[FPEnv][AArch64] Add lowering and instruction selection for strict conversions

[john.brawn]

Summary

Strict fp-to-int and int-to-fp conversions can be handled in the same way that the non-strict versions are (by using the appropriate instruction or converting to a function call when we have no instruction).

[pengfei]

llvm/test/CodeGen/AArch64/fp-intrinsics.ll

1

I think you may need add option "-disable-strictnode-mutation" to ensure the code generation doesn't come from mutation before strict FP default enabled. The same to other patches.

[john.brawn]

llvm/test/CodeGen/AArch64/fp-intrinsics.ll

1

Currently a lot of it is coming from strict node mutation. The tests here are primarily for making sure opt doesn't crash with an assertion if you're using it with the default options.

[dmgreen]

LGTM

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

2615–2617

Can you format this whilst you are here.

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM,
   setOperationAction(ISD::SELECT_CC, MVT::f128, Custom);
   setOperationAction(ISD::FP_EXTEND, MVT::f128, Custom);
 
   // Lowering for many of the conversions is actually specified by the non-f128
   // type. The LowerXXX function will be trivial when f128 isn't involved.
   setOperationAction(ISD::FP_TO_SINT, MVT::i32, Custom);
   setOperationAction(ISD::FP_TO_SINT, MVT::i64, Custom);
   setOperationAction(ISD::FP_TO_SINT, MVT::i128, Custom);
+  setOperationAction(ISD::STRICT_FP_TO_SINT, MVT::i32, Custom);
+  setOperationAction(ISD::STRICT_FP_TO_SINT, MVT::i64, Custom);
+  setOperationAction(ISD::STRICT_FP_TO_SINT, MVT::i128, Custom);
   setOperationAction(ISD::FP_TO_UINT, MVT::i32, Custom);
   setOperationAction(ISD::FP_TO_UINT, MVT::i64, Custom);
   setOperationAction(ISD::FP_TO_UINT, MVT::i128, Custom);
+  setOperationAction(ISD::STRICT_FP_TO_UINT, MVT::i32, Custom);
+  setOperationAction(ISD::STRICT_FP_TO_UINT, MVT::i64, Custom);
+  setOperationAction(ISD::STRICT_FP_TO_UINT, MVT::i128, Custom);
   setOperationAction(ISD::SINT_TO_FP, MVT::i32, Custom);
   setOperationAction(ISD::SINT_TO_FP, MVT::i64, Custom);
   setOperationAction(ISD::SINT_TO_FP, MVT::i128, Custom);
+  setOperationAction(ISD::STRICT_SINT_TO_FP, MVT::i32, Custom);
+  setOperationAction(ISD::STRICT_SINT_TO_FP, MVT::i64, Custom);
+  setOperationAction(ISD::STRICT_SINT_TO_FP, MVT::i128, Custom);
   setOperationAction(ISD::UINT_TO_FP, MVT::i32, Custom);
   setOperationAction(ISD::UINT_TO_FP, MVT::i64, Custom);
   setOperationAction(ISD::UINT_TO_FP, MVT::i128, Custom);
+  setOperationAction(ISD::STRICT_UINT_TO_FP, MVT::i32, Custom);
+  setOperationAction(ISD::STRICT_UINT_TO_FP, MVT::i64, Custom);
+  setOperationAction(ISD::STRICT_UINT_TO_FP, MVT::i128, Custom);
   setOperationAction(ISD::FP_ROUND, MVT::f32, Custom);
   setOperationAction(ISD::FP_ROUND, MVT::f64, Custom);
   setOperationAction(ISD::STRICT_FP_ROUND, MVT::f32, Custom);
   setOperationAction(ISD::STRICT_FP_ROUND, MVT::f64, Custom);
 
   // Variable arguments.
   setOperationAction(ISD::VASTART, MVT::Other, Custom);
   setOperationAction(ISD::VAARG, MVT::Other, Custom);
if (Opc) {
     Value = DAG.getNode(Opc, DL, VTs, LHS, RHS);
     Overflow = Value.getValue(1);
   }
   return std::make_pair(Value, Overflow);
 }
 
 SDValue AArch64TargetLowering::LowerF128Call(SDValue Op, SelectionDAG &DAG,
                                              RTLIB::Libcall Call) const {
-  SmallVector<SDValue, 2> Ops(Op->op_begin(), Op->op_end());
+  bool IsStrict = Op->isStrictFPOpcode();
+  unsigned Offset = IsStrict ? 1 : 0;
+  SDValue Chain = IsStrict ? Op.getOperand(0) : SDValue();
+  SmallVector<SDValue, 2> Ops(Op->op_begin() + Offset, Op->op_end());
   MakeLibCallOptions CallOptions;
-  return makeLibCall(DAG, Call, MVT::f128, Ops, CallOptions, SDLoc(Op)).first;
+  SDValue Result;
+  SDLoc dl(Op);
+  std::tie(Result, Chain) = makeLibCall(DAG, Call, Op.getValueType(), Ops,
+                                        CallOptions, dl, Chain);
+  return IsStrict ? DAG.getMergeValues({Result, Chain}, dl) : Result;
 }
 
 // Returns true if the given Op is the overflow flag result of an overflow
 // intrinsic operation.
 static bool isOverflowIntrOpRes(SDValue Op) {
   unsigned Opc = Op.getOpcode();
   return (Op.getResNo() == 1 &&
           (Opc == ISD::SADDO || Opc == ISD::UADDO || Opc == ISD::SSUBO ||
SDValue AArch64TargetLowering::LowerVectorFP_TO_INT(SDValue Op,
   }
 
   // Type changing conversions are illegal.
   return Op;
 }
 
 SDValue AArch64TargetLowering::LowerFP_TO_INT(SDValue Op,
                                               SelectionDAG &DAG) const {
-  if (Op.getOperand(0).getValueType().isVector())
+  bool IsStrict = Op->isStrictFPOpcode();
+  SDValue SrcVal = Op.getOperand(IsStrict ? 1 : 0);
+
+  if (SrcVal.getValueType().isVector())
     return LowerVectorFP_TO_INT(Op, DAG);
 
   // f16 conversions are promoted to f32 when full fp16 is not supported.
-  if (Op.getOperand(0).getValueType() == MVT::f16 &&
-      !Subtarget->hasFullFP16()) {
+  if (SrcVal.getValueType() == MVT::f16 && !Subtarget->hasFullFP16()) {
+    assert(!IsStrict && "Lowering of strict fp16 not yet implemented");
     SDLoc dl(Op);
     return DAG.getNode(
         Op.getOpcode(), dl, Op.getValueType(),
-        DAG.getNode(ISD::FP_EXTEND, dl, MVT::f32, Op.getOperand(0)));
+        DAG.getNode(ISD::FP_EXTEND, dl, MVT::f32, SrcVal));
   }
 
-  if (Op.getOperand(0).getValueType() != MVT::f128) {
+  if (SrcVal.getValueType() != MVT::f128) {
     // It's legal except when f128 is involved
     return Op;
   }
 
   RTLIB::Libcall LC;
-  if (Op.getOpcode() == ISD::FP_TO_SINT)
-    LC = RTLIB::getFPTOSINT(Op.getOperand(0).getValueType(), Op.getValueType());
+  if (Op.getOpcode() == ISD::FP_TO_SINT ||
+      Op.getOpcode() == ISD::STRICT_FP_TO_SINT)
+    LC = RTLIB::getFPTOSINT(SrcVal.getValueType(), Op.getValueType());
   else
-    LC = RTLIB::getFPTOUINT(Op.getOperand(0).getValueType(), Op.getValueType());
+    LC = RTLIB::getFPTOUINT(SrcVal.getValueType(), Op.getValueType());
 
-  SmallVector<SDValue, 2> Ops(Op->op_begin(), Op->op_end());
-  MakeLibCallOptions CallOptions;
-  return makeLibCall(DAG, LC, Op.getValueType(), Ops, CallOptions, SDLoc(Op)).first;
+  return LowerF128Call(Op, DAG, LC);
 }
 
 static SDValue LowerVectorINT_TO_FP(SDValue Op, SelectionDAG &DAG) {
   // Warning: We maintain cost tables in AArch64TargetTransformInfo.cpp.
   // Any additional optimization in this function should be recorded
   // in the cost tables.
   EVT VT = Op.getValueType();
   SDLoc dl(Op);
static SDValue LowerVectorINT_TO_FP(SDValue Op, SelectionDAG &DAG) {
   return Op;
 }
 
 SDValue AArch64TargetLowering::LowerINT_TO_FP(SDValue Op,
                                             SelectionDAG &DAG) const {
   if (Op.getValueType().isVector())
     return LowerVectorINT_TO_FP(Op, DAG);
 
+  bool IsStrict = Op->isStrictFPOpcode();
+  SDValue SrcVal = Op.getOperand(IsStrict ? 1 : 0);
+
   // f16 conversions are promoted to f32 when full fp16 is not supported.
   if (Op.getValueType() == MVT::f16 &&
       !Subtarget->hasFullFP16()) {
+    assert(!IsStrict && "Lowering of strict fp16 not yet implemented");
     SDLoc dl(Op);
     return DAG.getNode(
         ISD::FP_ROUND, dl, MVT::f16,
-        DAG.getNode(Op.getOpcode(), dl, MVT::f32, Op.getOperand(0)),
+        DAG.getNode(Op.getOpcode(), dl, MVT::f32, SrcVal),
         DAG.getIntPtrConstant(0, dl));
   }
 
   // i128 conversions are libcalls.
-  if (Op.getOperand(0).getValueType() == MVT::i128)
+  if (SrcVal.getValueType() == MVT::i128)
     return SDValue();
 
   // Other conversions are legal, unless it's to the completely software-based
   // fp128.
   if (Op.getValueType() != MVT::f128)
     return Op;
 
   RTLIB::Libcall LC;
-  if (Op.getOpcode() == ISD::SINT_TO_FP)
-    LC = RTLIB::getSINTTOFP(Op.getOperand(0).getValueType(), Op.getValueType());
+  if (Op.getOpcode() == ISD::SINT_TO_FP ||
+      Op.getOpcode() == ISD::STRICT_SINT_TO_FP)
+    LC = RTLIB::getSINTTOFP(SrcVal.getValueType(), Op.getValueType());
   else
-    LC = RTLIB::getUINTTOFP(Op.getOperand(0).getValueType(), Op.getValueType());
+    LC = RTLIB::getUINTTOFP(SrcVal.getValueType(), Op.getValueType());
 
   return LowerF128Call(Op, DAG, LC);
 }
 
 SDValue AArch64TargetLowering::LowerFSINCOS(SDValue Op,
                                             SelectionDAG &DAG) const {
   // For iOS, we want to call an alternative entry point: __sincos_stret,
   // which returns the values in two S / D registers.
SDValue AArch64TargetLowering::LowerOperation(SDValue Op,
   case ISD::OR:
     return LowerVectorOR(Op, DAG);
   case ISD::XOR:
     return LowerXOR(Op, DAG);
   case ISD::PREFETCH:
     return LowerPREFETCH(Op, DAG);
   case ISD::SINT_TO_FP:
   case ISD::UINT_TO_FP:
+  case ISD::STRICT_SINT_TO_FP:
+  case ISD::STRICT_UINT_TO_FP:
     return LowerINT_TO_FP(Op, DAG);
   case ISD::FP_TO_SINT:
   case ISD::FP_TO_UINT:
+  case ISD::STRICT_FP_TO_SINT:
+  case ISD::STRICT_FP_TO_UINT:
     return LowerFP_TO_INT(Op, DAG);
   case ISD::FSINCOS:
     return LowerFSINCOS(Op, DAG);
   case ISD::FLT_ROUNDS_:
     return LowerFLT_ROUNDS_(Op, DAG);
   case ISD::MUL:
     return LowerMUL(Op, DAG);
   case ISD::INTRINSIC_WO_CHAIN:

llvm/lib/Target/AArch64/AArch64InstrInfo.td

 defm FCVTAS : FPToIntegerUnscaled<0b00, 0b100, "fcvtas", int_aarch64_neon_fcvtas>;
 defm FCVTAU : FPToIntegerUnscaled<0b00, 0b101, "fcvtau", int_aarch64_neon_fcvtau>;
 defm FCVTMS : FPToIntegerUnscaled<0b10, 0b000, "fcvtms", int_aarch64_neon_fcvtms>;
 defm FCVTMU : FPToIntegerUnscaled<0b10, 0b001, "fcvtmu", int_aarch64_neon_fcvtmu>;
 defm FCVTNS : FPToIntegerUnscaled<0b00, 0b000, "fcvtns", int_aarch64_neon_fcvtns>;
 defm FCVTNU : FPToIntegerUnscaled<0b00, 0b001, "fcvtnu", int_aarch64_neon_fcvtnu>;
 defm FCVTPS : FPToIntegerUnscaled<0b01, 0b000, "fcvtps", int_aarch64_neon_fcvtps>;
 defm FCVTPU : FPToIntegerUnscaled<0b01, 0b001, "fcvtpu", int_aarch64_neon_fcvtpu>;
-defm FCVTZS : FPToIntegerUnscaled<0b11, 0b000, "fcvtzs", fp_to_sint>;
-defm FCVTZU : FPToIntegerUnscaled<0b11, 0b001, "fcvtzu", fp_to_uint>;
-defm FCVTZS : FPToIntegerScaled<0b11, 0b000, "fcvtzs", fp_to_sint>;
-defm FCVTZU : FPToIntegerScaled<0b11, 0b001, "fcvtzu", fp_to_uint>;
+defm FCVTZS : FPToIntegerUnscaled<0b11, 0b000, "fcvtzs", any_fp_to_sint>;
+defm FCVTZU : FPToIntegerUnscaled<0b11, 0b001, "fcvtzu", any_fp_to_uint>;
+defm FCVTZS : FPToIntegerScaled<0b11, 0b000, "fcvtzs", any_fp_to_sint>;
+defm FCVTZU : FPToIntegerScaled<0b11, 0b001, "fcvtzu", any_fp_to_uint>;
 
 multiclass FPToIntegerIntPats<Intrinsic round, string INST> {
   def : Pat<(i32 (round f16:$Rn)), (!cast<Instruction>(INST # UWHr) $Rn)>;
   def : Pat<(i64 (round f16:$Rn)), (!cast<Instruction>(INST # UXHr) $Rn)>;
   def : Pat<(i32 (round f32:$Rn)), (!cast<Instruction>(INST # UWSr) $Rn)>;
   def : Pat<(i64 (round f32:$Rn)), (!cast<Instruction>(INST # UXSr) $Rn)>;
   def : Pat<(i32 (round f64:$Rn)), (!cast<Instruction>(INST # UWDr) $Rn)>;
   def : Pat<(i64 (round f64:$Rn)), (!cast<Instruction>(INST # UXDr) $Rn)>;
def : Pat<(i64 (llround f32:$Rn)),
           (!cast<Instruction>(FCVTASUXSr) f32:$Rn)>;
 def : Pat<(i64 (llround f64:$Rn)),
           (!cast<Instruction>(FCVTASUXDr) f64:$Rn)>;
 
 //===----------------------------------------------------------------------===//
 // Scaled integer to floating point conversion instructions.
 //===----------------------------------------------------------------------===//
 
-defm SCVTF : IntegerToFP<0, "scvtf", sint_to_fp>;
-defm UCVTF : IntegerToFP<1, "ucvtf", uint_to_fp>;
+defm SCVTF : IntegerToFP<0, "scvtf", any_sint_to_fp>;
+defm UCVTF : IntegerToFP<1, "ucvtf", any_uint_to_fp>;
 
 //===----------------------------------------------------------------------===//
 // Unscaled integer to floating point conversion instruction.
 //===----------------------------------------------------------------------===//
 
 defm FMOV : UnscaledConversion<"fmov">;
 
 // Add pseudo ops for FMOV 0 so we can mark them as isReMaterializable

llvm/test/CodeGen/AArch64/fp-intrinsics.ll

 ; RUN: llc -mtriple=aarch64-none-eabi %s -o - | FileCheck %s
 
 ; Check that constrained fp intrinsics are correctly lowered.
 
-; FIXME: We're not generating the right instructions for some of these
-; operations (see further FIXMEs down below).
 
 ; Single-precision intrinsics
 
 ; CHECK-LABEL: add_f32:
 ; CHECK: fadd s0, s0, s1
 define float @add_f32(float %x, float %y) #0 {
   %val = call float @llvm.experimental.constrained.fadd.f32(float %x, float %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
   ret float %val

 ; CHECK-LABEL: fptosi_i32_f32:
 ; CHECK: fcvtzs w0, s0
 define i32 @fptosi_i32_f32(float %x) #0 {
   %val = call i32 @llvm.experimental.constrained.fptosi.i32.f32(float %x, metadata !"fpexcept.strict") #0
   ret i32 %val
 }
 
 ; CHECK-LABEL: fptoui_i32_f32:
-; FIXME-CHECK: fcvtzu w0, s0
+; CHECK: fcvtzu w0, s0
 define i32 @fptoui_i32_f32(float %x) #0 {
   %val = call i32 @llvm.experimental.constrained.fptoui.i32.f32(float %x, metadata !"fpexcept.strict") #0
   ret i32 %val
 }
 
 ; CHECK-LABEL: fptosi_i64_f32:
 ; CHECK: fcvtzs x0, s0
 define i64 @fptosi_i64_f32(float %x) #0 {
   %val = call i64 @llvm.experimental.constrained.fptosi.i64.f32(float %x, metadata !"fpexcept.strict") #0
   ret i64 %val
 }
 
 ; CHECK-LABEL: fptoui_i64_f32:
-; FIXME-CHECK: fcvtzu x0, s0
+; CHECK: fcvtzu x0, s0
 define i64 @fptoui_i64_f32(float %x) #0 {
   %val = call i64 @llvm.experimental.constrained.fptoui.i64.f32(float %x, metadata !"fpexcept.strict") #0
   ret i64 %val
 }
 
 ; CHECK-LABEL: sitofp_f32_i32:
-; FIXME-CHECK: scvtf s0, w0
+; CHECK: scvtf s0, w0
 define float @sitofp_f32_i32(i32 %x) #0 {
   %val = call float @llvm.experimental.constrained.sitofp.f32.i32(i32 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
   ret float %val
 }
 
 ; CHECK-LABEL: uitofp_f32_i32:
-; FIXME-CHECK: ucvtf s0, w0
+; CHECK: ucvtf s0, w0
 define float @uitofp_f32_i32(i32 %x) #0 {
   %val = call float @llvm.experimental.constrained.uitofp.f32.i32(i32 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
   ret float %val
 }
 
-; TODO: sitofp_f32_i64 (missing STRICT_SINT_TO_FP handling)
+; CHECK-LABEL: sitofp_f32_i64:
+; CHECK: scvtf s0, x0
+define float @sitofp_f32_i64(i64 %x) #0 {
+  %val = call float @llvm.experimental.constrained.sitofp.f32.i64(i64 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret float %val
+}
+
+; CHECK-LABEL: uitofp_f32_i64:
+; CHECK: ucvtf s0, x0
+define float @uitofp_f32_i64(i64 %x) #0 {
+  %val = call float @llvm.experimental.constrained.uitofp.f32.i64(i64 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret float %val
+}
+
+; CHECK-LABEL: sitofp_f32_i128:
+; CHECK: bl __floattisf
+define float @sitofp_f32_i128(i128 %x) #0 {
+  %val = call float @llvm.experimental.constrained.sitofp.f32.i128(i128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret float %val
+}
 
-; TODO: uitofp_f32_i64 (missing STRICT_SINT_TO_FP handling)
+; CHECK-LABEL: uitofp_f32_i128:
+; CHECK: bl __floatuntisf
+define float @uitofp_f32_i128(i128 %x) #0 {
+  %val = call float @llvm.experimental.constrained.uitofp.f32.i128(i128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret float %val
+}
 
 ; CHECK-LABEL: sqrt_f32:
 ; CHECK: fsqrt s0, s0
 define float @sqrt_f32(float %x) #0 {
   %val = call float @llvm.experimental.constrained.sqrt.f32(float %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
   ret float %val
 }
 

 ; CHECK-LABEL: fptosi_i32_f64:
 ; CHECK: fcvtzs w0, d0
 define i32 @fptosi_i32_f64(double %x) #0 {
   %val = call i32 @llvm.experimental.constrained.fptosi.i32.f64(double %x, metadata !"fpexcept.strict") #0
   ret i32 %val
 }
 
 ; CHECK-LABEL: fptoui_i32_f64:
-; FIXME-CHECK: fcvtzu w0, d0
+; CHECK: fcvtzu w0, d0
 define i32 @fptoui_i32_f64(double %x) #0 {
   %val = call i32 @llvm.experimental.constrained.fptoui.i32.f64(double %x, metadata !"fpexcept.strict") #0
   ret i32 %val
 }
 
 ; CHECK-LABEL: fptosi_i64_f64:
 ; CHECK: fcvtzs x0, d0
 define i64 @fptosi_i64_f64(double %x) #0 {
   %val = call i64 @llvm.experimental.constrained.fptosi.i64.f64(double %x, metadata !"fpexcept.strict") #0
   ret i64 %val
 }
 
 ; CHECK-LABEL: fptoui_i64_f64:
-; FIXME-CHECK: fcvtzu x0, d0
+; CHECK: fcvtzu x0, d0
 define i64 @fptoui_i64_f64(double %x) #0 {
   %val = call i64 @llvm.experimental.constrained.fptoui.i64.f64(double %x, metadata !"fpexcept.strict") #0
   ret i64 %val
 }
 
 ; CHECK-LABEL: sitofp_f64_i32:
-; FIXME-CHECK: scvtf d0, w0
+; CHECK: scvtf d0, w0
 define double @sitofp_f64_i32(i32 %x) #0 {
   %val = call double @llvm.experimental.constrained.sitofp.f64.i32(i32 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
   ret double %val
 }
 
 ; CHECK-LABEL: uitofp_f64_i32:
-; FIXME-CHECK: ucvtf d0, w0
+; CHECK: ucvtf d0, w0
 define double @uitofp_f64_i32(i32 %x) #0 {
   %val = call double @llvm.experimental.constrained.uitofp.f64.i32(i32 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
   ret double %val
 }
 
-; TODO sitofp_f64_i64 (missing STRICT_SINT_TO_FP handling)
+; CHECK-LABEL: sitofp_f64_i64:
+; CHECK: scvtf d0, x0
+define double @sitofp_f64_i64(i64 %x) #0 {
+  %val = call double @llvm.experimental.constrained.sitofp.f64.i64(i64 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret double %val
+}
 
 ; CHECK-LABEL: uitofp_f64_i64:
-; FIXME-CHECK: ucvtf d0, x0
+; CHECK: ucvtf d0, x0
 define double @uitofp_f64_i64(i64 %x) #0 {
   %val = call double @llvm.experimental.constrained.uitofp.f64.i64(i64 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
   ret double %val
 }
 
+; CHECK-LABEL: sitofp_f64_i128:
+; CHECK: bl __floattidf
+define double @sitofp_f64_i128(i128 %x) #0 {
+  %val = call double @llvm.experimental.constrained.sitofp.f64.i128(i128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret double %val
+}
+
+; CHECK-LABEL: uitofp_f64_i128:
+; CHECK: bl __floatuntidf
+define double @uitofp_f64_i128(i128 %x) #0 {
+  %val = call double @llvm.experimental.constrained.uitofp.f64.i128(i128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret double %val
+}
+
 ; CHECK-LABEL: sqrt_f64:
 ; CHECK: fsqrt d0, d0
 define double @sqrt_f64(double %x) #0 {
   %val = call double @llvm.experimental.constrained.sqrt.f64(double %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
   ret double %val
 }
 
 ; CHECK-LABEL: powi_f64:

 ; CHECK: fcmpe d0, d1
 define i32 @fcmps_une_f64(double %a, double %b) #0 {
   %cmp = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"une", metadata !"fpexcept.strict") #0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 
-; Single/Double conversion intrinsics
+; Long-double-precision intrinsics
+
+; CHECK-LABEL: add_f128:
+; CHECK: bl __addtf3
+define fp128 @add_f128(fp128 %x, fp128 %y) #0 {
+  %val = call fp128 @llvm.experimental.constrained.fadd.f128(fp128 %x, fp128 %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: sub_f128:
+; CHECK: bl __subtf3
+define fp128 @sub_f128(fp128 %x, fp128 %y) #0 {
+  %val = call fp128 @llvm.experimental.constrained.fsub.f128(fp128 %x, fp128 %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: mul_f128:
+; CHECK: bl __multf3
+define fp128 @mul_f128(fp128 %x, fp128 %y) #0 {
+  %val = call fp128 @llvm.experimental.constrained.fmul.f128(fp128 %x, fp128 %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: div_f128:
+; CHECK: bl __divtf3
+define fp128 @div_f128(fp128 %x, fp128 %y) #0 {
+  %val = call fp128 @llvm.experimental.constrained.fdiv.f128(fp128 %x, fp128 %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: frem_f128:
+; CHECK: bl fmodl
+define fp128 @frem_f128(fp128 %x, fp128 %y) #0 {
+  %val = call fp128 @llvm.experimental.constrained.frem.f128(fp128 %x, fp128 %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: fma_f128:
+; CHECK: fmal
+define fp128 @fma_f128(fp128 %x, fp128 %y, fp128 %z) #0 {
+  %val = call fp128 @llvm.experimental.constrained.fma.f128(fp128 %x, fp128 %y, fp128 %z, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: fptosi_i32_f128:
+; CHECK: bl __fixtfsi
+define i32 @fptosi_i32_f128(fp128 %x) #0 {
+  %val = call i32 @llvm.experimental.constrained.fptosi.i32.f128(fp128 %x, metadata !"fpexcept.strict") #0
+  ret i32 %val
+}
+
+; CHECK-LABEL: fptoui_i32_f128:
+; CHECK: bl __fixunstfsi
+define i32 @fptoui_i32_f128(fp128 %x) #0 {
+  %val = call i32 @llvm.experimental.constrained.fptoui.i32.f128(fp128 %x, metadata !"fpexcept.strict") #0
+  ret i32 %val
+}
+
+; CHECK-LABEL: fptosi_i64_f128:
+; CHECK: bl __fixtfdi
+define i64 @fptosi_i64_f128(fp128 %x) #0 {
+  %val = call i64 @llvm.experimental.constrained.fptosi.i64.f128(fp128 %x, metadata !"fpexcept.strict") #0
+  ret i64 %val
+}
+
+; CHECK-LABEL: fptoui_i64_f128:
+; CHECK: bl __fixunstfdi
+define i64 @fptoui_i64_f128(fp128 %x) #0 {
+  %val = call i64 @llvm.experimental.constrained.fptoui.i64.f128(fp128 %x, metadata !"fpexcept.strict") #0
+  ret i64 %val
+}
+
+; CHECK-LABEL: sitofp_f128_i32:
+; CHECK: bl __floatsitf
+define fp128 @sitofp_f128_i32(i32 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.sitofp.f128.i32(i32 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: uitofp_f128_i32:
+; CHECK: bl __floatunsitf
+define fp128 @uitofp_f128_i32(i32 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.uitofp.f128.i32(i32 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: sitofp_f128_i64:
+; CHECK: bl __floatditf
+define fp128 @sitofp_f128_i64(i64 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.sitofp.f128.i64(i64 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: uitofp_f128_i64:
+; CHECK: bl __floatunditf
+define fp128 @uitofp_f128_i64(i64 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.uitofp.f128.i64(i64 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: sitofp_f128_i128:
+; CHECK: bl __floattitf
+define fp128 @sitofp_f128_i128(i128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.sitofp.f128.i128(i128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: uitofp_f128_i128:
+; CHECK: bl __floatuntitf
+define fp128 @uitofp_f128_i128(i128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.uitofp.f128.i128(i128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: sqrt_f128:
+; CHECK: bl sqrtl
+define fp128 @sqrt_f128(fp128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.sqrt.f128(fp128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: powi_f128:
+; CHECK: bl __powitf2
+define fp128 @powi_f128(fp128 %x, i32 %y) #0 {
+  %val = call fp128 @llvm.experimental.constrained.powi.f128(fp128 %x, i32 %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: sin_f128:
+; CHECK: bl sinl
+define fp128 @sin_f128(fp128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.sin.f128(fp128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: cos_f128:
+; CHECK: bl cosl
+define fp128 @cos_f128(fp128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.cos.f128(fp128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: pow_f128:
+; CHECK: bl powl
+define fp128 @pow_f128(fp128 %x, fp128 %y) #0 {
+  %val = call fp128 @llvm.experimental.constrained.pow.f128(fp128 %x, fp128 %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: log_f128:
+; CHECK: bl logl
+define fp128 @log_f128(fp128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.log.f128(fp128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: log10_f128:
+; CHECK: bl log10l
+define fp128 @log10_f128(fp128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.log10.f128(fp128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: log2_f128:
+; CHECK: bl log2l
+define fp128 @log2_f128(fp128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.log2.f128(fp128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: exp_f128:
+; CHECK: bl expl
+define fp128 @exp_f128(fp128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.exp.f128(fp128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: exp2_f128:
+; CHECK: bl exp2l
+define fp128 @exp2_f128(fp128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.exp2.f128(fp128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: rint_f128:
+; CHECK: bl rintl
+define fp128 @rint_f128(fp128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.rint.f128(fp128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: nearbyint_f128:
+; CHECK: bl nearbyintl
+define fp128 @nearbyint_f128(fp128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.nearbyint.f128(fp128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: lrint_f128:
+; CHECK: bl lrintl
+define i32 @lrint_f128(fp128 %x) #0 {
+  %val = call i32 @llvm.experimental.constrained.lrint.f128(fp128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret i32 %val
+}
+
+; CHECK-LABEL: llrint_f128:
+; CHECK: bl llrintl
+define i64 @llrint_f128(fp128 %x) #0 {
+  %val = call i64 @llvm.experimental.constrained.llrint.f128(fp128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret i64 %val
+}
+
+; CHECK-LABEL: maxnum_f128:
+; CHECK: bl fmaxl
+define fp128 @maxnum_f128(fp128 %x, fp128 %y) #0 {
+  %val = call fp128 @llvm.experimental.constrained.maxnum.f128(fp128 %x, fp128 %y, metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: minnum_f128:
+; CHECK: bl fminl
+define fp128 @minnum_f128(fp128 %x, fp128 %y) #0 {
+  %val = call fp128 @llvm.experimental.constrained.minnum.f128(fp128 %x, fp128 %y, metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: ceil_f128:
+; CHECK: bl ceill
+define fp128 @ceil_f128(fp128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.ceil.f128(fp128 %x, metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: floor_f128:
+; CHECK: bl floorl
+define fp128 @floor_f128(fp128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.floor.f128(fp128 %x, metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: lround_f128:
+; CHECK: bl lroundl
+define i32 @lround_f128(fp128 %x) #0 {
+  %val = call i32 @llvm.experimental.constrained.lround.f128(fp128 %x, metadata !"fpexcept.strict") #0
+  ret i32 %val
+}
+
+; CHECK-LABEL: llround_f128:
+; CHECK: bl llroundl
+define i64 @llround_f128(fp128 %x) #0 {
+  %val = call i64 @llvm.experimental.constrained.llround.f128(fp128 %x, metadata !"fpexcept.strict") #0
+  ret i64 %val
+}
+
+; CHECK-LABEL: round_f128:
+; CHECK: bl roundl
+define fp128 @round_f128(fp128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.round.f128(fp128 %x, metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: trunc_f128:
+; CHECK: bl truncl
+define fp128 @trunc_f128(fp128 %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.trunc.f128(fp128 %x, metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; TODO: fcmp (missing STRICT_FSETCC handling)
 
-; CHECK-LABEL: fptrunc_f32:
+
+; Intrinsics to convert between floating-point types
+
+; CHECK-LABEL: fptrunc_f32_f64:
 ; CHECK: fcvt s0, d0
-define float @fptrunc_f32(double %x) #0 {
+define float @fptrunc_f32_f64(double %x) #0 {
   %val = call float @llvm.experimental.constrained.fptrunc.f32.f64(double %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
   ret float %val
 }
 
-; CHECK-LABEL: fpext_f32:
+; CHECK-LABEL: fptrunc_f32_f128:
+; CHECK: bl __trunctfsf2
+define float @fptrunc_f32_f128(fp128 %x) #0 {
+  %val = call float @llvm.experimental.constrained.fptrunc.f32.f128(fp128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret float %val
+}
+
+; CHECK-LABEL: fptrunc_f64_f128:
+; CHECK: bl __trunctfdf2
+define double @fptrunc_f64_f128(fp128 %x) #0 {
+  %val = call double @llvm.experimental.constrained.fptrunc.f64.f128(fp128 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
+  ret double %val
+}
+
+; CHECK-LABEL: fpext_f64_f32:
 ; CHECK: fcvt d0, s0
-define double @fpext_f32(float %x) #0 {
+define double @fpext_f64_f32(float %x) #0 {
   %val = call double @llvm.experimental.constrained.fpext.f64.f32(float %x, metadata !"fpexcept.strict") #0
   ret double %val
 }
 
+; CHECK-LABEL: fpext_f128_f32:
+; CHECK: bl __extendsftf2
+define fp128 @fpext_f128_f32(float %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.fpext.f128.f32(float %x, metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
+; CHECK-LABEL: fpext_f128_f64:
+; CHECK: bl __extenddftf2
+define fp128 @fpext_f128_f64(double %x) #0 {
+  %val = call fp128 @llvm.experimental.constrained.fpext.f128.f64(double %x, metadata !"fpexcept.strict") #0
+  ret fp128 %val
+}
+
 
 attributes #0 = { strictfp }
 
 declare float @llvm.experimental.constrained.fadd.f32(float, float, metadata, metadata)
 declare float @llvm.experimental.constrained.fsub.f32(float, float, metadata, metadata)
 declare float @llvm.experimental.constrained.fmul.f32(float, float, metadata, metadata)
 declare float @llvm.experimental.constrained.fdiv.f32(float, float, metadata, metadata)
 declare float @llvm.experimental.constrained.frem.f32(float, float, metadata, metadata)
 declare float @llvm.experimental.constrained.fma.f32(float, float, float, metadata, metadata)
 declare i32 @llvm.experimental.constrained.fptosi.i32.f32(float, metadata)
 declare i32 @llvm.experimental.constrained.fptoui.i32.f32(float, metadata)
 declare i64 @llvm.experimental.constrained.fptosi.i64.f32(float, metadata)
 declare i64 @llvm.experimental.constrained.fptoui.i64.f32(float, metadata)
 declare float @llvm.experimental.constrained.sitofp.f32.i32(i32, metadata, metadata)
 declare float @llvm.experimental.constrained.uitofp.f32.i32(i32, metadata, metadata)
 declare float @llvm.experimental.constrained.sitofp.f32.i64(i64, metadata, metadata)
 declare float @llvm.experimental.constrained.uitofp.f32.i64(i64, metadata, metadata)
+declare float @llvm.experimental.constrained.sitofp.f32.i128(i128, metadata, metadata)
+declare float @llvm.experimental.constrained.uitofp.f32.i128(i128, metadata, metadata)
 declare float @llvm.experimental.constrained.sqrt.f32(float, metadata, metadata)
 declare float @llvm.experimental.constrained.powi.f32(float, i32, metadata, metadata)
 declare float @llvm.experimental.constrained.sin.f32(float, metadata, metadata)
 declare float @llvm.experimental.constrained.cos.f32(float, metadata, metadata)
 declare float @llvm.experimental.constrained.pow.f32(float, float, metadata, metadata)
 declare float @llvm.experimental.constrained.log.f32(float, metadata, metadata)
 declare float @llvm.experimental.constrained.log10.f32(float, metadata, metadata)
 declare float @llvm.experimental.constrained.log2.f32(float, metadata, metadata)

 declare i32 @llvm.experimental.constrained.fptosi.i32.f64(double, metadata)
 declare i32 @llvm.experimental.constrained.fptoui.i32.f64(double, metadata)
 declare i64 @llvm.experimental.constrained.fptosi.i64.f64(double, metadata)
 declare i64 @llvm.experimental.constrained.fptoui.i64.f64(double, metadata)
 declare double @llvm.experimental.constrained.sitofp.f64.i32(i32, metadata, metadata)
 declare double @llvm.experimental.constrained.uitofp.f64.i32(i32, metadata, metadata)
 declare double @llvm.experimental.constrained.sitofp.f64.i64(i64, metadata, metadata)
 declare double @llvm.experimental.constrained.uitofp.f64.i64(i64, metadata, metadata)
+declare double @llvm.experimental.constrained.sitofp.f64.i128(i128, metadata, metadata)
+declare double @llvm.experimental.constrained.uitofp.f64.i128(i128, metadata, metadata)
 declare double @llvm.experimental.constrained.sqrt.f64(double, metadata, metadata)
 declare double @llvm.experimental.constrained.powi.f64(double, i32, metadata, metadata)
 declare double @llvm.experimental.constrained.sin.f64(double, metadata, metadata)
 declare double @llvm.experimental.constrained.cos.f64(double, metadata, metadata)
 declare double @llvm.experimental.constrained.pow.f64(double, double, metadata, metadata)
 declare double @llvm.experimental.constrained.log.f64(double, metadata, metadata)
 declare double @llvm.experimental.constrained.log10.f64(double, metadata, metadata)
 declare double @llvm.experimental.constrained.log2.f64(double, metadata, metadata)

 declare double @llvm.experimental.constrained.floor.f64(double, metadata)
 declare i32 @llvm.experimental.constrained.lround.f64(double, metadata)
 declare i64 @llvm.experimental.constrained.llround.f64(double, metadata)
 declare double @llvm.experimental.constrained.round.f64(double, metadata)
 declare double @llvm.experimental.constrained.trunc.f64(double, metadata)
 declare i1 @llvm.experimental.constrained.fcmps.f64(double, double, metadata, metadata)
 declare i1 @llvm.experimental.constrained.fcmp.f64(double, double, metadata, metadata)
 
+declare fp128 @llvm.experimental.constrained.fadd.f128(fp128, fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.fsub.f128(fp128, fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.fmul.f128(fp128, fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.fdiv.f128(fp128, fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.frem.f128(fp128, fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.fma.f128(fp128, fp128, fp128, metadata, metadata)
+declare i32 @llvm.experimental.constrained.fptosi.i32.f128(fp128, metadata)
+declare i32 @llvm.experimental.constrained.fptoui.i32.f128(fp128, metadata)
+declare i64 @llvm.experimental.constrained.fptosi.i64.f128(fp128, metadata)
+declare i64 @llvm.experimental.constrained.fptoui.i64.f128(fp128, metadata)
+declare fp128 @llvm.experimental.constrained.sitofp.f128.i32(i32, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.uitofp.f128.i32(i32, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.sitofp.f128.i64(i64, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.uitofp.f128.i64(i64, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.sitofp.f128.i128(i128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.uitofp.f128.i128(i128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.sqrt.f128(fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.powi.f128(fp128, i32, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.sin.f128(fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.cos.f128(fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.pow.f128(fp128, fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.log.f128(fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.log10.f128(fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.log2.f128(fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.exp.f128(fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.exp2.f128(fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.rint.f128(fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.nearbyint.f128(fp128, metadata, metadata)
+declare i32 @llvm.experimental.constrained.lrint.f128(fp128, metadata, metadata)
+declare i64 @llvm.experimental.constrained.llrint.f128(fp128, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.maxnum.f128(fp128, fp128, metadata)
+declare fp128 @llvm.experimental.constrained.minnum.f128(fp128, fp128, metadata)
+declare fp128 @llvm.experimental.constrained.ceil.f128(fp128, metadata)
+declare fp128 @llvm.experimental.constrained.floor.f128(fp128, metadata)
+declare i32 @llvm.experimental.constrained.lround.f128(fp128, metadata)
+declare i64 @llvm.experimental.constrained.llround.f128(fp128, metadata)
+declare fp128 @llvm.experimental.constrained.round.f128(fp128, metadata)
+declare fp128 @llvm.experimental.constrained.trunc.f128(fp128, metadata)
+declare i1 @llvm.experimental.constrained.fcmps.f128(fp128, fp128, metadata, metadata)
+declare i1 @llvm.experimental.constrained.fcmp.f128(fp128, fp128, metadata, metadata)
+
 declare float @llvm.experimental.constrained.fptrunc.f32.f64(double, metadata, metadata)
+declare float @llvm.experimental.constrained.fptrunc.f32.f128(fp128, metadata, metadata)
+declare double @llvm.experimental.constrained.fptrunc.f64.f128(fp128, metadata, metadata)
 declare double @llvm.experimental.constrained.fpext.f64.f32(float, metadata)
+declare fp128 @llvm.experimental.constrained.fpext.f128.f32(float, metadata)
+declare fp128 @llvm.experimental.constrained.fpext.f128.f64(double, metadata)

llvm/test/CodeGen/AArch64/fpconv-vector-op-scalarize-strict.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s -mtriple=aarch64-apple-darwin | FileCheck %s
 
 ; Check that the legalizer doesn't crash when scalarizing FP conversion
 ; instructions' operands.  The operands are all illegal on AArch64,
 ; ensuring they are legalized.  The results are all legal.
 
 define <1 x double> @test_sitofp(<1 x i1> %in) #0 {
 ; CHECK-LABEL: test_sitofp:
 ; CHECK:       ; %bb.0: ; %entry
-; CHECK-NEXT:    sub sp, sp, #16 ; =16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    sbfx w8, w0, #0, #1
-; CHECK-NEXT:    mov w9, #1127219200
-; CHECK-NEXT:    eor w8, w8, #0x80000000
-; CHECK-NEXT:    stp w8, w9, [sp, #8]
-; CHECK-NEXT:    ldr d0, [sp, #8]
-; CHECK-NEXT:    mov x8, #2147483648
-; CHECK-NEXT:    movk x8, #17200, lsl #48
-; CHECK-NEXT:    fmov d1, x8
-; CHECK-NEXT:    fsub d0, d0, d1
-; CHECK-NEXT:    add sp, sp, #16 ; =16
+; CHECK-NEXT:    scvtf d0, w8
 ; CHECK-NEXT:    ret
 entry:
   %0 = call <1 x double> @llvm.experimental.constrained.sitofp.v1f64.v1i1(<1 x i1> %in, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret <1 x double> %0
 }
 
 define <1 x double> @test_uitofp(<1 x i1> %in) #0 {
 ; CHECK-LABEL: test_uitofp:
 ; CHECK:       ; %bb.0: ; %entry
-; CHECK-NEXT:    sub sp, sp, #16 ; =16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    and w8, w0, #0x1
-; CHECK-NEXT:    mov w9, #1127219200
-; CHECK-NEXT:    stp w8, w9, [sp, #8]
-; CHECK-NEXT:    ldr d0, [sp, #8]
-; CHECK-NEXT:    mov x8, #4841369599423283200
-; CHECK-NEXT:    fmov d1, x8
-; CHECK-NEXT:    fsub d0, d0, d1
-; CHECK-NEXT:    add sp, sp, #16 ; =16
+; CHECK-NEXT:    ucvtf d0, w8
 ; CHECK-NEXT:    ret
 entry:
   %0 = call <1 x double> @llvm.experimental.constrained.uitofp.v1f64.v1i1(<1 x i1> %in, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret <1 x double> %0
 }
 
 attributes #0 = { strictfp }
 
 declare <1 x double> @llvm.experimental.constrained.sitofp.v1f64.v1i1(<1 x i1>, metadata, metadata)
 declare <1 x double> @llvm.experimental.constrained.uitofp.v1f64.v1i1(<1 x i1>, metadata, metadata)