
 
 ; CHECK:********** MI Scheduling **********
 ; CHECK-LABEL:stp_i64_unscale:%bb.0 entry
 ; CHECK:Cluster ld/st SU(5) - SU(2)
 ; CHECK:Cluster ld/st SU(4) - SU(3)
-; CHECK:SU(5):   STURXi %1, %0, -32
-; CHECK:SU(2):   STURXi %1, %0, -24
-; CHECK:SU(4):   STURXi %1, %0, -16
-; CHECK:SU(3):   STURXi %1, %0, -8
+; CHECK:SU(5):   STURXi %1:gpr64, %0:gpr64common, -32
+; CHECK:SU(2):   STURXi %1:gpr64, %0:gpr64common, -24
+; CHECK:SU(4):   STURXi %1:gpr64, %0:gpr64common, -16
+; CHECK:SU(3):   STURXi %1:gpr64, %0:gpr64common, -8
 define void @stp_i64_unscale(i64* nocapture %P, i64 %v) #0 {
 entry:
   %arrayidx = getelementptr inbounds i64, i64* %P, i64 -3
   store i64 %v, i64* %arrayidx
   %arrayidx1 = getelementptr inbounds i64, i64* %P, i64 -1
   store i64 %v, i64* %arrayidx1
   %arrayidx2 = getelementptr inbounds i64, i64* %P, i64 -2
   store i64 %v, i64* %arrayidx2
   %arrayidx3 = getelementptr inbounds i64, i64* %P, i64 -4
   store i64 %v, i64* %arrayidx3
   ret void
 }
 
 ; CHECK:********** MI Scheduling **********
 ; CHECK-LABEL:stp_i32_unscale:%bb.0 entry
 ; CHECK:Cluster ld/st SU(5) - SU(2)
 ; CHECK:Cluster ld/st SU(4) - SU(3)
-; CHECK:SU(5):   STURWi %1, %0, -16
-; CHECK:SU(2):   STURWi %1, %0, -12
-; CHECK:SU(4):   STURWi %1, %0, -8
-; CHECK:SU(3):   STURWi %1, %0, -4
+; CHECK:SU(5):   STURWi %1:gpr32, %0:gpr64common, -16
+; CHECK:SU(2):   STURWi %1:gpr32, %0:gpr64common, -12
+; CHECK:SU(4):   STURWi %1:gpr32, %0:gpr64common, -8
+; CHECK:SU(3):   STURWi %1:gpr32, %0:gpr64common, -4
 define void @stp_i32_unscale(i32* nocapture %P, i32 %v) #0 {
 entry:
   %arrayidx = getelementptr inbounds i32, i32* %P, i32 -3
   store i32 %v, i32* %arrayidx
   %arrayidx1 = getelementptr inbounds i32, i32* %P, i32 -1
   store i32 %v, i32* %arrayidx1
   %arrayidx2 = getelementptr inbounds i32, i32* %P, i32 -2
   store i32 %v, i32* %arrayidx2
   %arrayidx3 = getelementptr inbounds i32, i32* %P, i32 -4
   store i32 %v, i32* %arrayidx3
   ret void
 }
 
 ; CHECK:********** MI Scheduling **********
 ; CHECK-LABEL:stp_double:%bb.0
 ; CHECK:Cluster ld/st SU(3) - SU(4)
 ; CHECK:Cluster ld/st SU(2) - SU(5)
-; CHECK:SU(3):   STRDui %1, %0, 1
-; CHECK:SU(4):   STRDui %1, %0, 2
-; CHECK:SU(2):   STRDui %1, %0, 3
-; CHECK:SU(5):   STRDui %1, %0, 4
+; CHECK:SU(3):   STRDui %1:fpr64, %0:gpr64common, 1
+; CHECK:SU(4):   STRDui %1:fpr64, %0:gpr64common, 2
+; CHECK:SU(2):   STRDui %1:fpr64, %0:gpr64common, 3
+; CHECK:SU(5):   STRDui %1:fpr64, %0:gpr64common, 4
 define void @stp_double(double* nocapture %P, double %v)  {
 entry:
   %arrayidx = getelementptr inbounds double, double* %P, i64 3
   store double %v, double* %arrayidx
   %arrayidx1 = getelementptr inbounds double, double* %P, i64 1
   store double %v, double* %arrayidx1
   %arrayidx2 = getelementptr inbounds double, double* %P, i64 2
   store double %v, double* %arrayidx2
   %arrayidx3 = getelementptr inbounds double, double* %P, i64 4
   store double %v, double* %arrayidx3
   ret void
 }
 
 ; CHECK:********** MI Scheduling **********
 ; CHECK-LABEL:stp_float:%bb.0
 ; CHECK:Cluster ld/st SU(3) - SU(4)
 ; CHECK:Cluster ld/st SU(2) - SU(5)
-; CHECK:SU(3):   STRSui %1, %0, 1
-; CHECK:SU(4):   STRSui %1, %0, 2
-; CHECK:SU(2):   STRSui %1, %0, 3
-; CHECK:SU(5):   STRSui %1, %0, 4
+; CHECK:SU(3):   STRSui %1:fpr32, %0:gpr64common, 1
+; CHECK:SU(4):   STRSui %1:fpr32, %0:gpr64common, 2
+; CHECK:SU(2):   STRSui %1:fpr32, %0:gpr64common, 3
+; CHECK:SU(5):   STRSui %1:fpr32, %0:gpr64common, 4
 define void @stp_float(float* nocapture %P, float %v)  {
 entry:
   %arrayidx = getelementptr inbounds float, float* %P, i64 3
   store float %v, float* %arrayidx
   %arrayidx1 = getelementptr inbounds float, float* %P, i64 1
   store float %v, float* %arrayidx1
   %arrayidx2 = getelementptr inbounds float, float* %P, i64 2
   store float %v, float* %arrayidx2
   %arrayidx3 = getelementptr inbounds float, float* %P, i64 4
   store float %v, float* %arrayidx3
   ret void
 }
 
 ; CHECK: ********** MI Scheduling **********
 ; CHECK-LABEL: stp_volatile:%bb.0
 ; CHECK-NOT: Cluster ld/st
-; CHECK:SU(2):   STRXui %1, %0, 3; mem:Volatile
-; CHECK:SU(3):   STRXui %1, %0, 2; mem:Volatile
-; CHECK:SU(4):   STRXui %1, %0, 1; mem:Volatile
-; CHECK:SU(5):   STRXui %1, %0, 4; mem:Volatile
+; CHECK:SU(2):   STRXui %1:gpr64, %0:gpr64common, 3; mem:Volatile
+; CHECK:SU(3):   STRXui %1:gpr64, %0:gpr64common, 2; mem:Volatile
+; CHECK:SU(4):   STRXui %1:gpr64, %0:gpr64common, 1; mem:Volatile
+; CHECK:SU(5):   STRXui %1:gpr64, %0:gpr64common, 4; mem:Volatile
 define i64 @stp_volatile(i64* nocapture %P, i64 %v) {
 entry:
   %arrayidx = getelementptr inbounds i64, i64* %P, i64 3
   store volatile i64 %v, i64* %arrayidx
   %arrayidx1 = getelementptr inbounds i64, i64* %P, i64 2
   store volatile i64 %v, i64* %arrayidx1
   %arrayidx2 = getelementptr inbounds i64, i64* %P, i64 1
   store volatile i64 %v, i64* %arrayidx2
   %arrayidx3 = getelementptr inbounds i64, i64* %P, i64 4
   store volatile i64 %v, i64* %arrayidx3
   ret i64 %v
 }
 

llvm/trunk/test/CodeGen/AArch64/arm64-misched-forwarding-A53.ll

 ; REQUIRES: asserts
 ; RUN: llc < %s -mtriple=arm64-linux-gnu -mcpu=cortex-a53 -pre-RA-sched=source -enable-misched -verify-misched -debug-only=machine-scheduler -o - 2>&1 > /dev/null | FileCheck %s
 ;
 ; For Cortex-A53, shiftable operands that are not actually shifted
 ; are not needed for an additional two cycles.
 ;
 ; CHECK: ********** MI Scheduling **********
 ; CHECK: shiftable
-; CHECK: SU(2):   %2:gpr64common = SUBXri %1, 20, 0
+; CHECK: SU(2):   %2:gpr64common = SUBXri %1:gpr64common, 20, 0
 ; CHECK:   Successors:
 ; CHECK-NEXT:    SU(4): Data Latency=1 Reg=%2
 ; CHECK-NEXT:    SU(3): Data Latency=2 Reg=%2
 ; CHECK: ********** INTERVALS **********
 define i64 @shiftable(i64 %A, i64 %B) {
         %tmp0 = sub i64 %B, 20
         %tmp1 = shl i64 %tmp0, 5;
         %tmp2 = add i64 %A, %tmp1;
         %tmp3 = add i64 %A, %tmp0
         %tmp4 = mul i64 %tmp2, %tmp3
 
         ret i64 %tmp4
 }

llvm/trunk/test/CodeGen/AArch64/arm64-misched-memdep-bug.ll

 ; REQUIRES: asserts
 ; RUN: llc < %s -mtriple=arm64-linux-gnu -mcpu=cortex-a57 -enable-misched -verify-misched -debug-only=machine-scheduler -o - 2>&1 > /dev/null | FileCheck %s
 ;
 ; Test for bug in misched memory dependency calculation.
 ;
 ; CHECK: ********** MI Scheduling **********
 ; CHECK: misched_bug:%bb.0 entry
-; CHECK: SU(2):   %2:gpr32 = LDRWui %0, 1; mem:LD4[%ptr1_plus1]
+; CHECK: SU(2):   %2:gpr32 = LDRWui %0:gpr64common, 1; mem:LD4[%ptr1_plus1]
 ; CHECK:   Successors:
 ; CHECK-NEXT:    SU(5): Data Latency=4 Reg=%2
 ; CHECK-NEXT:    SU(4): Ord  Latency=0
-; CHECK: SU(3):   STRWui %wzr, %0, 0; mem:ST4[%ptr1]
+; CHECK: SU(3):   STRWui %wzr, %0:gpr64common, 0; mem:ST4[%ptr1]
 ; CHECK:   Successors:
 ; CHECK: SU(4): Ord  Latency=0
-; CHECK: SU(4):   STRWui %wzr, %1, 0; mem:ST4[%ptr2]
+; CHECK: SU(4):   STRWui %wzr, %1:gpr64common, 0; mem:ST4[%ptr2]
 ; CHECK: SU(5):   %w0 = COPY %2
 ; CHECK: ** ScheduleDAGMI::schedule picking next node
 define i32 @misched_bug(i32* %ptr1, i32* %ptr2) {
 entry:
   %ptr1_plus1 = getelementptr inbounds i32, i32* %ptr1, i64 1
   %val1 = load i32, i32* %ptr1_plus1, align 4
   store i32 0, i32* %ptr1, align 4
   store i32 0, i32* %ptr2, align 4
   ret i32 %val1
 }

llvm/trunk/test/CodeGen/ARM/misched-int-basic-thumb2.mir

--- |
   }
 #
 # CHECK:       ********** MI Scheduling **********
 # CHECK:       SU(2):   %2:rgpr = t2MOVi32imm @g1
 # CHECK_A9:    Latency    : 2
 # CHECK_SWIFT: Latency    : 2
 # CHECK_R52:   Latency    : 2
 #
-# CHECK:       SU(3):   %3:rgpr = t2LDRi12 %2, 0, 14, %noreg; mem:LD4[@g1](dereferenceable)
+# CHECK:       SU(3):   %3:rgpr = t2LDRi12 %2:rgpr, 0, 14, %noreg; mem:LD4[@g1](dereferenceable)
 # CHECK_A9:    Latency    : 1
 # CHECK_SWIFT: Latency    : 3
 # CHECK_R52:   Latency    : 4
 #
-# CHECK :      SU(6):   %6 = t2ADDrr %3, %3, 14, %noreg, %noreg
+# CHECK :      SU(6):   %6 = t2ADDrr %3:rgpr, %3:rgpr, 14, %noreg, %noreg
 # CHECK_A9:    Latency    : 1
 # CHECK_SWIFT: Latency    : 1
 # CHECK_R52:   Latency    : 3
 
-# CHECK:       SU(7):   %7:rgpr = t2SDIV %6, %5, 14, %noreg
+# CHECK:       SU(7):   %7:rgpr = t2SDIV %6:rgpr, %5:rgpr, 14, %noreg
 # CHECK_A9:    Latency    : 0
 # CHECK_SWIFT: Latency    : 14
 # CHECK_R52:   Latency    : 8
 
-# CHECK:       SU(8):   t2STRi12 %7, %2, 0, 14, %noreg; mem:ST4[@g1]
+# CHECK:       SU(8):   t2STRi12 %7:rgpr, %2:rgpr, 0, 14, %noreg; mem:ST4[@g1]
 # CHECK_A9:    Latency    : 1
 # CHECK_SWIFT: Latency    : 0
 # CHECK_R52:   Latency    : 4
 #
-# CHECK:       SU(9):   %8:rgpr = t2SMULBB %1, %1, 14, %noreg
+# CHECK:       SU(9):   %8:rgpr = t2SMULBB %1:rgpr, %1:rgpr, 14, %noreg
 # CHECK_A9:    Latency    : 2
 # CHECK_SWIFT: Latency    : 4
 # CHECK_R52:   Latency    : 4
 #
-# CHECK:       SU(10):   %9:rgpr = t2SMLABB %0, %0, %8, 14, %noreg
+# CHECK:       SU(10):   %9:rgpr = t2SMLABB %0:rgpr, %0:rgpr, %8:rgpr, 14, %noreg
 # CHECK_A9:    Latency    : 2
 # CHECK_SWIFT: Latency    : 4
 # CHECK_R52:   Latency    : 4
 #
-# CHECK:       SU(11):   %10:rgpr = t2UXTH %9, 0, 14, %noreg
+# CHECK:       SU(11):   %10:rgpr = t2UXTH %9:rgpr, 0, 14, %noreg
 # CHECK_A9:    Latency    : 1
 # CHECK_SWIFT: Latency    : 1
 # CHECK_R52:   Latency    : 3
 #
-# CHECK:       SU(12):   %11:rgpr = t2MUL %10, %7, 14, %noreg
+# CHECK:       SU(12):   %11:rgpr = t2MUL %10:rgpr, %7:rgpr, 14, %noreg
 # CHECK_A9:    Latency    : 2
 # CHECK_SWIFT: Latency    : 4
 # CHECK_R52:   Latency    : 4
 #
-# CHECK:       SU(13):   %12:rgpr = t2MLA %11, %11, %11, 14, %noreg
+# CHECK:       SU(13):   %12:rgpr = t2MLA %11:rgpr, %11:rgpr, %11:rgpr, 14, %noreg
 # CHECK_A9:    Latency    : 2
 # CHECK_SWIFT: Latency    : 4
 # CHECK_R52:   Latency    : 4
 #
-# CHECK:       SU(14):   %13:rgpr, %14:rgpr = t2UMULL %12, %12, 14, %noreg
+# CHECK:       SU(14):   %13:rgpr, %14:rgpr = t2UMULL %12:rgpr, %12:rgpr, 14, %noreg
 # CHECK_A9:    Latency    : 3
 # CHECK_SWIFT: Latency    : 5
 # CHECK_R52:   Latency    : 4
 #
-# CHECK:       SU(18):   %19:rgpr, %20:rgpr = t2UMLAL %12, %12, %19, %20, 14, %noreg
+# CHECK:       SU(18):   %19:rgpr, %20:rgpr = t2UMLAL %12:rgpr, %12:rgpr, %19:rgpr, %20:rgpr, 14, %noreg
 # CHECK_A9:    Latency    : 3
 # CHECK_SWIFT: Latency    : 7
 # CHECK_R52:   Latency    : 4
 # CHECK:  ** ScheduleDAGMILive::schedule picking next node
 ...
 ---
 name:            foo
 alignment:       1

llvm/trunk/test/CodeGen/ARM/misched-int-basic.mir

entry:
     %conv1130 = zext i32 %add10 to i64
     %mul12 = mul nuw nsw i64 %conv1130, %conv1130
     %mul13 = mul nsw i64 %mul12, %mul12
     %add14 = add nuw nsw i64 %mul13, %mul12
     ret i64 %add14
   }
 
 # CHECK:       ********** MI Scheduling **********
-# CHECK:       SU(2):   %2:gpr = SMULBB %1, %1, 14, %noreg
+# CHECK:       SU(2):   %2:gpr = SMULBB %1:gpr, %1:gpr, 14, %noreg
 # CHECK_A9:    Latency    : 2
 # CHECK_SWIFT: Latency    : 4
 # CHECK_R52:   Latency    : 4
 #
-# CHECK:       SU(3):   %3:gprnopc = SMLABB %0, %0, %2, 14, %noreg
+# CHECK:       SU(3):   %3:gprnopc = SMLABB %0:gprnopc, %0:gprnopc, %2:gpr, 14, %noreg
 # CHECK_A9:    Latency    : 2
 # CHECK_SWIFT: Latency    : 4
 # CHECK_R52:   Latency    : 4
 #
-# CHECK:       SU(4):   %4:gprnopc = UXTH %3, 0, 14, %noreg
+# CHECK:       SU(4):   %4:gprnopc = UXTH %3:gprnopc, 0, 14, %noreg
 # CHECK_A9:    Latency    : 1
 # CHECK_SWIFT: Latency    : 1
 # CHECK_R52:   Latency    : 3
 #
-# CHECK:       SU(5):   %5:gprnopc = MUL %4, %4, 14, %noreg, %noreg
+# CHECK:       SU(5):   %5:gprnopc = MUL %4:gprnopc, %4:gprnopc, 14, %noreg, %noreg
 # CHECK_A9:    Latency    : 2
 # CHECK_SWIFT: Latency    : 4
 # CHECK_R52:   Latency    : 4
 #
-# CHECK:       SU(6):   %6:gprnopc = MLA %5, %5, %5, 14, %noreg, %noreg
+# CHECK:       SU(6):   %6:gprnopc = MLA %5:gprnopc, %5:gprnopc, %5:gprnopc, 14, %noreg, %noreg
 # CHECK_A9:    Latency    : 2
 # CHECK_SWIFT: Latency    : 4
 # CHECK_R52:   Latency    : 4
 #
-# CHECK:       SU(7):   %7:gprnopc, %8:gprnopc = UMULL %6, %6, 14, %noreg, %noreg
+# CHECK:       SU(7):   %7:gprnopc, %8:gprnopc = UMULL %6:gprnopc, %6:gprnopc, 14, %noreg, %noreg
 # CHECK_A9:    Latency    : 3
 # CHECK_SWIFT: Latency    : 5
 # CHECK_R52:   Latency    : 4
 #
-# CHECK:       SU(11):   %13:gpr, %14:gprnopc = UMLAL %6, %6, %13, %14, 14, %noreg, %noreg
+# CHECK:       SU(11):   %13:gpr, %14:gprnopc = UMLAL %6:gprnopc, %6:gprnopc, %13:gpr, %14:gprnopc, 14, %noreg, %noreg
 # CHECK_SWIFT: Latency    : 7
 # CHECK_A9:    Latency    : 3
 # CHECK_R52:   Latency    : 4
 # CHECK:  ** ScheduleDAGMILive::schedule picking next node
 ...
 ---
 name:            foo
 alignment:       2

llvm/trunk/test/CodeGen/ARM/single-issue-r52.mir

define <8 x i8> @foo(i8* %A) {
     %tmp3 = extractvalue %struct.__neon_int8x8x4_t %tmp1, 1
     %tmp4 = add <8 x i8> %tmp2, %tmp3
     ret <8 x i8> %tmp4
   }
   declare %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4.v8i8.p0i8(i8*, i32)
 
 # CHECK: ********** MI Scheduling **********
 # CHECK: ScheduleDAGMILive::schedule starting
-# CHECK: SU(1):   %1:qqpr = VLD4d8Pseudo %0, 8, 14, %noreg; mem:LD32[%A](align=8)
+# CHECK: SU(1):   %1:qqpr = VLD4d8Pseudo %0:gpr, 8, 14, %noreg; mem:LD32[%A](align=8)
 # CHECK: Latency            : 8
 # CHECK: Single Issue       : true;
-# CHECK: SU(2):   %4:dpr = VADDv8i8 %1.dsub_0, %1.dsub_1, 14, %noreg
+# CHECK: SU(2):   %4:dpr = VADDv8i8 %1.dsub_0:qqpr, %1.dsub_1:qqpr, 14, %noreg
 # CHECK: Latency            : 5
 # CHECK: Single Issue       : false;
-# CHECK: SU(3):   %5:gpr, %6:gpr = VMOVRRD %4, 14, %noreg
+# CHECK: SU(3):   %5:gpr, %6:gpr = VMOVRRD %4:dpr, 14, %noreg
 # CHECK: Latency            : 4
 # CHECK: Single Issue       : false;
 
 # TOPDOWN: Scheduling SU(1) %1:qqpr = VLD4d8Pseudo
 # TOPDOWN: Bump cycle to end group
 # TOPDOWN: Scheduling SU(2) %4:dpr = VADDv8i8
 
 # BOTTOMUP: Scheduling SU(2) %4:dpr = VADDv8i8

llvm/trunk/test/CodeGen/X86/GlobalISel/x86_64-fallback.ll

 ; RUN: llc -O0 -mtriple=x86_64-linux-gnu -global-isel -global-isel-abort=2 -pass-remarks-missed='gisel*' -verify-machineinstrs %s -o %t.out 2> %t.err
 ; RUN: FileCheck %s --check-prefix=FALLBACK-WITH-REPORT-OUT < %t.out
 ; RUN: FileCheck %s --check-prefix=FALLBACK-WITH-REPORT-ERR < %t.err
 ; This file checks that the fallback path to selection dag works.
 ; The test is fragile in the sense that it must be updated to expose
 ; something that fails with global-isel.
 ; When we cannot produce a test case anymore, that means we can remove
 ; the fallback path.
 
 ; Check that we fallback on invoke translation failures.
-; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %1(s80), %0(p0); mem:ST10[%ptr](align=16) (in function: test_x86_fp80_dump)
+; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %1:_(s80), %0:_(p0); mem:ST10[%ptr](align=16) (in function: test_x86_fp80_dump)
 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for test_x86_fp80_dump
 ; FALLBACK-WITH-REPORT-OUT-LABEL: test_x86_fp80_dump:
 define void @test_x86_fp80_dump(x86_fp80* %ptr){
   store x86_fp80 0xK4002A000000000000000, x86_fp80* %ptr, align 16
   ret void
 }
 
 ; Check that we fallback on byVal argument

llvm/trunk/test/CodeGen/X86/misched-copy.ll

 ; REQUIRES: asserts
 ; RUN: llc < %s -verify-machineinstrs -mtriple=i686-- -mcpu=core2 -pre-RA-sched=source -enable-misched -verify-misched -debug-only=machine-scheduler -o - 2>&1 > /dev/null | FileCheck %s
 ;
 ; Test scheduling of copy instructions.
 ;
 ; Argument copies should be hoisted to the top of the block.
 ; Return copies should be sunk to the end.
 ; MUL_HiLo PhysReg use copies should be just above the mul.
 ; MUL_HiLo PhysReg def copies should be just below the mul.
 ;
 ; CHECK: *** Final schedule for %bb.1 ***
 ; CHECK:      %eax = COPY
-; CHECK-NEXT: MUL32r %{{[0-9]+}}, implicit-def %eax, implicit-def %edx, implicit-def dead %eflags, implicit %eax
+; CHECK-NEXT: MUL32r %{{[0-9]+}}:gr32, implicit-def %eax, implicit-def %edx, implicit-def dead %eflags, implicit %eax
 ; CHECK-NEXT: COPY %e{{[ad]}}x
 ; CHECK-NEXT: COPY %e{{[ad]}}x
 ; CHECK:      DIVSSrm
 define i64 @mulhoist(i32 %a, i32 %b) #0 {
 entry:
   br label %body
 
 body:

llvm/trunk/unittests/CodeGen/MachineOperandTest.cpp

TEST(MachineOperandTest, PrintSubRegIndex) {
   // MachineOperand.
   ASSERT_TRUE(MO.isImm());
   ASSERT_TRUE(MO.getImm() == 3);
 
   // Print a MachineOperand containing a SubRegIdx. Here we check that without a
   // TRI and IntrinsicInfo we can print the operand as a subreg index.
   std::string str;
   raw_string_ostream OS(str);
-  ModuleSlotTracker DummyMST(nullptr);
   MachineOperand::printSubRegIdx(OS, MO.getImm(), nullptr);
   ASSERT_TRUE(OS.str() == "%subreg.3");
 }
 
 TEST(MachineOperandTest, PrintCPI) {
   // Create a MachineOperand with a constant pool index and print it.
   MachineOperand MO = MachineOperand::CreateCPI(0, 8);
 
TEST(MachineOperandTest, PrintRegisterLiveOut) {
   MO.print(OS, /*TRI=*/nullptr, /*IntrinsicInfo=*/nullptr);
   ASSERT_TRUE(OS.str() == "liveout(<unknown>)");
 }
 
 TEST(MachineOperandTest, PrintMetadata) {
   LLVMContext Ctx;
   Module M("MachineOperandMDNodeTest", Ctx);
   NamedMDNode *MD = M.getOrInsertNamedMetadata("namedmd");
-  ModuleSlotTracker DummyMST(&M);
+  ModuleSlotTracker MST(&M);
   Metadata *MDS = MDString::get(Ctx, "foo");
   MDNode *Node = MDNode::get(Ctx, MDS);
   MD->addOperand(Node);
 
   // Create a MachineOperand with a metadata and print it.
   MachineOperand MO = MachineOperand::CreateMetadata(Node);
 
   // Checking some preconditions on the newly created
   // MachineOperand.
   ASSERT_TRUE(MO.isMetadata());
   ASSERT_TRUE(MO.getMetadata() == Node);
 
   std::string str;
   // Print a MachineOperand containing a metadata node.
   raw_string_ostream OS(str);
-  MO.print(OS, DummyMST, LLT{}, false, false, 0, /*TRI=*/nullptr,
+  MO.print(OS, MST, LLT{}, /*PrintDef=*/false, /*IsVerbose=*/false,
+           /*ShouldPrintRegisterTies=*/false, 0, /*TRI=*/nullptr,
            /*IntrinsicInfo=*/nullptr);
   ASSERT_TRUE(OS.str() == "!0");
 }
 
 TEST(MachineOperandTest, PrintMCSymbol) {
   MCAsmInfo MAI;
   MCContext Ctx(&MAI, /*MRI=*/nullptr, /*MOFI=*/nullptr);
   MCSymbol *Sym = Ctx.getOrCreateSymbol("foo");