; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mattr=+sve < %s | FileCheck %s

target triple = "aarch64-unknown-linux-gnu"

;
; ASR
;

define <vscale x 16 x i8> @asr_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: asr_i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    asr z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT:    ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.u.nxv16i8(<vscale x 16 x i1> %pg,
                                                                 <vscale x 16 x i8> %a,
                                                                 <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @asr_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: asr_i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    asr z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT:    ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.u.nxv8i16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x i16> %a,
                                                                 <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @asr_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: asr_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    asr z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT:    ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.u.nxv4i32(<vscale x 4 x i1> %pg,
                                                                 <vscale x 4 x i32> %a,
                                                                 <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @asr_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: asr_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    asr z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT:    ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.asr.u.nxv2i64(<vscale x 2 x i1> %pg,
                                                                 <vscale x 2 x i64> %a,
                                                                 <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

;
; ASR (immediate)
;

define <vscale x 16 x i8> @asr_imm_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a) {
; CHECK-LABEL: asr_imm_i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    asr z0.b, z0.b, #3
; CHECK-NEXT:    ret
  %imm = insertelement <vscale x 16 x i8> undef, i8 3, i32 0
  %imm.splat = shufflevector <vscale x 16 x i8> %imm, <vscale x 16 x i8> undef, <vscale x 16 x i32> zeroinitializer
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.u.nxv16i8(<vscale x 16 x i1> %pg,
                                                                 <vscale x 16 x i8> %a,
                                                                 <vscale x 16 x i8> %imm.splat)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @asr_imm_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a) {
; CHECK-LABEL: asr_imm_i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    asr z0.h, z0.h, #4
; CHECK-NEXT:    ret
  %imm = insertelement <vscale x 8 x i16> undef, i16 4, i32 0
  %imm.splat = shufflevector <vscale x 8 x i16> %imm, <vscale x 8 x i16> undef, <vscale x 8 x i32> zeroinitializer
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.u.nxv8i16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x i16> %a,
                                                                 <vscale x 8 x i16> %imm.splat)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @asr_imm_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a) {
; CHECK-LABEL: asr_imm_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    asr z0.s, z0.s, #5
; CHECK-NEXT:    ret
  %imm = insertelement <vscale x 4 x i32> undef, i32 5, i32 0
  %imm.splat = shufflevector <vscale x 4 x i32> %imm, <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.u.nxv4i32(<vscale x 4 x i1> %pg,
                                                                 <vscale x 4 x i32> %a,
                                                                 <vscale x 4 x i32> %imm.splat)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @asr_imm_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a) {
; CHECK-LABEL: asr_imm_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    asr z0.d, z0.d, #6
; CHECK-NEXT:    ret
  %imm = insertelement <vscale x 2 x i64> undef, i64 6, i32 0
  %imm.splat = shufflevector <vscale x 2 x i64> %imm, <vscale x 2 x i64> undef, <vscale x 2 x i32> zeroinitializer
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.asr.u.nxv2i64(<vscale x 2 x i1> %pg,
                                                                 <vscale x 2 x i64> %a,
                                                                 <vscale x 2 x i64> %imm.splat)
  ret <vscale x 2 x i64> %out
}

;
; LSL
;

define <vscale x 16 x i8> @lsl_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: lsl_i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsl z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT:    ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.u.nxv16i8(<vscale x 16 x i1> %pg,
                                                                 <vscale x 16 x i8> %a,
                                                                 <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @lsl_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: lsl_i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsl z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT:    ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.u.nxv8i16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x i16> %a,
                                                                 <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @lsl_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: lsl_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsl z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT:    ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.u.nxv4i32(<vscale x 4 x i1> %pg,
                                                                 <vscale x 4 x i32> %a,
                                                                 <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @lsl_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: lsl_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsl z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT:    ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.lsl.u.nxv2i64(<vscale x 2 x i1> %pg,
                                                                 <vscale x 2 x i64> %a,
                                                                 <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

;
; LSL (immediate)
;

define <vscale x 16 x i8> @lsl_imm_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a) {
; CHECK-LABEL: lsl_imm_i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsl z0.b, z0.b, #7
; CHECK-NEXT:    ret
  %imm = insertelement <vscale x 16 x i8> undef, i8 7, i32 0
  %imm.splat = shufflevector <vscale x 16 x i8> %imm, <vscale x 16 x i8> undef, <vscale x 16 x i32> zeroinitializer
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.u.nxv16i8(<vscale x 16 x i1> %pg,
                                                                 <vscale x 16 x i8> %a,
                                                                 <vscale x 16 x i8> %imm.splat)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @lsl_imm_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a) {
; CHECK-LABEL: lsl_imm_i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsl z0.h, z0.h, #8
; CHECK-NEXT:    ret
  %imm = insertelement <vscale x 8 x i16> undef, i16 8, i32 0
  %imm.splat = shufflevector <vscale x 8 x i16> %imm, <vscale x 8 x i16> undef, <vscale x 8 x i32> zeroinitializer
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.u.nxv8i16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x i16> %a,
                                                                 <vscale x 8 x i16> %imm.splat)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @lsl_imm_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a) {
; CHECK-LABEL: lsl_imm_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsl z0.s, z0.s, #9
; CHECK-NEXT:    ret
  %imm = insertelement <vscale x 4 x i32> undef, i32 9, i32 0
  %imm.splat = shufflevector <vscale x 4 x i32> %imm, <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.u.nxv4i32(<vscale x 4 x i1> %pg,
                                                                 <vscale x 4 x i32> %a,
                                                                 <vscale x 4 x i32> %imm.splat)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @lsl_imm_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a) {
; CHECK-LABEL: lsl_imm_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsl z0.d, z0.d, #10
; CHECK-NEXT:    ret
  %imm = insertelement <vscale x 2 x i64> undef, i64 10, i32 0
  %imm.splat = shufflevector <vscale x 2 x i64> %imm, <vscale x 2 x i64> undef, <vscale x 2 x i32> zeroinitializer
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.lsl.u.nxv2i64(<vscale x 2 x i1> %pg,
                                                                 <vscale x 2 x i64> %a,
                                                                 <vscale x 2 x i64> %imm.splat)
  ret <vscale x 2 x i64> %out
}

;
; LSR
;

define <vscale x 16 x i8> @lsr_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: lsr_i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsr z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT:    ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.u.nxv16i8(<vscale x 16 x i1> %pg,
                                                                 <vscale x 16 x i8> %a,
                                                                 <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @lsr_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: lsr_i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsr z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT:    ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.u.nxv8i16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x i16> %a,
                                                                 <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @lsr_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: lsr_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsr z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT:    ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.u.nxv4i32(<vscale x 4 x i1> %pg,
                                                                 <vscale x 4 x i32> %a,
                                                                 <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @lsr_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: lsr_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsr z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT:    ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.lsr.u.nxv2i64(<vscale x 2 x i1> %pg,
                                                                 <vscale x 2 x i64> %a,
                                                                 <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

;
; LSR (immediate)
;

define <vscale x 16 x i8> @lsr_imm_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a) {
; CHECK-LABEL: lsr_imm_i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsr z0.b, z0.b, #8
; CHECK-NEXT:    ret
  %imm = insertelement <vscale x 16 x i8> undef, i8 8, i32 0
  %imm.splat = shufflevector <vscale x 16 x i8> %imm, <vscale x 16 x i8> undef, <vscale x 16 x i32> zeroinitializer
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.u.nxv16i8(<vscale x 16 x i1> %pg,
                                                                 <vscale x 16 x i8> %a,
                                                                 <vscale x 16 x i8> %imm.splat)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @lsr_imm_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a) {
; CHECK-LABEL: lsr_imm_i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsr z0.h, z0.h, #12
; CHECK-NEXT:    ret
  %imm = insertelement <vscale x 8 x i16> undef, i16 12, i32 0
  %imm.splat = shufflevector <vscale x 8 x i16> %imm, <vscale x 8 x i16> undef, <vscale x 8 x i32> zeroinitializer
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.u.nxv8i16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x i16> %a,
                                                                 <vscale x 8 x i16> %imm.splat)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @lsr_imm_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a) {
; CHECK-LABEL: lsr_imm_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsr z0.s, z0.s, #13
; CHECK-NEXT:    ret
  %imm = insertelement <vscale x 4 x i32> undef, i32 13, i32 0
  %imm.splat = shufflevector <vscale x 4 x i32> %imm, <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.u.nxv4i32(<vscale x 4 x i1> %pg,
                                                                 <vscale x 4 x i32> %a,
                                                                 <vscale x 4 x i32> %imm.splat)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @lsr_imm_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a) {
; CHECK-LABEL: lsr_imm_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsr z0.d, z0.d, #14
; CHECK-NEXT:    ret
  %imm = insertelement <vscale x 2 x i64> undef, i64 14, i32 0
  %imm.splat = shufflevector <vscale x 2 x i64> %imm, <vscale x 2 x i64> undef, <vscale x 2 x i32> zeroinitializer
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.lsr.u.nxv2i64(<vscale x 2 x i1> %pg,
                                                                 <vscale x 2 x i64> %a,
                                                                 <vscale x 2 x i64> %imm.splat)
  ret <vscale x 2 x i64> %out
}

declare <vscale x 16 x i8> @llvm.aarch64.sve.asr.u.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.asr.u.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.asr.u.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.asr.u.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)

declare <vscale x 16 x i8> @llvm.aarch64.sve.lsl.u.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.lsl.u.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.lsl.u.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.lsl.u.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)

declare <vscale x 16 x i8> @llvm.aarch64.sve.lsr.u.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.lsr.u.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.lsr.u.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.lsr.u.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)