; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -aarch64-sve-vector-bits-min=256  < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_256
; RUN: llc -aarch64-sve-vector-bits-min=512  < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512
; RUN: llc -aarch64-sve-vector-bits-min=2048 < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512

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

; Don't use SVE for 128-bit vectors.
define void @sabd_v16i8_v16i16(ptr %a, ptr %b) #0 {
; CHECK-LABEL: sabd_v16i8_v16i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr q0, [x0]
; CHECK-NEXT:    ldr q1, [x1]
; CHECK-NEXT:    sabd v0.16b, v0.16b, v1.16b
; CHECK-NEXT:    str q0, [x0]
; CHECK-NEXT:    ret
  %a.ld = load <16 x i8>, ptr %a
  %b.ld = load <16 x i8>, ptr %b
  %a.sext = sext <16 x i8> %a.ld to <16 x i16>
  %b.sext = sext <16 x i8> %b.ld to <16 x i16>
  %sub = sub <16 x i16> %a.sext, %b.sext
  %abs = call <16 x i16> @llvm.abs.v16i16(<16 x i16> %sub, i1 true)
  %trunc = trunc <16 x i16> %abs to <16 x i8>
  store <16 x i8> %trunc, ptr %a
  ret void
}

; Don't use SVE for 128-bit vectors.
define void @sabd_v16i8_v16i32(ptr %a, ptr %b) #0 {
; CHECK-LABEL: sabd_v16i8_v16i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr q0, [x0]
; CHECK-NEXT:    ldr q1, [x1]
; CHECK-NEXT:    sabd v0.16b, v0.16b, v1.16b
; CHECK-NEXT:    str q0, [x0]
; CHECK-NEXT:    ret
  %a.ld = load <16 x i8>, ptr %a
  %b.ld = load <16 x i8>, ptr %b
  %a.sext = sext <16 x i8> %a.ld to <16 x i32>
  %b.sext = sext <16 x i8> %b.ld to <16 x i32>
  %sub = sub <16 x i32> %a.sext, %b.sext
  %abs = call <16 x i32> @llvm.abs.v16i32(<16 x i32> %sub, i1 true)
  %trunc = trunc <16 x i32> %abs to <16 x i8>
  store <16 x i8> %trunc, ptr %a
  ret void
}

; Don't use SVE for 128-bit vectors.
define void @sabd_v16i8_v16i64(ptr %a, ptr %b) #0 {
; CHECK-LABEL: sabd_v16i8_v16i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr q0, [x0]
; CHECK-NEXT:    ldr q1, [x1]
; CHECK-NEXT:    sabd v0.16b, v0.16b, v1.16b
; CHECK-NEXT:    str q0, [x0]
; CHECK-NEXT:    ret
  %a.ld = load <16 x i8>, ptr %a
  %b.ld = load <16 x i8>, ptr %b
  %a.sext = sext <16 x i8> %a.ld to <16 x i64>
  %b.sext = sext <16 x i8> %b.ld to <16 x i64>
  %sub = sub <16 x i64> %a.sext, %b.sext
  %abs = call <16 x i64> @llvm.abs.v16i64(<16 x i64> %sub, i1 true)
  %trunc = trunc <16 x i64> %abs to <16 x i8>
  store <16 x i8> %trunc, ptr %a
  ret void
}

define void @sabd_v32i8_v32i16(ptr %a, ptr %b) #0 {
; CHECK-LABEL: sabd_v32i8_v32i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.b, vl32
; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x0]
; CHECK-NEXT:    ld1b { z1.b }, p0/z, [x1]
; CHECK-NEXT:    sabd z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT:    st1b { z0.b }, p0, [x0]
; CHECK-NEXT:    ret
  %a.ld = load <32 x i8>, ptr %a
  %b.ld = load <32 x i8>, ptr %b
  %a.sext = sext <32 x i8> %a.ld to <32 x i16>
  %b.sext = sext <32 x i8> %b.ld to <32 x i16>
  %sub = sub <32 x i16> %a.sext, %b.sext
  %abs = call <32 x i16> @llvm.abs.v32i16(<32 x i16> %sub, i1 true)
  %trunc = trunc <32 x i16> %abs to <32 x i8>
  store <32 x i8> %trunc, ptr %a
  ret void
}

define void @uabd_v32i8_v32i16(ptr %a, ptr %b) #0 {
; CHECK-LABEL: uabd_v32i8_v32i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.b, vl32
; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x0]
; CHECK-NEXT:    ld1b { z1.b }, p0/z, [x1]
; CHECK-NEXT:    uabd z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT:    st1b { z0.b }, p0, [x0]
; CHECK-NEXT:    ret
  %a.ld = load <32 x i8>, ptr %a
  %b.ld = load <32 x i8>, ptr %b
  %a.zext = zext <32 x i8> %a.ld to <32 x i16>
  %b.zext = zext <32 x i8> %b.ld to <32 x i16>
  %sub = sub <32 x i16> %a.zext, %b.zext
  %abs = call <32 x i16> @llvm.abs.v32i16(<32 x i16> %sub, i1 true)
  %trunc = trunc <32 x i16> %abs to <32 x i8>
  store <32 x i8> %trunc, ptr %a
  ret void
}

define void @sabd_v32i8_v32i32(ptr %a, ptr %b) #0 {
; CHECK-LABEL: sabd_v32i8_v32i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.b, vl32
; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x0]
; CHECK-NEXT:    ld1b { z1.b }, p0/z, [x1]
; CHECK-NEXT:    sabd z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT:    st1b { z0.b }, p0, [x0]
; CHECK-NEXT:    ret
  %a.ld = load <32 x i8>, ptr %a
  %b.ld = load <32 x i8>, ptr %b
  %a.sext = sext <32 x i8> %a.ld to <32 x i32>
  %b.sext = sext <32 x i8> %b.ld to <32 x i32>
  %sub = sub <32 x i32> %a.sext, %b.sext
  %abs = call <32 x i32> @llvm.abs.v32i32(<32 x i32> %sub, i1 true)
  %trunc = trunc <32 x i32> %abs to <32 x i8>
  store <32 x i8> %trunc, ptr %a
  ret void
}

define void @sabd_v32i8_v32i64(ptr %a, ptr %b) #0 {
; CHECK-LABEL: sabd_v32i8_v32i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ptrue p0.b, vl32
; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x0]
; CHECK-NEXT:    ld1b { z1.b }, p0/z, [x1]
; CHECK-NEXT:    sabd z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT:    st1b { z0.b }, p0, [x0]
; CHECK-NEXT:    ret
  %a.ld = load <32 x i8>, ptr %a
  %b.ld = load <32 x i8>, ptr %b
  %a.sext = sext <32 x i8> %a.ld to <32 x i64>
  %b.sext = sext <32 x i8> %b.ld to <32 x i64>
  %sub = sub <32 x i64> %a.sext, %b.sext
  %abs = call <32 x i64> @llvm.abs.v32i64(<32 x i64> %sub, i1 true)
  %trunc = trunc <32 x i64> %abs to <32 x i8>
  store <32 x i8> %trunc, ptr %a
  ret void
}

define void @sabd_v64i8_v64i64(ptr %a, ptr %b) #0 {
; VBITS_GE_256-LABEL: sabd_v64i8_v64i64:
; VBITS_GE_256:       // %bb.0:
; VBITS_GE_256-NEXT:    ptrue p0.b, vl32
; VBITS_GE_256-NEXT:    mov w8, #32 // =0x20
; VBITS_GE_256-NEXT:    ld1b { z0.b }, p0/z, [x0, x8]
; VBITS_GE_256-NEXT:    ld1b { z1.b }, p0/z, [x1, x8]
; VBITS_GE_256-NEXT:    ld1b { z2.b }, p0/z, [x0]
; VBITS_GE_256-NEXT:    ld1b { z3.b }, p0/z, [x1]
; VBITS_GE_256-NEXT:    sabd z0.b, p0/m, z0.b, z1.b
; VBITS_GE_256-NEXT:    movprfx z1, z2
; VBITS_GE_256-NEXT:    sabd z1.b, p0/m, z1.b, z3.b
; VBITS_GE_256-NEXT:    st1b { z0.b }, p0, [x0, x8]
; VBITS_GE_256-NEXT:    st1b { z1.b }, p0, [x0]
; VBITS_GE_256-NEXT:    ret
;
; VBITS_GE_512-LABEL: sabd_v64i8_v64i64:
; VBITS_GE_512:       // %bb.0:
; VBITS_GE_512-NEXT:    ptrue p0.b, vl64
; VBITS_GE_512-NEXT:    ld1b { z0.b }, p0/z, [x0]
; VBITS_GE_512-NEXT:    ld1b { z1.b }, p0/z, [x1]
; VBITS_GE_512-NEXT:    sabd z0.b, p0/m, z0.b, z1.b
; VBITS_GE_512-NEXT:    st1b { z0.b }, p0, [x0]
; VBITS_GE_512-NEXT:    ret
  %a.ld = load <64 x i8>, ptr %a
  %b.ld = load <64 x i8>, ptr %b
  %a.sext = sext <64 x i8> %a.ld to <64 x i64>
  %b.sext = sext <64 x i8> %b.ld to <64 x i64>
  %sub = sub <64 x i64> %a.sext, %b.sext
  %abs = call <64 x i64> @llvm.abs.v64i64(<64 x i64> %sub, i1 true)
  %trunc = trunc <64 x i64> %abs to <64 x i8>
  store <64 x i8> %trunc, ptr %a
  ret void
}

attributes #0 = { "target-features"="+neon,+sve" }