[VP][RISCV] Add vp.ceil and RISC-V support

[craig.topper]

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-ceil-vp.ll

15

This is using the wrong AVL and the mask has been ignored.

[eopXD]

Update code.

[craig.topper]

llvm/docs/LangRef.rst

21434

"ceil value" -> ceiling

21448

"ceil value" -> ceiling

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

328

VP_CEIL is only valid for vectors. MVT::f16 is a scalar.

665

Isn't this already done by line 701 after updating FloatingPointVPOps?

909

Already done by line 919?

1983

Swap the if and else so IsVP doesn't need to be inverted

1984

Use std::tie(Mask, VL) = getDefaultVLOps(VT, ContainerVT, DL, DAG, Subtarget)

[eopXD]

Address comments.

[craig.topper]

llvm/include/llvm/IR/VPIntrinsics.def

252

This should be VP_FCEIL to match the naming of ISD::FCEIL.

[eopXD]

Address comments.

[craig.topper]

Missing test for scalable vectors.

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vp-ceil.ll

1 ↗

(On Diff #462954)

This does not follow the established naming like fixed-vectors-vfadd-vp.ll

[eopXD]

Rename test case and add scalable vector test case.

[frasercrmck]

Forgive me if I've missed something but you're adding support for widening and splitting in the legalizer without adding tests for that behaviour.

[craig.topper]

llvm/docs/LangRef.rst

21448

Remove the word "value". I believe you copied "absolute value" and only changed the word "absolute". "absolute value" is the name of an operation "ceiling value" is not.

[craig.topper]

In D134586#3817430, @frasercrmck wrote:

Forgive me if I've missed something but you're adding support for widening and splitting in the legalizer without adding tests for that behaviour.

There's a <vscale x 7 x double> <vscale x 16 x double>, <15 x double> and <32 x double> test. Does that cover it?

[frasercrmck]

In D134586#3818275, @craig.topper wrote:

In D134586#3817430, @frasercrmck wrote:

Forgive me if I've missed something but you're adding support for widening and splitting in the legalizer without adding tests for that behaviour.

There's a <vscale x 7 x double> <vscale x 16 x double>, <15 x double> and <32 x double> test. Does that cover it?

Yes, thanks. To my shame I didn't read through the whole tests before making that comment.

[eopXD]

Address comment.

[craig.topper]

LGTM

[eopXD]

Rebase to latest main.

[eopXD]

Received build failure message when generating llvm-sphinx-docs, investigating into this. Patch reverted for now.

llvm/docs/LangRef.rst

 .. code-block:: llvm
 
       %r = call <4 x i1> @llvm.vp.icmp.v4i32(<4 x i32> %a, <4 x i32> %b, metadata !"ne", <4 x i1> %mask, i32 %evl)
       ;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
 
       %t = icmp ne <4 x i32> %a, %b
       %also.r = select <4 x i1> %mask, <4 x i1> %t, <4 x i1> poison
 
+.. _int_vp_ceil:
+
+'``llvm.vp.ceil.*``' Intrinsics
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+This is an overloaded intrinsic.
+
+::
+
+      declare <16 x float>  @llvm.vp.ceil.v16f32 (<16 x float> <op>, <16 x i1> <mask>, i32 <vector_length>)
+      declare <vscale x 4 x float>  @llvm.vp.ceil.nxv4f32 (<vscale x 4 x float> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
+      declare <256 x double>  @llvm.vp.ceil.v256f64 (<256 x double> <op>, <256 x i1> <mask>, i32 <vector_length>)
+
+Overview:
+"""""""""
+
+Predicated floating-point ceiling of a vector of floating-point values.
+
+
+Arguments:
+""""""""""
+
+The first operand and the result have the same vector of floating-point type.
+The second operand is the vector mask and has the same number of elements as the
+result vector type. The third operand is the explicit vector length of the
+operation.
+
+Semantics:
+""""""""""
+
+The '``llvm.vp.ceil``' intrinsic performs floating-point ceiling
+(:ref:`ceil <int_ceil>`) of the first vector operand on each enabled lane.  The
+result on disabled lanes is undefined.
+
+Examples:
+"""""""""
+
+.. code-block:: llvm
+
+      %r = call <4 x float> @llvm.vp.ceil.v4f32(<4 x float> %a, <4 x i1> %mask, i32 %evl)
+      ;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
+
+      %t = call <4 x float> @llvm.ceil.v4f32(<4 x float> %a)
+      %also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> undef
 
 .. _int_mload_mstore:
 
 Masked Vector Load and Store Intrinsics
 ---------------------------------------
 
 LLVM provides intrinsics for predicated vector load and store operations. The predicate is specified by a mask operand, which holds one bit per vector element, switching the associated vector lane on or off. The memory addresses corresponding to the "off" lanes are not accessed. When all bits of the mask are on, the intrinsic is identical to a regular vector load or store. When all bits are off, no memory is accessed.
 

llvm/include/llvm/IR/Intrinsics.td

def int_vp_minnum : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
                                LLVMMatchType<0>,
                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
                                llvm_i32_ty]>;
   def int_vp_maxnum : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
                              [ LLVMMatchType<0>,
                                LLVMMatchType<0>,
                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
                                llvm_i32_ty]>;
+  def int_vp_ceil : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                             [ LLVMMatchType<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
 
   // Casts
   def int_vp_trunc : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
                              [ llvm_anyvector_ty,
                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
                                llvm_i32_ty]>;
   def int_vp_zext : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
                              [ llvm_anyvector_ty,

llvm/include/llvm/IR/VPIntrinsics.def

 END_REGISTER_VP(vp_sqrt, VP_SQRT)
 
 // llvm.vp.fma(x,y,z,mask,vlen)
 BEGIN_REGISTER_VP(vp_fma, 3, 4, VP_FMA, -1)
 VP_PROPERTY_CONSTRAINEDFP(1, 1, experimental_constrained_fma)
 END_REGISTER_VP(vp_fma, VP_FMA)
 
 // llvm.vp.fmuladd(x,y,z,mask,vlen)
 BEGIN_REGISTER_VP(vp_fmuladd, 3, 4, VP_FMULADD, -1)
 VP_PROPERTY_CONSTRAINEDFP(1, 1, experimental_constrained_fmuladd)
 END_REGISTER_VP(vp_fmuladd, VP_FMULADD)
 
 // llvm.vp.minnum(x, y, mask,vlen)
 BEGIN_REGISTER_VP(vp_minnum, 2, 3, VP_FMINNUM, -1)
 END_REGISTER_VP(vp_minnum, VP_FMINNUM)
 
 // llvm.vp.maxnum(x, y, mask,vlen)
 BEGIN_REGISTER_VP(vp_maxnum, 2, 3, VP_FMAXNUM, -1)
 END_REGISTER_VP(vp_maxnum, VP_FMAXNUM)
+
+// llvm.vp.ceil(x,mask,vlen)
+BEGIN_REGISTER_VP(vp_ceil, 1, 2, VP_FCEIL, -1)
+END_REGISTER_VP(vp_ceil, VP_FCEIL)
+
 ///// } Floating-Point Arithmetic
 
 ///// Type Casts {
 // Specialized helper macro for type conversions.
 // <operation>(%x, %mask, %evl).
 #ifdef HELPER_REGISTER_FP_CAST_VP
 #error                                                                         \
     "The internal helper macro HELPER_REGISTER_FP_CAST_VP is already defined!"

llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp

#endif
   case ISD::BSWAP:
   case ISD::CTLZ:
   case ISD::CTTZ:
   case ISD::CTLZ_ZERO_UNDEF:
   case ISD::CTTZ_ZERO_UNDEF:
   case ISD::CTPOP:
   case ISD::FABS: case ISD::VP_FABS:
   case ISD::FCEIL:
+  case ISD::VP_FCEIL:
   case ISD::FCOS:
   case ISD::FEXP:
   case ISD::FEXP2:
   case ISD::FFLOOR:
   case ISD::FLOG:
   case ISD::FLOG10:
   case ISD::FLOG2:
   case ISD::FNEARBYINT:
#include "llvm/IR/ConstrainedOps.def"
   case ISD::CTLZ:
   case ISD::CTLZ_ZERO_UNDEF:
   case ISD::CTPOP:
   case ISD::CTTZ:
   case ISD::CTTZ_ZERO_UNDEF:
   case ISD::FNEG: case ISD::VP_FNEG:
   case ISD::VP_FABS:
   case ISD::VP_SQRT:
+  case ISD::VP_FCEIL:
   case ISD::FREEZE:
   case ISD::ARITH_FENCE:
   case ISD::FCANONICALIZE:
     Res = WidenVecRes_Unary(N);
     break;
   case ISD::FMA: case ISD::VP_FMA:
   case ISD::FSHL:
   case ISD::FSHR:

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

if (Subtarget.hasStdExtZfh()) {
     setOperationAction({ISD::FREM, ISD::FCEIL, ISD::FFLOOR, ISD::FNEARBYINT,
                         ISD::FRINT, ISD::FROUND, ISD::FROUNDEVEN, ISD::FTRUNC,
                         ISD::FPOW, ISD::FPOWI, ISD::FCOS, ISD::FSIN,
                         ISD::FSINCOS, ISD::FEXP, ISD::FEXP2, ISD::FLOG,
                         ISD::FLOG2, ISD::FLOG10},
                        MVT::f16, Promote);
 
     // FIXME: Need to promote f16 STRICT_* to f32 libcalls, but we don't have
     // complete support for all operations in LegalizeDAG.
     setOperationAction({ISD::STRICT_FCEIL, ISD::STRICT_FFLOOR,
                         ISD::STRICT_FNEARBYINT, ISD::STRICT_FRINT,
                         ISD::STRICT_FROUND, ISD::STRICT_FROUNDEVEN,
                         ISD::STRICT_FTRUNC},
                        MVT::f16, Promote);
 
     // We need to custom promote this.
     if (Subtarget.is64Bit())
if (Subtarget.hasVInstructions()) {
 
     static const unsigned FloatingPointVPOps[] = {
         ISD::VP_FADD,        ISD::VP_FSUB,        ISD::VP_FMUL,
         ISD::VP_FDIV,        ISD::VP_FNEG,        ISD::VP_FABS,
         ISD::VP_FMA,         ISD::VP_REDUCE_FADD, ISD::VP_REDUCE_SEQ_FADD,
         ISD::VP_REDUCE_FMIN, ISD::VP_REDUCE_FMAX, ISD::VP_MERGE,
         ISD::VP_SELECT,      ISD::VP_SINT_TO_FP,  ISD::VP_UINT_TO_FP,
         ISD::VP_SETCC,       ISD::VP_FP_ROUND,    ISD::VP_FP_EXTEND,
-        ISD::VP_SQRT,        ISD::VP_FMINNUM,     ISD::VP_FMAXNUM};
+        ISD::VP_SQRT,        ISD::VP_FMINNUM,     ISD::VP_FMAXNUM,
+        ISD::VP_FCEIL};
 
     static const unsigned IntegerVecReduceOps[] = {
         ISD::VECREDUCE_ADD,  ISD::VECREDUCE_AND,  ISD::VECREDUCE_OR,
         ISD::VECREDUCE_XOR,  ISD::VECREDUCE_SMAX, ISD::VECREDUCE_SMIN,
         ISD::VECREDUCE_UMAX, ISD::VECREDUCE_UMIN};
 
     static const unsigned FloatingPointVecReduceOps[] = {
         ISD::VECREDUCE_FADD, ISD::VECREDUCE_SEQ_FADD, ISD::VECREDUCE_FMIN,
const auto SetCommonVFPActions = [&](MVT VT) {
       // Expand various condition codes (explained above).
       setCondCodeAction(VFPCCToExpand, VT, Expand);
 
       setOperationAction({ISD::FMINNUM, ISD::FMAXNUM}, VT, Legal);
 
       setOperationAction({ISD::FTRUNC, ISD::FCEIL, ISD::FFLOOR, ISD::FROUND},
                          VT, Custom);
 
       setOperationAction(FloatingPointVecReduceOps, VT, Custom);
 
       // Expand FP operations that need libcalls.
       setOperationAction(ISD::FREM, VT, Expand);
       setOperationAction(ISD::FPOW, VT, Expand);
       setOperationAction(ISD::FCOS, VT, Expand);
       setOperationAction(ISD::FSIN, VT, Expand);
       setOperationAction(ISD::FSINCOS, VT, Expand);
       setOperationAction(ISD::FEXP, VT, Expand);
if (Subtarget.useRVVForFixedLengthVectors()) {
                             ISD::FMA, ISD::FMINNUM, ISD::FMAXNUM},
                            VT, Custom);
 
         setOperationAction({ISD::FP_ROUND, ISD::FP_EXTEND}, VT, Custom);
 
         setOperationAction({ISD::FTRUNC, ISD::FCEIL, ISD::FFLOOR, ISD::FROUND},
                            VT, Custom);
 
         setCondCodeAction(VFPCCToExpand, VT, Expand);
 
         setOperationAction({ISD::VSELECT, ISD::SELECT}, VT, Custom);
         setOperationAction(ISD::SELECT_CC, VT, Expand);
 
         setOperationAction(ISD::BITCAST, VT, Custom);
 
         setOperationAction(FloatingPointVecReduceOps, VT, Custom);
 
static SDValue lowerFP_TO_INT_SAT(SDValue Op, SelectionDAG &DAG,
   return Res;
 }
 
 static RISCVFPRndMode::RoundingMode matchRoundingOp(unsigned Opc) {
   switch (Opc) {
   case ISD::FROUNDEVEN: return RISCVFPRndMode::RNE;
   case ISD::FTRUNC:     return RISCVFPRndMode::RTZ;
   case ISD::FFLOOR:     return RISCVFPRndMode::RDN;
-  case ISD::FCEIL:      return RISCVFPRndMode::RUP;
+  case ISD::FCEIL:
+  case ISD::VP_FCEIL:
+    return RISCVFPRndMode::RUP;
   case ISD::FROUND:     return RISCVFPRndMode::RMM;
   }
 
   return RISCVFPRndMode::Invalid;
 }
 
-// Expand vector FTRUNC, FCEIL, FFLOOR, and FROUND by converting to the integer
-// domain/ and back. Taking care to avoid converting values that are nan or
-// already correct.
+// Expand vector FTRUNC, FCEIL, FFLOOR, FROUND and VP_FCEIL 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_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;
   if (VT.isFixedLengthVector()) {
     ContainerVT = getContainerForFixedLengthVector(DAG, VT, Subtarget);
     Src = convertToScalableVector(ContainerVT, Src, DAG, Subtarget);
   }
 
-  auto [TrueMask, VL] = getDefaultVLOps(VT, ContainerVT, DL, DAG, Subtarget);
+  SDValue Mask, VL;
+  bool IsVP = Op->getOpcode() == ISD::VP_FCEIL;
+
+  if (IsVP) {
+    Mask = Op.getOperand(1);
+    VL = Op.getOperand(2);
+  } else {
+    std::tie(Mask, 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);
+  SDValue Abs = DAG.getNode(RISCVISD::FABS_VL, DL, ContainerVT, Src, Mask, 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});
+  Mask =
+      DAG.getNode(RISCVISD::SETCC_VL, DL, SetccVT,
+                   DAG.getUNDEF(SetccVT), Mask, VL});
 
   // 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:
+  case ISD::VP_FCEIL:
   case ISD::FFLOOR:
   case ISD::FROUND: {
     RISCVFPRndMode::RoundingMode FRM = matchRoundingOp(Op.getOpcode());
     assert(FRM != RISCVFPRndMode::Invalid);
-    Truncated = DAG.getNode(RISCVISD::VFCVT_X_F_VL, DL, IntVT, Src, Mask,
+    Truncated = DAG.getNode(RISCVISD::VFCVT_X_F_VL, DL, IntVT, Src,
+                            Mask,
                             DAG.getTargetConstant(FRM, DL, XLenVT), VL);
     break;
   }
   case ISD::FTRUNC:
-    Truncated =
-        DAG.getNode(RISCVISD::VFCVT_RTZ_X_F_VL, DL, IntVT, Src, Mask, VL);
+    Truncated = DAG.getNode(RISCVISD::VFCVT_RTZ_X_F_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,
SDValue RISCVTargetLowering::LowerOperation(SDValue Op,
   case ISD::VP_SETCC:
     if (Op.getOperand(0).getSimpleValueType().getVectorElementType() == MVT::i1)
       return lowerVPSetCCMaskOp(Op, DAG);
     return lowerVPOp(Op, DAG, RISCVISD::SETCC_VL, /*HasMergeOp*/ true);
   case ISD::EXPERIMENTAL_VP_STRIDED_LOAD:
     return lowerVPStridedLoad(Op, DAG);
   case ISD::EXPERIMENTAL_VP_STRIDED_STORE:
     return lowerVPStridedStore(Op, DAG);
+  case ISD::VP_FCEIL:
+    return lowerFTRUNC_FCEIL_FFLOOR_FROUND(Op, DAG, Subtarget);
   }
 }
 
 static SDValue getTargetNode(GlobalAddressSDNode *N, SDLoc DL, EVT Ty,
                              SelectionDAG &DAG, unsigned Flags) {
   return DAG.getTargetGlobalAddress(N->getGlobal(), DL, Ty, 0, Flags);
 }
 

llvm/test/CodeGen/RISCV/rvv/ceil-vp.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
+
+declare <vscale x 1 x half> @llvm.vp.ceil.nxv1f16(<vscale x 1 x half>, <vscale x 1 x i1>, i32)
+
+define <vscale x 1 x half> @vfabs_vv_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv1f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI0_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
+; 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
+  %v = call <vscale x 1 x half> @llvm.vp.ceil.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 %evl)
+  ret <vscale x 1 x half> %v
+}
+
+define <vscale x 1 x half> @vfabs_vv_nxv1f16_unmasked(<vscale x 1 x half> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv1f16_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI1_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+  %v = call <vscale x 1 x half> @llvm.vp.ceil.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 %evl)
+  ret <vscale x 1 x half> %v
+}
+
+declare <vscale x 2 x half> @llvm.vp.ceil.nxv2f16(<vscale x 2 x half>, <vscale x 2 x i1>, i32)
+
+define <vscale x 2 x half> @vfabs_vv_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv2f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI2_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
+; 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
+  %v = call <vscale x 2 x half> @llvm.vp.ceil.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 %evl)
+  ret <vscale x 2 x half> %v
+}
+
+define <vscale x 2 x half> @vfabs_vv_nxv2f16_unmasked(<vscale x 2 x half> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv2f16_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI3_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
+  %v = call <vscale x 2 x half> @llvm.vp.ceil.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 %evl)
+  ret <vscale x 2 x half> %v
+}
+
+declare <vscale x 4 x half> @llvm.vp.ceil.nxv4f16(<vscale x 4 x half>, <vscale x 4 x i1>, i32)
+
+define <vscale x 4 x half> @vfabs_vv_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv4f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI4_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
+; 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
+  %v = call <vscale x 4 x half> @llvm.vp.ceil.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 %evl)
+  ret <vscale x 4 x half> %v
+}
+
+define <vscale x 4 x half> @vfabs_vv_nxv4f16_unmasked(<vscale x 4 x half> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv4f16_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI5_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
+  %v = call <vscale x 4 x half> @llvm.vp.ceil.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 %evl)
+  ret <vscale x 4 x half> %v
+}
+
+declare <vscale x 8 x half> @llvm.vp.ceil.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, i32)
+
+define <vscale x 8 x half> @vfabs_vv_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv8f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI6_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI6_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vfabs.v v12, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
+; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v10
+; 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
+  %v = call <vscale x 8 x half> @llvm.vp.ceil.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 %evl)
+  ret <vscale x 8 x half> %v
+}
+
+define <vscale x 8 x half> @vfabs_vv_nxv8f16_unmasked(<vscale x 8 x half> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv8f16_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI7_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI7_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vfabs.v v10, v8
+; CHECK-NEXT:    vmflt.vf v0, v10, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
+  %v = call <vscale x 8 x half> @llvm.vp.ceil.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 %evl)
+  ret <vscale x 8 x half> %v
+}
+
+declare <vscale x 16 x half> @llvm.vp.ceil.nxv16f16(<vscale x 16 x half>, <vscale x 16 x i1>, i32)
+
+define <vscale x 16 x half> @vfabs_vv_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv16f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI8_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI8_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vfabs.v v16, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
+; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v12
+; 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
+  %v = call <vscale x 16 x half> @llvm.vp.ceil.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 %evl)
+  ret <vscale x 16 x half> %v
+}
+
+define <vscale x 16 x half> @vfabs_vv_nxv16f16_unmasked(<vscale x 16 x half> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv16f16_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI9_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI9_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vfabs.v v12, v8
+; CHECK-NEXT:    vmflt.vf v0, v12, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
+  %v = call <vscale x 16 x half> @llvm.vp.ceil.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 %evl)
+  ret <vscale x 16 x half> %v
+}
+
+declare <vscale x 32 x half> @llvm.vp.ceil.nxv32f16(<vscale x 32 x half>, <vscale x 32 x i1>, i32)
+
+define <vscale x 32 x half> @vfabs_vv_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv32f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI10_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI10_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v24, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, ma
+; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
+; CHECK-NEXT:    fsrm a0
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT:    ret
+  %v = call <vscale x 32 x half> @llvm.vp.ceil.nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 %evl)
+  ret <vscale x 32 x half> %v
+}
+
+define <vscale x 32 x half> @vfabs_vv_nxv32f16_unmasked(<vscale x 32 x half> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv32f16_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI11_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI11_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v16, v8
+; CHECK-NEXT:    vmflt.vf v0, v16, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 32 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 32 x i1> %head, <vscale x 32 x i1> poison, <vscale x 32 x i32> zeroinitializer
+  %v = call <vscale x 32 x half> @llvm.vp.ceil.nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x i1> %m, i32 %evl)
+  ret <vscale x 32 x half> %v
+}
+
+declare <vscale x 1 x float> @llvm.vp.ceil.nxv1f32(<vscale x 1 x float>, <vscale x 1 x i1>, i32)
+
+define <vscale x 1 x float> @vfabs_vv_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv1f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI12_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI12_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
+; 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
+  %v = call <vscale x 1 x float> @llvm.vp.ceil.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 %evl)
+  ret <vscale x 1 x float> %v
+}
+
+define <vscale x 1 x float> @vfabs_vv_nxv1f32_unmasked(<vscale x 1 x float> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv1f32_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI13_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI13_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+  %v = call <vscale x 1 x float> @llvm.vp.ceil.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 %evl)
+  ret <vscale x 1 x float> %v
+}
+
+declare <vscale x 2 x float> @llvm.vp.ceil.nxv2f32(<vscale x 2 x float>, <vscale x 2 x i1>, i32)
+
+define <vscale x 2 x float> @vfabs_vv_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv2f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI14_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI14_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
+; 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
+  %v = call <vscale x 2 x float> @llvm.vp.ceil.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 %evl)
+  ret <vscale x 2 x float> %v
+}
+
+define <vscale x 2 x float> @vfabs_vv_nxv2f32_unmasked(<vscale x 2 x float> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv2f32_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI15_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI15_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
+  %v = call <vscale x 2 x float> @llvm.vp.ceil.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 %evl)
+  ret <vscale x 2 x float> %v
+}
+
+declare <vscale x 4 x float> @llvm.vp.ceil.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, i32)
+
+define <vscale x 4 x float> @vfabs_vv_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv4f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI16_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI16_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vfabs.v v12, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
+; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v10
+; 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
+  %v = call <vscale x 4 x float> @llvm.vp.ceil.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 %evl)
+  ret <vscale x 4 x float> %v
+}
+
+define <vscale x 4 x float> @vfabs_vv_nxv4f32_unmasked(<vscale x 4 x float> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv4f32_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI17_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI17_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vfabs.v v10, v8
+; CHECK-NEXT:    vmflt.vf v0, v10, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
+  %v = call <vscale x 4 x float> @llvm.vp.ceil.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 %evl)
+  ret <vscale x 4 x float> %v
+}
+
+declare <vscale x 8 x float> @llvm.vp.ceil.nxv8f32(<vscale x 8 x float>, <vscale x 8 x i1>, i32)
+
+define <vscale x 8 x float> @vfabs_vv_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv8f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI18_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI18_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vfabs.v v16, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
+; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v12
+; 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
+  %v = call <vscale x 8 x float> @llvm.vp.ceil.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 %evl)
+  ret <vscale x 8 x float> %v
+}
+
+define <vscale x 8 x float> @vfabs_vv_nxv8f32_unmasked(<vscale x 8 x float> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv8f32_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI19_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI19_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vfabs.v v12, v8
+; CHECK-NEXT:    vmflt.vf v0, v12, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
+  %v = call <vscale x 8 x float> @llvm.vp.ceil.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 %evl)
+  ret <vscale x 8 x float> %v
+}
+
+declare <vscale x 16 x float> @llvm.vp.ceil.nxv16f32(<vscale x 16 x float>, <vscale x 16 x i1>, i32)
+
+define <vscale x 16 x float> @vfabs_vv_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv16f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI20_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI20_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v24, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
+; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
+; CHECK-NEXT:    fsrm a0
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x float> @llvm.vp.ceil.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 %evl)
+  ret <vscale x 16 x float> %v
+}
+
+define <vscale x 16 x float> @vfabs_vv_nxv16f32_unmasked(<vscale x 16 x float> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv16f32_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI21_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI21_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v16, v8
+; CHECK-NEXT:    vmflt.vf v0, v16, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
+  %v = call <vscale x 16 x float> @llvm.vp.ceil.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 %evl)
+  ret <vscale x 16 x float> %v
+}
+
+declare <vscale x 1 x double> @llvm.vp.ceil.nxv1f64(<vscale x 1 x double>, <vscale x 1 x i1>, i32)
+
+define <vscale x 1 x double> @vfabs_vv_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv1f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI22_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI22_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
+; 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
+  %v = call <vscale x 1 x double> @llvm.vp.ceil.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 %evl)
+  ret <vscale x 1 x double> %v
+}
+
+define <vscale x 1 x double> @vfabs_vv_nxv1f64_unmasked(<vscale x 1 x double> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv1f64_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI23_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI23_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+  %v = call <vscale x 1 x double> @llvm.vp.ceil.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 %evl)
+  ret <vscale x 1 x double> %v
+}
+
+declare <vscale x 2 x double> @llvm.vp.ceil.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, i32)
+
+define <vscale x 2 x double> @vfabs_vv_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv2f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI24_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI24_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vfabs.v v12, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
+; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v10
+; 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
+  %v = call <vscale x 2 x double> @llvm.vp.ceil.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 %evl)
+  ret <vscale x 2 x double> %v
+}
+
+define <vscale x 2 x double> @vfabs_vv_nxv2f64_unmasked(<vscale x 2 x double> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv2f64_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI25_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI25_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vfabs.v v10, v8
+; CHECK-NEXT:    vmflt.vf v0, v10, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
+  %v = call <vscale x 2 x double> @llvm.vp.ceil.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 %evl)
+  ret <vscale x 2 x double> %v
+}
+
+declare <vscale x 4 x double> @llvm.vp.ceil.nxv4f64(<vscale x 4 x double>, <vscale x 4 x i1>, i32)
+
+define <vscale x 4 x double> @vfabs_vv_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv4f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI26_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI26_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vfabs.v v16, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
+; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v12
+; 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
+  %v = call <vscale x 4 x double> @llvm.vp.ceil.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 %evl)
+  ret <vscale x 4 x double> %v
+}
+
+define <vscale x 4 x double> @vfabs_vv_nxv4f64_unmasked(<vscale x 4 x double> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv4f64_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI27_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI27_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vfabs.v v12, v8
+; CHECK-NEXT:    vmflt.vf v0, v12, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
+  %v = call <vscale x 4 x double> @llvm.vp.ceil.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 %evl)
+  ret <vscale x 4 x double> %v
+}
+
+declare <vscale x 7 x double> @llvm.vp.ceil.nxv7f64(<vscale x 7 x double>, <vscale x 7 x i1>, i32)
+
+define <vscale x 7 x double> @vfabs_vv_nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv7f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI28_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI28_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v24, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
+; CHECK-NEXT:    fsrm a0
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT:    ret
+  %v = call <vscale x 7 x double> @llvm.vp.ceil.nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 %evl)
+  ret <vscale x 7 x double> %v
+}
+
+define <vscale x 7 x double> @vfabs_vv_nxv7f64_unmasked(<vscale x 7 x double> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv7f64_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI29_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI29_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v16, v8
+; CHECK-NEXT:    vmflt.vf v0, v16, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 7 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 7 x i1> %head, <vscale x 7 x i1> poison, <vscale x 7 x i32> zeroinitializer
+  %v = call <vscale x 7 x double> @llvm.vp.ceil.nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 %evl)
+  ret <vscale x 7 x double> %v
+}
+
+declare <vscale x 8 x double> @llvm.vp.ceil.nxv8f64(<vscale x 8 x double>, <vscale x 8 x i1>, i32)
+
+define <vscale x 8 x double> @vfabs_vv_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv8f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI30_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI30_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v24, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
+; CHECK-NEXT:    fsrm a0
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT:    ret
+  %v = call <vscale x 8 x double> @llvm.vp.ceil.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 %evl)
+  ret <vscale x 8 x double> %v
+}
+
+define <vscale x 8 x double> @vfabs_vv_nxv8f64_unmasked(<vscale x 8 x double> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv8f64_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI31_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI31_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v16, v8
+; CHECK-NEXT:    vmflt.vf v0, v16, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; 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
+  %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
+  %v = call <vscale x 8 x double> @llvm.vp.ceil.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 %evl)
+  ret <vscale x 8 x double> %v
+}
+
+; Test splitting.
+declare <vscale x 16 x double> @llvm.vp.ceil.nxv16f64(<vscale x 16 x double>, <vscale x 16 x i1>, i32)
+
+define <vscale x 16 x double> @vfabs_vv_nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv16f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vmv1r.v v1, v0
+; CHECK-NEXT:    li a2, 0
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    srli a4, a1, 3
+; CHECK-NEXT:    vsetvli a3, zero, e8, mf4, ta, mu
+; CHECK-NEXT:    sub a3, a0, a1
+; CHECK-NEXT:    vslidedown.vx v0, v0, a4
+; CHECK-NEXT:    bltu a0, a3, .LBB32_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    mv a2, a3
+; CHECK-NEXT:  .LBB32_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a3, vlenb
+; CHECK-NEXT:    slli a3, a3, 3
+; CHECK-NEXT:    sub sp, sp, a3
+; CHECK-NEXT:    lui a3, %hi(.LCPI32_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI32_0)(a3)
+; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
+; CHECK-NEXT:    fsrmi a2, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
+; CHECK-NEXT:    addi a3, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a3) # Unknown-size Folded Spill
+; CHECK-NEXT:    fsrm a2
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
+; CHECK-NEXT:    bltu a0, a1, .LBB32_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    mv a0, a1
+; CHECK-NEXT:  .LBB32_4:
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfabs.v v16, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v24
+; 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:    addi a0, sp, 16
+; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x double> @llvm.vp.ceil.nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 %evl)
+  ret <vscale x 16 x double> %v
+}
+
+define <vscale x 16 x double> @vfabs_vv_nxv16f64_unmasked(<vscale x 16 x double> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vfabs_vv_nxv16f64_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    mv a2, a0
+; CHECK-NEXT:    bltu a0, a1, .LBB33_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    mv a2, a1
+; CHECK-NEXT:  .LBB33_2:
+; CHECK-NEXT:    lui a3, %hi(.LCPI33_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI33_0)(a3)
+; CHECK-NEXT:    li a3, 0
+; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v24, v8
+; CHECK-NEXT:    vmflt.vf v0, v24, ft0
+; CHECK-NEXT:    fsrmi a2, 3
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
+; CHECK-NEXT:    fsrm a2
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    sub a1, a0, a1
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT:    bltu a0, a1, .LBB33_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    mv a3, a1
+; CHECK-NEXT:  .LBB33_4:
+; CHECK-NEXT:    vsetvli zero, a3, e64, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v24, v16
+; CHECK-NEXT:    vmflt.vf v0, v24, ft0
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
+; CHECK-NEXT:    fsrm a0
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
+  %v = call <vscale x 16 x double> @llvm.vp.ceil.nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> %m, i32 %evl)
+  ret <vscale x 16 x double> %v
+}

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-ceil-vp.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 -riscv-v-vector-bits-min=128 \
+; RUN:   -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -target-abi=lp64d -riscv-v-vector-bits-min=128 \
+; RUN:   -verify-machineinstrs < %s | FileCheck %s
+
+declare <2 x half> @llvm.vp.ceil.v2f16(<2 x half>, <2 x i1>, i32)
+
+define <2 x half> @vp_ceil_v2f16(<2 x half> %va, <2 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v2f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI0_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI0_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
+; 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
+  %v = call <2 x half> @llvm.vp.ceil.v2f16(<2 x half> %va, <2 x i1> %m, i32 %evl)
+  ret <2 x half> %v
+}
+
+define <2 x half> @vp_ceil_v2f16_unmasked(<2 x half> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v2f16_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI1_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI1_0)(a1)
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, mu
+; CHECK-NEXT:    vmset.m v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
+; 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
+  %head = insertelement <2 x i1> poison, i1 true, i32 0
+  %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
+  %v = call <2 x half> @llvm.vp.ceil.v2f16(<2 x half> %va, <2 x i1> %m, i32 %evl)
+  ret <2 x half> %v
+}
+
+declare <4 x half> @llvm.vp.ceil.v4f16(<4 x half>, <4 x i1>, i32)
+
+define <4 x half> @vp_ceil_v4f16(<4 x half> %va, <4 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v4f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI2_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI2_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
+; 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
+  %v = call <4 x half> @llvm.vp.ceil.v4f16(<4 x half> %va, <4 x i1> %m, i32 %evl)
+  ret <4 x half> %v
+}
+
+define <4 x half> @vp_ceil_v4f16_unmasked(<4 x half> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v4f16_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI3_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI3_0)(a1)
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
+; CHECK-NEXT:    vmset.m v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
+; 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
+  %head = insertelement <4 x i1> poison, i1 true, i32 0
+  %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
+  %v = call <4 x half> @llvm.vp.ceil.v4f16(<4 x half> %va, <4 x i1> %m, i32 %evl)
+  ret <4 x half> %v
+}
+
+declare <8 x half> @llvm.vp.ceil.v8f16(<8 x half>, <8 x i1>, i32)
+
+define <8 x half> @vp_ceil_v8f16(<8 x half> %va, <8 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v8f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI4_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI4_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
+; 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
+  %v = call <8 x half> @llvm.vp.ceil.v8f16(<8 x half> %va, <8 x i1> %m, i32 %evl)
+  ret <8 x half> %v
+}
+
+define <8 x half> @vp_ceil_v8f16_unmasked(<8 x half> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v8f16_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI5_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI5_0)(a1)
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; CHECK-NEXT:    vmset.m v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
+; 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
+  %head = insertelement <8 x i1> poison, i1 true, i32 0
+  %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
+  %v = call <8 x half> @llvm.vp.ceil.v8f16(<8 x half> %va, <8 x i1> %m, i32 %evl)
+  ret <8 x half> %v
+}
+
+declare <16 x half> @llvm.vp.ceil.v16f16(<16 x half>, <16 x i1>, i32)
+
+define <16 x half> @vp_ceil_v16f16(<16 x half> %va, <16 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v16f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI6_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI6_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vfabs.v v12, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
+; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v10
+; 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
+  %v = call <16 x half> @llvm.vp.ceil.v16f16(<16 x half> %va, <16 x i1> %m, i32 %evl)
+  ret <16 x half> %v
+}
+
+define <16 x half> @vp_ceil_v16f16_unmasked(<16 x half> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v16f16_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI7_0)
+; CHECK-NEXT:    flh ft0, %lo(.LCPI7_0)(a1)
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT:    vmset.m v0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vfabs.v v12, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
+; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v10
+; 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
+  %head = insertelement <16 x i1> poison, i1 true, i32 0
+  %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
+  %v = call <16 x half> @llvm.vp.ceil.v16f16(<16 x half> %va, <16 x i1> %m, i32 %evl)
+  ret <16 x half> %v
+}
+
+declare <2 x float> @llvm.vp.ceil.v2f32(<2 x float>, <2 x i1>, i32)
+
+define <2 x float> @vp_ceil_v2f32(<2 x float> %va, <2 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v2f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI8_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI8_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
+; 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
+  %v = call <2 x float> @llvm.vp.ceil.v2f32(<2 x float> %va, <2 x i1> %m, i32 %evl)
+  ret <2 x float> %v
+}
+
+define <2 x float> @vp_ceil_v2f32_unmasked(<2 x float> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v2f32_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI9_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI9_0)(a1)
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, mu
+; CHECK-NEXT:    vmset.m v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
+; 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
+  %head = insertelement <2 x i1> poison, i1 true, i32 0
+  %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
+  %v = call <2 x float> @llvm.vp.ceil.v2f32(<2 x float> %va, <2 x i1> %m, i32 %evl)
+  ret <2 x float> %v
+}
+
+declare <4 x float> @llvm.vp.ceil.v4f32(<4 x float>, <4 x i1>, i32)
+
+define <4 x float> @vp_ceil_v4f32(<4 x float> %va, <4 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v4f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI10_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI10_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
+; 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
+  %v = call <4 x float> @llvm.vp.ceil.v4f32(<4 x float> %va, <4 x i1> %m, i32 %evl)
+  ret <4 x float> %v
+}
+
+define <4 x float> @vp_ceil_v4f32_unmasked(<4 x float> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v4f32_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI11_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI11_0)(a1)
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
+; CHECK-NEXT:    vmset.m v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
+; 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
+  %head = insertelement <4 x i1> poison, i1 true, i32 0
+  %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
+  %v = call <4 x float> @llvm.vp.ceil.v4f32(<4 x float> %va, <4 x i1> %m, i32 %evl)
+  ret <4 x float> %v
+}
+
+declare <8 x float> @llvm.vp.ceil.v8f32(<8 x float>, <8 x i1>, i32)
+
+define <8 x float> @vp_ceil_v8f32(<8 x float> %va, <8 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v8f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI12_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI12_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vfabs.v v12, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
+; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v10
+; 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
+  %v = call <8 x float> @llvm.vp.ceil.v8f32(<8 x float> %va, <8 x i1> %m, i32 %evl)
+  ret <8 x float> %v
+}
+
+define <8 x float> @vp_ceil_v8f32_unmasked(<8 x float> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v8f32_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI13_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI13_0)(a1)
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; CHECK-NEXT:    vmset.m v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vfabs.v v12, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
+; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v10
+; 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
+  %head = insertelement <8 x i1> poison, i1 true, i32 0
+  %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
+  %v = call <8 x float> @llvm.vp.ceil.v8f32(<8 x float> %va, <8 x i1> %m, i32 %evl)
+  ret <8 x float> %v
+}
+
+declare <16 x float> @llvm.vp.ceil.v16f32(<16 x float>, <16 x i1>, i32)
+
+define <16 x float> @vp_ceil_v16f32(<16 x float> %va, <16 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v16f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI14_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI14_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vfabs.v v16, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
+; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v12
+; 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
+  %v = call <16 x float> @llvm.vp.ceil.v16f32(<16 x float> %va, <16 x i1> %m, i32 %evl)
+  ret <16 x float> %v
+}
+
+define <16 x float> @vp_ceil_v16f32_unmasked(<16 x float> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v16f32_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI15_0)
+; CHECK-NEXT:    flw ft0, %lo(.LCPI15_0)(a1)
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT:    vmset.m v0
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vfabs.v v16, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
+; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v12
+; 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
+  %head = insertelement <16 x i1> poison, i1 true, i32 0
+  %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
+  %v = call <16 x float> @llvm.vp.ceil.v16f32(<16 x float> %va, <16 x i1> %m, i32 %evl)
+  ret <16 x float> %v
+}
+
+declare <2 x double> @llvm.vp.ceil.v2f64(<2 x double>, <2 x i1>, i32)
+
+define <2 x double> @vp_ceil_v2f64(<2 x double> %va, <2 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v2f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI16_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI16_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
+; 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
+  %v = call <2 x double> @llvm.vp.ceil.v2f64(<2 x double> %va, <2 x i1> %m, i32 %evl)
+  ret <2 x double> %v
+}
+
+define <2 x double> @vp_ceil_v2f64_unmasked(<2 x double> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v2f64_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI17_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI17_0)(a1)
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, mu
+; CHECK-NEXT:    vmset.m v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vfabs.v v9, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
+; CHECK-NEXT:    vmflt.vf v0, v9, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
+; 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
+  %head = insertelement <2 x i1> poison, i1 true, i32 0
+  %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
+  %v = call <2 x double> @llvm.vp.ceil.v2f64(<2 x double> %va, <2 x i1> %m, i32 %evl)
+  ret <2 x double> %v
+}
+
+declare <4 x double> @llvm.vp.ceil.v4f64(<4 x double>, <4 x i1>, i32)
+
+define <4 x double> @vp_ceil_v4f64(<4 x double> %va, <4 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v4f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI18_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI18_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vfabs.v v12, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
+; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v10
+; 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
+  %v = call <4 x double> @llvm.vp.ceil.v4f64(<4 x double> %va, <4 x i1> %m, i32 %evl)
+  ret <4 x double> %v
+}
+
+define <4 x double> @vp_ceil_v4f64_unmasked(<4 x double> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v4f64_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI19_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI19_0)(a1)
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
+; CHECK-NEXT:    vmset.m v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vfabs.v v12, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
+; CHECK-NEXT:    vmflt.vf v10, v12, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v10
+; 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
+  %head = insertelement <4 x i1> poison, i1 true, i32 0
+  %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
+  %v = call <4 x double> @llvm.vp.ceil.v4f64(<4 x double> %va, <4 x i1> %m, i32 %evl)
+  ret <4 x double> %v
+}
+
+declare <8 x double> @llvm.vp.ceil.v8f64(<8 x double>, <8 x i1>, i32)
+
+define <8 x double> @vp_ceil_v8f64(<8 x double> %va, <8 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v8f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI20_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI20_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vfabs.v v16, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
+; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v12
+; 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
+  %v = call <8 x double> @llvm.vp.ceil.v8f64(<8 x double> %va, <8 x i1> %m, i32 %evl)
+  ret <8 x double> %v
+}
+
+define <8 x double> @vp_ceil_v8f64_unmasked(<8 x double> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v8f64_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI21_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI21_0)(a1)
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; CHECK-NEXT:    vmset.m v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vfabs.v v16, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
+; CHECK-NEXT:    vmflt.vf v12, v16, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v12
+; 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
+  %head = insertelement <8 x i1> poison, i1 true, i32 0
+  %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
+  %v = call <8 x double> @llvm.vp.ceil.v8f64(<8 x double> %va, <8 x i1> %m, i32 %evl)
+  ret <8 x double> %v
+}
+
+declare <15 x double> @llvm.vp.ceil.v15f64(<15 x double>, <15 x i1>, i32)
+
+define <15 x double> @vp_ceil_v15f64(<15 x double> %va, <15 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v15f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI22_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI22_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v24, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
+; CHECK-NEXT:    fsrm a0
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT:    ret
+  %v = call <15 x double> @llvm.vp.ceil.v15f64(<15 x double> %va, <15 x i1> %m, i32 %evl)
+  ret <15 x double> %v
+}
+
+define <15 x double> @vp_ceil_v15f64_unmasked(<15 x double> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v15f64_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI23_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI23_0)(a1)
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT:    vmset.m v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v24, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
+; CHECK-NEXT:    fsrm a0
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT:    ret
+  %head = insertelement <15 x i1> poison, i1 true, i32 0
+  %m = shufflevector <15 x i1> %head, <15 x i1> poison, <15 x i32> zeroinitializer
+  %v = call <15 x double> @llvm.vp.ceil.v15f64(<15 x double> %va, <15 x i1> %m, i32 %evl)
+  ret <15 x double> %v
+}
+
+declare <16 x double> @llvm.vp.ceil.v16f64(<16 x double>, <16 x i1>, i32)
+
+define <16 x double> @vp_ceil_v16f64(<16 x double> %va, <16 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v16f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI24_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI24_0)(a1)
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v24, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
+; CHECK-NEXT:    fsrm a0
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT:    ret
+  %v = call <16 x double> @llvm.vp.ceil.v16f64(<16 x double> %va, <16 x i1> %m, i32 %evl)
+  ret <16 x double> %v
+}
+
+define <16 x double> @vp_ceil_v16f64_unmasked(<16 x double> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v16f64_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, %hi(.LCPI25_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI25_0)(a1)
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT:    vmset.m v0
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v24, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vmflt.vf v16, v24, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
+; CHECK-NEXT:    fsrm a0
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT:    ret
+  %head = insertelement <16 x i1> poison, i1 true, i32 0
+  %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
+  %v = call <16 x double> @llvm.vp.ceil.v16f64(<16 x double> %va, <16 x i1> %m, i32 %evl)
+  ret <16 x double> %v
+}
+
+declare <32 x double> @llvm.vp.ceil.v32f64(<32 x double>, <32 x i1>, i32)
+
+define <32 x double> @vp_ceil_v32f64(<32 x double> %va, <32 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v32f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vmv1r.v v1, v0
+; CHECK-NEXT:    li a1, 0
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf4, ta, mu
+; CHECK-NEXT:    addi a2, a0, -16
+; CHECK-NEXT:    vslidedown.vi v0, v0, 2
+; CHECK-NEXT:    bltu a0, a2, .LBB26_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    mv a1, a2
+; CHECK-NEXT:  .LBB26_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
+; CHECK-NEXT:    lui a2, %hi(.LCPI26_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI26_0)(a2)
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
+; CHECK-NEXT:    fsrmi a1, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
+; CHECK-NEXT:    fsrm a1
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    li a1, 16
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
+; CHECK-NEXT:    bltu a0, a1, .LBB26_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    li a0, 16
+; CHECK-NEXT:  .LBB26_4:
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfabs.v v16, v8, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vmflt.vf v24, v16, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v24
+; 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:    addi a0, sp, 16
+; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    ret
+  %v = call <32 x double> @llvm.vp.ceil.v32f64(<32 x double> %va, <32 x i1> %m, i32 %evl)
+  ret <32 x double> %v
+}
+
+define <32 x double> @vp_ceil_v32f64_unmasked(<32 x double> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ceil_v32f64_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a1, 0
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT:    addi a2, a0, -16
+; CHECK-NEXT:    vmset.m v1
+; CHECK-NEXT:    bltu a0, a2, .LBB27_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    mv a1, a2
+; CHECK-NEXT:  .LBB27_2:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
+; CHECK-NEXT:    lui a2, %hi(.LCPI27_0)
+; CHECK-NEXT:    fld ft0, %lo(.LCPI27_0)(a2)
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vmflt.vf v2, v24, ft0, v0.t
+; CHECK-NEXT:    fsrmi a1, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v2
+; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
+; CHECK-NEXT:    fsrm a1
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    li a1, 16
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
+; CHECK-NEXT:    bltu a0, a1, .LBB27_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    li a0, 16
+; CHECK-NEXT:  .LBB27_4:
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfabs.v v24, v8, v0.t
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vmflt.vf v1, v24, ft0, v0.t
+; CHECK-NEXT:    fsrmi a0, 3
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
+; CHECK-NEXT:    fsrm a0
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    ret
+  %head = insertelement <32 x i1> poison, i1 true, i32 0
+  %m = shufflevector <32 x i1> %head, <32 x i1> poison, <32 x i32> zeroinitializer
+  %v = call <32 x double> @llvm.vp.ceil.v32f64(<32 x double> %va, <32 x i1> %m, i32 %evl)
+  ret <32 x double> %v
+}

llvm/unittests/IR/VPIntrinsicTest.cpp

for (const char *BinaryIntOpcode : BinaryIntOpcodes)
           << ".v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32) ";
 
     const char *BinaryFPOpcodes[] = {"fadd", "fsub",   "fmul",  "fdiv",
                                      "frem", "minnum", "maxnum"};
     for (const char *BinaryFPOpcode : BinaryFPOpcodes)
       Str << " declare <8 x float> @llvm.vp." << BinaryFPOpcode
           << ".v8f32(<8 x float>, <8 x float>, <8 x i1>, i32) ";
 
+    Str << " declare <8 x float> @llvm.vp.ceil.v8f32(<8 x float>, <8 x i1>, "
+           "i32)";
     Str << " declare <8 x float> @llvm.vp.fneg.v8f32(<8 x float>, <8 x i1>, "
            "i32)";
     Str << " declare <8 x float> @llvm.vp.fabs.v8f32(<8 x float>, <8 x i1>, "
            "i32)";
     Str << " declare <8 x float> @llvm.vp.sqrt.v8f32(<8 x float>, <8 x i1>, "
            "i32)";
     Str << " declare <8 x float> @llvm.vp.fma.v8f32(<8 x float>, <8 x float>, "
            "<8 x float>, <8 x i1>, i32) ";