; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -asm-verbose=1 < %s | FileCheck %s

;
; LD1SB/LD1B
;

define <vscale x 16 x i32> @ld1b_i8_sext_i32(ptr %base) {
; CHECK-LABEL: ld1b_i8_sext_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    ld1sb { z0.s }, p0/z, [x0]
; CHECK-NEXT:    ld1sb { z1.s }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ld1sb { z2.s }, p0/z, [x0, #2, mul vl]
; CHECK-NEXT:    ld1sb { z3.s }, p0/z, [x0, #3, mul vl]
; CHECK-NEXT:    ret
  %wide.load = load <vscale x 16 x i8>, ptr %base
  %res = sext <vscale x 16 x i8> %wide.load to <vscale x 16 x i32>
  ret <vscale x 16 x i32> %res
}

define <vscale x 16 x i32> @ld1b_i8_zext_i32(ptr %base) {
; CHECK-LABEL: ld1b_i8_zext_i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    ld1b { z0.s }, p0/z, [x0]
; CHECK-NEXT:    ld1b { z1.s }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ld1b { z2.s }, p0/z, [x0, #2, mul vl]
; CHECK-NEXT:    ld1b { z3.s }, p0/z, [x0, #3, mul vl]
; CHECK-NEXT:    ret
  %wide.load = load <vscale x 16 x i8>, ptr %base
  %res = zext <vscale x 16 x i8> %wide.load to <vscale x 16 x i32>
  ret <vscale x 16 x i32> %res
}

define <vscale x 16 x i64> @ld1b_i8_sext(ptr %base) {
; CHECK-LABEL: ld1b_i8_sext:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    ld1sb { z0.d }, p0/z, [x0]
; CHECK-NEXT:    ld1sb { z1.d }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ld1sb { z2.d }, p0/z, [x0, #2, mul vl]
; CHECK-NEXT:    ld1sb { z3.d }, p0/z, [x0, #3, mul vl]
; CHECK-NEXT:    ld1sb { z4.d }, p0/z, [x0, #4, mul vl]
; CHECK-NEXT:    ld1sb { z5.d }, p0/z, [x0, #5, mul vl]
; CHECK-NEXT:    ld1sb { z6.d }, p0/z, [x0, #6, mul vl]
; CHECK-NEXT:    ld1sb { z7.d }, p0/z, [x0, #7, mul vl]
; CHECK-NEXT:    ret
  %wide.load = load <vscale x 16 x i8>, ptr %base
  %res = sext <vscale x 16 x i8> %wide.load to <vscale x 16 x i64>
  ret <vscale x 16 x i64> %res
}

define <vscale x 16 x i64> @ld1b_i8_zext(ptr %base) {
; CHECK-LABEL: ld1b_i8_zext:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    ld1b { z0.d }, p0/z, [x0]
; CHECK-NEXT:    ld1b { z1.d }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ld1b { z2.d }, p0/z, [x0, #2, mul vl]
; CHECK-NEXT:    ld1b { z3.d }, p0/z, [x0, #3, mul vl]
; CHECK-NEXT:    ld1b { z4.d }, p0/z, [x0, #4, mul vl]
; CHECK-NEXT:    ld1b { z5.d }, p0/z, [x0, #5, mul vl]
; CHECK-NEXT:    ld1b { z6.d }, p0/z, [x0, #6, mul vl]
; CHECK-NEXT:    ld1b { z7.d }, p0/z, [x0, #7, mul vl]
; CHECK-NEXT:    ret
  %wide.load = load <vscale x 16 x i8>, ptr %base
  %res = zext <vscale x 16 x i8> %wide.load to <vscale x 16 x i64>
  ret <vscale x 16 x i64> %res
}

;
; LD1H
;

define <vscale x 8 x i64> @ld1h_i16_sext(ptr %base) {
; CHECK-LABEL: ld1h_i16_sext:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    ld1sh { z0.d }, p0/z, [x0]
; CHECK-NEXT:    ld1sh { z1.d }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ld1sh { z2.d }, p0/z, [x0, #2, mul vl]
; CHECK-NEXT:    ld1sh { z3.d }, p0/z, [x0, #3, mul vl]
; CHECK-NEXT:    ret
  %wide.load = load <vscale x 8 x i16>, ptr %base
  %res = sext <vscale x 8 x i16> %wide.load to <vscale x 8 x i64>
  ret <vscale x 8 x i64> %res
}

define <vscale x 8 x i64> @ld1h_i16_zext(ptr %base) {
; CHECK-LABEL: ld1h_i16_zext:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0]
; CHECK-NEXT:    ld1h { z1.d }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ld1h { z2.d }, p0/z, [x0, #2, mul vl]
; CHECK-NEXT:    ld1h { z3.d }, p0/z, [x0, #3, mul vl]
; CHECK-NEXT:    ret
  %wide.load = load <vscale x 8 x i16>, ptr %base
  %res = zext <vscale x 8 x i16> %wide.load to <vscale x 8 x i64>
  ret <vscale x 8 x i64> %res
}

;
; LD1W
;

define <vscale x 4 x i64> @ld1w_i32_sext(ptr %base) {
; CHECK-LABEL: ld1w_i32_sext:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    ld1sw { z0.d }, p0/z, [x0]
; CHECK-NEXT:    ld1sw { z1.d }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ret
  %wide.load = load <vscale x 4 x i32>, ptr %base
  %res = sext <vscale x 4 x i32> %wide.load to <vscale x 4 x i64>
  ret <vscale x 4 x i64> %res
}

define <vscale x 4 x i64> @ld1w_i32_zext(ptr %base) {
; CHECK-LABEL: ld1w_i32_zext:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0]
; CHECK-NEXT:    ld1w { z1.d }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ret
  %wide.load = load <vscale x 4 x i32>, ptr %base
  %res = zext <vscale x 4 x i32> %wide.load to <vscale x 4 x i64>
  ret <vscale x 4 x i64> %res
}


; Extending loads from unpacked to wide illegal types

define <vscale x 4 x i64> @zload_4i8_4i64(ptr %a) {
; CHECK-LABEL: zload_4i8_4i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    ld1b { z0.d }, p0/z, [x0]
; CHECK-NEXT:    ld1b { z1.d }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ret
  %aval = load <vscale x 4 x i8>, ptr %a
  %aext = zext <vscale x 4 x i8> %aval to <vscale x 4 x i64>
  ret <vscale x 4 x i64> %aext
}

define <vscale x 4 x i64> @zload_4i16_4i64(ptr %a) {
; CHECK-LABEL: zload_4i16_4i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0]
; CHECK-NEXT:    ld1h { z1.d }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ret
  %aval = load <vscale x 4 x i16>, ptr %a
  %aext = zext <vscale x 4 x i16> %aval to <vscale x 4 x i64>
  ret <vscale x 4 x i64> %aext
}

define <vscale x 8 x i32> @zload_8i8_8i32(ptr %a) {
; CHECK-LABEL: zload_8i8_8i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    ld1b { z0.s }, p0/z, [x0]
; CHECK-NEXT:    ld1b { z1.s }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ret
  %aval = load <vscale x 8 x i8>, ptr %a
  %aext = zext <vscale x 8 x i8> %aval to <vscale x 8 x i32>
  ret <vscale x 8 x i32> %aext
}

define <vscale x 8 x i64> @zload_8i8_8i64(ptr %a) {
; CHECK-LABEL: zload_8i8_8i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    ld1b { z0.d }, p0/z, [x0]
; CHECK-NEXT:    ld1b { z1.d }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ld1b { z2.d }, p0/z, [x0, #2, mul vl]
; CHECK-NEXT:    ld1b { z3.d }, p0/z, [x0, #3, mul vl]
; CHECK-NEXT:    ret
  %aval = load <vscale x 8 x i8>, ptr %a
  %aext = zext <vscale x 8 x i8> %aval to <vscale x 8 x i64>
  ret <vscale x 8 x i64> %aext
}

define <vscale x 4 x i64> @sload_4i8_4i64(ptr %a) {
; CHECK-LABEL: sload_4i8_4i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    ld1sb { z0.d }, p0/z, [x0]
; CHECK-NEXT:    ld1sb { z1.d }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ret
  %aval = load <vscale x 4 x i8>, ptr %a
  %aext = sext <vscale x 4 x i8> %aval to <vscale x 4 x i64>
  ret <vscale x 4 x i64> %aext
}

define <vscale x 4 x i64> @sload_4i16_4i64(ptr %a) {
; CHECK-LABEL: sload_4i16_4i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    ld1sh { z0.d }, p0/z, [x0]
; CHECK-NEXT:    ld1sh { z1.d }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ret
  %aval = load <vscale x 4 x i16>, ptr %a
  %aext = sext <vscale x 4 x i16> %aval to <vscale x 4 x i64>
  ret <vscale x 4 x i64> %aext
}

define <vscale x 8 x i32> @sload_8i8_8i32(ptr %a) {
; CHECK-LABEL: sload_8i8_8i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    ld1sb { z0.s }, p0/z, [x0]
; CHECK-NEXT:    ld1sb { z1.s }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ret
  %aval = load <vscale x 8 x i8>, ptr %a
  %aext = sext <vscale x 8 x i8> %aval to <vscale x 8 x i32>
  ret <vscale x 8 x i32> %aext
}

define <vscale x 8 x i64> @sload_8i8_8i64(ptr %a) {
; CHECK-LABEL: sload_8i8_8i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    ld1sb { z0.d }, p0/z, [x0]
; CHECK-NEXT:    ld1sb { z1.d }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT:    ld1sb { z2.d }, p0/z, [x0, #2, mul vl]
; CHECK-NEXT:    ld1sb { z3.d }, p0/z, [x0, #3, mul vl]
; CHECK-NEXT:    ret
  %aval = load <vscale x 8 x i8>, ptr %a
  %aext = sext <vscale x 8 x i8> %aval to <vscale x 8 x i64>
  ret <vscale x 8 x i64> %aext
}

; Ensure we don't try to promote a predicate load to a sign-extended load.
define <vscale x 16 x i8> @sload_16i1_16i8(ptr %addr) {
; CHECK-LABEL: sload_16i1_16i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr p0, [x0]
; CHECK-NEXT:    mov z0.b, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT:    ret
  %load = load <vscale x 16 x i1>, ptr %addr
  %zext = sext <vscale x 16 x i1> %load to <vscale x 16 x i8>
  ret <vscale x 16 x i8> %zext
}

; Ensure we don't try to promote a predicate load to a zero-extended load.
define <vscale x 16 x i8> @zload_16i1_16i8(ptr %addr) {
; CHECK-LABEL: zload_16i1_16i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr p0, [x0]
; CHECK-NEXT:    mov z0.b, p0/z, #1 // =0x1
; CHECK-NEXT:    ret
  %load = load <vscale x 16 x i1>, ptr %addr
  %zext = zext <vscale x 16 x i1> %load to <vscale x 16 x i8>
  ret <vscale x 16 x i8> %zext
}