[CodeGen] Add lrint/llrint builtins

This patch add the ISD::LRINT and ISD::LLRINT along with new
intrinsics.  The changes are straightforward as for other
floating-point rounding functions, with just some adjustments
required to handle the return value being an interger.

The idea is to optimize lrint/llrint generation for AArch64
in a subsequent patch.  Current semantic is just route it to libm
symbol.

Reviewed By: craig.topper

Differential Revision: https://reviews.llvm.org/D62017


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@361875 91177308-0d34-0410-b5e6-96231b3b80d8

docs/LangRef.rst

@@ -12449,6 +12449,80 @@ Semantics:
 This function returns the same values as the libm ``llround``
 functions would, but without setting errno.
 
+'``llvm.lrint.*``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+This is an overloaded intrinsic. You can use ``llvm.lrint`` on any
+floating-point type. Not all targets support all types however.
+
+::
+
+      declare i32 @llvm.lrint.i32.f32(float %Val)
+      declare i32 @llvm.lrint.i32.f64(double %Val)
+      declare i32 @llvm.lrint.i32.f80(float %Val)
+      declare i32 @llvm.lrint.i32.f128(double %Val)
+      declare i32 @llvm.lrint.i32.ppcf128(double %Val)
+
+      declare i64 @llvm.lrint.i64.f32(float %Val)
+      declare i64 @llvm.lrint.i64.f64(double %Val)
+      declare i64 @llvm.lrint.i64.f80(float %Val)
+      declare i64 @llvm.lrint.i64.f128(double %Val)
+      declare i64 @llvm.lrint.i64.ppcf128(double %Val)
+
+Overview:
+"""""""""
+
+The '``llvm.lrint.*``' intrinsics returns the operand rounded to the
+nearest integer.
+
+Arguments:
+""""""""""
+
+The argument is a floating-point number and return is an integer type.
+
+Semantics:
+""""""""""
+
+This function returns the same values as the libm ``lrint``
+functions would, but without setting errno.
+
+'``llvm.llrint.*``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+This is an overloaded intrinsic. You can use ``llvm.llrint`` on any
+floating-point type. Not all targets support all types however.
+
+::
+
+      declare i64 @llvm.llrint.i64.f32(float %Val)
+      declare i64 @llvm.llrint.i64.f64(double %Val)
+      declare i64 @llvm.llrint.i64.f80(float %Val)
+      declare i64 @llvm.llrint.i64.f128(double %Val)
+      declare i64 @llvm.llrint.i64.ppcf128(double %Val)
+
+Overview:
+"""""""""
+
+The '``llvm.llrint.*``' intrinsics returns the operand rounded to the
+nearest integer.
+
+Arguments:
+""""""""""
+
+The argument is a floating-point number and return is an integer type.
+
+Semantics:
+""""""""""
+
+This function returns the same values as the libm ``llrint``
+functions would, but without setting errno.
+
 Bit Manipulation Intrinsics
 ---------------------------
 

include/llvm/CodeGen/ISDOpcodes.h

@@ -610,7 +610,7 @@ namespace ISD {
     FNEG, FABS, FSQRT, FCBRT, FSIN, FCOS, FPOWI, FPOW,
     FLOG, FLOG2, FLOG10, FEXP, FEXP2,
     FCEIL, FTRUNC, FRINT, FNEARBYINT, FROUND, FFLOOR,
-    LROUND, LLROUND,
+    LROUND, LLROUND, LRINT, LLRINT,
 
     /// FMINNUM/FMAXNUM - Perform floating-point minimum or maximum on two
     /// values.

include/llvm/IR/Intrinsics.td

@@ -541,6 +541,8 @@ let IntrProperties = [IntrNoMem, IntrSpeculatable] in {
 
   def int_lround : Intrinsic<[llvm_anyint_ty], [llvm_anyfloat_ty]>;
   def int_llround : Intrinsic<[llvm_anyint_ty], [llvm_anyfloat_ty]>;
+  def int_lrint : Intrinsic<[llvm_anyint_ty], [llvm_anyfloat_ty]>;
+  def int_llrint : Intrinsic<[llvm_anyint_ty], [llvm_anyfloat_ty]>;
 }
 
 def int_minnum : Intrinsic<[llvm_anyfloat_ty],

include/llvm/IR/RuntimeLibcalls.def

@@ -264,6 +264,16 @@ HANDLE_LIBCALL(LLROUND_F64, "llround")
 HANDLE_LIBCALL(LLROUND_F80, "llroundl")
 HANDLE_LIBCALL(LLROUND_F128, "llroundl")
 HANDLE_LIBCALL(LLROUND_PPCF128, "llroundl")
+HANDLE_LIBCALL(LRINT_F32, "lrintf")
+HANDLE_LIBCALL(LRINT_F64, "lrint")
+HANDLE_LIBCALL(LRINT_F80, "lrintl")
+HANDLE_LIBCALL(LRINT_F128, "lrintl")
+HANDLE_LIBCALL(LRINT_PPCF128, "lrintl")
+HANDLE_LIBCALL(LLRINT_F32, "llrintf")
+HANDLE_LIBCALL(LLRINT_F64, "llrint")
+HANDLE_LIBCALL(LLRINT_F80, "llrintl")
+HANDLE_LIBCALL(LLRINT_F128, "llrintl")
+HANDLE_LIBCALL(LLRINT_PPCF128, "llrintl")
 
 // Conversion
 HANDLE_LIBCALL(FPEXT_F32_PPCF128, "__gcc_stoq")

lib/CodeGen/SelectionDAG/LegalizeDAG.cpp

@@ -1003,6 +1003,8 @@ void SelectionDAGLegalize::LegalizeOp(SDNode *Node) {
   case ISD::EXTRACT_VECTOR_ELT:
   case ISD::LROUND:
   case ISD::LLROUND:
+  case ISD::LRINT:
+  case ISD::LLRINT:
     Action = TLI.getOperationAction(Node->getOpcode(),
                                     Node->getOperand(0).getValueType());
     break;
@@ -2919,6 +2921,18 @@ bool SelectionDAGLegalize::ExpandNode(SDNode *Node) {
                                          RTLIB::LLROUND_F128,
                                          RTLIB::LLROUND_PPCF128));
     break;
+  case ISD::LRINT:
+    Results.push_back(ExpandArgFPLibCall(Node, RTLIB::LRINT_F32,
+                                         RTLIB::LRINT_F64, RTLIB::LRINT_F80,
+                                         RTLIB::LRINT_F128,
+                                         RTLIB::LRINT_PPCF128));
+    break;
+  case ISD::LLRINT:
+    Results.push_back(ExpandArgFPLibCall(Node, RTLIB::LLRINT_F32,
+                                         RTLIB::LLRINT_F64, RTLIB::LLRINT_F80,
+                                         RTLIB::LLRINT_F128,
+                                         RTLIB::LLRINT_PPCF128));
+    break;
   case ISD::VAARG:
     Results.push_back(DAG.expandVAArg(Node));
     Results.push_back(Results[0].getValue(1));

lib/CodeGen/SelectionDAG/LegalizeFloatTypes.cpp

@@ -774,6 +774,8 @@ bool DAGTypeLegalizer::SoftenFloatOperand(SDNode *N, unsigned OpNo) {
   case ISD::FP_TO_UINT:  Res = SoftenFloatOp_FP_TO_XINT(N); break;
   case ISD::LROUND:      Res = SoftenFloatOp_LROUND(N); break;
   case ISD::LLROUND:     Res = SoftenFloatOp_LLROUND(N); break;
+  case ISD::LRINT:       Res = SoftenFloatOp_LRINT(N); break;
+  case ISD::LLRINT:      Res = SoftenFloatOp_LLRINT(N); break;
   case ISD::SELECT:      Res = SoftenFloatOp_SELECT(N); break;
   case ISD::SELECT_CC:   Res = SoftenFloatOp_SELECT_CC(N); break;
   case ISD::SETCC:       Res = SoftenFloatOp_SETCC(N); break;
@@ -1068,6 +1070,34 @@ SDValue DAGTypeLegalizer::SoftenFloatOp_LLROUND(SDNode *N) {
                          NVT, Op, false, SDLoc(N)).first;
 }
 
+SDValue DAGTypeLegalizer::SoftenFloatOp_LRINT(SDNode *N) {
+  EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
+
+  SDValue Op = GetSoftenedFloat(N->getOperand(0));
+  EVT RetVT = N->getOperand(0).getValueType().getSimpleVT().SimpleTy;
+  return TLI.makeLibCall(DAG, GetFPLibCall(RetVT,
+                                           RTLIB::LRINT_F32,
+                                           RTLIB::LRINT_F64,
+                                           RTLIB::LRINT_F80,
+                                           RTLIB::LRINT_F128,
+                                           RTLIB::LRINT_PPCF128),
+                         NVT, Op, false, SDLoc(N)).first;
+}
+
+SDValue DAGTypeLegalizer::SoftenFloatOp_LLRINT(SDNode *N) {
+  EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
+
+  SDValue Op = GetSoftenedFloat(N->getOperand(0));
+  EVT RetVT = N->getOperand(0).getValueType().getSimpleVT().SimpleTy;
+  return TLI.makeLibCall(DAG, GetFPLibCall(RetVT,
+                                           RTLIB::LLRINT_F32,
+                                           RTLIB::LLRINT_F64,
+                                           RTLIB::LLRINT_F80,
+                                           RTLIB::LLRINT_F128,
+                                           RTLIB::LLRINT_PPCF128),
+                         NVT, Op, false, SDLoc(N)).first;
+}
+
 //===----------------------------------------------------------------------===//
 //  Float Result Expansion
 //===----------------------------------------------------------------------===//
@@ -1602,6 +1632,8 @@ bool DAGTypeLegalizer::ExpandFloatOperand(SDNode *N, unsigned OpNo) {
   case ISD::FP_TO_UINT: Res = ExpandFloatOp_FP_TO_UINT(N); break;
   case ISD::LROUND:     Res = ExpandFloatOp_LROUND(N); break;
   case ISD::LLROUND:    Res = ExpandFloatOp_LLROUND(N); break;
+  case ISD::LRINT:      Res = ExpandFloatOp_LRINT(N); break;
+  case ISD::LLRINT:     Res = ExpandFloatOp_LLRINT(N); break;
   case ISD::SELECT_CC:  Res = ExpandFloatOp_SELECT_CC(N); break;
   case ISD::SETCC:      Res = ExpandFloatOp_SETCC(N); break;
   case ISD::STORE:      Res = ExpandFloatOp_STORE(cast<StoreSDNode>(N),
@@ -1796,6 +1828,30 @@ SDValue DAGTypeLegalizer::ExpandFloatOp_LLROUND(SDNode *N) {
                          RVT, N->getOperand(0), false, SDLoc(N)).first;
 }
 
+SDValue DAGTypeLegalizer::ExpandFloatOp_LRINT(SDNode *N) {
+  EVT RVT = N->getValueType(0);
+  EVT RetVT = N->getOperand(0).getValueType().getSimpleVT().SimpleTy;
+  return TLI.makeLibCall(DAG, GetFPLibCall(RetVT,
+                                           RTLIB::LRINT_F32,
+                                           RTLIB::LRINT_F64,
+                                           RTLIB::LRINT_F80,
+                                           RTLIB::LRINT_F128,
+                                           RTLIB::LRINT_PPCF128),
+                         RVT, N->getOperand(0), false, SDLoc(N)).first;
+}
+
+SDValue DAGTypeLegalizer::ExpandFloatOp_LLRINT(SDNode *N) {
+  EVT RVT = N->getValueType(0);
+  EVT RetVT = N->getOperand(0).getValueType().getSimpleVT().SimpleTy;
+  return TLI.makeLibCall(DAG, GetFPLibCall(RetVT,
+                                           RTLIB::LLRINT_F32,
+                                           RTLIB::LLRINT_F64,
+                                           RTLIB::LLRINT_F80,
+                                           RTLIB::LLRINT_F128,
+                                           RTLIB::LLRINT_PPCF128),
+                         RVT, N->getOperand(0), false, SDLoc(N)).first;
+}
+
 //===----------------------------------------------------------------------===//
 //  Float Operand Promotion
 //===----------------------------------------------------------------------===//

lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp

@@ -1624,6 +1624,7 @@ void DAGTypeLegalizer::ExpandIntegerResult(SDNode *N, unsigned ResNo) {
   case ISD::FP_TO_SINT:  ExpandIntRes_FP_TO_SINT(N, Lo, Hi); break;
   case ISD::FP_TO_UINT:  ExpandIntRes_FP_TO_UINT(N, Lo, Hi); break;
   case ISD::LLROUND:     ExpandIntRes_LLROUND(N, Lo, Hi); break;
+  case ISD::LLRINT:      ExpandIntRes_LLRINT(N, Lo, Hi); break;
   case ISD::LOAD:        ExpandIntRes_LOAD(cast<LoadSDNode>(N), Lo, Hi); break;
   case ISD::MUL:         ExpandIntRes_MUL(N, Lo, Hi); break;
   case ISD::READCYCLECOUNTER: ExpandIntRes_READCYCLECOUNTER(N, Lo, Hi); break;
@@ -2517,6 +2518,32 @@ void DAGTypeLegalizer::ExpandIntRes_LLROUND(SDNode *N, SDValue &Lo,
                Lo, Hi);
 }
 
+void DAGTypeLegalizer::ExpandIntRes_LLRINT(SDNode *N, SDValue &Lo,
+                                            SDValue &Hi) {
+  RTLIB::Libcall LC = RTLIB::UNKNOWN_LIBCALL;
+  EVT VT = N->getOperand(0).getValueType().getSimpleVT().SimpleTy;
+  if (VT == MVT::f32)
+    LC = RTLIB::LLRINT_F32;
+  else if (VT == MVT::f64)
+    LC = RTLIB::LLRINT_F64;
+  else if (VT == MVT::f80)
+    LC = RTLIB::LLRINT_F80;
+  else if (VT == MVT::f128)
+    LC = RTLIB::LLRINT_F128;
+  else if (VT == MVT::ppcf128)
+    LC = RTLIB::LLRINT_PPCF128;
+  assert(LC != RTLIB::UNKNOWN_LIBCALL && "Unexpected llrint input type!");
+
+  SDValue Op = N->getOperand(0);
+  if (getTypeAction(Op.getValueType()) == TargetLowering::TypePromoteFloat)
+    Op = GetPromotedFloat(Op);
+
+  SDLoc dl(N);
+  EVT RetVT = N->getValueType(0);
+  SplitInteger(TLI.makeLibCall(DAG, LC, RetVT, Op, true/*irrelevant*/, dl).first,
+               Lo, Hi);
+}
+
 void DAGTypeLegalizer::ExpandIntRes_LOAD(LoadSDNode *N,
                                          SDValue &Lo, SDValue &Hi) {
   if (ISD::isNormalLoad(N)) {

lib/CodeGen/SelectionDAG/LegalizeTypes.h

@@ -419,6 +419,7 @@ private:
   void ExpandIntRes_FP_TO_SINT        (SDNode *N, SDValue &Lo, SDValue &Hi);
   void ExpandIntRes_FP_TO_UINT        (SDNode *N, SDValue &Lo, SDValue &Hi);
   void ExpandIntRes_LLROUND           (SDNode *N, SDValue &Lo, SDValue &Hi);
+  void ExpandIntRes_LLRINT            (SDNode *N, SDValue &Lo, SDValue &Hi);
 
   void ExpandIntRes_Logical           (SDNode *N, SDValue &Lo, SDValue &Hi);
   void ExpandIntRes_ADDSUB            (SDNode *N, SDValue &Lo, SDValue &Hi);
@@ -556,6 +557,8 @@ private:
   SDValue SoftenFloatOp_FP_TO_XINT(SDNode *N);
   SDValue SoftenFloatOp_LROUND(SDNode *N);
   SDValue SoftenFloatOp_LLROUND(SDNode *N);
+  SDValue SoftenFloatOp_LRINT(SDNode *N);
+  SDValue SoftenFloatOp_LLRINT(SDNode *N);
   SDValue SoftenFloatOp_SELECT(SDNode *N);
   SDValue SoftenFloatOp_SELECT_CC(SDNode *N);
   SDValue SoftenFloatOp_SETCC(SDNode *N);
@@ -617,6 +620,8 @@ private:
   SDValue ExpandFloatOp_FP_TO_UINT(SDNode *N);
   SDValue ExpandFloatOp_LROUND(SDNode *N);
   SDValue ExpandFloatOp_LLROUND(SDNode *N);
+  SDValue ExpandFloatOp_LRINT(SDNode *N);
+  SDValue ExpandFloatOp_LLRINT(SDNode *N);
   SDValue ExpandFloatOp_SELECT_CC(SDNode *N);
   SDValue ExpandFloatOp_SETCC(SDNode *N);
   SDValue ExpandFloatOp_STORE(SDNode *N, unsigned OpNo);

lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp

@@ -6029,12 +6029,16 @@ void SelectionDAGBuilder::visitIntrinsicCall(const CallInst &I,
     return;
   }
   case Intrinsic::lround:
-  case Intrinsic::llround: {
+  case Intrinsic::llround:
+  case Intrinsic::lrint:
+  case Intrinsic::llrint: {
     unsigned Opcode;
     switch (Intrinsic) {
     default: llvm_unreachable("Impossible intrinsic");  // Can't reach here.
     case Intrinsic::lround:  Opcode = ISD::LROUND;  break;
     case Intrinsic::llround: Opcode = ISD::LLROUND; break;
+    case Intrinsic::lrint:   Opcode = ISD::LRINT;   break;
+    case Intrinsic::llrint:  Opcode = ISD::LLRINT;  break;
     }
 
     EVT RetVT = TLI.getValueType(DAG.getDataLayout(), I.getType());

lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp

@@ -332,6 +332,8 @@ std::string SDNode::getOperationName(const SelectionDAG *G) const {
   case ISD::FP_TO_FP16:                 return "fp_to_fp16";
   case ISD::LROUND:                     return "lround";
   case ISD::LLROUND:                    return "llround";
+  case ISD::LRINT:                      return "lrint";
+  case ISD::LLRINT:                     return "llrint";
 
     // Control flow instructions
   case ISD::BR:                         return "br";

lib/CodeGen/TargetLoweringBase.cpp

@@ -713,6 +713,8 @@ void TargetLoweringBase::initActions() {
     setOperationAction(ISD::FROUND,     VT, Expand);
     setOperationAction(ISD::LROUND,     VT, Expand);
     setOperationAction(ISD::LLROUND,    VT, Expand);
+    setOperationAction(ISD::LRINT,      VT, Expand);
+    setOperationAction(ISD::LLRINT,     VT, Expand);
   }
 
   // Default ISD::TRAP to expand (which turns it into abort).

lib/IR/Verifier.cpp

@@ -4622,7 +4622,9 @@ void Verifier::visitIntrinsicCall(Intrinsic::ID ID, CallBase &Call) {
     break;
   }
   case Intrinsic::lround:
-  case Intrinsic::llround: {
+  case Intrinsic::llround:
+  case Intrinsic::lrint:
+  case Intrinsic::llrint: {
     Type *ValTy = Call.getArgOperand(0)->getType();
     Type *ResultTy = Call.getType();
     Assert(!ValTy->isVectorTy() && !ResultTy->isVectorTy(),

lib/Target/X86/X86ISelLowering.cpp

@@ -674,6 +674,8 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
     setOperationAction(ISD::FMA, MVT::f80, Expand);
     setOperationAction(ISD::LROUND, MVT::f80, Expand);
     setOperationAction(ISD::LLROUND, MVT::f80, Expand);
+    setOperationAction(ISD::LRINT, MVT::f80, Expand);
+    setOperationAction(ISD::LLRINT, MVT::f80, Expand);
   }
 
   // Always use a library call for pow.

test/CodeGen/AArch64/llrint-conv.ll

@@ -0,0 +1,56 @@
+; RUN: llc < %s -mtriple=aarch64 -mattr=+neon | FileCheck %s
+
+; CHECK-LABEL: testmsws:
+; CHECK:       bl      llrintf
+define i32 @testmsws(float %x) {
+entry:
+  %0 = tail call i64 @llvm.llrint.f32(float %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+; CHECK-LABEL: testmsxs:
+; CHECK:       b       llrintf
+define i64 @testmsxs(float %x) {
+entry:
+  %0 = tail call i64 @llvm.llrint.f32(float %x)
+  ret i64 %0
+}
+
+; CHECK-LABEL: testmswd:
+; CHECK:       bl      llrint
+define i32 @testmswd(double %x) {
+entry:
+  %0 = tail call i64 @llvm.llrint.f64(double %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+; CHECK-LABEL: testmsxd:
+; CHECK:       b       llrint
+define i64 @testmsxd(double %x) {
+entry:
+  %0 = tail call i64 @llvm.llrint.f64(double %x)
+  ret i64 %0
+}
+
+; CHECK-LABEL: testmswl:
+; CHECK:       bl      llrintl
+define i32 @testmswl(fp128 %x) {
+entry:
+  %0 = tail call i64 @llvm.llrint.f128(fp128 %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+; CHECK-LABEL: testmsll:
+; CHECK:       b       llrintl
+define i64 @testmsll(fp128 %x) {
+entry:
+  %0 = tail call i64 @llvm.llrint.f128(fp128 %x)
+  ret i64 %0
+}
+
+declare i64 @llvm.llrint.f32(float) nounwind readnone
+declare i64 @llvm.llrint.f64(double) nounwind readnone
+declare i64 @llvm.llrint.f128(fp128) nounwind readnone

test/CodeGen/AArch64/lrint-conv.ll

@@ -0,0 +1,56 @@
+; RUN: llc < %s -mtriple=aarch64 -mattr=+neon | FileCheck %s
+
+; CHECK-LABEL: testmsws:
+; CHECK:       bl      lrintf
+define i32 @testmsws(float %x) {
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f32(float %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+; CHECK-LABEL: testmsxs:
+; CHECK:       b       lrintf
+define i64 @testmsxs(float %x) {
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f32(float %x)
+  ret i64 %0
+}
+
+; CHECK-LABEL: testmswd:
+; CHECK:       bl      lrint
+define i32 @testmswd(double %x) {
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f64(double %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+; CHECK-LABEL: testmsxd:
+; CHECK:       b       lrint
+define i64 @testmsxd(double %x) {
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f64(double %x)
+  ret i64 %0
+}
+
+; CHECK-LABEL: testmswl:
+; CHECK:       bl      lrintl
+define dso_local i32 @testmswl(fp128 %x) {
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f128(fp128 %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+; CHECK-LABEL: testmsll:
+; CHECK:       b       lrintl
+define dso_local i64 @testmsll(fp128 %x) {
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f128(fp128 %x)
+  ret i64 %0
+}
+
+declare i64 @llvm.lrint.i64.f32(float) nounwind readnone
+declare i64 @llvm.lrint.i64.f64(double) nounwind readnone
+declare i64 @llvm.lrint.i64.f128(fp128) nounwind readnone

test/CodeGen/ARM/llrint-conv.ll

@@ -0,0 +1,25 @@
+; RUN: llc < %s -mtriple=arm-eabi -float-abi=soft | FileCheck %s --check-prefix=SOFTFP
+; RUN: llc < %s -mtriple=arm-eabi -float-abi=hard | FileCheck %s --check-prefix=HARDFP
+
+; SOFTFP-LABEL: testmsxs_builtin:
+; SOFTFP:       bl      llrintf
+; HARDFP-LABEL: testmsxs_builtin:
+; HARDFP:       bl      llrintf
+define i64 @testmsxs_builtin(float %x) {
+entry:
+  %0 = tail call i64 @llvm.llrint.f32(float %x)
+  ret i64 %0
+}
+
+; SOFTFP-LABEL: testmsxd_builtin:
+; SOFTFP:       bl      llrint
+; HARDFP-LABEL: testmsxd_builtin:
+; HARDFP:       bl      llrint
+define i64 @testmsxd_builtin(double %x) {
+entry:
+  %0 = tail call i64 @llvm.llrint.f64(double %x)
+  ret i64 %0
+}
+
+declare i64 @llvm.llrint.f32(float) nounwind readnone
+declare i64 @llvm.llrint.f64(double) nounwind readnone

test/CodeGen/ARM/lrint-conv.ll

@@ -0,0 +1,25 @@
+; RUN: llc < %s -mtriple=arm-eabi -float-abi=soft | FileCheck %s --check-prefix=SOFTFP
+; RUN: llc < %s -mtriple=arm-eabi -float-abi=hard | FileCheck %s --check-prefix=HARDFP
+
+; SOFTFP-LABEL: testmsws_builtin:
+; SOFTFP:       bl      lrintf
+; HARDFP-LABEL: testmsws_builtin:
+; HARDFP:       bl      lrintf
+define i32 @testmsws_builtin(float %x) {
+entry:
+  %0 = tail call i32 @llvm.lrint.i32.f32(float %x)
+  ret i32 %0
+}
+
+; SOFTFP-LABEL: testmswd_builtin:
+; SOFTFP:       bl      lrint
+; HARDFP-LABEL: testmswd_builtin:
+; HARDFP:       bl      lrint
+define i32 @testmswd_builtin(double %x) {
+entry:
+  %0 = tail call i32 @llvm.lrint.i32.f64(double %x)
+  ret i32 %0
+}
+
+declare i32 @llvm.lrint.i32.f32(float) nounwind readnone
+declare i32 @llvm.lrint.i32.f64(double) nounwind readnone

test/CodeGen/Mips/llrint-conv.ll

@@ -0,0 +1,56 @@
+; RUN: llc < %s -mtriple=mips64el -mattr=+soft-float | FileCheck %s
+
+define signext i32 @testmsws(float %x) {
+; CHECK-LABEL: testmsws:
+; CHECK:       jal     llrintf
+entry:
+  %0 = tail call i64 @llvm.llrint.f32(float %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+define i64 @testmsxs(float %x) {
+; CHECK-LABEL: testmsxs:
+; CHECK:       jal     llrintf
+entry:
+  %0 = tail call i64 @llvm.llrint.f32(float %x)
+  ret i64 %0
+}
+
+define signext i32 @testmswd(double %x) {
+; CHECK-LABEL: testmswd:
+; CHECK:       jal     llrint
+entry:
+  %0 = tail call i64 @llvm.llrint.f64(double %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+define i64 @testmsxd(double %x) {
+; CHECK-LABEL: testmsxd:
+; CHECK:       jal     llrint
+entry:
+  %0 = tail call i64 @llvm.llrint.f64(double %x)
+  ret i64 %0
+}
+
+define signext i32 @testmswl(fp128 %x) {
+; CHECK-LABEL: testmswl:
+; CHECK:       jal     llrintl
+entry:
+  %0 = tail call i64 @llvm.llrint.f128(fp128 %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+define i64 @testmsll(fp128 %x) {
+; CHECK-LABEL: testmsll:
+; CHECK:       jal     llrintl
+entry:
+  %0 = tail call i64 @llvm.llrint.f128(fp128 %x)
+  ret i64 %0
+}
+
+declare i64 @llvm.llrint.f32(float) nounwind readnone
+declare i64 @llvm.llrint.f64(double) nounwind readnone
+declare i64 @llvm.llrint.f128(fp128) nounwind readnone

test/CodeGen/Mips/lrint-conv.ll

@@ -0,0 +1,56 @@
+; RUN: llc < %s -mtriple=mips64el -mattr=+soft-float | FileCheck %s
+
+define signext i32 @testmsws(float %x) {
+; CHECK-LABEL: testmsws:
+; CHECK:       jal     lrintf
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f32(float %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+define i64 @testmsxs(float %x) {
+; CHECK-LABEL: testmsxs:
+; CHECK:       jal     lrintf
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f32(float %x)
+  ret i64 %0
+}
+
+define signext i32 @testmswd(double %x) {
+; CHECK-LABEL: testmswd:
+; CHECK:       jal     lrint
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f64(double %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+define i64 @testmsxd(double %x) {
+; CHECK-LABEL: testmsxd:
+; CHECK:       jal     lrint
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f64(double %x)
+  ret i64 %0
+}
+
+define signext i32 @testmswl(fp128 %x) {
+; CHECK-LABEL: testmswl:
+; CHECK:       jal     lrintl
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f128(fp128 %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+define signext i64 @testmsll(fp128 %x) {
+; CHECK-LABEL: testmsll:
+; CHECK:       jal     lrintl
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f128(fp128 %x)
+  ret i64 %0
+}
+
+declare i64 @llvm.lrint.i64.f32(float) nounwind readnone
+declare i64 @llvm.lrint.i64.f64(double) nounwind readnone
+declare i64 @llvm.lrint.i64.f128(fp128) nounwind readnone

test/CodeGen/PowerPC/llrint-conv.ll

@@ -0,0 +1,56 @@
+; RUN: llc < %s -mtriple=powerpc64le | FileCheck %s
+
+; CHECK-LABEL: testmsws:
+; CHECK:       bl      llrintf
+define signext i32 @testmsws(float %x) {
+entry:
+  %0 = tail call i64 @llvm.llrint.f32(float %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+; CHECK-LABEL: testmsxs:
+; CHECK:       bl      llrintf
+define i64 @testmsxs(float %x) {
+entry:
+  %0 = tail call i64 @llvm.llrint.f32(float %x)
+  ret i64 %0
+}
+
+; CHECK-LABEL: testmswd:
+; CHECK:       bl      llrint
+define signext i32 @testmswd(double %x) {
+entry:
+  %0 = tail call i64 @llvm.llrint.f64(double %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+; CHECK-LABEL: testmsxd:
+; CHECK:       bl      llrint
+define i64 @testmsxd(double %x) {
+entry:
+  %0 = tail call i64 @llvm.llrint.f64(double %x)
+  ret i64 %0
+}
+
+; CHECK-LABEL: testmswl:
+; CHECK:       bl      llrintl
+define signext i32 @testmswl(ppc_fp128 %x) {
+entry:
+  %0 = tail call i64 @llvm.llrint.ppcf128(ppc_fp128 %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+; CHECK-LABEL: testmsll:
+; CHECK:       bl      llrintl
+define i64 @testmsll(ppc_fp128 %x) {
+entry:
+  %0 = tail call i64 @llvm.llrint.ppcf128(ppc_fp128 %x)
+  ret i64 %0
+}
+
+declare i64 @llvm.llrint.f32(float) nounwind readnone
+declare i64 @llvm.llrint.f64(double) nounwind readnone
+declare i64 @llvm.llrint.ppcf128(ppc_fp128) nounwind readnone

test/CodeGen/PowerPC/lrint-conv.ll

@@ -0,0 +1,56 @@
+; RUN: llc < %s -mtriple=powerpc64le | FileCheck %s
+
+; CHECK-LABEL: testmsws:
+; CHECK:       bl      lrintf
+define signext i32 @testmsws(float %x) {
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f32(float %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+; CHECK-LABEL: testmsxs:
+; CHECK:       bl      lrintf
+define i64 @testmsxs(float %x) {
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f32(float %x)
+  ret i64 %0
+}
+
+; CHECK-LABEL: testmswd:
+; CHECK:       bl      lrint
+define signext i32 @testmswd(double %x) {
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f64(double %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+; CHECK-LABEL: testmsxd:
+; CHECK:       bl      lrint
+define i64 @testmsxd(double %x) {
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f64(double %x)
+  ret i64 %0
+}
+
+; CHECK-LABEL: testmswl:
+; CHECK:       bl      lrintl
+define signext i32 @testmswl(ppc_fp128 %x) {
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.ppcf128(ppc_fp128 %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+; CHECK-LABEL: testmsll:
+; CHECK:       bl      lrintl
+define i64 @testmsll(ppc_fp128 %x) {
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.ppcf128(ppc_fp128 %x)
+  ret i64 %0
+}
+
+declare i64 @llvm.lrint.i64.f32(float) nounwind readnone
+declare i64 @llvm.lrint.i64.f64(double) nounwind readnone
+declare i64 @llvm.lrint.i64.ppcf128(ppc_fp128) nounwind readnone

test/CodeGen/X86/llrint-conv-i32.ll

@@ -0,0 +1,60 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=i686-unknown             | FileCheck %s
+; RUN: llc < %s -mtriple=i686-unknown -mattr=sse2 | FileCheck %s --check-prefix=SSE2
+
+define i64 @testmsxs_builtin(float %x) {
+; CHECK-LABEL: testmsxs_builtin:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    pushl %eax
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    flds {{[0-9]+}}(%esp)
+; CHECK-NEXT:    fstps (%esp)
+; CHECK-NEXT:    calll llrintf
+; CHECK-NEXT:    popl %ecx
+; CHECK-NEXT:    .cfi_def_cfa_offset 4
+; CHECK-NEXT:    retl
+;
+; SSE2-LABEL: testmsxs_builtin:
+; SSE2:       # %bb.0: # %entry
+; SSE2-NEXT:    pushl %eax
+; SSE2-NEXT:    .cfi_def_cfa_offset 8
+; SSE2-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
+; SSE2-NEXT:    movss %xmm0, (%esp)
+; SSE2-NEXT:    calll llrintf
+; SSE2-NEXT:    popl %ecx
+; SSE2-NEXT:    .cfi_def_cfa_offset 4
+; SSE2-NEXT:    retl
+entry:
+  %0 = tail call i64 @llvm.llrint.f32(float %x)
+  ret i64 %0
+}
+
+define i64 @testmsxd_builtin(double %x) {
+; CHECK-LABEL: testmsxd_builtin:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    subl $8, %esp
+; CHECK-NEXT:    .cfi_def_cfa_offset 12
+; CHECK-NEXT:    fldl {{[0-9]+}}(%esp)
+; CHECK-NEXT:    fstpl (%esp)
+; CHECK-NEXT:    calll llrint
+; CHECK-NEXT:    addl $8, %esp
+; CHECK-NEXT:    .cfi_def_cfa_offset 4
+; CHECK-NEXT:    retl
+;
+; SSE2-LABEL: testmsxd_builtin:
+; SSE2:       # %bb.0: # %entry
+; SSE2-NEXT:    subl $8, %esp
+; SSE2-NEXT:    .cfi_def_cfa_offset 12
+; SSE2-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
+; SSE2-NEXT:    movsd %xmm0, (%esp)
+; SSE2-NEXT:    calll llrint
+; SSE2-NEXT:    addl $8, %esp
+; SSE2-NEXT:    .cfi_def_cfa_offset 4
+; SSE2-NEXT:    retl
+entry:
+  %0 = tail call i64 @llvm.llrint.f64(double %x)
+  ret i64 %0
+}
+
+declare i64 @llvm.llrint.f32(float) nounwind readnone
+declare i64 @llvm.llrint.f64(double) nounwind readnone

test/CodeGen/X86/llrint-conv.ll

@@ -0,0 +1,83 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s
+
+define i32 @testmsws(float %x) {
+; CHECK-LABEL: testmsws:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    callq llrintf
+; CHECK-NEXT:    # kill: def $eax killed $eax killed $rax
+; CHECK-NEXT:    popq %rcx
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    retq
+entry:
+  %0 = tail call i64 @llvm.llrint.f32(float %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+define i64 @testmsxs(float %x) {
+; CHECK-LABEL: testmsxs:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    jmp llrintf # TAILCALL
+entry:
+  %0 = tail call i64 @llvm.llrint.f32(float %x)
+  ret i64 %0
+}
+
+define i32 @testmswd(double %x) {
+; CHECK-LABEL: testmswd:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    callq llrint
+; CHECK-NEXT:    # kill: def $eax killed $eax killed $rax
+; CHECK-NEXT:    popq %rcx
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    retq
+entry:
+  %0 = tail call i64 @llvm.llrint.f64(double %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+define i64 @testmsxd(double %x) {
+; CHECK-LABEL: testmsxd:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    jmp llrint # TAILCALL
+entry:
+  %0 = tail call i64 @llvm.llrint.f64(double %x)
+  ret i64 %0
+}
+
+define dso_local i32 @testmswl(x86_fp80 %x) {
+; CHECK-LABEL: testmswl:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    subq $24, %rsp
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
+; CHECK-NEXT:    fldt {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    fstpt (%rsp)
+; CHECK-NEXT:    callq llrintl
+; CHECK-NEXT:    # kill: def $eax killed $eax killed $rax
+; CHECK-NEXT:    addq $24, %rsp
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    retq
+entry:
+  %0 = tail call i64 @llvm.llrint.f80(x86_fp80 %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+define dso_local i64 @testmsll(x86_fp80 %x) {
+; CHECK-LABEL: testmsll:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    jmp llrintl # TAILCALL
+entry:
+  %0 = tail call i64 @llvm.llrint.f80(x86_fp80 %x)
+  ret i64 %0
+}
+
+declare i64 @llvm.llrint.f32(float) nounwind readnone
+declare i64 @llvm.llrint.f64(double) nounwind readnone
+declare i64 @llvm.llrint.f80(x86_fp80) nounwind readnone

test/CodeGen/X86/lrint-conv-i32.ll

@@ -0,0 +1,32 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=i686-unknown             | FileCheck %s
+; RUN: llc < %s -mtriple=i686-unknown -mattr=sse2 | FileCheck %s --check-prefix=SSE2
+
+define i32 @testmsws_builtin(float %x) {
+; CHECK-LABEL: testmsws_builtin:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    jmp lrintf # TAILCALL
+;
+; SSE2-LABEL: testmsws_builtin:
+; SSE2:       # %bb.0: # %entry
+; SSE2-NEXT:    jmp lrintf # TAILCALL
+entry:
+  %0 = tail call i32 @llvm.lrint.i32.f32(float %x)
+  ret i32 %0
+}
+
+define i32 @testmswd_builtin(double %x) {
+; CHECK-LABEL: testmswd_builtin:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    jmp lrint # TAILCALL
+;
+; SSE2-LABEL: testmswd_builtin:
+; SSE2:       # %bb.0: # %entry
+; SSE2-NEXT:    jmp lrint # TAILCALL
+entry:
+  %0 = tail call i32 @llvm.lrint.i32.f64(double %x)
+  ret i32 %0
+}
+
+declare i32 @llvm.lrint.i32.f32(float) nounwind readnone
+declare i32 @llvm.lrint.i32.f64(double) nounwind readnone

test/CodeGen/X86/lrint-conv.ll

@@ -0,0 +1,83 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s
+
+define i32 @testmsws(float %x) {
+; CHECK-LABEL: testmsws:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    callq lrintf
+; CHECK-NEXT:    # kill: def $eax killed $eax killed $rax
+; CHECK-NEXT:    popq %rcx
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    retq
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f32(float %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+define i64 @testmsxs(float %x) {
+; CHECK-LABEL: testmsxs:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    jmp lrintf # TAILCALL
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f32(float %x)
+  ret i64 %0
+}
+
+define i32 @testmswd(double %x) {
+; CHECK-LABEL: testmswd:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    callq lrint
+; CHECK-NEXT:    # kill: def $eax killed $eax killed $rax
+; CHECK-NEXT:    popq %rcx
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    retq
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f64(double %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+define i64 @testmsxd(double %x) {
+; CHECK-LABEL: testmsxd:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    jmp lrint # TAILCALL
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f64(double %x)
+  ret i64 %0
+}
+
+define dso_local i32 @testmswl(x86_fp80 %x) {
+; CHECK-LABEL: testmswl:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    subq $24, %rsp
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
+; CHECK-NEXT:    fldt {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    fstpt (%rsp)
+; CHECK-NEXT:    callq lrintl
+; CHECK-NEXT:    # kill: def $eax killed $eax killed $rax
+; CHECK-NEXT:    addq $24, %rsp
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    retq
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f80(x86_fp80 %x)
+  %conv = trunc i64 %0 to i32
+  ret i32 %conv
+}
+
+define dso_local i64 @testmsll(x86_fp80 %x) {
+; CHECK-LABEL: testmsll:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    jmp lrintl # TAILCALL
+entry:
+  %0 = tail call i64 @llvm.lrint.i64.f80(x86_fp80 %x)
+  ret i64 %0
+}
+
+declare i64 @llvm.lrint.i64.f32(float) nounwind readnone
+declare i64 @llvm.lrint.i64.f64(double) nounwind readnone
+declare i64 @llvm.lrint.i64.f80(x86_fp80) nounwind readnone