; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
; RUN: llc -mtriple=aarch64 -mattr=+sve < %s -o - | FileCheck --check-prefixes=CHECK,SVE %s
; RUN: llc -mtriple=aarch64 -mattr=+sve2 < %s -o - | FileCheck --check-prefixes=CHECK,SVE2 %s

define <vscale x 2 x i64> @xar_nxv2i64_l(<vscale x 2 x i64> %x, <vscale x 2 x i64> %y) {
; SVE-LABEL: xar_nxv2i64_l:
; SVE:       // %bb.0:
; SVE-NEXT:    eor z0.d, z0.d, z1.d
; SVE-NEXT:    lsr z1.d, z0.d, #4
; SVE-NEXT:    lsl z0.d, z0.d, #60
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    ret
;
; SVE2-LABEL: xar_nxv2i64_l:
; SVE2:       // %bb.0:
; SVE2-NEXT:    xar z0.d, z0.d, z1.d, #4
; SVE2-NEXT:    ret
    %a = xor <vscale x 2 x i64> %x, %y
    %b = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %a, <vscale x 2 x i64> splat (i64 60))
    ret <vscale x 2 x i64> %b
}

define <vscale x 2 x i64> @xar_nxv2i64_r(<vscale x 2 x i64> %x, <vscale x 2 x i64> %y) {
; SVE-LABEL: xar_nxv2i64_r:
; SVE:       // %bb.0:
; SVE-NEXT:    eor z0.d, z0.d, z1.d
; SVE-NEXT:    lsl z1.d, z0.d, #60
; SVE-NEXT:    lsr z0.d, z0.d, #4
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    ret
;
; SVE2-LABEL: xar_nxv2i64_r:
; SVE2:       // %bb.0:
; SVE2-NEXT:    xar z0.d, z0.d, z1.d, #4
; SVE2-NEXT:    ret
    %a = xor <vscale x 2 x i64> %x, %y
    %b = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %a, <vscale x 2 x i64> splat (i64 4))
    ret <vscale x 2 x i64> %b
}


define <vscale x 4 x i32> @xar_nxv4i32_l(<vscale x 4 x i32> %x, <vscale x 4 x i32> %y) {
; SVE-LABEL: xar_nxv4i32_l:
; SVE:       // %bb.0:
; SVE-NEXT:    eor z0.d, z0.d, z1.d
; SVE-NEXT:    lsr z1.s, z0.s, #4
; SVE-NEXT:    lsl z0.s, z0.s, #28
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    ret
;
; SVE2-LABEL: xar_nxv4i32_l:
; SVE2:       // %bb.0:
; SVE2-NEXT:    xar z0.s, z0.s, z1.s, #4
; SVE2-NEXT:    ret
    %a = xor <vscale x 4 x i32> %x, %y
    %b = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %a, <vscale x 4 x i32> splat (i32 28))
    ret <vscale x 4 x i32> %b
}

define <vscale x 4 x i32> @xar_nxv4i32_r(<vscale x 4 x i32> %x, <vscale x 4 x i32> %y) {
; SVE-LABEL: xar_nxv4i32_r:
; SVE:       // %bb.0:
; SVE-NEXT:    eor z0.d, z0.d, z1.d
; SVE-NEXT:    lsl z1.s, z0.s, #28
; SVE-NEXT:    lsr z0.s, z0.s, #4
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    ret
;
; SVE2-LABEL: xar_nxv4i32_r:
; SVE2:       // %bb.0:
; SVE2-NEXT:    xar z0.s, z0.s, z1.s, #4
; SVE2-NEXT:    ret
    %a = xor <vscale x 4 x i32> %x, %y
    %b = call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %a, <vscale x 4 x i32> splat (i32 4))
    ret <vscale x 4 x i32> %b
}

define <vscale x 8 x i16> @xar_nxv8i16_l(<vscale x 8 x i16> %x, <vscale x 8 x i16> %y) {
; SVE-LABEL: xar_nxv8i16_l:
; SVE:       // %bb.0:
; SVE-NEXT:    eor z0.d, z0.d, z1.d
; SVE-NEXT:    lsr z1.h, z0.h, #4
; SVE-NEXT:    lsl z0.h, z0.h, #12
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    ret
;
; SVE2-LABEL: xar_nxv8i16_l:
; SVE2:       // %bb.0:
; SVE2-NEXT:    xar z0.h, z0.h, z1.h, #4
; SVE2-NEXT:    ret
    %a = xor <vscale x 8 x i16> %x, %y
    %b = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %a, <vscale x 8 x i16> splat (i16 12))
    ret <vscale x 8 x i16> %b
}

define <vscale x 8 x i16> @xar_nxv8i16_r(<vscale x 8 x i16> %x, <vscale x 8 x i16> %y) {
; SVE-LABEL: xar_nxv8i16_r:
; SVE:       // %bb.0:
; SVE-NEXT:    eor z0.d, z0.d, z1.d
; SVE-NEXT:    lsl z1.h, z0.h, #12
; SVE-NEXT:    lsr z0.h, z0.h, #4
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    ret
;
; SVE2-LABEL: xar_nxv8i16_r:
; SVE2:       // %bb.0:
; SVE2-NEXT:    xar z0.h, z0.h, z1.h, #4
; SVE2-NEXT:    ret
    %a = xor <vscale x 8 x i16> %x, %y
    %b = call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %a, <vscale x 8 x i16> splat (i16 4))
    ret <vscale x 8 x i16> %b
}

define <vscale x 16 x i8> @xar_nxv16i8_l(<vscale x 16 x i8> %x, <vscale x 16 x i8> %y) {
; SVE-LABEL: xar_nxv16i8_l:
; SVE:       // %bb.0:
; SVE-NEXT:    eor z0.d, z0.d, z1.d
; SVE-NEXT:    lsr z1.b, z0.b, #4
; SVE-NEXT:    lsl z0.b, z0.b, #4
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    ret
;
; SVE2-LABEL: xar_nxv16i8_l:
; SVE2:       // %bb.0:
; SVE2-NEXT:    xar z0.b, z0.b, z1.b, #4
; SVE2-NEXT:    ret
    %a = xor <vscale x 16 x i8> %x, %y
    %b = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %a, <vscale x 16 x i8> splat (i8 4))
    ret <vscale x 16 x i8> %b
}

define <vscale x 16 x i8> @xar_nxv16i8_r(<vscale x 16 x i8> %x, <vscale x 16 x i8> %y) {
; SVE-LABEL: xar_nxv16i8_r:
; SVE:       // %bb.0:
; SVE-NEXT:    eor z0.d, z0.d, z1.d
; SVE-NEXT:    lsl z1.b, z0.b, #4
; SVE-NEXT:    lsr z0.b, z0.b, #4
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    ret
;
; SVE2-LABEL: xar_nxv16i8_r:
; SVE2:       // %bb.0:
; SVE2-NEXT:    xar z0.b, z0.b, z1.b, #4
; SVE2-NEXT:    ret
    %a = xor <vscale x 16 x i8> %x, %y
    %b = call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %a, <vscale x 16 x i8> splat (i8 4))
    ret <vscale x 16 x i8> %b
}

; Shift is not a constant.
define <vscale x 2 x i64> @xar_nxv2i64_l_neg1(<vscale x 2 x i64> %x, <vscale x 2 x i64> %y, <vscale x 2 x i64> %z) {
; CHECK-LABEL: xar_nxv2i64_l_neg1:
; CHECK:       // %bb.0:
; CHECK-NEXT:    movprfx z3, z2
; CHECK-NEXT:    subr z3.d, z3.d, #0 // =0x0
; CHECK-NEXT:    eor z0.d, z0.d, z1.d
; CHECK-NEXT:    and z2.d, z2.d, #0x3f
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    and z3.d, z3.d, #0x3f
; CHECK-NEXT:    lslr z2.d, p0/m, z2.d, z0.d
; CHECK-NEXT:    lsr z0.d, p0/m, z0.d, z3.d
; CHECK-NEXT:    orr z0.d, z2.d, z0.d
; CHECK-NEXT:    ret
    %a = xor <vscale x 2 x i64> %x, %y
    %b = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %a, <vscale x 2 x i64> %z)
    ret <vscale x 2 x i64> %b
}

; OR instead of an XOR.
; TODO: We could use usra instruction here for SVE2.
define <vscale x 2 x i64> @xar_nxv2i64_l_neg2_1(<vscale x 2 x i64> %x, <vscale x 2 x i64> %y) {
; SVE-LABEL: xar_nxv2i64_l_neg2_1:
; SVE:       // %bb.0:
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    lsr z1.d, z0.d, #4
; SVE-NEXT:    lsl z0.d, z0.d, #60
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    ret
;
; SVE2-LABEL: xar_nxv2i64_l_neg2_1:
; SVE2:       // %bb.0:
; SVE2-NEXT:    movi v2.2d, #0000000000000000
; SVE2-NEXT:    orr z0.d, z0.d, z1.d
; SVE2-NEXT:    xar z0.d, z0.d, z2.d, #4
; SVE2-NEXT:    ret
    %a = or <vscale x 2 x i64> %x, %y
    %b = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %a, <vscale x 2 x i64> splat (i64 60))
    ret <vscale x 2 x i64> %b
}

define <vscale x 4 x i32> @xar_nxv2i32_l_neg2_2(<vscale x 4 x i32> %x, <vscale x 4 x i32> %y) {
; SVE-LABEL: xar_nxv2i32_l_neg2_2:
; SVE:       // %bb.0:
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    lsr z1.s, z0.s, #4
; SVE-NEXT:    lsl z0.s, z0.s, #28
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    ret
;
; SVE2-LABEL: xar_nxv2i32_l_neg2_2:
; SVE2:       // %bb.0:
; SVE2-NEXT:    movi v2.2d, #0000000000000000
; SVE2-NEXT:    orr z0.d, z0.d, z1.d
; SVE2-NEXT:    xar z0.s, z0.s, z2.s, #4
; SVE2-NEXT:    ret
    %a = or <vscale x 4 x i32> %x, %y
    %b = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %a, <vscale x 4 x i32> splat (i32 60))
    ret <vscale x 4 x i32> %b
}

define <vscale x 8 x i16> @xar_nxv2i16_l_neg2_3(<vscale x 8 x i16> %x, <vscale x 8 x i16> %y) {
; SVE-LABEL: xar_nxv2i16_l_neg2_3:
; SVE:       // %bb.0:
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    lsr z1.h, z0.h, #4
; SVE-NEXT:    lsl z0.h, z0.h, #12
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    ret
;
; SVE2-LABEL: xar_nxv2i16_l_neg2_3:
; SVE2:       // %bb.0:
; SVE2-NEXT:    movi v2.2d, #0000000000000000
; SVE2-NEXT:    orr z0.d, z0.d, z1.d
; SVE2-NEXT:    xar z0.h, z0.h, z2.h, #4
; SVE2-NEXT:    ret
    %a = or <vscale x 8 x i16> %x, %y
    %b = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %a, <vscale x 8 x i16> splat (i16 60))
    ret <vscale x 8 x i16> %b
}

define <vscale x 16 x i8> @xar_nxv2i8_l_neg2_4(<vscale x 16 x i8> %x, <vscale x 16 x i8> %y) {
; SVE-LABEL: xar_nxv2i8_l_neg2_4:
; SVE:       // %bb.0:
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    lsr z1.b, z0.b, #4
; SVE-NEXT:    lsl z0.b, z0.b, #4
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    ret
;
; SVE2-LABEL: xar_nxv2i8_l_neg2_4:
; SVE2:       // %bb.0:
; SVE2-NEXT:    movi v2.2d, #0000000000000000
; SVE2-NEXT:    orr z0.d, z0.d, z1.d
; SVE2-NEXT:    xar z0.b, z0.b, z2.b, #4
; SVE2-NEXT:    ret
    %a = or <vscale x 16 x i8> %x, %y
    %b = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %a, <vscale x 16 x i8> splat (i8 60))
    ret <vscale x 16 x i8> %b
}

; Rotate amount is 0.
define <vscale x 2 x i64> @xar_nxv2i64_l_neg3(<vscale x 2 x i64> %x, <vscale x 2 x i64> %y) {
; CHECK-LABEL: xar_nxv2i64_l_neg3:
; CHECK:       // %bb.0:
; CHECK-NEXT:    eor z0.d, z0.d, z1.d
; CHECK-NEXT:    ret
    %a = xor <vscale x 2 x i64> %x, %y
    %b = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %a, <vscale x 2 x i64> splat (i64 64))
    ret <vscale x 2 x i64> %b
}

; Uses individual shifts instead of funnel shifts, just one test.
define <vscale x 2 x i64> @xar_nxv2i64_shifts(<vscale x 2 x i64> %x, <vscale x 2 x i64> %y) {
; SVE-LABEL: xar_nxv2i64_shifts:
; SVE:       // %bb.0:
; SVE-NEXT:    eor z0.d, z0.d, z1.d
; SVE-NEXT:    lsr z1.d, z0.d, #4
; SVE-NEXT:    lsl z0.d, z0.d, #60
; SVE-NEXT:    orr z0.d, z0.d, z1.d
; SVE-NEXT:    ret
;
; SVE2-LABEL: xar_nxv2i64_shifts:
; SVE2:       // %bb.0:
; SVE2-NEXT:    xar z0.d, z0.d, z1.d, #4
; SVE2-NEXT:    ret
    %xor = xor <vscale x 2 x i64> %x, %y
    %shl = shl <vscale x 2 x i64> %xor, splat (i64 60)
    %shr = lshr <vscale x 2 x i64> %xor, splat (i64 4)
    %or = or <vscale x 2 x i64> %shl, %shr
    ret <vscale x 2 x i64> %or
}

; Not a rotate operation as 60 + 3 != 64
define <vscale x 2 x i64> @xar_nxv2i64_shifts_neg(<vscale x 2 x i64> %x, <vscale x 2 x i64> %y) {
; CHECK-LABEL: xar_nxv2i64_shifts_neg:
; CHECK:       // %bb.0:
; CHECK-NEXT:    eor z0.d, z0.d, z1.d
; CHECK-NEXT:    lsl z1.d, z0.d, #60
; CHECK-NEXT:    lsr z0.d, z0.d, #3
; CHECK-NEXT:    orr z0.d, z1.d, z0.d
; CHECK-NEXT:    ret
    %xor = xor <vscale x 2 x i64> %x, %y
    %shl = shl <vscale x 2 x i64> %xor, splat (i64 60)
    %shr = lshr <vscale x 2 x i64> %xor, splat (i64 3)
    %or = or <vscale x 2 x i64> %shl, %shr
    ret <vscale x 2 x i64> %or
}

; Don't use XAR if REV[BHW] can be used.

define <vscale x 8 x i16> @revb_nxv8i16(<vscale x 8 x i16> %r) {
; CHECK-LABEL: revb_nxv8i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.h
; CHECK-NEXT:    revb z0.h, p0/m, z0.h
; CHECK-NEXT:    ret
  %or = tail call <vscale x 8 x i16> @llvm.fshl(<vscale x 8 x i16> %r, <vscale x 8 x i16> %r, <vscale x 8 x i16> splat (i16 8))
  ret <vscale x 8 x i16> %or
}

define <vscale x 4 x i32> @revh_nxv4i32(<vscale x 4 x i32> %r) {
; CHECK-LABEL: revh_nxv4i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    revh z0.s, p0/m, z0.s
; CHECK-NEXT:    ret
  %or = tail call <vscale x 4 x i32> @llvm.fshl(<vscale x 4 x i32> %r, <vscale x 4 x i32> %r, <vscale x 4 x i32> splat (i32 16))
  ret <vscale x 4 x i32> %or
}

define <vscale x 2 x i64> @revw_nx2i64(<vscale x 2 x i64> %r) {
; CHECK-LABEL: revw_nx2i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    revw z0.d, p0/m, z0.d
; CHECK-NEXT:    ret
  %or = tail call <vscale x 2 x i64> @llvm.fshl(<vscale x 2 x i64> %r, <vscale x 2 x i64> %r, <vscale x 2 x i64> splat (i64 32))
  ret <vscale x 2 x i64> %or
}

; As above, one test with rotate right.
define <vscale x 2 x i64> @revw_nx2i64_r(<vscale x 2 x i64> %a) {
; CHECK-LABEL: revw_nx2i64_r:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    revw z0.d, p0/m, z0.d
; CHECK-NEXT:    ret
  %r = tail call <vscale x 2 x i64> @llvm.fshr(<vscale x 2 x i64> %a, <vscale x 2 x i64> %a, <vscale x 2 x i64> splat (i64 32))
  ret <vscale x 2 x i64> %r
}

; As above, one test with predicated shifts instead of rotate left.
define <vscale x 4 x i32> @revh_nx4i32_shifts_l(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a) {
; CHECK-LABEL: revh_nx4i32_shifts_l:
; CHECK:       // %bb.0:
; CHECK-NEXT:    revh z0.s, p0/m, z0.s
; CHECK-NEXT:    ret
  %shl = tail call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.u(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> splat (i32 16))
  %shr = tail call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.u(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> splat (i32 16))
  %or = or <vscale x 4 x i32> %shl, %shr
  ret <vscale x 4 x i32> %or
}

; As above, one test with predicated shifts instead of rotate right.
define <vscale x 8 x i16> @revb_nx8i16_shifts_r(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a) {
; CHECK-LABEL: revb_nx8i16_shifts_r:
; CHECK:       // %bb.0:
; CHECK-NEXT:    revb z0.h, p0/m, z0.h
; CHECK-NEXT:    ret
  %shr = tail call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.u(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> splat (i16 8))
  %shl = tail call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.u(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> splat (i16 8))
  %or = or <vscale x 8 x i16> %shr, %shl
  ret <vscale x 8 x i16> %or
}

declare <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>)