; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2p1 < %s | FileCheck %s

; Merge

define <vscale x 8 x i16> @test_pmov_to_vector_i16(<vscale x 8 x i16> %zn, <vscale x 8 x i1> %pn) {
; CHECK-LABEL: test_pmov_to_vector_i16:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset w30, -16
; CHECK-NEXT:    mov w0, #1 // =0x1
; CHECK-NEXT:    bl llvm.aarch64.sve.pmov.to.vector.lane.merging.nxv8i16
; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT:    ret
  entry:
  %res = call <vscale x 8 x i16> @llvm.aarch64.sve.pmov.to.vector.lane.merging.nxv8i16(<vscale x 8 x i16> %zn, <vscale x 8 x i1> %pn, i32 1)
  ret <vscale x 8 x i16> %res
}

define <vscale x 4 x i32> @test_pmov_to_vector_i32(<vscale x 4 x i32> %zn, <vscale x 4 x i1> %pn) {
; CHECK-LABEL: test_pmov_to_vector_i32:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset w30, -16
; CHECK-NEXT:    mov w0, #3 // =0x3
; CHECK-NEXT:    bl llvm.aarch64.sve.pmov.to.vector.lane.merging.nxv4i32
; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT:    ret
  entry:
  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.pmov.to.vector.lane.merging.nxv4i32(<vscale x 4 x i32> %zn, <vscale x 4 x i1> %pn, i32 3)
  ret <vscale x 4 x i32> %res
}

define <vscale x 2 x i64> @test_pmov_to_vector_i64(<vscale x 2 x i64> %zn, <vscale x 2 x i1> %pn) {
; CHECK-LABEL: test_pmov_to_vector_i64:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset w30, -16
; CHECK-NEXT:    mov w0, #7 // =0x7
; CHECK-NEXT:    bl llvm.aarch64.sve.pmov.to.vector.lane.merging.nxv2i64
; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT:    ret
  entry:
  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.pmov.to.vector.lane.merging.nxv2i64(<vscale x 2 x i64> %zn, <vscale x 2 x i1> %pn, i32 7)
  ret <vscale x 2 x i64> %res
}


; Zero

define <vscale x 16 x i8> @test_pmov_to_vector_zero_i8(<vscale x 16 x i1> %pn) {
; CHECK-LABEL: test_pmov_to_vector_zero_i8:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset w30, -16
; CHECK-NEXT:    bl llvm.aarch64.sve.pmov.to.vector.lane.zeroing.nxv16i8
; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT:    ret
  entry:
  %res = call <vscale x 16 x i8> @llvm.aarch64.sve.pmov.to.vector.lane.zeroing.nxv16i8(<vscale x 16 x i1> %pn)
  ret <vscale x 16 x i8> %res
}

define <vscale x 8 x i16> @test_pmov_to_vector_zero_i16(<vscale x 8 x i1> %pn) {
; CHECK-LABEL: test_pmov_to_vector_zero_i16:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset w30, -16
; CHECK-NEXT:    bl llvm.aarch64.sve.pmov.to.vector.lane.zeroing.nxv8i16
; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT:    ret
  entry:
  %res = call <vscale x 8 x i16> @llvm.aarch64.sve.pmov.to.vector.lane.zeroing.nxv8i16(<vscale x 8 x i1> %pn)
  ret <vscale x 8 x i16> %res
}

define <vscale x 4 x i32> @test_pmov_to_vector_zero_i32(<vscale x 4 x i1> %pn) {
; CHECK-LABEL: test_pmov_to_vector_zero_i32:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset w30, -16
; CHECK-NEXT:    bl llvm.aarch64.sve.pmov.to.vector.lane.zeroing.nxv4i32
; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT:    ret
  entry:
  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.pmov.to.vector.lane.zeroing.nxv4i32(<vscale x 4 x i1> %pn)
  ret <vscale x 4 x i32> %res
}

define <vscale x 2 x i64> @test_pmov_to_vector_zero_i64(<vscale x 2 x i1> %pn) {
; CHECK-LABEL: test_pmov_to_vector_zero_i64:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset w30, -16
; CHECK-NEXT:    bl llvm.aarch64.sve.pmov.to.vector.lane.zeroing.nxv2i64
; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT:    ret
  entry:
  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.pmov.to.vector.lane.zeroing.nxv2i64(<vscale x 2 x i1> %pn)
  ret <vscale x 2 x i64> %res
}

declare <vscale x 8 x i16> @llvm.aarch64.sve.pmov.to.vector.lane.merging.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i1>, i32)
declare <vscale x 4 x i32> @llvm.aarch64.sve.pmov.to.vector.lane.merging.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i1>, i32)
declare <vscale x 2 x i64> @llvm.aarch64.sve.pmov.to.vector.lane.merging.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, i32)

declare <vscale x 16 x i8> @llvm.aarch64.sve.pmov.to.vector.lane.zeroing.nxv16i8(<vscale x 16 x i1>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.pmov.to.vector.lane.zeroing.nxv8i16(<vscale x 8 x i1>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.pmov.to.vector.lane.zeroing.nxv4i32(<vscale x 4 x i1>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.pmov.to.vector.lane.zeroing.nxv2i64(<vscale x 2 x i1>)