; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
; RUN:   -mcpu=pwr8 -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr < %s | FileCheck %s
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-aix-xcoff \
; RUN:   -mcpu=pwr8 -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr < %s | FileCheck %s
; RUN: llc -verify-machineinstrs -mtriple=powerpc-aix-xcoff \
; RUN:   -mcpu=pwr8 -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr < %s | FileCheck %s

define void @test1(<16 x i8> %0) {
; CHECK-LABEL: test1:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    blr
entry:
  %1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4sbs(<16 x i8> %0, <4 x i32> zeroinitializer)
  ret void
}

define void @test2(<8 x i16> %0) {
; CHECK-LABEL: test2:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    blr
entry:
  %1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4shs(<8 x i16> %0, <4 x i32> zeroinitializer)
  ret void
}

define void @test3(<16 x i8> %0) {
; CHECK-LABEL: test3:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    blr
entry:
  %1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4ubs(<16 x i8> %0, <4 x i32> zeroinitializer)
  ret void
}

define void @test4(<16 x i8> %0) {
; CHECK-LABEL: test4:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vspltisw v3, 1
; CHECK-NEXT:    vsum4sbs v2, v2, v3
; CHECK-NEXT:    blr
entry:
  %1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4sbs(<16 x i8> %0, <4 x i32> <i32 1, i32 1, i32 1, i32 1>)
  ret void
}

define void @test5(<8 x i16> %0) {
; CHECK-LABEL: test5:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vspltisw v3, 1
; CHECK-NEXT:    vsum4shs v2, v2, v3
; CHECK-NEXT:    blr
entry:
  %1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4shs(<8 x i16> %0, <4 x i32> <i32 1, i32 1, i32 1, i32 1>)
  ret void
}

define void @test6(<16 x i8> %0) {
; CHECK-LABEL: test6:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vspltisw v3, 1
; CHECK-NEXT:    vsum4ubs v2, v2, v3
; CHECK-NEXT:    blr
entry:
  %1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4ubs(<16 x i8> %0, <4 x i32> <i32 1, i32 1, i32 1, i32 1>)
  ret void
}

define <4 x i32> @test7(<16 x i8> %0) {
; CHECK-LABEL: test7:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    xxlxor v3, v3, v3
; CHECK-NEXT:    vsum4sbs v2, v2, v3
; CHECK-NEXT:    blr
entry:
  %1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4sbs(<16 x i8> %0, <4 x i32> zeroinitializer)
  ret <4 x i32> %1
}

define <4 x i32> @test8(<8 x i16> %0) {
; CHECK-LABEL: test8:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    xxlxor v3, v3, v3
; CHECK-NEXT:    vsum4shs v2, v2, v3
; CHECK-NEXT:    blr
entry:
  %1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4shs(<8 x i16> %0, <4 x i32> zeroinitializer)
  ret <4 x i32> %1
}

define <4 x i32> @test9(<16 x i8> %0) {
; CHECK-LABEL: test9:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    xxlxor v3, v3, v3
; CHECK-NEXT:    vsum4ubs v2, v2, v3
; CHECK-NEXT:    blr
entry:
  %1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4ubs(<16 x i8> %0, <4 x i32> zeroinitializer)
  ret <4 x i32> %1
}

define <4 x i32> @test10(<16 x i8> %0, <16 x i8> %1) {
; CHECK-LABEL: test10:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    xxlxor v3, v3, v3
; CHECK-NEXT:    vsum4sbs v2, v2, v3
; CHECK-NEXT:    blr
entry:
  %2 = tail call <4 x i32> @llvm.ppc.altivec.vsum4sbs(<16 x i8> %0, <4 x i32> zeroinitializer)
  %3 = tail call <4 x i32> @llvm.ppc.altivec.vsum4sbs(<16 x i8> %1, <4 x i32> zeroinitializer)
  ret <4 x i32> %2
}

define <4 x i32> @test11(<8 x i16> %0, <8 x i16> %1) {
; CHECK-LABEL: test11:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    xxlxor v3, v3, v3
; CHECK-NEXT:    vsum4shs v2, v2, v3
; CHECK-NEXT:    blr
entry:
  %2 = tail call <4 x i32> @llvm.ppc.altivec.vsum4shs(<8 x i16> %0, <4 x i32> zeroinitializer)
  %3 = tail call <4 x i32> @llvm.ppc.altivec.vsum4shs(<8 x i16> %1, <4 x i32> zeroinitializer)
  ret <4 x i32> %2
}

define <4 x i32> @test12(<16 x i8> %0, <16 x i8> %1) {
; CHECK-LABEL: test12:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    xxlxor v3, v3, v3
; CHECK-NEXT:    vsum4ubs v2, v2, v3
; CHECK-NEXT:    blr
entry:
  %2 = tail call <4 x i32> @llvm.ppc.altivec.vsum4ubs(<16 x i8> %0, <4 x i32> zeroinitializer)
  %3 = tail call <4 x i32> @llvm.ppc.altivec.vsum4ubs(<16 x i8> %1, <4 x i32> zeroinitializer)
  ret <4 x i32> %2
}

declare <4 x i32> @llvm.ppc.altivec.vsum4sbs(<16 x i8>, <4 x i32>)
declare <4 x i32> @llvm.ppc.altivec.vsum4shs(<8 x i16>, <4 x i32>)
declare <4 x i32> @llvm.ppc.altivec.vsum4ubs(<16 x i8>, <4 x i32>)