; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v \
; RUN:     -verify-machineinstrs < %s | FileCheck %s
; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v \
; RUN:     -verify-machineinstrs < %s | FileCheck %s

declare <vscale x 1 x i8> @llvm.vp.load.nxv1i8.p0nxv1i8(<vscale x 1 x i8>*, <vscale x 1 x i1>, i32)

define <vscale x 1 x i8> @vpload_nxv1i8(<vscale x 1 x i8>* %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv1i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, mu
; CHECK-NEXT:    vle8.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x i8> @llvm.vp.load.nxv1i8.p0nxv1i8(<vscale x 1 x i8>* %ptr, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x i8> %load
}

define <vscale x 1 x i8> @vpload_nxv1i8_allones_mask(<vscale x 1 x i8>* %ptr, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv1i8_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, mu
; CHECK-NEXT:    vle8.v v8, (a0)
; CHECK-NEXT:    ret
  %a = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
  %b = shufflevector <vscale x 1 x i1> %a, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
  %load = call <vscale x 1 x i8> @llvm.vp.load.nxv1i8.p0nxv1i8(<vscale x 1 x i8>* %ptr, <vscale x 1 x i1> %b, i32 %evl)
  ret <vscale x 1 x i8> %load
}

declare <vscale x 2 x i8> @llvm.vp.load.nxv2i8.p0nxv2i8(<vscale x 2 x i8>*, <vscale x 2 x i1>, i32)

define <vscale x 2 x i8> @vpload_nxv2i8(<vscale x 2 x i8>* %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv2i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf4, ta, mu
; CHECK-NEXT:    vle8.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x i8> @llvm.vp.load.nxv2i8.p0nxv2i8(<vscale x 2 x i8>* %ptr, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x i8> %load
}

declare <vscale x 3 x i8> @llvm.vp.load.nxv3i8.p0nxv3i8(<vscale x 3 x i8>*, <vscale x 3 x i1>, i32)

define <vscale x 3 x i8> @vpload_nxv3i8(<vscale x 3 x i8>* %ptr, <vscale x 3 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv3i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, mu
; CHECK-NEXT:    vle8.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 3 x i8> @llvm.vp.load.nxv3i8.p0nxv3i8(<vscale x 3 x i8>* %ptr, <vscale x 3 x i1> %m, i32 %evl)
  ret <vscale x 3 x i8> %load
}

declare <vscale x 4 x i8> @llvm.vp.load.nxv4i8.p0nxv4i8(<vscale x 4 x i8>*, <vscale x 4 x i1>, i32)

define <vscale x 4 x i8> @vpload_nxv4i8(<vscale x 4 x i8>* %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv4i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, mu
; CHECK-NEXT:    vle8.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x i8> @llvm.vp.load.nxv4i8.p0nxv4i8(<vscale x 4 x i8>* %ptr, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x i8> %load
}

declare <vscale x 8 x i8> @llvm.vp.load.nxv8i8.p0nxv8i8(<vscale x 8 x i8>*, <vscale x 8 x i1>, i32)

define <vscale x 8 x i8> @vpload_nxv8i8(<vscale x 8 x i8>* %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv8i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, mu
; CHECK-NEXT:    vle8.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x i8> @llvm.vp.load.nxv8i8.p0nxv8i8(<vscale x 8 x i8>* %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret <vscale x 8 x i8> %load
}

define <vscale x 8 x i8> @vpload_nxv8i8_allones_mask(<vscale x 8 x i8>* %ptr, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv8i8_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, mu
; CHECK-NEXT:    vle8.v v8, (a0)
; CHECK-NEXT:    ret
  %a = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
  %b = shufflevector <vscale x 8 x i1> %a, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
  %load = call <vscale x 8 x i8> @llvm.vp.load.nxv8i8.p0nxv8i8(<vscale x 8 x i8>* %ptr, <vscale x 8 x i1> %b, i32 %evl)
  ret <vscale x 8 x i8> %load
}

declare <vscale x 1 x i16> @llvm.vp.load.nxv1i16.p0nxv1i16(<vscale x 1 x i16>*, <vscale x 1 x i1>, i32)

define <vscale x 1 x i16> @vpload_nxv1i16(<vscale x 1 x i16>* %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv1i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, mu
; CHECK-NEXT:    vle16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x i16> @llvm.vp.load.nxv1i16.p0nxv1i16(<vscale x 1 x i16>* %ptr, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x i16> %load
}

declare <vscale x 2 x i16> @llvm.vp.load.nxv2i16.p0nxv2i16(<vscale x 2 x i16>*, <vscale x 2 x i1>, i32)

define <vscale x 2 x i16> @vpload_nxv2i16(<vscale x 2 x i16>* %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv2i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, mu
; CHECK-NEXT:    vle16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x i16> @llvm.vp.load.nxv2i16.p0nxv2i16(<vscale x 2 x i16>* %ptr, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x i16> %load
}

define <vscale x 2 x i16> @vpload_nxv2i16_allones_mask(<vscale x 2 x i16>* %ptr, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv2i16_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, mu
; CHECK-NEXT:    vle16.v v8, (a0)
; CHECK-NEXT:    ret
  %a = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
  %b = shufflevector <vscale x 2 x i1> %a, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
  %load = call <vscale x 2 x i16> @llvm.vp.load.nxv2i16.p0nxv2i16(<vscale x 2 x i16>* %ptr, <vscale x 2 x i1> %b, i32 %evl)
  ret <vscale x 2 x i16> %load
}

declare <vscale x 4 x i16> @llvm.vp.load.nxv4i16.p0nxv4i16(<vscale x 4 x i16>*, <vscale x 4 x i1>, i32)

define <vscale x 4 x i16> @vpload_nxv4i16(<vscale x 4 x i16>* %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv4i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, mu
; CHECK-NEXT:    vle16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x i16> @llvm.vp.load.nxv4i16.p0nxv4i16(<vscale x 4 x i16>* %ptr, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x i16> %load
}

declare <vscale x 8 x i16> @llvm.vp.load.nxv8i16.p0nxv8i16(<vscale x 8 x i16>*, <vscale x 8 x i1>, i32)

define <vscale x 8 x i16> @vpload_nxv8i16(<vscale x 8 x i16>* %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv8i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, mu
; CHECK-NEXT:    vle16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x i16> @llvm.vp.load.nxv8i16.p0nxv8i16(<vscale x 8 x i16>* %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret <vscale x 8 x i16> %load
}

declare <vscale x 1 x i32> @llvm.vp.load.nxv1i32.p0nxv1i32(<vscale x 1 x i32>*, <vscale x 1 x i1>, i32)

define <vscale x 1 x i32> @vpload_nxv1i32(<vscale x 1 x i32>* %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv1i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, mu
; CHECK-NEXT:    vle32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x i32> @llvm.vp.load.nxv1i32.p0nxv1i32(<vscale x 1 x i32>* %ptr, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x i32> %load
}

declare <vscale x 2 x i32> @llvm.vp.load.nxv2i32.p0nxv2i32(<vscale x 2 x i32>*, <vscale x 2 x i1>, i32)

define <vscale x 2 x i32> @vpload_nxv2i32(<vscale x 2 x i32>* %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv2i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, mu
; CHECK-NEXT:    vle32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x i32> @llvm.vp.load.nxv2i32.p0nxv2i32(<vscale x 2 x i32>* %ptr, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x i32> %load
}

declare <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>*, <vscale x 4 x i1>, i32)

define <vscale x 4 x i32> @vpload_nxv4i32(<vscale x 4 x i32>* %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv4i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, mu
; CHECK-NEXT:    vle32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* %ptr, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x i32> %load
}

define <vscale x 4 x i32> @vpload_nxv4i32_allones_mask(<vscale x 4 x i32>* %ptr, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv4i32_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, mu
; CHECK-NEXT:    vle32.v v8, (a0)
; CHECK-NEXT:    ret
  %a = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
  %b = shufflevector <vscale x 4 x i1> %a, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
  %load = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* %ptr, <vscale x 4 x i1> %b, i32 %evl)
  ret <vscale x 4 x i32> %load
}

declare <vscale x 8 x i32> @llvm.vp.load.nxv8i32.p0nxv8i32(<vscale x 8 x i32>*, <vscale x 8 x i1>, i32)

define <vscale x 8 x i32> @vpload_nxv8i32(<vscale x 8 x i32>* %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv8i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, mu
; CHECK-NEXT:    vle32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x i32> @llvm.vp.load.nxv8i32.p0nxv8i32(<vscale x 8 x i32>* %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret <vscale x 8 x i32> %load
}

declare <vscale x 1 x i64> @llvm.vp.load.nxv1i64.p0nxv1i64(<vscale x 1 x i64>*, <vscale x 1 x i1>, i32)

define <vscale x 1 x i64> @vpload_nxv1i64(<vscale x 1 x i64>* %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv1i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m1, ta, mu
; CHECK-NEXT:    vle64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x i64> @llvm.vp.load.nxv1i64.p0nxv1i64(<vscale x 1 x i64>* %ptr, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x i64> %load
}

define <vscale x 1 x i64> @vpload_nxv1i64_allones_mask(<vscale x 1 x i64>* %ptr, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv1i64_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m1, ta, mu
; CHECK-NEXT:    vle64.v v8, (a0)
; CHECK-NEXT:    ret
  %a = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
  %b = shufflevector <vscale x 1 x i1> %a, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
  %load = call <vscale x 1 x i64> @llvm.vp.load.nxv1i64.p0nxv1i64(<vscale x 1 x i64>* %ptr, <vscale x 1 x i1> %b, i32 %evl)
  ret <vscale x 1 x i64> %load
}

declare <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0nxv2i64(<vscale x 2 x i64>*, <vscale x 2 x i1>, i32)

define <vscale x 2 x i64> @vpload_nxv2i64(<vscale x 2 x i64>* %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv2i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m2, ta, mu
; CHECK-NEXT:    vle64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0nxv2i64(<vscale x 2 x i64>* %ptr, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x i64> %load
}

declare <vscale x 4 x i64> @llvm.vp.load.nxv4i64.p0nxv4i64(<vscale x 4 x i64>*, <vscale x 4 x i1>, i32)

define <vscale x 4 x i64> @vpload_nxv4i64(<vscale x 4 x i64>* %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv4i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m4, ta, mu
; CHECK-NEXT:    vle64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x i64> @llvm.vp.load.nxv4i64.p0nxv4i64(<vscale x 4 x i64>* %ptr, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x i64> %load
}

declare <vscale x 8 x i64> @llvm.vp.load.nxv8i64.p0nxv8i64(<vscale x 8 x i64>*, <vscale x 8 x i1>, i32)

define <vscale x 8 x i64> @vpload_nxv8i64(<vscale x 8 x i64>* %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv8i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
; CHECK-NEXT:    vle64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x i64> @llvm.vp.load.nxv8i64.p0nxv8i64(<vscale x 8 x i64>* %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret <vscale x 8 x i64> %load
}

declare <vscale x 1 x half> @llvm.vp.load.nxv1f16.p0nxv1f16(<vscale x 1 x half>*, <vscale x 1 x i1>, i32)

define <vscale x 1 x half> @vpload_nxv1f16(<vscale x 1 x half>* %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv1f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, mu
; CHECK-NEXT:    vle16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x half> @llvm.vp.load.nxv1f16.p0nxv1f16(<vscale x 1 x half>* %ptr, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x half> %load
}

declare <vscale x 2 x half> @llvm.vp.load.nxv2f16.p0nxv2f16(<vscale x 2 x half>*, <vscale x 2 x i1>, i32)

define <vscale x 2 x half> @vpload_nxv2f16(<vscale x 2 x half>* %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv2f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, mu
; CHECK-NEXT:    vle16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x half> @llvm.vp.load.nxv2f16.p0nxv2f16(<vscale x 2 x half>* %ptr, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x half> %load
}

define <vscale x 2 x half> @vpload_nxv2f16_allones_mask(<vscale x 2 x half>* %ptr, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv2f16_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, mu
; CHECK-NEXT:    vle16.v v8, (a0)
; CHECK-NEXT:    ret
  %a = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
  %b = shufflevector <vscale x 2 x i1> %a, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
  %load = call <vscale x 2 x half> @llvm.vp.load.nxv2f16.p0nxv2f16(<vscale x 2 x half>* %ptr, <vscale x 2 x i1> %b, i32 %evl)
  ret <vscale x 2 x half> %load
}

declare <vscale x 4 x half> @llvm.vp.load.nxv4f16.p0nxv4f16(<vscale x 4 x half>*, <vscale x 4 x i1>, i32)

define <vscale x 4 x half> @vpload_nxv4f16(<vscale x 4 x half>* %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv4f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, mu
; CHECK-NEXT:    vle16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x half> @llvm.vp.load.nxv4f16.p0nxv4f16(<vscale x 4 x half>* %ptr, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x half> %load
}

declare <vscale x 8 x half> @llvm.vp.load.nxv8f16.p0nxv8f16(<vscale x 8 x half>*, <vscale x 8 x i1>, i32)

define <vscale x 8 x half> @vpload_nxv8f16(<vscale x 8 x half>* %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv8f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, mu
; CHECK-NEXT:    vle16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x half> @llvm.vp.load.nxv8f16.p0nxv8f16(<vscale x 8 x half>* %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret <vscale x 8 x half> %load
}

declare <vscale x 1 x float> @llvm.vp.load.nxv1f32.p0nxv1f32(<vscale x 1 x float>*, <vscale x 1 x i1>, i32)

define <vscale x 1 x float> @vpload_nxv1f32(<vscale x 1 x float>* %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv1f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, mu
; CHECK-NEXT:    vle32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x float> @llvm.vp.load.nxv1f32.p0nxv1f32(<vscale x 1 x float>* %ptr, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x float> %load
}

declare <vscale x 2 x float> @llvm.vp.load.nxv2f32.p0nxv2f32(<vscale x 2 x float>*, <vscale x 2 x i1>, i32)

define <vscale x 2 x float> @vpload_nxv2f32(<vscale x 2 x float>* %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv2f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, mu
; CHECK-NEXT:    vle32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x float> @llvm.vp.load.nxv2f32.p0nxv2f32(<vscale x 2 x float>* %ptr, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x float> %load
}

declare <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>*, <vscale x 4 x i1>, i32)

define <vscale x 4 x float> @vpload_nxv4f32(<vscale x 4 x float>* %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv4f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, mu
; CHECK-NEXT:    vle32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>* %ptr, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x float> %load
}

declare <vscale x 8 x float> @llvm.vp.load.nxv8f32.p0nxv8f32(<vscale x 8 x float>*, <vscale x 8 x i1>, i32)

define <vscale x 8 x float> @vpload_nxv8f32(<vscale x 8 x float>* %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv8f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, mu
; CHECK-NEXT:    vle32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x float> @llvm.vp.load.nxv8f32.p0nxv8f32(<vscale x 8 x float>* %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret <vscale x 8 x float> %load
}

define <vscale x 8 x float> @vpload_nxv8f32_allones_mask(<vscale x 8 x float>* %ptr, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv8f32_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, mu
; CHECK-NEXT:    vle32.v v8, (a0)
; CHECK-NEXT:    ret
  %a = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
  %b = shufflevector <vscale x 8 x i1> %a, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
  %load = call <vscale x 8 x float> @llvm.vp.load.nxv8f32.p0nxv8f32(<vscale x 8 x float>* %ptr, <vscale x 8 x i1> %b, i32 %evl)
  ret <vscale x 8 x float> %load
}

declare <vscale x 1 x double> @llvm.vp.load.nxv1f64.p0nxv1f64(<vscale x 1 x double>*, <vscale x 1 x i1>, i32)

define <vscale x 1 x double> @vpload_nxv1f64(<vscale x 1 x double>* %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv1f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m1, ta, mu
; CHECK-NEXT:    vle64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x double> @llvm.vp.load.nxv1f64.p0nxv1f64(<vscale x 1 x double>* %ptr, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x double> %load
}

declare <vscale x 2 x double> @llvm.vp.load.nxv2f64.p0nxv2f64(<vscale x 2 x double>*, <vscale x 2 x i1>, i32)

define <vscale x 2 x double> @vpload_nxv2f64(<vscale x 2 x double>* %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv2f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m2, ta, mu
; CHECK-NEXT:    vle64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x double> @llvm.vp.load.nxv2f64.p0nxv2f64(<vscale x 2 x double>* %ptr, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x double> %load
}

declare <vscale x 4 x double> @llvm.vp.load.nxv4f64.p0nxv4f64(<vscale x 4 x double>*, <vscale x 4 x i1>, i32)

define <vscale x 4 x double> @vpload_nxv4f64(<vscale x 4 x double>* %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv4f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m4, ta, mu
; CHECK-NEXT:    vle64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x double> @llvm.vp.load.nxv4f64.p0nxv4f64(<vscale x 4 x double>* %ptr, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x double> %load
}

define <vscale x 4 x double> @vpload_nxv4f64_allones_mask(<vscale x 4 x double>* %ptr, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv4f64_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m4, ta, mu
; CHECK-NEXT:    vle64.v v8, (a0)
; CHECK-NEXT:    ret
  %a = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
  %b = shufflevector <vscale x 4 x i1> %a, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
  %load = call <vscale x 4 x double> @llvm.vp.load.nxv4f64.p0nxv4f64(<vscale x 4 x double>* %ptr, <vscale x 4 x i1> %b, i32 %evl)
  ret <vscale x 4 x double> %load
}

declare <vscale x 8 x double> @llvm.vp.load.nxv8f64.p0nxv8f64(<vscale x 8 x double>*, <vscale x 8 x i1>, i32)

define <vscale x 8 x double> @vpload_nxv8f64(<vscale x 8 x double>* %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv8f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
; CHECK-NEXT:    vle64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x double> @llvm.vp.load.nxv8f64.p0nxv8f64(<vscale x 8 x double>* %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret <vscale x 8 x double> %load
}

declare <vscale x 16 x double> @llvm.vp.load.nxv16f64.p0nxv16f64(<vscale x 16 x double>*, <vscale x 16 x i1>, i32)

define <vscale x 16 x double> @vpload_nxv16f64(<vscale x 16 x double>* %ptr, <vscale x 16 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv16f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmv1r.v v8, v0
; CHECK-NEXT:    li a3, 0
; CHECK-NEXT:    csrr a2, vlenb
; CHECK-NEXT:    srli a5, a2, 3
; CHECK-NEXT:    vsetvli a4, zero, e8, mf4, ta, mu
; CHECK-NEXT:    sub a4, a1, a2
; CHECK-NEXT:    vslidedown.vx v0, v0, a5
; CHECK-NEXT:    bltu a1, a4, .LBB37_2
; CHECK-NEXT:  # %bb.1:
; CHECK-NEXT:    mv a3, a4
; CHECK-NEXT:  .LBB37_2:
; CHECK-NEXT:    slli a4, a2, 3
; CHECK-NEXT:    add a4, a0, a4
; CHECK-NEXT:    vsetvli zero, a3, e64, m8, ta, mu
; CHECK-NEXT:    vle64.v v16, (a4), v0.t
; CHECK-NEXT:    bltu a1, a2, .LBB37_4
; CHECK-NEXT:  # %bb.3:
; CHECK-NEXT:    mv a1, a2
; CHECK-NEXT:  .LBB37_4:
; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
; CHECK-NEXT:    vmv1r.v v0, v8
; CHECK-NEXT:    vle64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 16 x double> @llvm.vp.load.nxv16f64.p0nxv16f64(<vscale x 16 x double>* %ptr, <vscale x 16 x i1> %m, i32 %evl)
  ret <vscale x 16 x double> %load
}

declare <vscale x 17 x double> @llvm.vp.load.nxv17f64.p0nxv17f64(<vscale x 17 x double>*, <vscale x 17 x i1>, i32)

declare <vscale x 1 x double> @llvm.vector.extract.nxv1f64(<vscale x 17 x double> %vec, i64 %idx)
declare <vscale x 16 x double> @llvm.vector.extract.nxv16f64(<vscale x 17 x double> %vec, i64 %idx)

; Note: We can't return <vscale x 17 x double> as that introduces a vector
; store can't yet be legalized through widening. In order to test purely the
; vp.load legalization, manually split it.

; Widen to nxv32f64 then split into 4 x nxv8f64, of which 1 is empty.

define <vscale x 16 x double> @vpload_nxv17f64(<vscale x 17 x double>* %ptr, <vscale x 1 x double>* %out, <vscale x 17 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpload_nxv17f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    csrr a3, vlenb
; CHECK-NEXT:    slli a5, a3, 1
; CHECK-NEXT:    vmv1r.v v8, v0
; CHECK-NEXT:    mv a4, a2
; CHECK-NEXT:    bltu a2, a5, .LBB38_2
; CHECK-NEXT:  # %bb.1:
; CHECK-NEXT:    mv a4, a5
; CHECK-NEXT:  .LBB38_2:
; CHECK-NEXT:    sub a7, a4, a3
; CHECK-NEXT:    li a6, 0
; CHECK-NEXT:    bltu a4, a7, .LBB38_4
; CHECK-NEXT:  # %bb.3:
; CHECK-NEXT:    mv a6, a7
; CHECK-NEXT:  .LBB38_4:
; CHECK-NEXT:    li a7, 0
; CHECK-NEXT:    srli t0, a3, 3
; CHECK-NEXT:    vsetvli t1, zero, e8, mf4, ta, mu
; CHECK-NEXT:    vslidedown.vx v0, v8, t0
; CHECK-NEXT:    slli t0, a3, 3
; CHECK-NEXT:    add t0, a0, t0
; CHECK-NEXT:    vsetvli zero, a6, e64, m8, ta, mu
; CHECK-NEXT:    vle64.v v16, (t0), v0.t
; CHECK-NEXT:    srli a6, a3, 2
; CHECK-NEXT:    sub t0, a2, a5
; CHECK-NEXT:    slli a5, a3, 4
; CHECK-NEXT:    bltu a2, t0, .LBB38_6
; CHECK-NEXT:  # %bb.5:
; CHECK-NEXT:    mv a7, t0
; CHECK-NEXT:  .LBB38_6:
; CHECK-NEXT:    vsetvli a2, zero, e8, mf2, ta, mu
; CHECK-NEXT:    vslidedown.vx v0, v8, a6
; CHECK-NEXT:    add a2, a0, a5
; CHECK-NEXT:    bltu a7, a3, .LBB38_8
; CHECK-NEXT:  # %bb.7:
; CHECK-NEXT:    mv a7, a3
; CHECK-NEXT:  .LBB38_8:
; CHECK-NEXT:    vsetvli zero, a7, e64, m8, ta, mu
; CHECK-NEXT:    vle64.v v24, (a2), v0.t
; CHECK-NEXT:    bltu a4, a3, .LBB38_10
; CHECK-NEXT:  # %bb.9:
; CHECK-NEXT:    mv a4, a3
; CHECK-NEXT:  .LBB38_10:
; CHECK-NEXT:    vsetvli zero, a4, e64, m8, ta, mu
; CHECK-NEXT:    vmv1r.v v0, v8
; CHECK-NEXT:    vle64.v v8, (a0), v0.t
; CHECK-NEXT:    vs1r.v v24, (a1)
; CHECK-NEXT:    ret
  %load = call <vscale x 17 x double> @llvm.vp.load.nxv17f64.p0nxv17f64(<vscale x 17 x double>* %ptr, <vscale x 17 x i1> %m, i32 %evl)
  %lo = call <vscale x 16 x double> @llvm.vector.extract.nxv16f64(<vscale x 17 x double> %load, i64 0)
  %hi = call <vscale x 1 x double> @llvm.vector.extract.nxv1f64(<vscale x 17 x double> %load, i64 16)
  store <vscale x 1 x double> %hi, <vscale x 1 x double>* %out
  ret <vscale x 16 x double> %lo
}