llvm/test/CodeGen/RISCV/rvv/vpstore.ll

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

declare void @llvm.vp.store.nxv1i8.p0(<vscale x 1 x i8>, ptr, <vscale x 1 x i1>, i32)

define void @vpstore_nxv1i8(<vscale x 1 x i8> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv1i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, ma
; CHECK-NEXT:    vse8.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv1i8.p0(<vscale x 1 x i8> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv2i8.p0(<vscale x 2 x i8>, ptr, <vscale x 2 x i1>, i32)

define void @vpstore_nxv2i8(<vscale x 2 x i8> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv2i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf4, ta, ma
; CHECK-NEXT:    vse8.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv2i8.p0(<vscale x 2 x i8> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv3i8.p0(<vscale x 3 x i8>, ptr, <vscale x 3 x i1>, i32)

define void @vpstore_nxv3i8(<vscale x 3 x i8> %val, ptr %ptr, <vscale x 3 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv3i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, ma
; CHECK-NEXT:    vse8.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv3i8.p0(<vscale x 3 x i8> %val, ptr %ptr, <vscale x 3 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv4i8.p0(<vscale x 4 x i8>, ptr, <vscale x 4 x i1>, i32)

define void @vpstore_nxv4i8(<vscale x 4 x i8> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv4i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, ma
; CHECK-NEXT:    vse8.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv4i8.p0(<vscale x 4 x i8> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv8i8.p0(<vscale x 8 x i8>, ptr, <vscale x 8 x i1>, i32)

define void @vpstore_nxv8i8(<vscale x 8 x i8> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv8i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, ma
; CHECK-NEXT:    vse8.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv8i8.p0(<vscale x 8 x i8> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv1i16.p0(<vscale x 1 x i16>, ptr, <vscale x 1 x i1>, i32)

define void @vpstore_nxv1i16(<vscale x 1 x i16> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv1i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, ma
; CHECK-NEXT:    vse16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv1i16.p0(<vscale x 1 x i16> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv2i16.p0(<vscale x 2 x i16>, ptr, <vscale x 2 x i1>, i32)

define void @vpstore_nxv2i16(<vscale x 2 x i16> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv2i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, ma
; CHECK-NEXT:    vse16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv2i16.p0(<vscale x 2 x i16> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv4i16.p0(<vscale x 4 x i16>, ptr, <vscale x 4 x i1>, i32)

define void @vpstore_nxv4i16(<vscale x 4 x i16> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv4i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, ma
; CHECK-NEXT:    vse16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv4i16.p0(<vscale x 4 x i16> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv8i12.nxv8i12.p0(<vscale x 8 x i12>, <vscale x 8 x i12>*, <vscale x 8 x i1>, i32)

define void @vpstore_nxv8i12(<vscale x 8 x i12> %val, <vscale x 8 x i12>* %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv8i12:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, ma
; CHECK-NEXT:    vse16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv8i12.nxv8i12.p0(<vscale x 8 x i12> %val, <vscale x 8 x i12>* %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv8i16.p0(<vscale x 8 x i16>, ptr, <vscale x 8 x i1>, i32)

define void @vpstore_nxv8i16(<vscale x 8 x i16> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv8i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, ma
; CHECK-NEXT:    vse16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv8i16.p0(<vscale x 8 x i16> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv1i32.p0(<vscale x 1 x i32>, ptr, <vscale x 1 x i1>, i32)

define void @vpstore_nxv1i32(<vscale x 1 x i32> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv1i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, ma
; CHECK-NEXT:    vse32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv1i32.p0(<vscale x 1 x i32> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv2i32.p0(<vscale x 2 x i32>, ptr, <vscale x 2 x i1>, i32)

define void @vpstore_nxv2i32(<vscale x 2 x i32> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv2i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, ma
; CHECK-NEXT:    vse32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv2i32.p0(<vscale x 2 x i32> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32>, ptr, <vscale x 4 x i1>, i32)

define void @vpstore_nxv4i32(<vscale x 4 x i32> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv4i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, ma
; CHECK-NEXT:    vse32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv8i32.p0(<vscale x 8 x i32>, ptr, <vscale x 8 x i1>, i32)

define void @vpstore_nxv8i32(<vscale x 8 x i32> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv8i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, ma
; CHECK-NEXT:    vse32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv8i32.p0(<vscale x 8 x i32> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv1i64.p0(<vscale x 1 x i64>, ptr, <vscale x 1 x i1>, i32)

define void @vpstore_nxv1i64(<vscale x 1 x i64> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv1i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m1, ta, ma
; CHECK-NEXT:    vse64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv1i64.p0(<vscale x 1 x i64> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64>, ptr, <vscale x 2 x i1>, i32)

define void @vpstore_nxv2i64(<vscale x 2 x i64> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv2i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m2, ta, ma
; CHECK-NEXT:    vse64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv4i64.p0(<vscale x 4 x i64>, ptr, <vscale x 4 x i1>, i32)

define void @vpstore_nxv4i64(<vscale x 4 x i64> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv4i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m4, ta, ma
; CHECK-NEXT:    vse64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv4i64.p0(<vscale x 4 x i64> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv8i64.p0(<vscale x 8 x i64>, ptr, <vscale x 8 x i1>, i32)

define void @vpstore_nxv8i64(<vscale x 8 x i64> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv8i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
; CHECK-NEXT:    vse64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv8i64.p0(<vscale x 8 x i64> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv1bf16.p0(<vscale x 1 x bfloat>, ptr, <vscale x 1 x i1>, i32)

define void @vpstore_nxv1bf16(<vscale x 1 x bfloat> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv1bf16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, ma
; CHECK-NEXT:    vse16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv1bf16.p0(<vscale x 1 x bfloat> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv2bf16.p0(<vscale x 2 x bfloat>, ptr, <vscale x 2 x i1>, i32)

define void @vpstore_nxv2bf16(<vscale x 2 x bfloat> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv2bf16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, ma
; CHECK-NEXT:    vse16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv2bf16.p0(<vscale x 2 x bfloat> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv4bf16.p0(<vscale x 4 x bfloat>, ptr, <vscale x 4 x i1>, i32)

define void @vpstore_nxv4bf16(<vscale x 4 x bfloat> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv4bf16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, ma
; CHECK-NEXT:    vse16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv4bf16.p0(<vscale x 4 x bfloat> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv8bf16.p0(<vscale x 8 x bfloat>, ptr, <vscale x 8 x i1>, i32)

define void @vpstore_nxv8bf16(<vscale x 8 x bfloat> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv8bf16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, ma
; CHECK-NEXT:    vse16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv8bf16.p0(<vscale x 8 x bfloat> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv1f16.p0(<vscale x 1 x half>, ptr, <vscale x 1 x i1>, i32)

define void @vpstore_nxv1f16(<vscale x 1 x half> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv1f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, ma
; CHECK-NEXT:    vse16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv1f16.p0(<vscale x 1 x half> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv2f16.p0(<vscale x 2 x half>, ptr, <vscale x 2 x i1>, i32)

define void @vpstore_nxv2f16(<vscale x 2 x half> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv2f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, ma
; CHECK-NEXT:    vse16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv2f16.p0(<vscale x 2 x half> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv4f16.p0(<vscale x 4 x half>, ptr, <vscale x 4 x i1>, i32)

define void @vpstore_nxv4f16(<vscale x 4 x half> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv4f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, ma
; CHECK-NEXT:    vse16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv4f16.p0(<vscale x 4 x half> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv8f16.p0(<vscale x 8 x half>, ptr, <vscale x 8 x i1>, i32)

define void @vpstore_nxv8f16(<vscale x 8 x half> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv8f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, ma
; CHECK-NEXT:    vse16.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv8f16.p0(<vscale x 8 x half> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv1f32.p0(<vscale x 1 x float>, ptr, <vscale x 1 x i1>, i32)

define void @vpstore_nxv1f32(<vscale x 1 x float> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv1f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, ma
; CHECK-NEXT:    vse32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv1f32.p0(<vscale x 1 x float> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv2f32.p0(<vscale x 2 x float>, ptr, <vscale x 2 x i1>, i32)

define void @vpstore_nxv2f32(<vscale x 2 x float> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv2f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, ma
; CHECK-NEXT:    vse32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv2f32.p0(<vscale x 2 x float> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv4f32.p0(<vscale x 4 x float>, ptr, <vscale x 4 x i1>, i32)

define void @vpstore_nxv4f32(<vscale x 4 x float> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv4f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, ma
; CHECK-NEXT:    vse32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv4f32.p0(<vscale x 4 x float> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv8f32.p0(<vscale x 8 x float>, ptr, <vscale x 8 x i1>, i32)

define void @vpstore_nxv8f32(<vscale x 8 x float> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv8f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, ma
; CHECK-NEXT:    vse32.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv8f32.p0(<vscale x 8 x float> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv1f64.p0(<vscale x 1 x double>, ptr, <vscale x 1 x i1>, i32)

define void @vpstore_nxv1f64(<vscale x 1 x double> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv1f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m1, ta, ma
; CHECK-NEXT:    vse64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv1f64.p0(<vscale x 1 x double> %val, ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv2f64.p0(<vscale x 2 x double>, ptr, <vscale x 2 x i1>, i32)

define void @vpstore_nxv2f64(<vscale x 2 x double> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv2f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m2, ta, ma
; CHECK-NEXT:    vse64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv2f64.p0(<vscale x 2 x double> %val, ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv4f64.p0(<vscale x 4 x double>, ptr, <vscale x 4 x i1>, i32)

define void @vpstore_nxv4f64(<vscale x 4 x double> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv4f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m4, ta, ma
; CHECK-NEXT:    vse64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv4f64.p0(<vscale x 4 x double> %val, ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv8f64.p0(<vscale x 8 x double>, ptr, <vscale x 8 x i1>, i32)

define void @vpstore_nxv8f64(<vscale x 8 x double> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv8f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
; CHECK-NEXT:    vse64.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv8f64.p0(<vscale x 8 x double> %val, ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
  ret void
}

define void @vpstore_nxv1i8_allones_mask(<vscale x 1 x i8> %val, ptr %ptr, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv1i8_allones_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, ma
; CHECK-NEXT:    vse8.v v8, (a0)
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv1i8.p0(<vscale x 1 x i8> %val, ptr %ptr, <vscale x 1 x i1> splat (i1 true), i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv16f64.p0(<vscale x 16 x double>, ptr, <vscale x 16 x i1>, i32)

define void @vpstore_nxv16f64(<vscale x 16 x double> %val, ptr %ptr, <vscale x 16 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv16f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    csrr a2, vlenb
; CHECK-NEXT:    mv a3, a1
; CHECK-NEXT:    bltu a1, a2, .LBB35_2
; CHECK-NEXT:  # %bb.1:
; CHECK-NEXT:    mv a3, a2
; CHECK-NEXT:  .LBB35_2:
; CHECK-NEXT:    vsetvli zero, a3, e64, m8, ta, ma
; CHECK-NEXT:    vse64.v v8, (a0), v0.t
; CHECK-NEXT:    srli a3, a2, 3
; CHECK-NEXT:    vsetvli a4, zero, e8, mf4, ta, ma
; CHECK-NEXT:    vslidedown.vx v0, v0, a3
; CHECK-NEXT:    sub a3, a1, a2
; CHECK-NEXT:    slli a2, a2, 3
; CHECK-NEXT:    sltu a1, a1, a3
; CHECK-NEXT:    addi a1, a1, -1
; CHECK-NEXT:    and a1, a1, a3
; CHECK-NEXT:    add a0, a0, a2
; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
; CHECK-NEXT:    vse64.v v16, (a0), v0.t
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv16f64.p0(<vscale x 16 x double> %val, ptr %ptr, <vscale x 16 x i1> %m, i32 %evl)
  ret void
}

declare void @llvm.vp.store.nxv17f64.p0(<vscale x 17 x double>, ptr, <vscale x 17 x i1>, i32)

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

define void @vpstore_nxv17f64(<vscale x 17 x double> %val, ptr %ptr, <vscale x 17 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpstore_nxv17f64:
; CHECK:       # %bb.0:
; 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:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
; CHECK-NEXT:    vmv1r.v v24, v0
; CHECK-NEXT:    addi a3, sp, 16
; CHECK-NEXT:    vs8r.v v16, (a3) # Unknown-size Folded Spill
; CHECK-NEXT:    csrr a3, vlenb
; CHECK-NEXT:    slli a4, a3, 1
; CHECK-NEXT:    mv a5, a2
; CHECK-NEXT:    bltu a2, a4, .LBB36_2
; CHECK-NEXT:  # %bb.1:
; CHECK-NEXT:    mv a5, a4
; CHECK-NEXT:  .LBB36_2:
; CHECK-NEXT:    mv a6, a5
; CHECK-NEXT:    bltu a5, a3, .LBB36_4
; CHECK-NEXT:  # %bb.3:
; CHECK-NEXT:    mv a6, a3
; CHECK-NEXT:  .LBB36_4:
; CHECK-NEXT:    vmv1r.v v0, v24
; CHECK-NEXT:    vl8re64.v v16, (a0)
; CHECK-NEXT:    vsetvli zero, a6, e64, m8, ta, ma
; CHECK-NEXT:    vse64.v v8, (a1), v0.t
; CHECK-NEXT:    sub a0, a5, a3
; CHECK-NEXT:    srli a6, a3, 3
; CHECK-NEXT:    vsetvli a7, zero, e8, mf4, ta, ma
; CHECK-NEXT:    vslidedown.vx v0, v24, a6
; CHECK-NEXT:    slli a6, a3, 3
; CHECK-NEXT:    sub a4, a2, a4
; CHECK-NEXT:    sltu a5, a5, a0
; CHECK-NEXT:    add a6, a1, a6
; CHECK-NEXT:    sltu a2, a2, a4
; CHECK-NEXT:    addi a5, a5, -1
; CHECK-NEXT:    addi a2, a2, -1
; CHECK-NEXT:    and a5, a5, a0
; CHECK-NEXT:    and a0, a2, a4
; CHECK-NEXT:    addi a2, sp, 16
; CHECK-NEXT:    vl8r.v v8, (a2) # Unknown-size Folded Reload
; CHECK-NEXT:    vsetvli zero, a5, e64, m8, ta, ma
; CHECK-NEXT:    vse64.v v8, (a6), v0.t
; CHECK-NEXT:    bltu a0, a3, .LBB36_6
; CHECK-NEXT:  # %bb.5:
; CHECK-NEXT:    mv a0, a3
; CHECK-NEXT:  .LBB36_6:
; CHECK-NEXT:    slli a2, a3, 4
; CHECK-NEXT:    srli a3, a3, 2
; CHECK-NEXT:    vsetvli a4, zero, e8, mf2, ta, ma
; CHECK-NEXT:    vslidedown.vx v0, v24, a3
; CHECK-NEXT:    add a1, a1, a2
; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; CHECK-NEXT:    vse64.v v16, (a1), v0.t
; CHECK-NEXT:    csrr a0, vlenb
; CHECK-NEXT:    slli a0, a0, 3
; CHECK-NEXT:    add sp, sp, a0
; CHECK-NEXT:    .cfi_def_cfa sp, 16
; CHECK-NEXT:    addi sp, sp, 16
; CHECK-NEXT:    .cfi_def_cfa_offset 0
; CHECK-NEXT:    ret
  call void @llvm.vp.store.nxv17f64.p0(<vscale x 17 x double> %val, ptr %ptr, <vscale x 17 x i1> %m, i32 %evl)
  ret void
}

define void @vpstore_all_active_nxv8i8(<vscale x 8 x i8> %val, ptr %ptr) {
; CHECK-LABEL: vpstore_all_active_nxv8i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vs1r.v v8, (a0)
; CHECK-NEXT:    ret
  %vscale = call i32 @llvm.vscale()
  %evl = mul i32 %vscale, 8
  call void @llvm.vp.store.nxv8i8.p0(<vscale x 8 x i8> %val, ptr %ptr, <vscale x 8 x i1> splat (i1 true), i32 %evl)
  ret void
}