; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+xop | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+xop | FileCheck %s

declare <2 x double> @llvm.x86.xop.vpermil2pd(<2 x double>, <2 x double>, <2 x double>, i8) nounwind readnone
declare <4 x double> @llvm.x86.xop.vpermil2pd.256(<4 x double>, <4 x double>, <4 x double>, i8) nounwind readnone

declare <4 x float> @llvm.x86.xop.vpermil2ps(<4 x float>, <4 x float>, <4 x float>, i8) nounwind readnone
declare <8 x float> @llvm.x86.xop.vpermil2ps.256(<8 x float>, <8 x float>, <8 x float>, i8) nounwind readnone

declare <16 x i8> @llvm.x86.xop.vpperm(<16 x i8>, <16 x i8>, <16 x i8>) nounwind readnone

define <16 x i8> @combine_vpperm_identity(<16 x i8> %a0, <16 x i8> %a1) {
; CHECK-LABEL: combine_vpperm_identity:
; CHECK:       # BB#0:
; CHECK-NEXT:    vpperm {{.*}}(%rip), %xmm1, %xmm0, %xmm0
; CHECK-NEXT:    vpperm {{.*}}(%rip), %xmm0, %xmm0, %xmm0
; CHECK-NEXT:    retq
  %res0 = call <16 x i8> @llvm.x86.xop.vpperm(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> <i8 31, i8 30, i8 29, i8 28, i8 27, i8 26, i8 25, i8 24, i8 23, i8 22, i8 21, i8 20, i8 19, i8 18, i8 17, i8 16>)
  %res1 = call <16 x i8> @llvm.x86.xop.vpperm(<16 x i8> %res0, <16 x i8> undef, <16 x i8> <i8 15, i8 14, i8 13, i8 12, i8 11, i8 10, i8 9, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
  ret <16 x i8> %res1
}

define <16 x i8> @combine_vpperm_as_unary_unpckhwd(<16 x i8> %a0, <16 x i8> %a1) {
; CHECK-LABEL: combine_vpperm_as_unary_unpckhwd:
; CHECK:       # BB#0:
; CHECK-NEXT:    vpperm {{.*}}(%rip), %xmm0, %xmm0, %xmm0
; CHECK-NEXT:    retq
  %res0 = call <16 x i8> @llvm.x86.xop.vpperm(<16 x i8> %a0, <16 x i8> %a0, <16 x i8> <i8 8, i8 24, i8 9, i8 25, i8 10, i8 26, i8 11, i8 27, i8 12, i8 28, i8 13, i8 29, i8 14, i8 30, i8 15, i8 31>)
  ret <16 x i8> %res0
}

define <16 x i8> @combine_vpperm_as_unpckhwd(<16 x i8> %a0, <16 x i8> %a1) {
; CHECK-LABEL: combine_vpperm_as_unpckhwd:
; CHECK:       # BB#0:
; CHECK-NEXT:    vpperm {{.*}}(%rip), %xmm1, %xmm0, %xmm0
; CHECK-NEXT:    retq
  %res0 = call <16 x i8> @llvm.x86.xop.vpperm(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> <i8 8, i8 24, i8 9, i8 25, i8 10, i8 26, i8 11, i8 27, i8 12, i8 28, i8 13, i8 29, i8 14, i8 30, i8 15, i8 31>)
  ret <16 x i8> %res0
}