test/CodeGen/RISCV/rvv/strided-vpload.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+m,+d,+zfh,+v,+zvfh \
; RUN:     -verify-machineinstrs < %s | FileCheck %s \
; RUN:     -check-prefixes=CHECK,CHECK-RV32
; RUN: llc -mtriple=riscv64 -mattr=+m,+d,+zfh,+v,+zvfh \
; RUN:     -verify-machineinstrs < %s | FileCheck %s \
; RUN:     -check-prefixes=CHECK,CHECK-RV64

declare <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i8(ptr, i8, <vscale x 1 x i1>, i32)

define <vscale x 1 x i8> @strided_vpload_nxv1i8_i8(ptr %ptr, i8 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv1i8_i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e8, mf8, ta, ma
; CHECK-NEXT:    vlse8.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i8(ptr %ptr, i8 %stride, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x i8> %load
}

declare <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i16(ptr, i16, <vscale x 1 x i1>, i32)

define <vscale x 1 x i8> @strided_vpload_nxv1i8_i16(ptr %ptr, i16 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv1i8_i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e8, mf8, ta, ma
; CHECK-NEXT:    vlse8.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i16(ptr %ptr, i16 %stride, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x i8> %load
}

declare <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i64(ptr, i64, <vscale x 1 x i1>, i32)

define <vscale x 1 x i8> @strided_vpload_nxv1i8_i64(ptr %ptr, i64 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-RV32-LABEL: strided_vpload_nxv1i8_i64:
; CHECK-RV32:       # %bb.0:
; CHECK-RV32-NEXT:    vsetvli zero, a3, e8, mf8, ta, ma
; CHECK-RV32-NEXT:    vlse8.v v8, (a0), a1, v0.t
; CHECK-RV32-NEXT:    ret
;
; CHECK-RV64-LABEL: strided_vpload_nxv1i8_i64:
; CHECK-RV64:       # %bb.0:
; CHECK-RV64-NEXT:    vsetvli zero, a2, e8, mf8, ta, ma
; CHECK-RV64-NEXT:    vlse8.v v8, (a0), a1, v0.t
; CHECK-RV64-NEXT:    ret
  %load = call <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i64(ptr %ptr, i64 %stride, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x i8> %load
}

define <vscale x 1 x i8> @strided_vpload_nxv1i8_i64_allones_mask(ptr %ptr, i64 signext %stride, i32 zeroext %evl) {
; CHECK-RV32-LABEL: strided_vpload_nxv1i8_i64_allones_mask:
; CHECK-RV32:       # %bb.0:
; CHECK-RV32-NEXT:    vsetvli zero, a3, e8, mf8, ta, ma
; CHECK-RV32-NEXT:    vlse8.v v8, (a0), a1
; CHECK-RV32-NEXT:    ret
;
; CHECK-RV64-LABEL: strided_vpload_nxv1i8_i64_allones_mask:
; CHECK-RV64:       # %bb.0:
; CHECK-RV64-NEXT:    vsetvli zero, a2, e8, mf8, ta, ma
; CHECK-RV64-NEXT:    vlse8.v v8, (a0), a1
; CHECK-RV64-NEXT:    ret
  %load = call <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i64(ptr %ptr, i64 %stride, <vscale x 1 x i1> splat (i1 true), i32 %evl)
  ret <vscale x 1 x i8> %load
}

declare <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i32(ptr, i32, <vscale x 1 x i1>, i32)

define <vscale x 1 x i8> @strided_vpload_nxv1i8(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv1i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e8, mf8, ta, ma
; CHECK-NEXT:    vlse8.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x i8> %load
}

define <vscale x 1 x i8> @strided_vpload_nxv1i8_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv1i8_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e8, mf8, ta, ma
; CHECK-NEXT:    vlse8.v v8, (a0), a1
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> splat (i1 true), i32 %evl)
  ret <vscale x 1 x i8> %load
}

declare <vscale x 2 x i8> @llvm.experimental.vp.strided.load.nxv2i8.p0.i32(ptr, i32, <vscale x 2 x i1>, i32)

define <vscale x 2 x i8> @strided_vpload_nxv2i8(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv2i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e8, mf4, ta, ma
; CHECK-NEXT:    vlse8.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x i8> @llvm.experimental.vp.strided.load.nxv2i8.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x i8> %load
}

declare <vscale x 4 x i8> @llvm.experimental.vp.strided.load.nxv4i8.p0.i32(ptr, i32, <vscale x 4 x i1>, i32)

define <vscale x 4 x i8> @strided_vpload_nxv4i8(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv4i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e8, mf2, ta, ma
; CHECK-NEXT:    vlse8.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x i8> @llvm.experimental.vp.strided.load.nxv4i8.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x i8> %load
}

declare <vscale x 8 x i8> @llvm.experimental.vp.strided.load.nxv8i8.p0.i32(ptr, i32, <vscale x 8 x i1>, i32)

define <vscale x 8 x i8> @strided_vpload_nxv8i8(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv8i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e8, m1, ta, ma
; CHECK-NEXT:    vlse8.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x i8> @llvm.experimental.vp.strided.load.nxv8i8.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 %evl)
  ret <vscale x 8 x i8> %load
}

define <vscale x 8 x i8> @strided_vpload_nxv8i8_unit_stride(ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv8i8_unit_stride:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, ma
; CHECK-NEXT:    vle8.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x i8> @llvm.experimental.vp.strided.load.nxv8i8.p0.i32(ptr %ptr, i32 1, <vscale x 8 x i1> %m, i32 %evl)
  ret <vscale x 8 x i8> %load
}

define <vscale x 8 x i8> @strided_vpload_nxv8i8_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv8i8_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e8, m1, ta, ma
; CHECK-NEXT:    vlse8.v v8, (a0), a1
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x i8> @llvm.experimental.vp.strided.load.nxv8i8.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> splat (i1 true), i32 %evl)
  ret <vscale x 8 x i8> %load
}

declare <vscale x 1 x i16> @llvm.experimental.vp.strided.load.nxv1i16.p0.i32(ptr, i32, <vscale x 1 x i1>, i32)

define <vscale x 1 x i16> @strided_vpload_nxv1i16(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv1i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e16, mf4, ta, ma
; CHECK-NEXT:    vlse16.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x i16> @llvm.experimental.vp.strided.load.nxv1i16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x i16> %load
}

declare <vscale x 2 x i16> @llvm.experimental.vp.strided.load.nxv2i16.p0.i32(ptr, i32, <vscale x 2 x i1>, i32)

define <vscale x 2 x i16> @strided_vpload_nxv2i16(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv2i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e16, mf2, ta, ma
; CHECK-NEXT:    vlse16.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x i16> @llvm.experimental.vp.strided.load.nxv2i16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x i16> %load
}

define <vscale x 2 x i16> @strided_vpload_nxv2i16_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv2i16_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e16, mf2, ta, ma
; CHECK-NEXT:    vlse16.v v8, (a0), a1
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x i16> @llvm.experimental.vp.strided.load.nxv2i16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> splat (i1 true), i32 %evl)
  ret <vscale x 2 x i16> %load
}

declare <vscale x 4 x i16> @llvm.experimental.vp.strided.load.nxv4i16.p0.i32(ptr, i32, <vscale x 4 x i1>, i32)

define <vscale x 4 x i16> @strided_vpload_nxv4i16(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv4i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e16, m1, ta, ma
; CHECK-NEXT:    vlse16.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x i16> @llvm.experimental.vp.strided.load.nxv4i16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x i16> %load
}

define <vscale x 4 x i16> @strided_vpload_nxv4i16_unit_stride(ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv4i16_unit_stride:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, ma
; CHECK-NEXT:    vle16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x i16> @llvm.experimental.vp.strided.load.nxv4i16.p0.i32(ptr %ptr, i32 2, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x i16> %load
}

declare <vscale x 8 x i16> @llvm.experimental.vp.strided.load.nxv8i16.p0.i32(ptr, i32, <vscale x 8 x i1>, i32)

define <vscale x 8 x i16> @strided_vpload_nxv8i16(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv8i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e16, m2, ta, ma
; CHECK-NEXT:    vlse16.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x i16> @llvm.experimental.vp.strided.load.nxv8i16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 %evl)
  ret <vscale x 8 x i16> %load
}

declare <vscale x 1 x i32> @llvm.experimental.vp.strided.load.nxv1i32.p0.i32(ptr, i32, <vscale x 1 x i1>, i32)

define <vscale x 1 x i32> @strided_vpload_nxv1i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv1i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e32, mf2, ta, ma
; CHECK-NEXT:    vlse32.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x i32> @llvm.experimental.vp.strided.load.nxv1i32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x i32> %load
}

declare <vscale x 2 x i32> @llvm.experimental.vp.strided.load.nxv2i32.p0.i32(ptr, i32, <vscale x 2 x i1>, i32)

define <vscale x 2 x i32> @strided_vpload_nxv2i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv2i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e32, m1, ta, ma
; CHECK-NEXT:    vlse32.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x i32> @llvm.experimental.vp.strided.load.nxv2i32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x i32> %load
}

define <vscale x 2 x i32> @strided_vpload_nxv2i32_unit_stride(ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv2i32_unit_stride:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, ma
; CHECK-NEXT:    vle32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x i32> @llvm.experimental.vp.strided.load.nxv2i32.p0.i32(ptr %ptr, i32 4, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x i32> %load
}

declare <vscale x 4 x i32> @llvm.experimental.vp.strided.load.nxv4i32.p0.i32(ptr, i32, <vscale x 4 x i1>, i32)

define <vscale x 4 x i32> @strided_vpload_nxv4i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv4i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e32, m2, ta, ma
; CHECK-NEXT:    vlse32.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x i32> @llvm.experimental.vp.strided.load.nxv4i32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x i32> %load
}

define <vscale x 4 x i32> @strided_vpload_nxv4i32_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv4i32_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e32, m2, ta, ma
; CHECK-NEXT:    vlse32.v v8, (a0), a1
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x i32> @llvm.experimental.vp.strided.load.nxv4i32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> splat (i1 true), i32 %evl)
  ret <vscale x 4 x i32> %load
}

declare <vscale x 8 x i32> @llvm.experimental.vp.strided.load.nxv8i32.p0.i32(ptr, i32, <vscale x 8 x i1>, i32)

define <vscale x 8 x i32> @strided_vpload_nxv8i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv8i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e32, m4, ta, ma
; CHECK-NEXT:    vlse32.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x i32> @llvm.experimental.vp.strided.load.nxv8i32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 %evl)
  ret <vscale x 8 x i32> %load
}

declare <vscale x 1 x i64> @llvm.experimental.vp.strided.load.nxv1i64.p0.i32(ptr, i32, <vscale x 1 x i1>, i32)

define <vscale x 1 x i64> @strided_vpload_nxv1i64(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv1i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
; CHECK-NEXT:    vlse64.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x i64> @llvm.experimental.vp.strided.load.nxv1i64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x i64> %load
}

define <vscale x 1 x i64> @strided_vpload_nxv1i64_unit_stride(ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv1i64_unit_stride:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m1, ta, ma
; CHECK-NEXT:    vle64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x i64> @llvm.experimental.vp.strided.load.nxv1i64.p0.i32(ptr %ptr, i32 8, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x i64> %load
}

define <vscale x 1 x i64> @strided_vpload_nxv1i64_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv1i64_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
; CHECK-NEXT:    vlse64.v v8, (a0), a1
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x i64> @llvm.experimental.vp.strided.load.nxv1i64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> splat (i1 true), i32 %evl)
  ret <vscale x 1 x i64> %load
}

declare <vscale x 2 x i64> @llvm.experimental.vp.strided.load.nxv2i64.p0.i32(ptr, i32, <vscale x 2 x i1>, i32)

define <vscale x 2 x i64> @strided_vpload_nxv2i64(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv2i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e64, m2, ta, ma
; CHECK-NEXT:    vlse64.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x i64> @llvm.experimental.vp.strided.load.nxv2i64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x i64> %load
}

declare <vscale x 4 x i64> @llvm.experimental.vp.strided.load.nxv4i64.p0.i32(ptr, i32, <vscale x 4 x i1>, i32)

define <vscale x 4 x i64> @strided_vpload_nxv4i64(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv4i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
; CHECK-NEXT:    vlse64.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x i64> @llvm.experimental.vp.strided.load.nxv4i64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x i64> %load
}

declare <vscale x 8 x i64> @llvm.experimental.vp.strided.load.nxv8i64.p0.i32(ptr, i32, <vscale x 8 x i1>, i32)

define <vscale x 8 x i64> @strided_vpload_nxv8i64(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv8i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; CHECK-NEXT:    vlse64.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x i64> @llvm.experimental.vp.strided.load.nxv8i64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 %evl)
  ret <vscale x 8 x i64> %load
}

declare <vscale x 1 x half> @llvm.experimental.vp.strided.load.nxv1f16.p0.i32(ptr, i32, <vscale x 1 x i1>, i32)

define <vscale x 1 x half> @strided_vpload_nxv1f16(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv1f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e16, mf4, ta, ma
; CHECK-NEXT:    vlse16.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x half> @llvm.experimental.vp.strided.load.nxv1f16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x half> %load
}

declare <vscale x 2 x half> @llvm.experimental.vp.strided.load.nxv2f16.p0.i32(ptr, i32, <vscale x 2 x i1>, i32)

define <vscale x 2 x half> @strided_vpload_nxv2f16(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv2f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e16, mf2, ta, ma
; CHECK-NEXT:    vlse16.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x half> @llvm.experimental.vp.strided.load.nxv2f16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x half> %load
}

define <vscale x 2 x half> @strided_vpload_nxv2f16_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv2f16_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e16, mf2, ta, ma
; CHECK-NEXT:    vlse16.v v8, (a0), a1
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x half> @llvm.experimental.vp.strided.load.nxv2f16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> splat (i1 true), i32 %evl)
  ret <vscale x 2 x half> %load
}

declare <vscale x 4 x half> @llvm.experimental.vp.strided.load.nxv4f16.p0.i32(ptr, i32, <vscale x 4 x i1>, i32)

define <vscale x 4 x half> @strided_vpload_nxv4f16(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv4f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e16, m1, ta, ma
; CHECK-NEXT:    vlse16.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x half> @llvm.experimental.vp.strided.load.nxv4f16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x half> %load
}

define <vscale x 4 x half> @strided_vpload_nxv4f16_unit_stride(ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv4f16_unit_stride:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, ma
; CHECK-NEXT:    vle16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x half> @llvm.experimental.vp.strided.load.nxv4f16.p0.i32(ptr %ptr, i32 2, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x half> %load
}

declare <vscale x 8 x half> @llvm.experimental.vp.strided.load.nxv8f16.p0.i32(ptr, i32, <vscale x 8 x i1>, i32)

define <vscale x 8 x half> @strided_vpload_nxv8f16(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv8f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e16, m2, ta, ma
; CHECK-NEXT:    vlse16.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x half> @llvm.experimental.vp.strided.load.nxv8f16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 %evl)
  ret <vscale x 8 x half> %load
}

declare <vscale x 1 x float> @llvm.experimental.vp.strided.load.nxv1f32.p0.i32(ptr, i32, <vscale x 1 x i1>, i32)

define <vscale x 1 x float> @strided_vpload_nxv1f32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv1f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e32, mf2, ta, ma
; CHECK-NEXT:    vlse32.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x float> @llvm.experimental.vp.strided.load.nxv1f32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x float> %load
}

declare <vscale x 2 x float> @llvm.experimental.vp.strided.load.nxv2f32.p0.i32(ptr, i32, <vscale x 2 x i1>, i32)

define <vscale x 2 x float> @strided_vpload_nxv2f32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv2f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e32, m1, ta, ma
; CHECK-NEXT:    vlse32.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x float> @llvm.experimental.vp.strided.load.nxv2f32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x float> %load
}

define <vscale x 2 x float> @strided_vpload_nxv2f32_unit_stride(ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv2f32_unit_stride:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, ma
; CHECK-NEXT:    vle32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x float> @llvm.experimental.vp.strided.load.nxv2f32.p0.i32(ptr %ptr, i32 4, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x float> %load
}

declare <vscale x 4 x float> @llvm.experimental.vp.strided.load.nxv4f32.p0.i32(ptr, i32, <vscale x 4 x i1>, i32)

define <vscale x 4 x float> @strided_vpload_nxv4f32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv4f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e32, m2, ta, ma
; CHECK-NEXT:    vlse32.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x float> @llvm.experimental.vp.strided.load.nxv4f32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x float> %load
}

declare <vscale x 8 x float> @llvm.experimental.vp.strided.load.nxv8f32.p0.i32(ptr, i32, <vscale x 8 x i1>, i32)

define <vscale x 8 x float> @strided_vpload_nxv8f32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv8f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e32, m4, ta, ma
; CHECK-NEXT:    vlse32.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x float> @llvm.experimental.vp.strided.load.nxv8f32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 %evl)
  ret <vscale x 8 x float> %load
}

define <vscale x 8 x float> @strided_vpload_nxv8f32_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv8f32_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e32, m4, ta, ma
; CHECK-NEXT:    vlse32.v v8, (a0), a1
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x float> @llvm.experimental.vp.strided.load.nxv8f32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> splat (i1 true), i32 %evl)
  ret <vscale x 8 x float> %load
}

declare <vscale x 1 x double> @llvm.experimental.vp.strided.load.nxv1f64.p0.i32(ptr, i32, <vscale x 1 x i1>, i32)

define <vscale x 1 x double> @strided_vpload_nxv1f64(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv1f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
; CHECK-NEXT:    vlse64.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x double> @llvm.experimental.vp.strided.load.nxv1f64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x double> %load
}

define <vscale x 1 x double> @strided_vpload_nxv1f64_unit_stride(ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv1f64_unit_stride:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m1, ta, ma
; CHECK-NEXT:    vle64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 1 x double> @llvm.experimental.vp.strided.load.nxv1f64.p0.i32(ptr %ptr, i32 8, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x double> %load
}

declare <vscale x 2 x double> @llvm.experimental.vp.strided.load.nxv2f64.p0.i32(ptr, i32, <vscale x 2 x i1>, i32)

define <vscale x 2 x double> @strided_vpload_nxv2f64(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv2f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e64, m2, ta, ma
; CHECK-NEXT:    vlse64.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 2 x double> @llvm.experimental.vp.strided.load.nxv2f64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 %evl)
  ret <vscale x 2 x double> %load
}

declare <vscale x 4 x double> @llvm.experimental.vp.strided.load.nxv4f64.p0.i32(ptr, i32, <vscale x 4 x i1>, i32)

define <vscale x 4 x double> @strided_vpload_nxv4f64(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv4f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
; CHECK-NEXT:    vlse64.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x double> @llvm.experimental.vp.strided.load.nxv4f64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 %evl)
  ret <vscale x 4 x double> %load
}

define <vscale x 4 x double> @strided_vpload_nxv4f64_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv4f64_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
; CHECK-NEXT:    vlse64.v v8, (a0), a1
; CHECK-NEXT:    ret
  %load = call <vscale x 4 x double> @llvm.experimental.vp.strided.load.nxv4f64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> splat (i1 true), i32 %evl)
  ret <vscale x 4 x double> %load
}

declare <vscale x 8 x double> @llvm.experimental.vp.strided.load.nxv8f64.p0.i32(ptr, i32, <vscale x 8 x i1>, i32)

define <vscale x 8 x double> @strided_vpload_nxv8f64(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv8f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; CHECK-NEXT:    vlse64.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %load = call <vscale x 8 x double> @llvm.experimental.vp.strided.load.nxv8f64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 %evl)
  ret <vscale x 8 x double> %load
}

; Widening
define <vscale x 3 x double> @strided_vpload_nxv3f64(ptr %ptr, i32 signext %stride, <vscale x 3 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv3f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
; CHECK-NEXT:    vlse64.v v8, (a0), a1, v0.t
; CHECK-NEXT:    ret
  %v = call <vscale x 3 x double> @llvm.experimental.vp.strided.load.nxv3f64.p0.i32(ptr %ptr, i32 %stride, <vscale x 3 x i1> %mask, i32 %evl)
  ret <vscale x 3 x double> %v
}

define <vscale x 3 x double> @strided_vpload_nxv3f64_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
; CHECK-LABEL: strided_vpload_nxv3f64_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
; CHECK-NEXT:    vlse64.v v8, (a0), a1
; CHECK-NEXT:    ret
  %v = call <vscale x 3 x double> @llvm.experimental.vp.strided.load.nxv3f64.p0.i32(ptr %ptr, i32 %stride, <vscale x 3 x i1> splat (i1 true), i32 %evl)
  ret <vscale x 3 x double> %v
}

declare <vscale x 3 x double> @llvm.experimental.vp.strided.load.nxv3f64.p0.i32(ptr, i32, <vscale x 3 x i1>, i32)

; Splitting
define <vscale x 16 x double> @strided_load_nxv16f64(ptr %ptr, i64 %stride, <vscale x 16 x i1> %mask, i32 zeroext %evl) {
; CHECK-RV32-LABEL: strided_load_nxv16f64:
; CHECK-RV32:       # %bb.0:
; CHECK-RV32-NEXT:    vmv1r.v v9, v0
; CHECK-RV32-NEXT:    csrr a4, vlenb
; CHECK-RV32-NEXT:    sub a2, a3, a4
; CHECK-RV32-NEXT:    sltu a5, a3, a2
; CHECK-RV32-NEXT:    addi a5, a5, -1
; CHECK-RV32-NEXT:    and a2, a5, a2
; CHECK-RV32-NEXT:    bltu a3, a4, .LBB49_2
; CHECK-RV32-NEXT:  # %bb.1:
; CHECK-RV32-NEXT:    mv a3, a4
; CHECK-RV32-NEXT:  .LBB49_2:
; CHECK-RV32-NEXT:    mul a5, a3, a1
; CHECK-RV32-NEXT:    add a5, a0, a5
; CHECK-RV32-NEXT:    srli a4, a4, 3
; CHECK-RV32-NEXT:    vsetvli a6, zero, e8, mf4, ta, ma
; CHECK-RV32-NEXT:    vslidedown.vx v8, v9, a4
; CHECK-RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; CHECK-RV32-NEXT:    vmv1r.v v0, v8
; CHECK-RV32-NEXT:    vlse64.v v16, (a5), a1, v0.t
; CHECK-RV32-NEXT:    vsetvli zero, a3, e64, m8, ta, ma
; CHECK-RV32-NEXT:    vmv1r.v v0, v9
; CHECK-RV32-NEXT:    vlse64.v v8, (a0), a1, v0.t
; CHECK-RV32-NEXT:    ret
;
; CHECK-RV64-LABEL: strided_load_nxv16f64:
; CHECK-RV64:       # %bb.0:
; CHECK-RV64-NEXT:    vmv1r.v v9, v0
; CHECK-RV64-NEXT:    csrr a4, vlenb
; CHECK-RV64-NEXT:    sub a3, a2, a4
; CHECK-RV64-NEXT:    sltu a5, a2, a3
; CHECK-RV64-NEXT:    addi a5, a5, -1
; CHECK-RV64-NEXT:    and a3, a5, a3
; CHECK-RV64-NEXT:    bltu a2, a4, .LBB49_2
; CHECK-RV64-NEXT:  # %bb.1:
; CHECK-RV64-NEXT:    mv a2, a4
; CHECK-RV64-NEXT:  .LBB49_2:
; CHECK-RV64-NEXT:    mul a5, a2, a1
; CHECK-RV64-NEXT:    add a5, a0, a5
; CHECK-RV64-NEXT:    srli a4, a4, 3
; CHECK-RV64-NEXT:    vsetvli a6, zero, e8, mf4, ta, ma
; CHECK-RV64-NEXT:    vslidedown.vx v8, v9, a4
; CHECK-RV64-NEXT:    vsetvli zero, a3, e64, m8, ta, ma
; CHECK-RV64-NEXT:    vmv1r.v v0, v8
; CHECK-RV64-NEXT:    vlse64.v v16, (a5), a1, v0.t
; CHECK-RV64-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; CHECK-RV64-NEXT:    vmv1r.v v0, v9
; CHECK-RV64-NEXT:    vlse64.v v8, (a0), a1, v0.t
; CHECK-RV64-NEXT:    ret
  %v = call <vscale x 16 x double> @llvm.experimental.vp.strided.load.nxv16f64.p0.i64(ptr %ptr, i64 %stride, <vscale x 16 x i1> %mask, i32 %evl)
  ret <vscale x 16 x double> %v
}

define <vscale x 16 x double> @strided_load_nxv16f64_allones_mask(ptr %ptr, i64 %stride, i32 zeroext %evl) {
; CHECK-RV32-LABEL: strided_load_nxv16f64_allones_mask:
; CHECK-RV32:       # %bb.0:
; CHECK-RV32-NEXT:    csrr a4, vlenb
; CHECK-RV32-NEXT:    sub a2, a3, a4
; CHECK-RV32-NEXT:    sltu a5, a3, a2
; CHECK-RV32-NEXT:    addi a5, a5, -1
; CHECK-RV32-NEXT:    and a2, a5, a2
; CHECK-RV32-NEXT:    bltu a3, a4, .LBB50_2
; CHECK-RV32-NEXT:  # %bb.1:
; CHECK-RV32-NEXT:    mv a3, a4
; CHECK-RV32-NEXT:  .LBB50_2:
; CHECK-RV32-NEXT:    mul a4, a3, a1
; CHECK-RV32-NEXT:    add a4, a0, a4
; CHECK-RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; CHECK-RV32-NEXT:    vlse64.v v16, (a4), a1
; CHECK-RV32-NEXT:    vsetvli zero, a3, e64, m8, ta, ma
; CHECK-RV32-NEXT:    vlse64.v v8, (a0), a1
; CHECK-RV32-NEXT:    ret
;
; CHECK-RV64-LABEL: strided_load_nxv16f64_allones_mask:
; CHECK-RV64:       # %bb.0:
; CHECK-RV64-NEXT:    csrr a4, vlenb
; CHECK-RV64-NEXT:    sub a3, a2, a4
; CHECK-RV64-NEXT:    sltu a5, a2, a3
; CHECK-RV64-NEXT:    addi a5, a5, -1
; CHECK-RV64-NEXT:    and a3, a5, a3
; CHECK-RV64-NEXT:    bltu a2, a4, .LBB50_2
; CHECK-RV64-NEXT:  # %bb.1:
; CHECK-RV64-NEXT:    mv a2, a4
; CHECK-RV64-NEXT:  .LBB50_2:
; CHECK-RV64-NEXT:    mul a4, a2, a1
; CHECK-RV64-NEXT:    add a4, a0, a4
; CHECK-RV64-NEXT:    vsetvli zero, a3, e64, m8, ta, ma
; CHECK-RV64-NEXT:    vlse64.v v16, (a4), a1
; CHECK-RV64-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; CHECK-RV64-NEXT:    vlse64.v v8, (a0), a1
; CHECK-RV64-NEXT:    ret
  %v = call <vscale x 16 x double> @llvm.experimental.vp.strided.load.nxv16f64.p0.i64(ptr %ptr, i64 %stride, <vscale x 16 x i1> splat (i1 true), i32 %evl)
  ret <vscale x 16 x double> %v
}

declare <vscale x 16 x double> @llvm.experimental.vp.strided.load.nxv16f64.p0.i64(ptr, i64, <vscale x 16 x i1>, i32)

; Widening + splitting (with HiIsEmpty == true)
; NOTE: We can't return <vscale x 17 x double> as that introduces a vector
; store that can't yet be legalized through widening. In order to test purely
; the vp.strided.load legalization, we manually split it.
define <vscale x 16 x double> @strided_load_nxv17f64(ptr %ptr, i64 %stride, <vscale x 17 x i1> %mask, i32 zeroext %evl, ptr %hi_ptr) {
; CHECK-RV32-LABEL: strided_load_nxv17f64:
; CHECK-RV32:       # %bb.0:
; CHECK-RV32-NEXT:    csrr a2, vlenb
; CHECK-RV32-NEXT:    slli a7, a2, 1
; CHECK-RV32-NEXT:    vmv1r.v v8, v0
; CHECK-RV32-NEXT:    mv a6, a3
; CHECK-RV32-NEXT:    bltu a3, a7, .LBB51_2
; CHECK-RV32-NEXT:  # %bb.1:
; CHECK-RV32-NEXT:    mv a6, a7
; CHECK-RV32-NEXT:  .LBB51_2:
; CHECK-RV32-NEXT:    sub a5, a6, a2
; CHECK-RV32-NEXT:    sltu t0, a6, a5
; CHECK-RV32-NEXT:    addi t0, t0, -1
; CHECK-RV32-NEXT:    and t0, t0, a5
; CHECK-RV32-NEXT:    mv a5, a6
; CHECK-RV32-NEXT:    bltu a6, a2, .LBB51_4
; CHECK-RV32-NEXT:  # %bb.3:
; CHECK-RV32-NEXT:    mv a5, a2
; CHECK-RV32-NEXT:  .LBB51_4:
; CHECK-RV32-NEXT:    mul t1, a5, a1
; CHECK-RV32-NEXT:    add t1, a0, t1
; CHECK-RV32-NEXT:    srli t2, a2, 3
; CHECK-RV32-NEXT:    vsetvli t3, zero, e8, mf4, ta, ma
; CHECK-RV32-NEXT:    vslidedown.vx v0, v8, t2
; CHECK-RV32-NEXT:    vsetvli zero, t0, e64, m8, ta, ma
; CHECK-RV32-NEXT:    vlse64.v v16, (t1), a1, v0.t
; CHECK-RV32-NEXT:    sub a7, a3, a7
; CHECK-RV32-NEXT:    sltu a3, a3, a7
; CHECK-RV32-NEXT:    addi a3, a3, -1
; CHECK-RV32-NEXT:    and a3, a3, a7
; CHECK-RV32-NEXT:    bltu a3, a2, .LBB51_6
; CHECK-RV32-NEXT:  # %bb.5:
; CHECK-RV32-NEXT:    mv a3, a2
; CHECK-RV32-NEXT:  .LBB51_6:
; CHECK-RV32-NEXT:    mul a6, a6, a1
; CHECK-RV32-NEXT:    add a6, a0, a6
; CHECK-RV32-NEXT:    srli a2, a2, 2
; CHECK-RV32-NEXT:    vsetvli a7, zero, e8, mf2, ta, ma
; CHECK-RV32-NEXT:    vslidedown.vx v0, v8, a2
; CHECK-RV32-NEXT:    vsetvli zero, a3, e64, m8, ta, ma
; CHECK-RV32-NEXT:    vlse64.v v24, (a6), a1, v0.t
; CHECK-RV32-NEXT:    vsetvli zero, a5, e64, m8, ta, ma
; CHECK-RV32-NEXT:    vmv1r.v v0, v8
; CHECK-RV32-NEXT:    vlse64.v v8, (a0), a1, v0.t
; CHECK-RV32-NEXT:    vs1r.v v24, (a4)
; CHECK-RV32-NEXT:    ret
;
; CHECK-RV64-LABEL: strided_load_nxv17f64:
; CHECK-RV64:       # %bb.0:
; CHECK-RV64-NEXT:    csrr a4, vlenb
; CHECK-RV64-NEXT:    slli a7, a4, 1
; CHECK-RV64-NEXT:    vmv1r.v v8, v0
; CHECK-RV64-NEXT:    mv a6, a2
; CHECK-RV64-NEXT:    bltu a2, a7, .LBB51_2
; CHECK-RV64-NEXT:  # %bb.1:
; CHECK-RV64-NEXT:    mv a6, a7
; CHECK-RV64-NEXT:  .LBB51_2:
; CHECK-RV64-NEXT:    sub a5, a6, a4
; CHECK-RV64-NEXT:    sltu t0, a6, a5
; CHECK-RV64-NEXT:    addi t0, t0, -1
; CHECK-RV64-NEXT:    and t0, t0, a5
; CHECK-RV64-NEXT:    mv a5, a6
; CHECK-RV64-NEXT:    bltu a6, a4, .LBB51_4
; CHECK-RV64-NEXT:  # %bb.3:
; CHECK-RV64-NEXT:    mv a5, a4
; CHECK-RV64-NEXT:  .LBB51_4:
; CHECK-RV64-NEXT:    mul t1, a5, a1
; CHECK-RV64-NEXT:    add t1, a0, t1
; CHECK-RV64-NEXT:    srli t2, a4, 3
; CHECK-RV64-NEXT:    vsetvli t3, zero, e8, mf4, ta, ma
; CHECK-RV64-NEXT:    vslidedown.vx v0, v8, t2
; CHECK-RV64-NEXT:    vsetvli zero, t0, e64, m8, ta, ma
; CHECK-RV64-NEXT:    vlse64.v v16, (t1), a1, v0.t
; CHECK-RV64-NEXT:    sub a7, a2, a7
; CHECK-RV64-NEXT:    sltu a2, a2, a7
; CHECK-RV64-NEXT:    addi a2, a2, -1
; CHECK-RV64-NEXT:    and a2, a2, a7
; CHECK-RV64-NEXT:    bltu a2, a4, .LBB51_6
; CHECK-RV64-NEXT:  # %bb.5:
; CHECK-RV64-NEXT:    mv a2, a4
; CHECK-RV64-NEXT:  .LBB51_6:
; CHECK-RV64-NEXT:    mul a6, a6, a1
; CHECK-RV64-NEXT:    add a6, a0, a6
; CHECK-RV64-NEXT:    srli a4, a4, 2
; CHECK-RV64-NEXT:    vsetvli a7, zero, e8, mf2, ta, ma
; CHECK-RV64-NEXT:    vslidedown.vx v0, v8, a4
; CHECK-RV64-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; CHECK-RV64-NEXT:    vlse64.v v24, (a6), a1, v0.t
; CHECK-RV64-NEXT:    vsetvli zero, a5, e64, m8, ta, ma
; CHECK-RV64-NEXT:    vmv1r.v v0, v8
; CHECK-RV64-NEXT:    vlse64.v v8, (a0), a1, v0.t
; CHECK-RV64-NEXT:    vs1r.v v24, (a3)
; CHECK-RV64-NEXT:    ret
  %v = call <vscale x 17 x double> @llvm.experimental.vp.strided.load.nxv17f64.p0.i64(ptr %ptr, i64 %stride, <vscale x 17 x i1> %mask, i32 %evl)
  %lo = call <vscale x 16 x double> @llvm.experimental.vector.extract.nxv16f64(<vscale x 17 x double> %v, i64 0)
  %hi = call <vscale x 1 x double> @llvm.experimental.vector.extract.nxv1f64(<vscale x 17 x double> %v, i64 16)
  store <vscale x 1 x double> %hi, ptr %hi_ptr
  ret <vscale x 16 x double> %lo
}

declare <vscale x 17 x double> @llvm.experimental.vp.strided.load.nxv17f64.p0.i64(ptr, i64, <vscale x 17 x i1>, i32)
declare <vscale x 1 x double> @llvm.experimental.vector.extract.nxv1f64(<vscale x 17 x double> %vec, i64 %idx)
declare <vscale x 16 x double> @llvm.experimental.vector.extract.nxv16f64(<vscale x 17 x double> %vec, i64 %idx)