; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple aarch64-none-linux-gnu < %s | FileCheck %s

declare <4 x i16>  @llvm.aarch64.neon.uaddlp.v4i16.v8i8(<8 x i8>) nounwind readnone
declare <8 x i16>  @llvm.aarch64.neon.uaddlp.v8i16.v16i8(<16 x i8>) nounwind readnone
declare <4 x i32>  @llvm.aarch64.neon.uaddlp.v4i32.v8i16(<8 x i16>) nounwind readnone
declare <2 x i64>  @llvm.aarch64.neon.uaddlp.v2i64.v4i32(<4 x i32>) nounwind readnone
declare <2 x i32>  @llvm.aarch64.neon.uaddlp.v2i32.v4i16(<4 x i16>) nounwind readnone

declare i16 @llvm.vector.reduce.add.v4i16(<4 x i16>) nounwind readnone
declare i16 @llvm.vector.reduce.add.v8i16(<8 x i16>) nounwind readnone
declare i32 @llvm.vector.reduce.add.v4i32(<4 x i32>) nounwind readnone
declare i64 @llvm.vector.reduce.add.v2i64(<2 x i64>) nounwind readnone
declare i32 @llvm.vector.reduce.add.v2i32(<2 x i32>) nounwind readnone

define i16 @uaddlv4h_from_v8i8(<8 x i8>* %A) nounwind {
; CHECK-LABEL: uaddlv4h_from_v8i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr d0, [x0]
; CHECK-NEXT:    uaddlv h0, v0.8b
; CHECK-NEXT:    fmov w0, s0
; CHECK-NEXT:    ret
  %tmp1 = load <8 x i8>, <8 x i8>* %A
  %tmp3 = call <4 x i16> @llvm.aarch64.neon.uaddlp.v4i16.v8i8(<8 x i8> %tmp1)
  %tmp5 = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> %tmp3)
  ret i16 %tmp5
}

define i16 @uaddlv16b_from_v16i8(<16 x i8>* %A) nounwind {
; CHECK-LABEL: uaddlv16b_from_v16i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr q0, [x0]
; CHECK-NEXT:    uaddlv h0, v0.16b
; CHECK-NEXT:    fmov w0, s0
; CHECK-NEXT:    ret
  %tmp1 = load <16 x i8>, <16 x i8>* %A
  %tmp3 = call <8 x i16> @llvm.aarch64.neon.uaddlp.v8i16.v16i8(<16 x i8> %tmp1)
  %tmp5 = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> %tmp3)
  ret i16 %tmp5
}

define i32 @uaddlv8h_from_v8i16(<8 x i16>* %A) nounwind {
; CHECK-LABEL: uaddlv8h_from_v8i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr q0, [x0]
; CHECK-NEXT:    uaddlv s0, v0.8h
; CHECK-NEXT:    fmov w0, s0
; CHECK-NEXT:    ret
  %tmp1 = load <8 x i16>, <8 x i16>* %A
  %tmp3 = call <4 x i32> @llvm.aarch64.neon.uaddlp.v4i32.v8i16(<8 x i16> %tmp1)
  %tmp5 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %tmp3)
  ret i32 %tmp5
}

define i64 @uaddlv4s_from_v4i32(<4 x i32>* %A) nounwind {
; CHECK-LABEL: uaddlv4s_from_v4i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr q0, [x0]
; CHECK-NEXT:    uaddlv d0, v0.4s
; CHECK-NEXT:    fmov x0, d0
; CHECK-NEXT:    ret
  %tmp1 = load <4 x i32>, <4 x i32>* %A
  %tmp3 = call <2 x i64> @llvm.aarch64.neon.uaddlp.v2i64.v4i32(<4 x i32> %tmp1)
  %tmp5 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %tmp3)
  ret i64 %tmp5
}

define i32 @uaddlv4h_from_v4i16(<4 x i16>* %A) nounwind {
; CHECK-LABEL: uaddlv4h_from_v4i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr d0, [x0]
; CHECK-NEXT:    uaddlv s0, v0.4h
; CHECK-NEXT:    fmov w0, s0
; CHECK-NEXT:    ret
  %tmp1 = load <4 x i16>, <4 x i16>* %A
  %tmp3 = call <2 x i32> @llvm.aarch64.neon.uaddlp.v2i32.v4i16(<4 x i16> %tmp1)
  %tmp5 = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %tmp3)
  ret i32 %tmp5
}