; RUN: llc < %s -mtriple=x86_64-apple-darwin -march=x86 -mcpu=corei7-avx | FileCheck %s

define <4 x double> @test_x86_avx_blend_pd_256(<4 x double> %a0, <4 x double> %a1) {
  ; CHECK: vblendpd
  %res = call <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double> %a0, <4 x double> %a1, i32 7) ; <<4 x double>> [#uses=1]
  ret <4 x double> %res
}
declare <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double>, <4 x double>, i32) nounwind readnone


define <8 x float> @test_x86_avx_blend_ps_256(<8 x float> %a0, <8 x float> %a1) {
  ; CHECK: vblendps
  %res = call <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float> %a0, <8 x float> %a1, i32 7) ; <<8 x float>> [#uses=1]
  ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone


define <8 x float> @test_x86_avx_dp_ps_256(<8 x float> %a0, <8 x float> %a1) {
  ; CHECK: vdpps
  %res = call <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float> %a0, <8 x float> %a1, i32 7) ; <<8 x float>> [#uses=1]
  ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone


define <2 x i64> @test_x86_sse2_psll_dq(<2 x i64> %a0) {
  ; CHECK: vpslldq {{.*#+}} xmm0 = zero,xmm0[0,1,2,3,4,5,6,7,8,9,10,11,12,13,14]
  %res = call <2 x i64> @llvm.x86.sse2.psll.dq(<2 x i64> %a0, i32 8) ; <<2 x i64>> [#uses=1]
  ret <2 x i64> %res
}
declare <2 x i64> @llvm.x86.sse2.psll.dq(<2 x i64>, i32) nounwind readnone


define <2 x i64> @test_x86_sse2_psrl_dq(<2 x i64> %a0) {
  ; CHECK: vpsrldq {{.*#+}} xmm0 = xmm0[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15],zero
  %res = call <2 x i64> @llvm.x86.sse2.psrl.dq(<2 x i64> %a0, i32 8) ; <<2 x i64>> [#uses=1]
  ret <2 x i64> %res
}
declare <2 x i64> @llvm.x86.sse2.psrl.dq(<2 x i64>, i32) nounwind readnone


define <2 x double> @test_x86_sse41_blendpd(<2 x double> %a0, <2 x double> %a1) {
  ; CHECK: vblendpd
  %res = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %a0, <2 x double> %a1, i8 2) ; <<2 x double>> [#uses=1]
  ret <2 x double> %res
}
declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i8) nounwind readnone


define <4 x float> @test_x86_sse41_blendps(<4 x float> %a0, <4 x float> %a1) {
  ; CHECK: vblendps
  %res = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
  ret <4 x float> %res
}
declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i8) nounwind readnone


define <8 x i16> @test_x86_sse41_pblendw(<8 x i16> %a0, <8 x i16> %a1) {
  ; CHECK: vpblendw
  %res = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %a0, <8 x i16> %a1, i8 7) ; <<8 x i16>> [#uses=1]
  ret <8 x i16> %res
}
declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i8) nounwind readnone