llvm/test/CodeGen/AArch64/active_lane_mask.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s --check-prefixes=CHECK,CHECK-SVE
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sme -force-streaming < %s | FileCheck %s --check-prefixes=CHECK,CHECK-STREAMING

; == Scalable ==

define <vscale x 16 x i1> @lane_mask_nxv16i1_i32(i32 %index, i32 %TC) {
; CHECK-LABEL: lane_mask_nxv16i1_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.b, w0, w1
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 %index, i32 %TC)
  ret <vscale x 16 x i1> %active.lane.mask
}

define <vscale x 8 x i1> @lane_mask_nxv8i1_i32(i32 %index, i32 %TC) {
; CHECK-LABEL: lane_mask_nxv8i1_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.h, w0, w1
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 %index, i32 %TC)
  ret <vscale x 8 x i1> %active.lane.mask
}

define <vscale x 4 x i1> @lane_mask_nxv4i1_i32(i32 %index, i32 %TC) {
; CHECK-LABEL: lane_mask_nxv4i1_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.s, w0, w1
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 %index, i32 %TC)
  ret <vscale x 4 x i1> %active.lane.mask
}

define <vscale x 2 x i1> @lane_mask_nxv2i1_i32(i32 %index, i32 %TC) {
; CHECK-LABEL: lane_mask_nxv2i1_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.d, w0, w1
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 %index, i32 %TC)
  ret <vscale x 2 x i1> %active.lane.mask
}

define <vscale x 16 x i1> @lane_mask_nxv16i1_i64(i64 %index, i64 %TC) {
; CHECK-LABEL: lane_mask_nxv16i1_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.b, x0, x1
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 %index, i64 %TC)
  ret <vscale x 16 x i1> %active.lane.mask
}

define <vscale x 8 x i1> @lane_mask_nxv8i1_i64(i64 %index, i64 %TC) {
; CHECK-LABEL: lane_mask_nxv8i1_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.h, x0, x1
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 %index, i64 %TC)
  ret <vscale x 8 x i1> %active.lane.mask
}

define <vscale x 4 x i1> @lane_mask_nxv4i1_i64(i64 %index, i64 %TC) {
; CHECK-LABEL: lane_mask_nxv4i1_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.s, x0, x1
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 %index, i64 %TC)
  ret <vscale x 4 x i1> %active.lane.mask
}

define <vscale x 2 x i1> @lane_mask_nxv2i1_i64(i64 %index, i64 %TC) {
; CHECK-LABEL: lane_mask_nxv2i1_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.d, x0, x1
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 %index, i64 %TC)
  ret <vscale x 2 x i1> %active.lane.mask
}

define <vscale x 16 x i1> @lane_mask_nxv16i1_i8(i8 %index, i8 %TC) {
; CHECK-LABEL: lane_mask_nxv16i1_i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    and w8, w1, #0xff
; CHECK-NEXT:    and w9, w0, #0xff
; CHECK-NEXT:    whilelo p0.b, w9, w8
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i8(i8 %index, i8 %TC)
  ret <vscale x 16 x i1> %active.lane.mask
}

define <vscale x 8 x i1> @lane_mask_nxv8i1_i8(i8 %index, i8 %TC) {
; CHECK-LABEL: lane_mask_nxv8i1_i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    and w8, w1, #0xff
; CHECK-NEXT:    and w9, w0, #0xff
; CHECK-NEXT:    whilelo p0.h, w9, w8
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i8(i8 %index, i8 %TC)
  ret <vscale x 8 x i1> %active.lane.mask
}

define <vscale x 4 x i1> @lane_mask_nxv4i1_i8(i8 %index, i8 %TC) {
; CHECK-LABEL: lane_mask_nxv4i1_i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    and w8, w1, #0xff
; CHECK-NEXT:    and w9, w0, #0xff
; CHECK-NEXT:    whilelo p0.s, w9, w8
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i8(i8 %index, i8 %TC)
  ret <vscale x 4 x i1> %active.lane.mask
}

define <vscale x 2 x i1> @lane_mask_nxv2i1_i8(i8 %index, i8 %TC) {
; CHECK-LABEL: lane_mask_nxv2i1_i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    and w8, w1, #0xff
; CHECK-NEXT:    and w9, w0, #0xff
; CHECK-NEXT:    whilelo p0.d, w9, w8
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i8(i8 %index, i8 %TC)
  ret <vscale x 2 x i1> %active.lane.mask
}


; Illegal types

define <vscale x 32 x i1> @lane_mask_nxv32i1_i32(i32 %index, i32 %TC) {
; CHECK-LABEL: lane_mask_nxv32i1_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    rdvl x8, #1
; CHECK-NEXT:    adds w8, w0, w8
; CHECK-NEXT:    csinv w8, w8, wzr, lo
; CHECK-NEXT:    whilelo p0.b, w0, w1
; CHECK-NEXT:    whilelo p1.b, w8, w1
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i32(i32 %index, i32 %TC)
  ret <vscale x 32 x i1> %active.lane.mask
}

define <vscale x 32 x i1> @lane_mask_nxv32i1_i64(i64 %index, i64 %TC) {
; CHECK-LABEL: lane_mask_nxv32i1_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    rdvl x8, #1
; CHECK-NEXT:    adds x8, x0, x8
; CHECK-NEXT:    csinv x8, x8, xzr, lo
; CHECK-NEXT:    whilelo p0.b, x0, x1
; CHECK-NEXT:    whilelo p1.b, x8, x1
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 %index, i64 %TC)
  ret <vscale x 32 x i1> %active.lane.mask
}

define <vscale x 32 x i1> @lane_mask_nxv32i1_i8(i8 %index, i8 %TC) {
; CHECK-LABEL: lane_mask_nxv32i1_i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    rdvl x8, #1
; CHECK-NEXT:    and w9, w0, #0xff
; CHECK-NEXT:    mov w10, #255 // =0xff
; CHECK-NEXT:    add w8, w9, w8, uxtb
; CHECK-NEXT:    and w11, w1, #0xff
; CHECK-NEXT:    cmp w8, #255
; CHECK-NEXT:    csel w8, w8, w10, lo
; CHECK-NEXT:    whilelo p0.b, w9, w11
; CHECK-NEXT:    whilelo p1.b, w8, w11
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i8(i8 %index, i8 %TC)
  ret <vscale x 32 x i1> %active.lane.mask
}

define <vscale x 7 x i1> @lane_mask_nxv7i1_i64(i64 %index, i64 %TC) {
; CHECK-LABEL: lane_mask_nxv7i1_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.h, x0, x1
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 7 x i1> @llvm.get.active.lane.mask.nxv7i1.i64(i64 %index, i64 %TC)
  ret <vscale x 7 x i1> %active.lane.mask
}

define <vscale x 1 x i1> @lane_mask_nxv1i1_i32(i32 %index, i32 %TC) {
; CHECK-LABEL: lane_mask_nxv1i1_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    index z0.s, #0, #1
; CHECK-NEXT:    mov z1.s, w0
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    uqadd z0.s, z0.s, z1.s
; CHECK-NEXT:    mov z1.s, w1
; CHECK-NEXT:    cmphi p0.s, p0/z, z1.s, z0.s
; CHECK-NEXT:    punpklo p0.h, p0.b
; CHECK-NEXT:    punpklo p0.h, p0.b
; CHECK-NEXT:    ret
  %active.lane.mask = call <vscale x 1 x i1> @llvm.get.active.lane.mask.nxv1i1.i32(i32 %index, i32 %TC)
  ret <vscale x 1 x i1> %active.lane.mask
}

; UTC_ARGS: --disable
; This test exists to protect against a compiler crash caused by an attempt to
; convert (via changeVectorElementType) an MVT into an EVT, which is impossible.
; The test's output is large and not relevant so check lines have been disabled.
define <vscale x 64 x i1> @lane_mask_nxv64i1_i64(i64 %index, i64 %TC) {
; CHECK-LABEL: lane_mask_nxv64i1_i64:
  %active.lane.mask = call <vscale x 64 x i1> @llvm.get.active.lane.mask.nxv64i1.i64(i64 %index, i64 %TC)
  ret <vscale x 64 x i1> %active.lane.mask
}
; UTC_ARGS: --enable

; == Fixed width ==

define <16 x i1> @lane_mask_v16i1_i32(i32 %index, i32 %TC) {
; CHECK-LABEL: lane_mask_v16i1_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.b, w0, w1
; CHECK-NEXT:    mov z0.b, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $z0
; CHECK-NEXT:    ret
  %active.lane.mask = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 %index, i32 %TC)
  ret <16 x i1> %active.lane.mask
}

define <8 x i1> @lane_mask_v8i1_i32(i32 %index, i32 %TC) {
; CHECK-LABEL: lane_mask_v8i1_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.b, w0, w1
; CHECK-NEXT:    mov z0.b, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $z0
; CHECK-NEXT:    ret
  %active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %TC)
  ret <8 x i1> %active.lane.mask
}

define <4 x i1> @lane_mask_v4i1_i32(i32 %index, i32 %TC) {
; CHECK-LABEL: lane_mask_v4i1_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.h, w0, w1
; CHECK-NEXT:    mov z0.h, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $z0
; CHECK-NEXT:    ret
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %TC)
  ret <4 x i1> %active.lane.mask
}

define <2 x i1> @lane_mask_v2i1_i32(i32 %index, i32 %TC) {
; CHECK-LABEL: lane_mask_v2i1_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.s, w0, w1
; CHECK-NEXT:    mov z0.s, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $z0
; CHECK-NEXT:    ret
  %active.lane.mask = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 %index, i32 %TC)
  ret <2 x i1> %active.lane.mask
}

define <16 x i1> @lane_mask_v16i1_i64(i64 %index, i64 %TC) {
; CHECK-LABEL: lane_mask_v16i1_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.b, x0, x1
; CHECK-NEXT:    mov z0.b, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $z0
; CHECK-NEXT:    ret
  %active.lane.mask = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 %index, i64 %TC)
  ret <16 x i1> %active.lane.mask
}

define <8 x i1> @lane_mask_v8i1_i64(i64 %index, i64 %TC) {
; CHECK-LABEL: lane_mask_v8i1_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.b, x0, x1
; CHECK-NEXT:    mov z0.b, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $z0
; CHECK-NEXT:    ret
  %active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 %index, i64 %TC)
  ret <8 x i1> %active.lane.mask
}

define <4 x i1> @lane_mask_v4i1_i64(i64 %index, i64 %TC) {
; CHECK-LABEL: lane_mask_v4i1_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.h, x0, x1
; CHECK-NEXT:    mov z0.h, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $z0
; CHECK-NEXT:    ret
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 %index, i64 %TC)
  ret <4 x i1> %active.lane.mask
}

define <2 x i1> @lane_mask_v2i1_i64(i64 %index, i64 %TC) {
; CHECK-LABEL: lane_mask_v2i1_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    whilelo p0.s, x0, x1
; CHECK-NEXT:    mov z0.s, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $z0
; CHECK-NEXT:    ret
  %active.lane.mask = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 %index, i64 %TC)
  ret <2 x i1> %active.lane.mask
}

define <16 x i1> @lane_mask_v16i1_i8(i8 %index, i8 %TC) {
; CHECK-SVE-LABEL: lane_mask_v16i1_i8:
; CHECK-SVE:       // %bb.0:
; CHECK-SVE-NEXT:    index z0.b, #0, #1
; CHECK-SVE-NEXT:    dup v1.16b, w0
; CHECK-SVE-NEXT:    uqadd v0.16b, v1.16b, v0.16b
; CHECK-SVE-NEXT:    dup v1.16b, w1
; CHECK-SVE-NEXT:    cmhi v0.16b, v1.16b, v0.16b
; CHECK-SVE-NEXT:    ret
;
; CHECK-STREAMING-LABEL: lane_mask_v16i1_i8:
; CHECK-STREAMING:       // %bb.0:
; CHECK-STREAMING-NEXT:    index z0.b, w0, #1
; CHECK-STREAMING-NEXT:    mov z1.b, w0
; CHECK-STREAMING-NEXT:    ptrue p0.b, vl16
; CHECK-STREAMING-NEXT:    cmphi p1.b, p0/z, z1.b, z0.b
; CHECK-STREAMING-NEXT:    mov z1.b, p1/z, #-1 // =0xffffffffffffffff
; CHECK-STREAMING-NEXT:    orr z0.d, z0.d, z1.d
; CHECK-STREAMING-NEXT:    mov z1.b, w1
; CHECK-STREAMING-NEXT:    cmphi p0.b, p0/z, z1.b, z0.b
; CHECK-STREAMING-NEXT:    mov z0.b, p0/z, #-1 // =0xffffffffffffffff
; CHECK-STREAMING-NEXT:    // kill: def $q0 killed $q0 killed $z0
; CHECK-STREAMING-NEXT:    ret
  %active.lane.mask = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i8(i8 %index, i8 %TC)
  ret <16 x i1> %active.lane.mask
}

define <8 x i1> @lane_mask_v8i1_i8(i8 %index, i8 %TC) {
; CHECK-SVE-LABEL: lane_mask_v8i1_i8:
; CHECK-SVE:       // %bb.0:
; CHECK-SVE-NEXT:    index z0.b, #0, #1
; CHECK-SVE-NEXT:    dup v1.8b, w0
; CHECK-SVE-NEXT:    uqadd v0.8b, v1.8b, v0.8b
; CHECK-SVE-NEXT:    dup v1.8b, w1
; CHECK-SVE-NEXT:    cmhi v0.8b, v1.8b, v0.8b
; CHECK-SVE-NEXT:    ret
;
; CHECK-STREAMING-LABEL: lane_mask_v8i1_i8:
; CHECK-STREAMING:       // %bb.0:
; CHECK-STREAMING-NEXT:    index z0.b, w0, #1
; CHECK-STREAMING-NEXT:    mov z1.b, w0
; CHECK-STREAMING-NEXT:    ptrue p0.b, vl8
; CHECK-STREAMING-NEXT:    cmphi p1.b, p0/z, z1.b, z0.b
; CHECK-STREAMING-NEXT:    mov z1.b, p1/z, #-1 // =0xffffffffffffffff
; CHECK-STREAMING-NEXT:    orr z0.d, z0.d, z1.d
; CHECK-STREAMING-NEXT:    mov z1.b, w1
; CHECK-STREAMING-NEXT:    cmphi p0.b, p0/z, z1.b, z0.b
; CHECK-STREAMING-NEXT:    mov z0.b, p0/z, #-1 // =0xffffffffffffffff
; CHECK-STREAMING-NEXT:    // kill: def $d0 killed $d0 killed $z0
; CHECK-STREAMING-NEXT:    ret
  %active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i8(i8 %index, i8 %TC)
  ret <8 x i1> %active.lane.mask
}

define <4 x i1> @lane_mask_v4i1_i8(i8 %index, i8 %TC) {
; CHECK-SVE-LABEL: lane_mask_v4i1_i8:
; CHECK-SVE:       // %bb.0:
; CHECK-SVE-NEXT:    dup v0.4h, w0
; CHECK-SVE-NEXT:    index z1.h, #0, #1
; CHECK-SVE-NEXT:    movi d2, #0xff00ff00ff00ff
; CHECK-SVE-NEXT:    dup v3.4h, w1
; CHECK-SVE-NEXT:    bic v0.4h, #255, lsl #8
; CHECK-SVE-NEXT:    bic v3.4h, #255, lsl #8
; CHECK-SVE-NEXT:    add v0.4h, v0.4h, v1.4h
; CHECK-SVE-NEXT:    umin v0.4h, v0.4h, v2.4h
; CHECK-SVE-NEXT:    cmhi v0.4h, v3.4h, v0.4h
; CHECK-SVE-NEXT:    ret
;
; CHECK-STREAMING-LABEL: lane_mask_v4i1_i8:
; CHECK-STREAMING:       // %bb.0:
; CHECK-STREAMING-NEXT:    mov z1.h, w0
; CHECK-STREAMING-NEXT:    index z0.h, #0, #1
; CHECK-STREAMING-NEXT:    ptrue p0.h, vl4
; CHECK-STREAMING-NEXT:    and z1.h, z1.h, #0xff
; CHECK-STREAMING-NEXT:    add z0.h, z1.h, z0.h
; CHECK-STREAMING-NEXT:    mov z1.h, w1
; CHECK-STREAMING-NEXT:    umin z0.h, z0.h, #255
; CHECK-STREAMING-NEXT:    and z1.h, z1.h, #0xff
; CHECK-STREAMING-NEXT:    cmphi p0.h, p0/z, z1.h, z0.h
; CHECK-STREAMING-NEXT:    mov z0.h, p0/z, #-1 // =0xffffffffffffffff
; CHECK-STREAMING-NEXT:    // kill: def $d0 killed $d0 killed $z0
; CHECK-STREAMING-NEXT:    ret
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i8(i8 %index, i8 %TC)
  ret <4 x i1> %active.lane.mask
}

define <2 x i1> @lane_mask_v2i1_i8(i8 %index, i8 %TC) {
; CHECK-SVE-LABEL: lane_mask_v2i1_i8:
; CHECK-SVE:       // %bb.0:
; CHECK-SVE-NEXT:    movi d0, #0x0000ff000000ff
; CHECK-SVE-NEXT:    dup v1.2s, w0
; CHECK-SVE-NEXT:    index z2.s, #0, #1
; CHECK-SVE-NEXT:    dup v3.2s, w1
; CHECK-SVE-NEXT:    and v1.8b, v1.8b, v0.8b
; CHECK-SVE-NEXT:    add v1.2s, v1.2s, v2.2s
; CHECK-SVE-NEXT:    and v2.8b, v3.8b, v0.8b
; CHECK-SVE-NEXT:    umin v0.2s, v1.2s, v0.2s
; CHECK-SVE-NEXT:    cmhi v0.2s, v2.2s, v0.2s
; CHECK-SVE-NEXT:    ret
;
; CHECK-STREAMING-LABEL: lane_mask_v2i1_i8:
; CHECK-STREAMING:       // %bb.0:
; CHECK-STREAMING-NEXT:    and w8, w0, #0xff
; CHECK-STREAMING-NEXT:    ptrue p0.s, vl2
; CHECK-STREAMING-NEXT:    index z0.s, w8, #1
; CHECK-STREAMING-NEXT:    and w8, w1, #0xff
; CHECK-STREAMING-NEXT:    mov z1.s, w8
; CHECK-STREAMING-NEXT:    umin z0.s, z0.s, #255
; CHECK-STREAMING-NEXT:    cmphi p0.s, p0/z, z1.s, z0.s
; CHECK-STREAMING-NEXT:    mov z0.s, p0/z, #-1 // =0xffffffffffffffff
; CHECK-STREAMING-NEXT:    // kill: def $d0 killed $d0 killed $z0
; CHECK-STREAMING-NEXT:    ret
  %active.lane.mask = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i8(i8 %index, i8 %TC)
  ret <2 x i1> %active.lane.mask
}

define <vscale x 4 x i1> @lane_mask_nxv4i1_imm3() {
; CHECK-LABEL: lane_mask_nxv4i1_imm3:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    ptrue p0.s, vl3
; CHECK-NEXT:    ret
entry:
  %active.lane.mask = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 3)
  ret <vscale x 4 x i1> %active.lane.mask
}

define <vscale x 4 x i1> @lane_mask_nxv4i1_imm5() {
; CHECK-LABEL: lane_mask_nxv4i1_imm5:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    mov w8, #5 // =0x5
; CHECK-NEXT:    whilelo p0.s, xzr, x8
; CHECK-NEXT:    ret
entry:
  %active.lane.mask = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 5)
  ret <vscale x 4 x i1> %active.lane.mask
}

define <vscale x 4 x i1> @lane_mask_nxv4i1_imm4() {
; CHECK-LABEL: lane_mask_nxv4i1_imm4:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    ptrue p0.s, vl4
; CHECK-NEXT:    ret
entry:
  %active.lane.mask = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 10, i64 14)
  ret <vscale x 4 x i1> %active.lane.mask
}

define <vscale x 16 x i1> @lane_mask_nxv16i1_imm10() {
; CHECK-LABEL: lane_mask_nxv16i1_imm10:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    mov w8, #10 // =0xa
; CHECK-NEXT:    whilelo p0.b, xzr, x8
; CHECK-NEXT:    ret
entry:
  %active.lane.mask = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 0, i64 10)
  ret <vscale x 16 x i1> %active.lane.mask
}

define <vscale x 16 x i1> @lane_mask_nxv16i1_imm256() vscale_range(16, 16) {
; CHECK-LABEL: lane_mask_nxv16i1_imm256:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    ptrue p0.b, vl256
; CHECK-NEXT:    ret
entry:
  %active.lane.mask = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 0, i64 256)
  ret <vscale x 16 x i1> %active.lane.mask
}

define <8 x i1> @lane_mask_v8i1_imm3() {
; CHECK-LABEL: lane_mask_v8i1_imm3:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    ptrue p0.b, vl3
; CHECK-NEXT:    mov z0.b, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $z0
; CHECK-NEXT:    ret
entry:
  %active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 0, i64 3)
  ret <8 x i1> %active.lane.mask
}

declare <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i32(i32, i32)
declare <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32, i32)
declare <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32, i32)
declare <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32, i32)
declare <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32, i32)
declare <vscale x 1 x i1> @llvm.get.active.lane.mask.nxv1i1.i32(i32, i32)

declare <vscale x 64 x i1> @llvm.get.active.lane.mask.nxv64i1.i64(i64, i64)
declare <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64, i64)
declare <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64, i64)
declare <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64, i64)
declare <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64, i64)
declare <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64, i64)

declare <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i8(i8, i8)
declare <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i8(i8, i8)
declare <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i8(i8, i8)
declare <vscale x 7 x i1> @llvm.get.active.lane.mask.nxv7i1.i8(i8, i8)
declare <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i8(i8, i8)
declare <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i8(i8, i8)

declare <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32, i32)
declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32, i32)
declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32)
declare <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32, i32)

declare <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64, i64)
declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64, i64)
declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64, i64)
declare <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64, i64)

declare <16 x i1> @llvm.get.active.lane.mask.v16i1.i8(i8, i8)
declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i8(i8, i8)
declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i8(i8, i8)
declare <2 x i1> @llvm.get.active.lane.mask.v2i1.i8(i8, i8)