[AArch64][GlobalISel] Select patterns which use shifted register operands

[paquette]

Summary

This adds GlobalISel equivalents for the following from AArch64InstrFormats:

• arith_shifted_reg32
• arith_shifted_reg64

And partial support for

• logical_shifted_reg32
• logical_shifted_reg32

The only thing missing for the logical cases is support for rotates. Other than the missing support, the transformation is identical for the arithmetic shifted register and the logical shifted register.

Lots of tests here:

• Add select-arith-shifted-reg.mir to show that we correctly select add and

sub instructions which use this pattern.

• Add select-logical-shifted-reg.mir to cover patterns which are not shared

between the arithmetic and logical cases.

• Update addsub-shifted.ll to show that we correctly fold shifts into

adds/subs.

• Update eon.ll to show that we can select the eon instruction by folding xors.

[aemerson]

llvm/lib/Target/AArch64/AArch64InstructionSelector.cpp

4553 ↗

(On Diff #214910)

Can simplify this a bit to MRI.getType(ShiftReg).getSizeInBits();

llvm/test/CodeGen/AArch64/GlobalISel/select-arith-shifted-reg.mir

37 ↗

(On Diff #214910)

The checks here are identical to the rhs case. Should we be trying to test a less degenerate case? Like:

%0:gpr(s64) = COPY $x0
%param2:gpr(s64) = COPY $x1
%1:gpr(s64) = G_CONSTANT i64 8
%2:gpr(s64) = G_SHL %0, %1:gpr(s64)
%3:gpr(s64) = G_ADD %2, %param2:gpr(s64)

[paquette]

Improve LHS test cases and simplify NumBits calculation

[aemerson]

LGTM.

llvm/trunk/lib/Target/AArch64/AArch64InstrFormats.td

: Operand<Ty>,
       ComplexPattern<Ty, 2, "SelectArithShiftedRegister", []> {
   let PrintMethod = "printShiftedRegister";
   let MIOperandInfo = (ops regclass, !cast<Operand>("arith_shift" # width));
 }
 
 def arith_shifted_reg32 : arith_shifted_reg<i32, GPR32, 32>;
 def arith_shifted_reg64 : arith_shifted_reg<i64, GPR64, 64>;
 
+def gi_arith_shifted_reg32 :
+  GIComplexOperandMatcher<s32, "selectArithShiftedRegister">,
+  GIComplexPatternEquiv<arith_shifted_reg32>;
+
+def gi_arith_shifted_reg64 :
+  GIComplexOperandMatcher<s64, "selectArithShiftedRegister">,
+  GIComplexPatternEquiv<arith_shifted_reg64>;
+
 // An arithmetic shifter operand:
 //  {7-6} - shift type: 00 = lsl, 01 = lsr, 10 = asr, 11 = ror
 //  {5-0} - imm6
 class logical_shift<int width> : Operand<i32> {
   let PrintMethod = "printShifter";
   let ParserMatchClass = !cast<AsmOperandClass>(
                          "LogicalShifterOperand" # width);
 }
 
 def logical_shift32 : logical_shift<32>;
 def logical_shift64 : logical_shift<64>;
 
 class logical_shifted_reg<ValueType Ty, RegisterClass regclass, Operand shiftop>
     : Operand<Ty>,
       ComplexPattern<Ty, 2, "SelectLogicalShiftedRegister", []> {
   let PrintMethod = "printShiftedRegister";
   let MIOperandInfo = (ops regclass, shiftop);
 }
 
 def logical_shifted_reg32 : logical_shifted_reg<i32, GPR32, logical_shift32>;
 def logical_shifted_reg64 : logical_shifted_reg<i64, GPR64, logical_shift64>;
 
+def gi_logical_shifted_reg32 :
+  GIComplexOperandMatcher<s32, "selectLogicalShiftedRegister">,
+  GIComplexPatternEquiv<logical_shifted_reg32>;
+
+def gi_logical_shifted_reg64 :
+  GIComplexOperandMatcher<s64, "selectLogicalShiftedRegister">,
+  GIComplexPatternEquiv<logical_shifted_reg64>;
+
 // A logical vector shifter operand:
 //  {7-6} - shift type: 00 = lsl
 //  {5-0} - imm6: #0, #8, #16, or #24
 def logical_vec_shift : Operand<i32> {
   let PrintMethod = "printShifter";
   let EncoderMethod = "getVecShifterOpValue";
   let ParserMatchClass = LogicalVecShifterOperand;
 }

llvm/trunk/lib/Target/AArch64/AArch64InstructionSelector.cpp

bool isWorthFoldingIntoExtendedReg(MachineInstr &MI,
                                      const MachineRegisterInfo &MRI) const;
   ComplexRendererFns
   selectAddrModeShiftedExtendXReg(MachineOperand &Root,
                                   unsigned SizeInBytes) const;
   ComplexRendererFns selectAddrModeRegisterOffset(MachineOperand &Root) const;
   ComplexRendererFns selectAddrModeXRO(MachineOperand &Root,
                                        unsigned SizeInBytes) const;
 
+  ComplexRendererFns selectShiftedRegister(MachineOperand &Root) const;
+
+  ComplexRendererFns selectArithShiftedRegister(MachineOperand &Root) const {
+    return selectShiftedRegister(Root);
+  }
+
+  ComplexRendererFns selectLogicalShiftedRegister(MachineOperand &Root) const {
+    // TODO: selectShiftedRegister should allow for rotates on logical shifts.
+    // For now, make them the same. The only difference between the two is that
+    // logical shifts are allowed to fold in rotates. Otherwise, these are
+    // functionally the same.
+    return selectShiftedRegister(Root);
+  }
+
   void renderTruncImm(MachineInstrBuilder &MIB, const MachineInstr &MI) const;
 
   // Materialize a GlobalValue or BlockAddress using a movz+movk sequence.
   void materializeLargeCMVal(MachineInstr &I, const Value *V,
                              unsigned OpFlags) const;
 
   // Optimization methods.
   bool tryOptVectorShuffle(MachineInstr &I) const;
if (selectAddrModeUnscaled(Root, Size).hasValue())
     return None;
 
   return {{
       [=](MachineInstrBuilder &MIB) { MIB.add(Root); },
       [=](MachineInstrBuilder &MIB) { MIB.addImm(0); },
   }};
 }
 
+/// Given a shift instruction, return the correct shift type for that
+/// instruction.
+static AArch64_AM::ShiftExtendType getShiftTypeForInst(MachineInstr &MI) {
+  // TODO: Handle AArch64_AM::ROR
+  switch (MI.getOpcode()) {
+  default:
+    return AArch64_AM::InvalidShiftExtend;
+  case TargetOpcode::G_SHL:
+    return AArch64_AM::LSL;
+  case TargetOpcode::G_LSHR:
+    return AArch64_AM::LSR;
+  case TargetOpcode::G_ASHR:
+    return AArch64_AM::ASR;
+  }
+}
+
+/// Select a "shifted register" operand. If the value is not shifted, set the
+/// shift operand to a default value of "lsl 0".
+///
+/// TODO: Allow shifted register to be rotated in logical instructions.
+InstructionSelector::ComplexRendererFns
+AArch64InstructionSelector::selectShiftedRegister(MachineOperand &Root) const {
+  if (!Root.isReg())
+    return None;
+  MachineRegisterInfo &MRI =
+      Root.getParent()->getParent()->getParent()->getRegInfo();
+
+  // Check if the operand is defined by an instruction which corresponds to
+  // a ShiftExtendType. E.g. a G_SHL, G_LSHR, etc.
+  //
+  // TODO: Handle AArch64_AM::ROR for logical instructions.
+  MachineInstr *ShiftInst = MRI.getVRegDef(Root.getReg());
+  if (!ShiftInst)
+    return None;
+  AArch64_AM::ShiftExtendType ShType = getShiftTypeForInst(*ShiftInst);
+  if (ShType == AArch64_AM::InvalidShiftExtend)
+    return None;
+  if (!isWorthFoldingIntoExtendedReg(*ShiftInst, MRI))
+    return None;
+
+  // Need an immediate on the RHS.
+  MachineOperand &ShiftRHS = ShiftInst->getOperand(2);
+  auto Immed = getImmedFromMO(ShiftRHS);
+  if (!Immed)
+    return None;
+
+  // We have something that we can fold. Fold in the shift's LHS and RHS into
+  // the instruction.
+  MachineOperand &ShiftLHS = ShiftInst->getOperand(1);
+  Register ShiftReg = ShiftLHS.getReg();
+
+  unsigned NumBits = MRI.getType(ShiftReg).getSizeInBits();
+  unsigned Val = *Immed & (NumBits - 1);
+  unsigned ShiftVal = AArch64_AM::getShifterImm(ShType, Val);
+
+  return {{[=](MachineInstrBuilder &MIB) { MIB.addUse(ShiftReg); },
+           [=](MachineInstrBuilder &MIB) { MIB.addImm(ShiftVal); }}};
+}
+
 void AArch64InstructionSelector::renderTruncImm(MachineInstrBuilder &MIB,
                                                 const MachineInstr &MI) const {
   const MachineRegisterInfo &MRI = MI.getParent()->getParent()->getRegInfo();
   assert(MI.getOpcode() == TargetOpcode::G_CONSTANT && "Expected G_CONSTANT");
   Optional<int64_t> CstVal = getConstantVRegVal(MI.getOperand(0).getReg(), MRI);
   assert(CstVal && "Expected constant value");
   MIB.addImm(CstVal.getValue());
 }

llvm/trunk/test/CodeGen/AArch64/GlobalISel/select-arith-shifted-reg.mir

+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=aarch64-unknown-unknown -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s
+
+---
+name:            add_shl_s64_rhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x0
+    ; CHECK-LABEL: name: add_shl_s64_rhs
+    ; CHECK: liveins: $x0
+    ; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
+    ; CHECK: [[ADDXrs:%[0-9]+]]:gpr64 = ADDXrs [[COPY]], [[COPY]], 8
+    ; CHECK: $x0 = COPY [[ADDXrs]]
+    ; CHECK: RET_ReallyLR implicit $x0
+    %0:gpr(s64) = COPY $x0
+    %1:gpr(s64) = G_CONSTANT i64 8
+    %2:gpr(s64) = G_SHL %0, %1:gpr(s64)
+    %3:gpr(s64) = G_ADD %0, %2:gpr(s64)
+    $x0 = COPY %3:gpr(s64)
+    RET_ReallyLR implicit $x0
+
+...
+---
+name:            add_shl_s64_lhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x0, $x1
+    ; CHECK-LABEL: name: add_shl_s64_lhs
+    ; CHECK: liveins: $x0, $x1
+    ; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
+    ; CHECK: [[COPY1:%[0-9]+]]:gpr64 = COPY $x1
+    ; CHECK: [[ADDXrs:%[0-9]+]]:gpr64 = ADDXrs [[COPY1]], [[COPY]], 8
+    ; CHECK: $x0 = COPY [[ADDXrs]]
+    ; CHECK: RET_ReallyLR implicit $x0
+    %0:gpr(s64) = COPY $x0
+    %4:gpr(s64) = COPY $x1
+    %1:gpr(s64) = G_CONSTANT i64 8
+    %2:gpr(s64) = G_SHL %0, %1:gpr(s64)
+    %3:gpr(s64) = G_ADD %2, %4:gpr(s64)
+    $x0 = COPY %3:gpr(s64)
+    RET_ReallyLR implicit $x0
+
+...
+---
+name:            sub_shl_s64_rhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x0
+    ; CHECK-LABEL: name: sub_shl_s64_rhs
+    ; CHECK: liveins: $x0
+    ; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
+    ; CHECK: [[SUBSXrs:%[0-9]+]]:gpr64 = SUBSXrs [[COPY]], [[COPY]], 8, implicit-def $nzcv
+    ; CHECK: $x0 = COPY [[SUBSXrs]]
+    ; CHECK: RET_ReallyLR implicit $x0
+    %0:gpr(s64) = COPY $x0
+    %1:gpr(s64) = G_CONSTANT i64 8
+    %2:gpr(s64) = G_SHL %0, %1:gpr(s64)
+    %3:gpr(s64) = G_SUB %0, %2:gpr(s64)
+    $x0 = COPY %3:gpr(s64)
+    RET_ReallyLR implicit $x0
+
+---
+name:            add_lshr_s64_rhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x0
+    %0:gpr(s64) = COPY $x0
+    %1:gpr(s64) = G_CONSTANT i64 8
+    %2:gpr(s64) = G_LSHR %0, %1:gpr(s64)
+    %3:gpr(s64) = G_ADD %0, %2:gpr(s64)
+    $x0 = COPY %3:gpr(s64)
+    RET_ReallyLR implicit $x0
+
+...
+---
+name:            add_lshr_s64_lhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x0, $x1
+    ; CHECK-LABEL: name: add_lshr_s64_lhs
+    ; CHECK: liveins: $x0, $x1
+    ; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
+    ; CHECK: %param2:gpr64 = COPY $x1
+    ; CHECK: [[ADDXrs:%[0-9]+]]:gpr64 = ADDXrs %param2, [[COPY]], 72
+    ; CHECK: $x0 = COPY [[ADDXrs]]
+    ; CHECK: RET_ReallyLR implicit $x0
+    %0:gpr(s64) = COPY $x0
+    %param2:gpr(s64) = COPY $x1
+    %1:gpr(s64) = G_CONSTANT i64 8
+    %2:gpr(s64) = G_LSHR %0, %1:gpr(s64)
+    %3:gpr(s64) = G_ADD %2, %param2:gpr(s64)
+    $x0 = COPY %3:gpr(s64)
+    RET_ReallyLR implicit $x0
+
+...
+---
+name:            sub_lshr_s64_rhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x0
+    ; CHECK-LABEL: name: sub_lshr_s64_rhs
+    ; CHECK: liveins: $x0
+    ; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
+    ; CHECK: [[SUBSXrs:%[0-9]+]]:gpr64 = SUBSXrs [[COPY]], [[COPY]], 72, implicit-def $nzcv
+    ; CHECK: $x0 = COPY [[SUBSXrs]]
+    ; CHECK: RET_ReallyLR implicit $x0
+    %0:gpr(s64) = COPY $x0
+    %1:gpr(s64) = G_CONSTANT i64 8
+    %2:gpr(s64) = G_LSHR %0, %1:gpr(s64)
+    %3:gpr(s64) = G_SUB %0, %2:gpr(s64)
+    $x0 = COPY %3:gpr(s64)
+    RET_ReallyLR implicit $x0
+
+...
+---
+name:            add_ashr_s64_rhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x0
+    ; CHECK-LABEL: name: add_ashr_s64_rhs
+    ; CHECK: liveins: $x0
+    ; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
+    ; CHECK: [[ADDXrs:%[0-9]+]]:gpr64 = ADDXrs [[COPY]], [[COPY]], 136
+    ; CHECK: $x0 = COPY [[ADDXrs]]
+    ; CHECK: RET_ReallyLR implicit $x0
+    %0:gpr(s64) = COPY $x0
+    %1:gpr(s64) = G_CONSTANT i64 8
+    %2:gpr(s64) = G_ASHR %0, %1:gpr(s64)
+    %3:gpr(s64) = G_ADD %0, %2:gpr(s64)
+    $x0 = COPY %3:gpr(s64)
+    RET_ReallyLR implicit $x0
+
+...
+---
+name:            add_ashr_s64_lhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x0, $x1
+    ; CHECK-LABEL: name: add_ashr_s64_lhs
+    ; CHECK: liveins: $x0, $x1
+    ; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
+    ; CHECK: %param2:gpr64 = COPY $x1
+    ; CHECK: [[ADDXrs:%[0-9]+]]:gpr64 = ADDXrs %param2, [[COPY]], 136
+    ; CHECK: $x0 = COPY [[ADDXrs]]
+    ; CHECK: RET_ReallyLR implicit $x0
+    %0:gpr(s64) = COPY $x0
+    %param2:gpr(s64) = COPY $x1
+    %1:gpr(s64) = G_CONSTANT i64 8
+    %2:gpr(s64) = G_ASHR %0, %1:gpr(s64)
+    %3:gpr(s64) = G_ADD %2, %param2:gpr(s64)
+    $x0 = COPY %3:gpr(s64)
+    RET_ReallyLR implicit $x0
+
+...
+---
+name:            sub_ashr_s64_rhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x0
+    ; CHECK-LABEL: name: sub_ashr_s64_rhs
+    ; CHECK: liveins: $x0
+    ; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
+    ; CHECK: [[SUBSXrs:%[0-9]+]]:gpr64 = SUBSXrs [[COPY]], [[COPY]], 136, implicit-def $nzcv
+    ; CHECK: $x0 = COPY [[SUBSXrs]]
+    ; CHECK: RET_ReallyLR implicit $x0
+    %0:gpr(s64) = COPY $x0
+    %1:gpr(s64) = G_CONSTANT i64 8
+    %2:gpr(s64) = G_ASHR %0, %1:gpr(s64)
+    %3:gpr(s64) = G_SUB %0, %2:gpr(s64)
+    $x0 = COPY %3:gpr(s64)
+    RET_ReallyLR implicit $x0
+
+---
+name:            add_shl_s32_rhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0
+    %0:gpr(s32) = COPY $w0
+    %1:gpr(s32) = G_CONSTANT i32 8
+    %2:gpr(s32) = G_SHL %0, %1:gpr(s32)
+    %3:gpr(s32) = G_ADD %0, %2:gpr(s32)
+    $w0 = COPY %3:gpr(s32)
+    RET_ReallyLR implicit $w0
+
+...
+---
+name:            add_shl_s32_lhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0, $w1
+    ; CHECK-LABEL: name: add_shl_s32_lhs
+    ; CHECK: liveins: $w0, $w1
+    ; CHECK: [[COPY:%[0-9]+]]:gpr32 = COPY $w0
+    ; CHECK: %param2:gpr32 = COPY $w1
+    ; CHECK: [[ADDWrs:%[0-9]+]]:gpr32 = ADDWrs %param2, [[COPY]], 8
+    ; CHECK: $w0 = COPY [[ADDWrs]]
+    ; CHECK: RET_ReallyLR implicit $w0
+    %0:gpr(s32) = COPY $w0
+    %param2:gpr(s32) = COPY $w1
+    %1:gpr(s32) = G_CONSTANT i32 8
+    %2:gpr(s32) = G_SHL %0, %1:gpr(s32)
+    %3:gpr(s32) = G_ADD %2, %param2:gpr(s32)
+    $w0 = COPY %3:gpr(s32)
+    RET_ReallyLR implicit $w0
+
+...
+---
+name:            sub_shl_s32_rhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0
+    ; CHECK-LABEL: name: sub_shl_s32_rhs
+    ; CHECK: liveins: $w0
+    ; CHECK: [[COPY:%[0-9]+]]:gpr32 = COPY $w0
+    ; CHECK: [[SUBSWrs:%[0-9]+]]:gpr32 = SUBSWrs [[COPY]], [[COPY]], 8, implicit-def $nzcv
+    ; CHECK: $w0 = COPY [[SUBSWrs]]
+    ; CHECK: RET_ReallyLR implicit $w0
+    %0:gpr(s32) = COPY $w0
+    %1:gpr(s32) = G_CONSTANT i32 8
+    %2:gpr(s32) = G_SHL %0, %1:gpr(s32)
+    %3:gpr(s32) = G_SUB %0, %2:gpr(s32)
+    $w0 = COPY %3:gpr(s32)
+    RET_ReallyLR implicit $w0
+
+...
+---
+name:            add_lshr_s32_rhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0
+    ; CHECK-LABEL: name: add_lshr_s32_rhs
+    ; CHECK: liveins: $w0
+    ; CHECK: [[COPY:%[0-9]+]]:gpr32 = COPY $w0
+    ; CHECK: [[ADDWrs:%[0-9]+]]:gpr32 = ADDWrs [[COPY]], [[COPY]], 72
+    ; CHECK: $w0 = COPY [[ADDWrs]]
+    ; CHECK: RET_ReallyLR implicit $w0
+    %0:gpr(s32) = COPY $w0
+    %1:gpr(s32) = G_CONSTANT i32 8
+    %2:gpr(s32) = G_LSHR %0, %1:gpr(s32)
+    %3:gpr(s32) = G_ADD %0, %2:gpr(s32)
+    $w0 = COPY %3:gpr(s32)
+    RET_ReallyLR implicit $w0
+
+...
+---
+name:            add_lshr_s32_lhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0, $w1
+    ; CHECK-LABEL: name: add_lshr_s32_lhs
+    ; CHECK: liveins: $w0, $w1
+    ; CHECK: [[COPY:%[0-9]+]]:gpr32 = COPY $w0
+    ; CHECK: %param2:gpr32 = COPY $w1
+    ; CHECK: [[ADDWrs:%[0-9]+]]:gpr32 = ADDWrs %param2, [[COPY]], 72
+    ; CHECK: $w0 = COPY [[ADDWrs]]
+    ; CHECK: RET_ReallyLR implicit $w0
+    %0:gpr(s32) = COPY $w0
+    %param2:gpr(s32) = COPY $w1
+    %1:gpr(s32) = G_CONSTANT i32 8
+    %2:gpr(s32) = G_LSHR %0, %1:gpr(s32)
+    %3:gpr(s32) = G_ADD %2, %param2:gpr(s32)
+    $w0 = COPY %3:gpr(s32)
+    RET_ReallyLR implicit $w0
+
+...
+---
+name:            sub_lshr_s32_rhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0
+    ; CHECK-LABEL: name: sub_lshr_s32_rhs
+    ; CHECK: liveins: $w0
+    ; CHECK: [[COPY:%[0-9]+]]:gpr32 = COPY $w0
+    ; CHECK: [[SUBSWrs:%[0-9]+]]:gpr32 = SUBSWrs [[COPY]], [[COPY]], 72, implicit-def $nzcv
+    ; CHECK: $w0 = COPY [[SUBSWrs]]
+    ; CHECK: RET_ReallyLR implicit $w0
+    %0:gpr(s32) = COPY $w0
+    %1:gpr(s32) = G_CONSTANT i32 8
+    %2:gpr(s32) = G_LSHR %0, %1:gpr(s32)
+    %3:gpr(s32) = G_SUB %0, %2:gpr(s32)
+    $w0 = COPY %3:gpr(s32)
+    RET_ReallyLR implicit $w0
+
+...
+---
+name:            add_ashr_s32_rhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0
+    ; CHECK-LABEL: name: add_ashr_s32_rhs
+    ; CHECK: liveins: $w0
+    ; CHECK: [[COPY:%[0-9]+]]:gpr32 = COPY $w0
+    ; CHECK: [[ADDWrs:%[0-9]+]]:gpr32 = ADDWrs [[COPY]], [[COPY]], 136
+    ; CHECK: $w0 = COPY [[ADDWrs]]
+    ; CHECK: RET_ReallyLR implicit $w0
+    %0:gpr(s32) = COPY $w0
+    %1:gpr(s32) = G_CONSTANT i32 8
+    %2:gpr(s32) = G_ASHR %0, %1:gpr(s32)
+    %3:gpr(s32) = G_ADD %0, %2:gpr(s32)
+    $w0 = COPY %3:gpr(s32)
+    RET_ReallyLR implicit $w0
+
+...
+---
+name:            add_ashr_s32_lhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0, $w1
+    ; CHECK-LABEL: name: add_ashr_s32_lhs
+    ; CHECK: liveins: $w0, $w1
+    ; CHECK: [[COPY:%[0-9]+]]:gpr32 = COPY $w0
+    ; CHECK: %param2:gpr32 = COPY $w1
+    ; CHECK: [[ADDWrs:%[0-9]+]]:gpr32 = ADDWrs %param2, [[COPY]], 136
+    ; CHECK: $w0 = COPY [[ADDWrs]]
+    ; CHECK: RET_ReallyLR implicit $w0
+    %0:gpr(s32) = COPY $w0
+    %param2:gpr(s32) = COPY $w1
+    %1:gpr(s32) = G_CONSTANT i32 8
+    %2:gpr(s32) = G_ASHR %0, %1:gpr(s32)
+    %3:gpr(s32) = G_ADD %2, %param2:gpr(s32)
+    $w0 = COPY %3:gpr(s32)
+    RET_ReallyLR implicit $w0
+
+...
+---
+name:            sub_ashr_s32_rhs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0
+    ; CHECK-LABEL: name: sub_ashr_s32_rhs
+    ; CHECK: liveins: $w0
+    ; CHECK: [[COPY:%[0-9]+]]:gpr32 = COPY $w0
+    ; CHECK: [[SUBSWrs:%[0-9]+]]:gpr32 = SUBSWrs [[COPY]], [[COPY]], 136, implicit-def $nzcv
+    ; CHECK: $w0 = COPY [[SUBSWrs]]
+    ; CHECK: RET_ReallyLR implicit $w0
+    %0:gpr(s32) = COPY $w0
+    %1:gpr(s32) = G_CONSTANT i32 8
+    %2:gpr(s32) = G_ASHR %0, %1:gpr(s32)
+    %3:gpr(s32) = G_SUB %0, %2:gpr(s32)
+    $w0 = COPY %3:gpr(s32)
+    RET_ReallyLR implicit $w0

llvm/trunk/test/CodeGen/AArch64/GlobalISel/select-logical-shifted-reg.mir

+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=aarch64-unknown-unknown -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s
+#
+# Test patterns related to logical_shifted_reg32/logical_shifted_reg64 which
+# are not shared with arith_shifted_reg32/arith_shifted_reg64.
+
+---
+name:            and_xor_bicxrs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x0
+    ; CHECK-LABEL: name: and_xor_bicxrs
+    ; CHECK: liveins: $x0
+    ; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
+    ; CHECK: [[BICXrs:%[0-9]+]]:gpr64 = BICXrs [[COPY]], [[COPY]], 8
+    ; CHECK: $x0 = COPY [[BICXrs]]
+    ; CHECK: RET_ReallyLR implicit $x0
+    %0:gpr(s64) = COPY $x0
+    %1:gpr(s64) = G_CONSTANT i64 8
+    %2:gpr(s64) = G_CONSTANT i64 -1
+    %3:gpr(s64) = G_SHL %0, %1:gpr(s64)
+    %4:gpr(s64) = G_XOR %3, %2:gpr(s64)
+    %5:gpr(s64) = G_AND %0, %4:gpr(s64)
+    $x0 = COPY %5:gpr(s64)
+    RET_ReallyLR implicit $x0
+...
+---
+name:            or_xor_ornxrs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x0
+    ; CHECK-LABEL: name: or_xor_ornxrs
+    ; CHECK: liveins: $x0
+    ; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
+    ; CHECK: [[ORNXrs:%[0-9]+]]:gpr64 = ORNXrs [[COPY]], [[COPY]], 8
+    ; CHECK: $x0 = COPY [[ORNXrs]]
+    ; CHECK: RET_ReallyLR implicit $x0
+    %0:gpr(s64) = COPY $x0
+    %1:gpr(s64) = G_CONSTANT i64 8
+    %2:gpr(s64) = G_CONSTANT i64 -1
+    %3:gpr(s64) = G_SHL %0, %1:gpr(s64)
+    %4:gpr(s64) = G_XOR %3, %2:gpr(s64)
+    %5:gpr(s64) = G_OR %0, %4:gpr(s64)
+    $x0 = COPY %5:gpr(s64)
+    RET_ReallyLR implicit $x0
+...
+---
+name:            xor_xor_eonxrs
+legalized:       true
+regBankSelected: true
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x0
+    ; CHECK-LABEL: name: xor_xor_eonxrs
+    ; CHECK: liveins: $x0
+    ; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
+    ; CHECK: [[EONXrs:%[0-9]+]]:gpr64 = EONXrs [[COPY]], [[COPY]], 8
+    ; CHECK: $x0 = COPY [[EONXrs]]
+    ; CHECK: RET_ReallyLR implicit $x0
+    %0:gpr(s64) = COPY $x0
+    %1:gpr(s64) = G_CONSTANT i64 8
+    %2:gpr(s64) = G_CONSTANT i64 -1
+    %3:gpr(s64) = G_SHL %0, %1:gpr(s64)
+    %4:gpr(s64) = G_XOR %3, %2:gpr(s64)
+    %5:gpr(s64) = G_XOR %0, %4:gpr(s64)
+    $x0 = COPY %5:gpr(s64)
+    RET_ReallyLR implicit $x0
+...

llvm/trunk/test/CodeGen/AArch64/addsub-shifted.ll

 ; RUN: llc -verify-machineinstrs %s -o - -mtriple=arm64-apple-ios7.0 | FileCheck %s
+; RUN: llc -verify-machineinstrs %s -o - -mtriple=arm64-apple-ios7.0 -global-isel -pass-remarks-missed=gisel* 2>&1 | FileCheck %s --check-prefixes=GISEL,FALLBACK
+
+; FALLBACK-NOT: remark
 
 @var32 = global i32 0
 @var64 = global i64 0
 
 define void @test_lsl_arith(i32 %lhs32, i32 %rhs32, i64 %lhs64, i64 %rhs64) {
 ; CHECK-LABEL: test_lsl_arith:
+; GISEL-LABEL: test_lsl_arith:
 
   %rhs1 = load volatile i32, i32* @var32
   %shift1 = shl i32 %rhs1, 18
   %val1 = add i32 %lhs32, %shift1
   store volatile i32 %val1, i32* @var32
 ; CHECK: add {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsl #18
+; GISEL: add {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsl #18
 
   %rhs2 = load volatile i32, i32* @var32
   %shift2 = shl i32 %rhs2, 31
   %val2 = add i32 %shift2, %lhs32
   store volatile i32 %val2, i32* @var32
 ; CHECK: add {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsl #31
+; GISEL: add {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsl #31
 
   %rhs3 = load volatile i32, i32* @var32
   %shift3 = shl i32 %rhs3, 5
   %val3 = sub i32 %lhs32, %shift3
   store volatile i32 %val3, i32* @var32
 ; CHECK: sub {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsl #5
+; GISEL: subs {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsl #5
 
 ; Subtraction is not commutative!
   %rhs4 = load volatile i32, i32* @var32
   %shift4 = shl i32 %rhs4, 19
   %val4 = sub i32 %shift4, %lhs32
   store volatile i32 %val4, i32* @var32
 ; CHECK-NOT: sub {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsl #19
+; GISEL-NOT: sub{{[s]?}} {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsl #19
 
   %lhs4a = load volatile i32, i32* @var32
   %shift4a = shl i32 %lhs4a, 15
   %val4a = sub i32 0, %shift4a
   store volatile i32 %val4a, i32* @var32
 ; CHECK: neg {{w[0-9]+}}, {{w[0-9]+}}, lsl #15
+; GISEL: negs {{w[0-9]+}}, {{w[0-9]+}}, lsl #15
 
   %rhs5 = load volatile i64, i64* @var64
   %shift5 = shl i64 %rhs5, 18
   %val5 = add i64 %lhs64, %shift5
   store volatile i64 %val5, i64* @var64
 ; CHECK: add {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsl #18
+; GISEL: add {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsl #18
 
   %rhs6 = load volatile i64, i64* @var64
   %shift6 = shl i64 %rhs6, 31
   %val6 = add i64 %shift6, %lhs64
   store volatile i64 %val6, i64* @var64
 ; CHECK: add {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsl #31
+; GISEL: add {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsl #31
 
   %rhs7 = load volatile i64, i64* @var64
   %shift7 = shl i64 %rhs7, 5
   %val7 = sub i64 %lhs64, %shift7
   store volatile i64 %val7, i64* @var64
 ; CHECK: sub {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsl #5
+; GISEL: subs {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsl #5
 
 ; Subtraction is not commutative!
   %rhs8 = load volatile i64, i64* @var64
   %shift8 = shl i64 %rhs8, 19
   %val8 = sub i64 %shift8, %lhs64
   store volatile i64 %val8, i64* @var64
 ; CHECK-NOT: sub {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsl #19
+; GISEL-NOT: sub{{[s]?}} {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsl #19
 
   %lhs8a = load volatile i64, i64* @var64
   %shift8a = shl i64 %lhs8a, 60
   %val8a = sub i64 0, %shift8a
   store volatile i64 %val8a, i64* @var64
 ; CHECK: neg {{x[0-9]+}}, {{x[0-9]+}}, lsl #60
+; GISEL: negs {{x[0-9]+}}, {{x[0-9]+}}, lsl #60
 
   ret void
 ; CHECK: ret
 }
 
 define void @test_lsr_arith(i32 %lhs32, i32 %rhs32, i64 %lhs64, i64 %rhs64) {
 ; CHECK-LABEL: test_lsr_arith:
 
   %shift1 = lshr i32 %rhs32, 18
   %val1 = add i32 %lhs32, %shift1
   store volatile i32 %val1, i32* @var32
 ; CHECK: add {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsr #18
+; GISEL: add {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsr #18
 
   %shift2 = lshr i32 %rhs32, 31
   %val2 = add i32 %shift2, %lhs32
   store volatile i32 %val2, i32* @var32
 ; CHECK: add {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsr #31
+; GISEL: add {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsr #31
 
   %shift3 = lshr i32 %rhs32, 5
   %val3 = sub i32 %lhs32, %shift3
   store volatile i32 %val3, i32* @var32
 ; CHECK: sub {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsr #5
+; GISEL: subs {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsr #5
 
 ; Subtraction is not commutative!
   %shift4 = lshr i32 %rhs32, 19
   %val4 = sub i32 %shift4, %lhs32
   store volatile i32 %val4, i32* @var32
 ; CHECK-NOT: sub {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsr #19
+; GISEL-NOT: sub{{[s]?}} {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, lsr #19
 
   %shift4a = lshr i32 %lhs32, 15
   %val4a = sub i32 0, %shift4a
   store volatile i32 %val4a, i32* @var32
 ; CHECK: neg {{w[0-9]+}}, {{w[0-9]+}}, lsr #15
+; GISEL: negs {{w[0-9]+}}, {{w[0-9]+}}, lsr #15
 
   %shift5 = lshr i64 %rhs64, 18
   %val5 = add i64 %lhs64, %shift5
   store volatile i64 %val5, i64* @var64
 ; CHECK: add {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsr #18
+; GISEL: add {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsr #18
 
   %shift6 = lshr i64 %rhs64, 31
   %val6 = add i64 %shift6, %lhs64
   store volatile i64 %val6, i64* @var64
 ; CHECK: add {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsr #31
+; GISEL: add {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsr #31
 
   %shift7 = lshr i64 %rhs64, 5
   %val7 = sub i64 %lhs64, %shift7
   store volatile i64 %val7, i64* @var64
 ; CHECK: sub {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsr #5
+; GISEL: subs {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsr #5
 
 ; Subtraction is not commutative!
   %shift8 = lshr i64 %rhs64, 19
   %val8 = sub i64 %shift8, %lhs64
   store volatile i64 %val8, i64* @var64
 ; CHECK-NOT: sub {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsr #19
+; GISEL-NOT: sub{{[s]?}} {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, lsr #19
 
   %shift8a = lshr i64 %lhs64, 45
   %val8a = sub i64 0, %shift8a
   store volatile i64 %val8a, i64* @var64
 ; CHECK: neg {{x[0-9]+}}, {{x[0-9]+}}, lsr #45
+; GISEL: negs {{x[0-9]+}}, {{x[0-9]+}}, lsr #45
 
   ret void
 ; CHECK: ret
+; GISEL: ret
 }
 
 define void @test_asr_arith(i32 %lhs32, i32 %rhs32, i64 %lhs64, i64 %rhs64) {
 ; CHECK-LABEL: test_asr_arith:
 
   %shift1 = ashr i32 %rhs32, 18
   %val1 = add i32 %lhs32, %shift1
   store volatile i32 %val1, i32* @var32
 ; CHECK: add {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, asr #18
+; GISEL: add {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, asr #18
 
   %shift2 = ashr i32 %rhs32, 31
   %val2 = add i32 %shift2, %lhs32
   store volatile i32 %val2, i32* @var32
 ; CHECK: add {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, asr #31
+; GISEL: add {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, asr #31
 
   %shift3 = ashr i32 %rhs32, 5
   %val3 = sub i32 %lhs32, %shift3
   store volatile i32 %val3, i32* @var32
 ; CHECK: sub {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, asr #5
+; GISEL: subs {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, asr #5
 
 ; Subtraction is not commutative!
   %shift4 = ashr i32 %rhs32, 19
   %val4 = sub i32 %shift4, %lhs32
   store volatile i32 %val4, i32* @var32
 ; CHECK-NOT: sub {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, asr #19
+; GISEL-NOT: sub{{[s]?}}  {{w[0-9]+}}, {{w[0-9]+}}, {{w[0-9]+}}, asr #19
 
   %shift4a = ashr i32 %lhs32, 15
   %val4a = sub i32 0, %shift4a
   store volatile i32 %val4a, i32* @var32
 ; CHECK: neg {{w[0-9]+}}, {{w[0-9]+}}, asr #15
+; GISEL: negs {{w[0-9]+}}, {{w[0-9]+}}, asr #15
 
   %shift5 = ashr i64 %rhs64, 18
   %val5 = add i64 %lhs64, %shift5
   store volatile i64 %val5, i64* @var64
 ; CHECK: add {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, asr #18
+; GISEL: add {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, asr #18
 
   %shift6 = ashr i64 %rhs64, 31
   %val6 = add i64 %shift6, %lhs64
   store volatile i64 %val6, i64* @var64
 ; CHECK: add {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, asr #31
+; GISEL: add {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, asr #31
 
   %shift7 = ashr i64 %rhs64, 5
   %val7 = sub i64 %lhs64, %shift7
   store volatile i64 %val7, i64* @var64
 ; CHECK: sub {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, asr #5
+; GISEL: subs {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, asr #5
 
 ; Subtraction is not commutative!
   %shift8 = ashr i64 %rhs64, 19
   %val8 = sub i64 %shift8, %lhs64
   store volatile i64 %val8, i64* @var64
 ; CHECK-NOT: sub {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, asr #19
+; GISEL-NOT: sub{{[s]?}}  {{x[0-9]+}}, {{x[0-9]+}}, {{x[0-9]+}}, asr #19
 
   %shift8a = ashr i64 %lhs64, 45
   %val8a = sub i64 0, %shift8a
   store volatile i64 %val8a, i64* @var64
 ; CHECK: neg {{x[0-9]+}}, {{x[0-9]+}}, asr #45
+; GISEL: negs {{x[0-9]+}}, {{x[0-9]+}}, asr #45
 
   ret void
 ; CHECK: ret
 }
 
 define void @test_cmp(i32 %lhs32, i32 %rhs32, i64 %lhs64, i64 %rhs64, i32 %v) {
 ; CHECK-LABEL: test_cmp:
 
; CHECK-LABEL: test_cmn:
   %shift1 = shl i32 %rhs32, 13
   %val1 = sub i32 0, %shift1
   %tst1 = icmp uge i32 %lhs32, %val1
   br i1 %tst1, label %t2, label %end
   ; Important that this isn't lowered to a cmn instruction because if %rhs32 ==
   ; 0 then the results will differ.
 ; CHECK: neg [[RHS:w[0-9]+]], {{w[0-9]+}}, lsl #13
 ; CHECK: cmp {{w[0-9]+}}, [[RHS]]
+; GISEL: negs [[RHS:w[0-9]+]], {{w[0-9]+}}, lsl #13
+; GISEL: cmp {{w[0-9]+}}, [[RHS]]
 
 t2:
   %shift2 = lshr i32 %rhs32, 20
   %val2 = sub i32 0, %shift2
   %tst2 = icmp ne i32 %lhs32, %val2
   br i1 %tst2, label %t3, label %end
 ; CHECK: cmn {{w[0-9]+}}, {{w[0-9]+}}, lsr #20
 
 t3:
   %shift3 = ashr i32 %rhs32, 9
   %val3 = sub i32 0, %shift3
   %tst3 = icmp eq i32 %lhs32, %val3
   br i1 %tst3, label %t4, label %end
 ; CHECK: cmn {{w[0-9]+}}, {{w[0-9]+}}, asr #9
 
 t4:
   %shift4 = shl i64 %rhs64, 43
   %val4 = sub i64 0, %shift4
   %tst4 = icmp slt i64 %lhs64, %val4
   br i1 %tst4, label %t5, label %end
   ; Again, it's important that cmn isn't used here in case %rhs64 == 0.
 ; CHECK: neg [[RHS:x[0-9]+]], {{x[0-9]+}}, lsl #43
 ; CHECK: cmp {{x[0-9]+}}, [[RHS]]
+; GISEL: negs [[RHS:x[0-9]+]], {{x[0-9]+}}, lsl #43
+; GISEL: cmp {{x[0-9]+}}, [[RHS]]
 
 t5:
   %shift5 = lshr i64 %rhs64, 20
   %val5 = sub i64 0, %shift5
   %tst5 = icmp ne i64 %lhs64, %val5
   br i1 %tst5, label %t6, label %end
 ; CHECK: cmn {{x[0-9]+}}, {{x[0-9]+}}, lsr #20
 
 t6:
   %shift6 = ashr i64 %rhs64, 59
   %val6 = sub i64 0, %shift6
   %tst6 = icmp ne i64 %lhs64, %val6
   br i1 %tst6, label %t7, label %end
 ; CHECK: cmn {{x[0-9]+}}, {{x[0-9]+}}, asr #59
 
 t7:
   ret i32 1
 end:
 
   ret i32 0
 ; CHECK: ret
+; GISEL: ret
 }
-

llvm/trunk/test/CodeGen/AArch64/eon.ll

 ; RUN: llc -mtriple=aarch64-none-linux-gnu < %s | FileCheck %s
+; RUN: llc %s -pass-remarks-missed=gisel* -mtriple=aarch64-none-linux-gnu -global-isel -o - 2>&1 | FileCheck %s
+
+; CHECK-NOT: remark
 
 ; Check that the eon instruction is generated instead of eor,movn
 define i64 @test1(i64 %a, i64 %b, i64 %c) {
 ; CHECK-LABEL: test1:
 ; CHECK: eon
 ; CHECK: ret
 entry:
   %shl = shl i64 %b, 4