[RISCV] Improve vector fround lowering by changing FRM.

[craig.topper]

Summary

This is a follow to D133238 which did this for ceil/floor.

[arcbbb]

Look good to me.

[frasercrmck]

LGTM too

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

1839

Mention FROUND in comment?

[reames]

LGTM to me too.

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

1894

Very minor style comment: the first three of these could be combined by tweaking the existing matchRoundingOp to directly map opcode to rounding mode and then reusing it here.

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

 //===-- RISCVISelLowering.cpp - RISCV DAG Lowering Implementation  --------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
static SDValue lowerFP_TO_INT_SAT(SDValue Op, SelectionDAG &DAG,
   SDValue FpToInt = DAG.getNode(
       Opc, DL, DstVT, Src,
       DAG.getTargetConstant(RISCVFPRndMode::RTZ, DL, Subtarget.getXLenVT()));
 
   SDValue ZeroInt = DAG.getConstant(0, DL, DstVT);
   return DAG.getSelectCC(DL, Src, Src, ZeroInt, FpToInt, ISD::CondCode::SETUO);
 }
 
 // Expand vector FTRUNC, FCEIL, and FFLOOR by converting to the integer domain
 // and back. Taking care to avoid converting values that are nan or already
 // correct.
-static SDValue lowerFTRUNC_FCEIL_FFLOOR(SDValue Op, SelectionDAG &DAG,
+static SDValue lowerFTRUNC_FCEIL_FFLOOR_FROUND(SDValue Op, SelectionDAG &DAG,
                                                const RISCVSubtarget &Subtarget) {
   MVT VT = Op.getSimpleValueType();
   assert(VT.isVector() && "Unexpected type");
 
   SDLoc DL(Op);
 
   SDValue Src = Op.getOperand(0);
 
   MVT ContainerVT = VT;
static SDValue lowerFTRUNC_FCEIL_FFLOOR_FROUND(SDValue Op, SelectionDAG &DAG,
   // Truncate to integer and convert back to FP.
   MVT IntVT = ContainerVT.changeVectorElementTypeToInteger();
   MVT XLenVT = Subtarget.getXLenVT();
   SDValue Truncated;
 
   switch (Op.getOpcode()) {
   default:
     llvm_unreachable("Unexpected opcode");
   case ISD::FCEIL:
     Truncated =
         DAG.getNode(RISCVISD::VFCVT_X_F_VL, DL, IntVT, Src, Mask,
                     DAG.getTargetConstant(RISCVFPRndMode::RUP, DL, XLenVT), VL);
     break;
   case ISD::FFLOOR:
     Truncated =
         DAG.getNode(RISCVISD::VFCVT_X_F_VL, DL, IntVT, Src, Mask,
                     DAG.getTargetConstant(RISCVFPRndMode::RDN, DL, XLenVT), VL);
     break;
+  case ISD::FROUND:
+    Truncated =
+        DAG.getNode(RISCVISD::VFCVT_X_F_VL, DL, IntVT, Src, Mask,
+                    DAG.getTargetConstant(RISCVFPRndMode::RMM, DL, XLenVT), VL);
+    break;
   case ISD::FTRUNC:
     Truncated = DAG.getNode(RISCVISD::FP_TO_SINT_VL, DL, IntVT, Src, Mask, VL);
     break;
   }
 
   Truncated = DAG.getNode(RISCVISD::SINT_TO_FP_VL, DL, ContainerVT, Truncated,
                           Mask, VL);
 
   // Restore the original sign so that -0.0 is preserved.
   Truncated = DAG.getNode(RISCVISD::FCOPYSIGN_VL, DL, ContainerVT, Truncated,
                           Src, Src, Mask, VL);
 
   if (!VT.isFixedLengthVector())
     return Truncated;
 
   return convertFromScalableVector(VT, Truncated, DAG, Subtarget);
 }
 
-// ISD::FROUND is defined to round to nearest with ties rounding away from 0.
-// This mode isn't supported in vector hardware on RISCV. But as long as we
-// aren't compiling with trapping math, we can emulate this with
-// floor(X + copysign(nextafter(0.5, 0.0), X)).
-// FIXME: Could be shorter by changing rounding mode, but we don't have FRM
-// dependencies modeled yet.
-static SDValue lowerFROUND(SDValue Op, SelectionDAG &DAG,
-                           const RISCVSubtarget &Subtarget) {
-  MVT VT = Op.getSimpleValueType();
-  assert(VT.isVector() && "Unexpected type");
-
-  SDLoc DL(Op);
-
-  SDValue Src = Op.getOperand(0);
-
-  MVT ContainerVT = VT;
-  if (VT.isFixedLengthVector()) {
-    ContainerVT = getContainerForFixedLengthVector(DAG, VT, Subtarget);
-    Src = convertToScalableVector(ContainerVT, Src, DAG, Subtarget);
-  }
-
-  SDValue TrueMask, VL;
-  std::tie(TrueMask, VL) = getDefaultVLOps(VT, ContainerVT, DL, DAG, Subtarget);
-
-  // Freeze the source since we are increasing the number of uses.
-  Src = DAG.getFreeze(Src);
-
-  // We do the conversion on the absolute value and fix the sign at the end.
-  SDValue Abs =
-      DAG.getNode(RISCVISD::FABS_VL, DL, ContainerVT, Src, TrueMask, VL);
-
-  // Determine the largest integer that can be represented exactly. This and
-  // values larger than it don't have any fractional bits so don't need to
-  // be converted.
-  const fltSemantics &FltSem = DAG.EVTToAPFloatSemantics(ContainerVT);
-  unsigned Precision = APFloat::semanticsPrecision(FltSem);
-  APFloat MaxVal = APFloat(FltSem);
-  MaxVal.convertFromAPInt(APInt::getOneBitSet(Precision, Precision - 1),
-                          /*IsSigned*/ false, APFloat::rmNearestTiesToEven);
-  SDValue MaxValNode =
-      DAG.getConstantFP(MaxVal, DL, ContainerVT.getVectorElementType());
-  SDValue MaxValSplat = DAG.getNode(RISCVISD::VFMV_V_F_VL, DL, ContainerVT,
-                                    DAG.getUNDEF(ContainerVT), MaxValNode, VL);
-
-  // If abs(Src) was larger than MaxVal or nan, keep it.
-  MVT SetccVT = MVT::getVectorVT(MVT::i1, ContainerVT.getVectorElementCount());
-  SDValue Mask = DAG.getNode(RISCVISD::SETCC_VL, DL, SetccVT,
-                             {Abs, MaxValSplat, DAG.getCondCode(ISD::SETOLT),
-                              DAG.getUNDEF(SetccVT), TrueMask, VL});
-
-  bool Ignored;
-  APFloat Point5Pred = APFloat(0.5f);
-  Point5Pred.convert(FltSem, APFloat::rmNearestTiesToEven, &Ignored);
-  Point5Pred.next(/*nextDown*/ true);
-  SDValue SplatVal =
-      DAG.getConstantFP(Point5Pred, DL, ContainerVT.getVectorElementType());
-  SDValue Splat = DAG.getNode(RISCVISD::VFMV_V_F_VL, DL, ContainerVT,
-                              DAG.getUNDEF(ContainerVT), SplatVal, VL);
-
-  // Add the adjustment.
-  SDValue Adjust = DAG.getNode(RISCVISD::FADD_VL, DL, ContainerVT, Abs, Splat,
-                               DAG.getUNDEF(ContainerVT), Mask, VL);
-
-  // Truncate to integer and convert back to fp.
-  MVT IntVT = ContainerVT.changeVectorElementTypeToInteger();
-  SDValue Truncated =
-      DAG.getNode(RISCVISD::FP_TO_SINT_VL, DL, IntVT, Adjust, Mask, VL);
-
-  Truncated = DAG.getNode(RISCVISD::SINT_TO_FP_VL, DL, ContainerVT, Truncated,
-                          Mask, VL);
-
-  // Restore the original sign and merge the original source to masked off
-  // lanes.
-  Truncated = DAG.getNode(RISCVISD::FCOPYSIGN_VL, DL, ContainerVT, Truncated,
-                          Src, Src, Mask, VL);
-
-  if (!VT.isFixedLengthVector())
-    return Truncated;
-
-  return convertFromScalableVector(VT, Truncated, DAG, Subtarget);
-}
-
 struct VIDSequence {
   int64_t StepNumerator;
   unsigned StepDenominator;
   int64_t Addend;
 };
 
 // Try to match an arithmetic-sequence BUILD_VECTOR [X,X+S,X+2*S,...,X+(N-1)*S]
 // to the (non-zero) step S and start value X. This can be then lowered as the
case ISD::UINT_TO_FP: {
     return convertFromScalableVector(VT, Src, DAG, Subtarget);
   }
   case ISD::FP_TO_SINT_SAT:
   case ISD::FP_TO_UINT_SAT:
     return lowerFP_TO_INT_SAT(Op, DAG, Subtarget);
   case ISD::FTRUNC:
   case ISD::FCEIL:
   case ISD::FFLOOR:
-    return lowerFTRUNC_FCEIL_FFLOOR(Op, DAG, Subtarget);
   case ISD::FROUND:
-    return lowerFROUND(Op, DAG, Subtarget);
+    return lowerFTRUNC_FCEIL_FFLOOR_FROUND(Op, DAG, Subtarget);
   case ISD::VECREDUCE_ADD:
   case ISD::VECREDUCE_UMAX:
   case ISD::VECREDUCE_SMAX:
   case ISD::VECREDUCE_UMIN:
   case ISD::VECREDUCE_SMIN:
     return lowerVECREDUCE(Op, DAG);
   case ISD::VECREDUCE_AND:
   case ISD::VECREDUCE_OR:

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

 //===-- RISCVTargetTransformInfo.cpp - RISC-V specific TTI ----------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
static const CostTblEntry VectorIntrinsicCostTable[]{
     {Intrinsic::trunc, MVT::v2f64, 7},
     {Intrinsic::trunc, MVT::v4f64, 7},
     {Intrinsic::trunc, MVT::v8f64, 7},
     {Intrinsic::trunc, MVT::v16f64, 7},
     {Intrinsic::trunc, MVT::nxv1f64, 7},
     {Intrinsic::trunc, MVT::nxv2f64, 7},
     {Intrinsic::trunc, MVT::nxv4f64, 7},
     {Intrinsic::trunc, MVT::nxv8f64, 7},
-    {Intrinsic::round, MVT::v2f32, 10},
-    {Intrinsic::round, MVT::v4f32, 10},
-    {Intrinsic::round, MVT::v8f32, 10},
-    {Intrinsic::round, MVT::v16f32, 10},
-    {Intrinsic::round, MVT::nxv2f32, 10},
-    {Intrinsic::round, MVT::nxv4f32, 10},
-    {Intrinsic::round, MVT::nxv8f32, 10},
-    {Intrinsic::round, MVT::nxv16f32, 10},
-    {Intrinsic::round, MVT::v2f64, 10},
-    {Intrinsic::round, MVT::v4f64, 10},
-    {Intrinsic::round, MVT::v8f64, 10},
-    {Intrinsic::round, MVT::v16f64, 10},
-    {Intrinsic::round, MVT::nxv1f64, 10},
-    {Intrinsic::round, MVT::nxv2f64, 10},
-    {Intrinsic::round, MVT::nxv4f64, 10},
-    {Intrinsic::round, MVT::nxv8f64, 10},
+    {Intrinsic::round, MVT::v2f32, 9},
+    {Intrinsic::round, MVT::v4f32, 9},
+    {Intrinsic::round, MVT::v8f32, 9},
+    {Intrinsic::round, MVT::v16f32, 9},
+    {Intrinsic::round, MVT::nxv2f32, 9},
+    {Intrinsic::round, MVT::nxv4f32, 9},
+    {Intrinsic::round, MVT::nxv8f32, 9},
+    {Intrinsic::round, MVT::nxv16f32, 9},
+    {Intrinsic::round, MVT::v2f64, 9},
+    {Intrinsic::round, MVT::v4f64, 9},
+    {Intrinsic::round, MVT::v8f64, 9},
+    {Intrinsic::round, MVT::v16f64, 9},
+    {Intrinsic::round, MVT::nxv1f64, 9},
+    {Intrinsic::round, MVT::nxv2f64, 9},
+    {Intrinsic::round, MVT::nxv4f64, 9},
+    {Intrinsic::round, MVT::nxv8f64, 9},
     {Intrinsic::fabs, MVT::v2f32, 1},
     {Intrinsic::fabs, MVT::v4f32, 1},
     {Intrinsic::fabs, MVT::v8f32, 1},
     {Intrinsic::fabs, MVT::v16f32, 1},
     {Intrinsic::fabs, MVT::nxv2f32, 1},
     {Intrinsic::fabs, MVT::nxv4f32, 1},
     {Intrinsic::fabs, MVT::nxv8f32, 1},
     {Intrinsic::fabs, MVT::nxv16f32, 1},

llvm/test/Analysis/CostModel/RISCV/fround.ll

;
   call <vscale x 4 x double> @llvm.nearbyint.nvx5f64(<vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.nearbyint.nvx8f64(<vscale x 8 x double> undef)
   ret void
 }
 
 define void @round() {
 ; CHECK-LABEL: 'round'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %1 = call float @llvm.round.f32(float undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %2 = call <2 x float> @llvm.round.v2f32(<2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %3 = call <4 x float> @llvm.round.v4f32(<4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %4 = call <8 x float> @llvm.round.v8f32(<8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %5 = call <16 x float> @llvm.round.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %6 = call <vscale x 2 x float> @llvm.round.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %7 = call <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %8 = call <vscale x 8 x float> @llvm.round.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %9 = call <vscale x 16 x float> @llvm.round.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %2 = call <2 x float> @llvm.round.v2f32(<2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %3 = call <4 x float> @llvm.round.v4f32(<4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %4 = call <8 x float> @llvm.round.v8f32(<8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %5 = call <16 x float> @llvm.round.v16f32(<16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %6 = call <vscale x 2 x float> @llvm.round.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %7 = call <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %8 = call <vscale x 8 x float> @llvm.round.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %9 = call <vscale x 16 x float> @llvm.round.nxv16f32(<vscale x 16 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.round.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call <2 x double> @llvm.round.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %12 = call <4 x double> @llvm.round.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %13 = call <8 x double> @llvm.round.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %14 = call <16 x double> @llvm.round.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %15 = call <vscale x 1 x double> @llvm.round.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %16 = call <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %17 = call <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %18 = call <vscale x 8 x double> @llvm.round.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %11 = call <2 x double> @llvm.round.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %12 = call <4 x double> @llvm.round.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %13 = call <8 x double> @llvm.round.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %14 = call <16 x double> @llvm.round.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %15 = call <vscale x 1 x double> @llvm.round.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 8 x double> @llvm.round.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.round.f32(float undef)
   call <2 x float> @llvm.round.v2f32(<2 x float> undef)
   call <4 x float> @llvm.round.v4f32(<4 x float> undef)
   call <8 x float> @llvm.round.v8f32(<8 x float> undef)
   call <16 x float> @llvm.round.v16f32(<16 x float> undef)
   call <vscale x 2 x float> @llvm.round.nvx2f32(<vscale x 2 x float> undef)

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp.ll

 
 define void @round_v8f16(<8 x half>* %x) {
 ; CHECK-LABEL: round_v8f16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
 ; CHECK-NEXT:    vle16.v v8, (a0)
 ; CHECK-NEXT:    lui a1, %hi(.LCPI100_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI100_0)(a1)
-; CHECK-NEXT:    lui a1, %hi(.LCPI100_1)
-; CHECK-NEXT:    flh ft1, %lo(.LCPI100_1)(a1)
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
-; CHECK-NEXT:    vfadd.vf v9, v9, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v9, v0.t
+; CHECK-NEXT:    fsrmi a1, 4
+; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
+; CHECK-NEXT:    fsrm a1
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    vse16.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <8 x half>, <8 x half>* %x
   %b = call <8 x half> @llvm.round.v8f16(<8 x half> %a)
   store <8 x half> %b, <8 x half>* %x
   ret void
 }
 declare <8 x half> @llvm.round.v8f16(<8 x half>)
 
 define void @round_v4f32(<4 x float>* %x) {
 ; CHECK-LABEL: round_v4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
 ; CHECK-NEXT:    vle32.v v8, (a0)
 ; CHECK-NEXT:    lui a1, %hi(.LCPI101_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI101_0)(a1)
-; CHECK-NEXT:    lui a1, %hi(.LCPI101_1)
-; CHECK-NEXT:    flw ft1, %lo(.LCPI101_1)(a1)
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
-; CHECK-NEXT:    vfadd.vf v9, v9, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v9, v0.t
+; CHECK-NEXT:    fsrmi a1, 4
+; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
+; CHECK-NEXT:    fsrm a1
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    vse32.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <4 x float>, <4 x float>* %x
   %b = call <4 x float> @llvm.round.v4f32(<4 x float> %a)
   store <4 x float> %b, <4 x float>* %x
   ret void
 }
 declare <4 x float> @llvm.round.v4f32(<4 x float>)
 
 define void @round_v2f64(<2 x double>* %x) {
 ; CHECK-LABEL: round_v2f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
 ; CHECK-NEXT:    vle64.v v8, (a0)
 ; CHECK-NEXT:    lui a1, %hi(.LCPI102_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI102_0)(a1)
-; CHECK-NEXT:    lui a1, %hi(.LCPI102_1)
-; CHECK-NEXT:    fld ft1, %lo(.LCPI102_1)(a1)
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
-; CHECK-NEXT:    vfadd.vf v9, v9, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v9, v0.t
+; CHECK-NEXT:    fsrmi a1, 4
+; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
+; CHECK-NEXT:    fsrm a1
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    vse64.v v8, (a0)
 ; CHECK-NEXT:    ret
   %a = load <2 x double>, <2 x double>* %x
   %b = call <2 x double> @llvm.round.v2f64(<2 x double> %a)
   store <2 x double> %b, <2 x double>* %x
   ret void

llvm/test/CodeGen/RISCV/rvv/fround-sdnode.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=ilp32d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d \
 ; RUN:     -verify-machineinstrs < %s | FileCheck %s
 
 define <vscale x 1 x half> @round_nxv1f16(<vscale x 1 x half> %x) {
 ; CHECK-LABEL: round_nxv1f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    lui a0, %hi(.LCPI0_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a0)
-; CHECK-NEXT:    lui a0, %hi(.LCPI0_1)
-; CHECK-NEXT:    flh ft1, %lo(.LCPI0_1)(a0)
+; CHECK-NEXT:    vsetvli a0, zero, e16, mf4, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
-; CHECK-NEXT:    vfadd.vf v9, v9, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v9, v0.t
+; CHECK-NEXT:    fsrmi a0, 4
+; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
+; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x half> @llvm.round.nxv1f16(<vscale x 1 x half> %x)
   ret <vscale x 1 x half> %a
 }
 declare <vscale x 1 x half> @llvm.round.nxv1f16(<vscale x 1 x half>)
 
 define <vscale x 2 x half> @round_nxv2f16(<vscale x 2 x half> %x) {
 ; CHECK-LABEL: round_nxv2f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    lui a0, %hi(.LCPI1_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a0)
-; CHECK-NEXT:    lui a0, %hi(.LCPI1_1)
-; CHECK-NEXT:    flh ft1, %lo(.LCPI1_1)(a0)
+; CHECK-NEXT:    vsetvli a0, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
-; CHECK-NEXT:    vfadd.vf v9, v9, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v9, v0.t
+; CHECK-NEXT:    fsrmi a0, 4
+; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
+; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x half> @llvm.round.nxv2f16(<vscale x 2 x half> %x)
   ret <vscale x 2 x half> %a
 }
 declare <vscale x 2 x half> @llvm.round.nxv2f16(<vscale x 2 x half>)
 
 define <vscale x 4 x half> @round_nxv4f16(<vscale x 4 x half> %x) {
 ; CHECK-LABEL: round_nxv4f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    lui a0, %hi(.LCPI2_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a0)
-; CHECK-NEXT:    lui a0, %hi(.LCPI2_1)
-; CHECK-NEXT:    flh ft1, %lo(.LCPI2_1)(a0)
+; CHECK-NEXT:    vsetvli a0, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
-; CHECK-NEXT:    vfadd.vf v9, v9, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v9, v0.t
+; CHECK-NEXT:    fsrmi a0, 4
+; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
+; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x half> @llvm.round.nxv4f16(<vscale x 4 x half> %x)
   ret <vscale x 4 x half> %a
 }
 declare <vscale x 4 x half> @llvm.round.nxv4f16(<vscale x 4 x half>)
 
 define <vscale x 8 x half> @round_nxv8f16(<vscale x 8 x half> %x) {
 ; CHECK-LABEL: round_nxv8f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    lui a0, %hi(.LCPI3_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a0)
-; CHECK-NEXT:    lui a0, %hi(.LCPI3_1)
-; CHECK-NEXT:    flh ft1, %lo(.LCPI3_1)(a0)
+; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
-; CHECK-NEXT:    vfadd.vf v10, v10, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v10, v10, v0.t
+; CHECK-NEXT:    fsrmi a0, 4
+; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
+; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x half> @llvm.round.nxv8f16(<vscale x 8 x half> %x)
   ret <vscale x 8 x half> %a
 }
 declare <vscale x 8 x half> @llvm.round.nxv8f16(<vscale x 8 x half>)
 
 define <vscale x 16 x half> @round_nxv16f16(<vscale x 16 x half> %x) {
 ; CHECK-LABEL: round_nxv16f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    lui a0, %hi(.LCPI4_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a0)
-; CHECK-NEXT:    lui a0, %hi(.LCPI4_1)
-; CHECK-NEXT:    flh ft1, %lo(.LCPI4_1)(a0)
+; CHECK-NEXT:    vsetvli a0, zero, e16, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
-; CHECK-NEXT:    vfadd.vf v12, v12, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v12, v12, v0.t
+; CHECK-NEXT:    fsrmi a0, 4
+; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
+; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 16 x half> @llvm.round.nxv16f16(<vscale x 16 x half> %x)
   ret <vscale x 16 x half> %a
 }
 declare <vscale x 16 x half> @llvm.round.nxv16f16(<vscale x 16 x half>)
 
 define <vscale x 32 x half> @round_nxv32f16(<vscale x 32 x half> %x) {
 ; CHECK-LABEL: round_nxv32f16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    lui a0, %hi(.LCPI5_0)
 ; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a0)
-; CHECK-NEXT:    lui a0, %hi(.LCPI5_1)
-; CHECK-NEXT:    flh ft1, %lo(.LCPI5_1)(a0)
+; CHECK-NEXT:    vsetvli a0, zero, e16, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
-; CHECK-NEXT:    vfadd.vf v16, v16, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v16, v16, v0.t
+; CHECK-NEXT:    fsrmi a0, 4
+; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
+; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 32 x half> @llvm.round.nxv32f16(<vscale x 32 x half> %x)
   ret <vscale x 32 x half> %a
 }
 declare <vscale x 32 x half> @llvm.round.nxv32f16(<vscale x 32 x half>)
 
 define <vscale x 1 x float> @round_nxv1f32(<vscale x 1 x float> %x) {
 ; CHECK-LABEL: round_nxv1f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    lui a0, %hi(.LCPI6_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI6_0)(a0)
-; CHECK-NEXT:    lui a0, %hi(.LCPI6_1)
-; CHECK-NEXT:    flw ft1, %lo(.LCPI6_1)(a0)
+; CHECK-NEXT:    vsetvli a0, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
-; CHECK-NEXT:    vfadd.vf v9, v9, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v9, v0.t
+; CHECK-NEXT:    fsrmi a0, 4
+; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
+; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x float> @llvm.round.nxv1f32(<vscale x 1 x float> %x)
   ret <vscale x 1 x float> %a
 }
 declare <vscale x 1 x float> @llvm.round.nxv1f32(<vscale x 1 x float>)
 
 define <vscale x 2 x float> @round_nxv2f32(<vscale x 2 x float> %x) {
 ; CHECK-LABEL: round_nxv2f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    lui a0, %hi(.LCPI7_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI7_0)(a0)
-; CHECK-NEXT:    lui a0, %hi(.LCPI7_1)
-; CHECK-NEXT:    flw ft1, %lo(.LCPI7_1)(a0)
+; CHECK-NEXT:    vsetvli a0, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
-; CHECK-NEXT:    vfadd.vf v9, v9, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v9, v0.t
+; CHECK-NEXT:    fsrmi a0, 4
+; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
+; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x float> @llvm.round.nxv2f32(<vscale x 2 x float> %x)
   ret <vscale x 2 x float> %a
 }
 declare <vscale x 2 x float> @llvm.round.nxv2f32(<vscale x 2 x float>)
 
 define <vscale x 4 x float> @round_nxv4f32(<vscale x 4 x float> %x) {
 ; CHECK-LABEL: round_nxv4f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    lui a0, %hi(.LCPI8_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI8_0)(a0)
-; CHECK-NEXT:    lui a0, %hi(.LCPI8_1)
-; CHECK-NEXT:    flw ft1, %lo(.LCPI8_1)(a0)
+; CHECK-NEXT:    vsetvli a0, zero, e32, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
-; CHECK-NEXT:    vfadd.vf v10, v10, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v10, v10, v0.t
+; CHECK-NEXT:    fsrmi a0, 4
+; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
+; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> %x)
   ret <vscale x 4 x float> %a
 }
 declare <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float>)
 
 define <vscale x 8 x float> @round_nxv8f32(<vscale x 8 x float> %x) {
 ; CHECK-LABEL: round_nxv8f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    lui a0, %hi(.LCPI9_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI9_0)(a0)
-; CHECK-NEXT:    lui a0, %hi(.LCPI9_1)
-; CHECK-NEXT:    flw ft1, %lo(.LCPI9_1)(a0)
+; CHECK-NEXT:    vsetvli a0, zero, e32, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
-; CHECK-NEXT:    vfadd.vf v12, v12, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v12, v12, v0.t
+; CHECK-NEXT:    fsrmi a0, 4
+; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
+; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x float> @llvm.round.nxv8f32(<vscale x 8 x float> %x)
   ret <vscale x 8 x float> %a
 }
 declare <vscale x 8 x float> @llvm.round.nxv8f32(<vscale x 8 x float>)
 
 define <vscale x 16 x float> @round_nxv16f32(<vscale x 16 x float> %x) {
 ; CHECK-LABEL: round_nxv16f32:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    lui a0, %hi(.LCPI10_0)
 ; CHECK-NEXT:    flw ft0, %lo(.LCPI10_0)(a0)
-; CHECK-NEXT:    lui a0, %hi(.LCPI10_1)
-; CHECK-NEXT:    flw ft1, %lo(.LCPI10_1)(a0)
+; CHECK-NEXT:    vsetvli a0, zero, e32, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
-; CHECK-NEXT:    vfadd.vf v16, v16, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v16, v16, v0.t
+; CHECK-NEXT:    fsrmi a0, 4
+; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
+; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 16 x float> @llvm.round.nxv16f32(<vscale x 16 x float> %x)
   ret <vscale x 16 x float> %a
 }
 declare <vscale x 16 x float> @llvm.round.nxv16f32(<vscale x 16 x float>)
 
 define <vscale x 1 x double> @round_nxv1f64(<vscale x 1 x double> %x) {
 ; CHECK-LABEL: round_nxv1f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    lui a0, %hi(.LCPI11_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI11_0)(a0)
-; CHECK-NEXT:    lui a0, %hi(.LCPI11_1)
-; CHECK-NEXT:    fld ft1, %lo(.LCPI11_1)(a0)
+; CHECK-NEXT:    vsetvli a0, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfabs.v v9, v8
 ; CHECK-NEXT:    vmflt.vf v0, v9, ft0
-; CHECK-NEXT:    vfadd.vf v9, v9, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v9, v9, v0.t
+; CHECK-NEXT:    fsrmi a0, 4
+; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
+; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 1 x double> @llvm.round.nxv1f64(<vscale x 1 x double> %x)
   ret <vscale x 1 x double> %a
 }
 declare <vscale x 1 x double> @llvm.round.nxv1f64(<vscale x 1 x double>)
 
 define <vscale x 2 x double> @round_nxv2f64(<vscale x 2 x double> %x) {
 ; CHECK-LABEL: round_nxv2f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    lui a0, %hi(.LCPI12_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI12_0)(a0)
-; CHECK-NEXT:    lui a0, %hi(.LCPI12_1)
-; CHECK-NEXT:    fld ft1, %lo(.LCPI12_1)(a0)
+; CHECK-NEXT:    vsetvli a0, zero, e64, m2, ta, mu
 ; CHECK-NEXT:    vfabs.v v10, v8
 ; CHECK-NEXT:    vmflt.vf v0, v10, ft0
-; CHECK-NEXT:    vfadd.vf v10, v10, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v10, v10, v0.t
+; CHECK-NEXT:    fsrmi a0, 4
+; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
+; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> %x)
   ret <vscale x 2 x double> %a
 }
 declare <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double>)
 
 define <vscale x 4 x double> @round_nxv4f64(<vscale x 4 x double> %x) {
 ; CHECK-LABEL: round_nxv4f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    lui a0, %hi(.LCPI13_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI13_0)(a0)
-; CHECK-NEXT:    lui a0, %hi(.LCPI13_1)
-; CHECK-NEXT:    fld ft1, %lo(.LCPI13_1)(a0)
+; CHECK-NEXT:    vsetvli a0, zero, e64, m4, ta, mu
 ; CHECK-NEXT:    vfabs.v v12, v8
 ; CHECK-NEXT:    vmflt.vf v0, v12, ft0
-; CHECK-NEXT:    vfadd.vf v12, v12, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v12, v12, v0.t
+; CHECK-NEXT:    fsrmi a0, 4
+; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
+; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double> %x)
   ret <vscale x 4 x double> %a
 }
 declare <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double>)
 
 define <vscale x 8 x double> @round_nxv8f64(<vscale x 8 x double> %x) {
 ; CHECK-LABEL: round_nxv8f64:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    lui a0, %hi(.LCPI14_0)
 ; CHECK-NEXT:    fld ft0, %lo(.LCPI14_0)(a0)
-; CHECK-NEXT:    lui a0, %hi(.LCPI14_1)
-; CHECK-NEXT:    fld ft1, %lo(.LCPI14_1)(a0)
+; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfabs.v v16, v8
 ; CHECK-NEXT:    vmflt.vf v0, v16, ft0
-; CHECK-NEXT:    vfadd.vf v16, v16, ft1, v0.t
-; CHECK-NEXT:    vfcvt.rtz.x.f.v v16, v16, v0.t
+; CHECK-NEXT:    fsrmi a0, 4
+; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
+; CHECK-NEXT:    fsrm a0
 ; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
 ; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
 ; CHECK-NEXT:    ret
   %a = call <vscale x 8 x double> @llvm.round.nxv8f64(<vscale x 8 x double> %x)
   ret <vscale x 8 x double> %a
 }
 declare <vscale x 8 x double> @llvm.round.nxv8f64(<vscale x 8 x double>)