test/CodeGen/X86/avx-intrinsics-x86.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+pclmul,+avx -show-mc-encoding | FileCheck %s --check-prefixes=CHECK,X86,AVX,X86-AVX
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+pclmul,+avx512f,+avx512bw,+avx512dq,+avx512vl -show-mc-encoding | FileCheck %s --check-prefixes=CHECK,X86,AVX512VL,X86-AVX512VL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+pclmul,+avx -show-mc-encoding | FileCheck %s --check-prefixes=CHECK,X64,AVX,X64-AVX
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+pclmul,+avx512f,+avx512bw,+avx512dq,+avx512vl -show-mc-encoding | FileCheck %s --check-prefixes=CHECK,X64,AVX512VL,X64-AVX512VL

define <4 x double> @test_x86_avx_addsub_pd_256(<4 x double> %a0, <4 x double> %a1) {
; CHECK-LABEL: test_x86_avx_addsub_pd_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vaddsubpd %ymm1, %ymm0, %ymm0 # encoding: [0xc5,0xfd,0xd0,0xc1]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <4 x double> @llvm.x86.avx.addsub.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
  ret <4 x double> %res
}
declare <4 x double> @llvm.x86.avx.addsub.pd.256(<4 x double>, <4 x double>) nounwind readnone


define <8 x float> @test_x86_avx_addsub_ps_256(<8 x float> %a0, <8 x float> %a1) {
; CHECK-LABEL: test_x86_avx_addsub_ps_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vaddsubps %ymm1, %ymm0, %ymm0 # encoding: [0xc5,0xff,0xd0,0xc1]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <8 x float> @llvm.x86.avx.addsub.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
  ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.addsub.ps.256(<8 x float>, <8 x float>) nounwind readnone


define <4 x double> @test_x86_avx_blendv_pd_256(<4 x double> %a0, <4 x double> %a1, <4 x double> %a2) {
; CHECK-LABEL: test_x86_avx_blendv_pd_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vblendvpd %ymm2, %ymm1, %ymm0, %ymm0 # encoding: [0xc4,0xe3,0x7d,0x4b,0xc1,0x20]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <4 x double> @llvm.x86.avx.blendv.pd.256(<4 x double> %a0, <4 x double> %a1, <4 x double> %a2) ; <<4 x double>> [#uses=1]
  ret <4 x double> %res
}
declare <4 x double> @llvm.x86.avx.blendv.pd.256(<4 x double>, <4 x double>, <4 x double>) nounwind readnone


define <8 x float> @test_x86_avx_blendv_ps_256(<8 x float> %a0, <8 x float> %a1, <8 x float> %a2) {
; CHECK-LABEL: test_x86_avx_blendv_ps_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vblendvps %ymm2, %ymm1, %ymm0, %ymm0 # encoding: [0xc4,0xe3,0x7d,0x4a,0xc1,0x20]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <8 x float> @llvm.x86.avx.blendv.ps.256(<8 x float> %a0, <8 x float> %a1, <8 x float> %a2) ; <<8 x float>> [#uses=1]
  ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.blendv.ps.256(<8 x float>, <8 x float>, <8 x float>) nounwind readnone


define <4 x double> @test_x86_avx_cmp_pd_256(<4 x double> %a0, <4 x double> %a1) {
; CHECK-LABEL: test_x86_avx_cmp_pd_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vcmpordpd %ymm1, %ymm0, %ymm0 # encoding: [0xc5,0xfd,0xc2,0xc1,0x07]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <4 x double> @llvm.x86.avx.cmp.pd.256(<4 x double> %a0, <4 x double> %a1, i8 7) ; <<4 x double>> [#uses=1]
  ret <4 x double> %res
}
declare <4 x double> @llvm.x86.avx.cmp.pd.256(<4 x double>, <4 x double>, i8) nounwind readnone


define <8 x float> @test_x86_avx_cmp_ps_256(<8 x float> %a0, <8 x float> %a1) {
; CHECK-LABEL: test_x86_avx_cmp_ps_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vcmpordps %ymm1, %ymm0, %ymm0 # encoding: [0xc5,0xfc,0xc2,0xc1,0x07]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a1, i8 7) ; <<8 x float>> [#uses=1]
  ret <8 x float> %res
}

define <8 x float> @test_x86_avx_cmp_ps_256_pseudo_op(<8 x float> %a0, <8 x float> %a1) {
; CHECK-LABEL: test_x86_avx_cmp_ps_256_pseudo_op:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vcmpeqps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x00]
; CHECK-NEXT:    vcmpltps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x01]
; CHECK-NEXT:    vcmpleps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x02]
; CHECK-NEXT:    vcmpunordps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x03]
; CHECK-NEXT:    vcmpneqps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x04]
; CHECK-NEXT:    vcmpnltps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x05]
; CHECK-NEXT:    vcmpnleps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x06]
; CHECK-NEXT:    vcmpordps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x07]
; CHECK-NEXT:    vcmpeq_uqps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x08]
; CHECK-NEXT:    vcmpngeps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x09]
; CHECK-NEXT:    vcmpngtps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x0a]
; CHECK-NEXT:    vcmpfalseps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x0b]
; CHECK-NEXT:    vcmpneq_oqps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x0c]
; CHECK-NEXT:    vcmpgeps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x0d]
; CHECK-NEXT:    vcmpgtps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x0e]
; CHECK-NEXT:    vcmptrueps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x0f]
; CHECK-NEXT:    vcmpeq_osps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x10]
; CHECK-NEXT:    vcmplt_oqps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x11]
; CHECK-NEXT:    vcmple_oqps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x12]
; CHECK-NEXT:    vcmpunord_sps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x13]
; CHECK-NEXT:    vcmpneq_usps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x14]
; CHECK-NEXT:    vcmpnlt_uqps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x15]
; CHECK-NEXT:    vcmpnle_uqps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x16]
; CHECK-NEXT:    vcmpord_sps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x17]
; CHECK-NEXT:    vcmpeq_usps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x18]
; CHECK-NEXT:    vcmpnge_uqps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x19]
; CHECK-NEXT:    vcmpngt_uqps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x1a]
; CHECK-NEXT:    vcmpfalse_osps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x1b]
; CHECK-NEXT:    vcmpneq_osps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x1c]
; CHECK-NEXT:    vcmpge_oqps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x1d]
; CHECK-NEXT:    vcmpgt_oqps %ymm1, %ymm0, %ymm1 # encoding: [0xc5,0xfc,0xc2,0xc9,0x1e]
; CHECK-NEXT:    vcmptrue_usps %ymm1, %ymm0, %ymm0 # encoding: [0xc5,0xfc,0xc2,0xc1,0x1f]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %a2 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a1, i8 0) ; <<8 x float>> [#uses=1]
  %a3 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a2, i8 1) ; <<8 x float>> [#uses=1]
  %a4 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a3, i8 2) ; <<8 x float>> [#uses=1]
  %a5 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a4, i8 3) ; <<8 x float>> [#uses=1]
  %a6 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a5, i8 4) ; <<8 x float>> [#uses=1]
  %a7 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a6, i8 5) ; <<8 x float>> [#uses=1]
  %a8 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a7, i8 6) ; <<8 x float>> [#uses=1]
  %a9 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a8, i8 7) ; <<8 x float>> [#uses=1]
  %a10 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a9, i8 8) ; <<8 x float>> [#uses=1]
  %a11 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a10, i8 9) ; <<8 x float>> [#uses=1]
  %a12 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a11, i8 10) ; <<8 x float>> [#uses=1]
  %a13 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a12, i8 11) ; <<8 x float>> [#uses=1]
  %a14 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a13, i8 12) ; <<8 x float>> [#uses=1]
  %a15 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a14, i8 13) ; <<8 x float>> [#uses=1]
  %a16 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a15, i8 14) ; <<8 x float>> [#uses=1]
  %a17 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a16, i8 15) ; <<8 x float>> [#uses=1]
  %a18 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a17, i8 16) ; <<8 x float>> [#uses=1]
  %a19 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a18, i8 17) ; <<8 x float>> [#uses=1]
  %a20 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a19, i8 18) ; <<8 x float>> [#uses=1]
  %a21 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a20, i8 19) ; <<8 x float>> [#uses=1]
  %a22 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a21, i8 20) ; <<8 x float>> [#uses=1]
  %a23 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a22, i8 21) ; <<8 x float>> [#uses=1]
  %a24 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a23, i8 22) ; <<8 x float>> [#uses=1]
  %a25 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a24, i8 23) ; <<8 x float>> [#uses=1]
  %a26 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a25, i8 24) ; <<8 x float>> [#uses=1]
  %a27 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a26, i8 25) ; <<8 x float>> [#uses=1]
  %a28 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a27, i8 26) ; <<8 x float>> [#uses=1]
  %a29 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a28, i8 27) ; <<8 x float>> [#uses=1]
  %a30 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a29, i8 28) ; <<8 x float>> [#uses=1]
  %a31 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a30, i8 29) ; <<8 x float>> [#uses=1]
  %a32 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a31, i8 30) ; <<8 x float>> [#uses=1]
  %res = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a32, i8 31) ; <<8 x float>> [#uses=1]
  ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float>, <8 x float>, i8) nounwind readnone


define <4 x float> @test_x86_avx_cvt_pd2_ps_256(<4 x double> %a0) {
; AVX-LABEL: test_x86_avx_cvt_pd2_ps_256:
; AVX:       # %bb.0:
; AVX-NEXT:    vcvtpd2ps %ymm0, %xmm0 # encoding: [0xc5,0xfd,0x5a,0xc0]
; AVX-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_cvt_pd2_ps_256:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vcvtpd2ps %ymm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x5a,0xc0]
; AVX512VL-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <4 x float> @llvm.x86.avx.cvt.pd2.ps.256(<4 x double> %a0) ; <<4 x float>> [#uses=1]
  ret <4 x float> %res
}
declare <4 x float> @llvm.x86.avx.cvt.pd2.ps.256(<4 x double>) nounwind readnone


define <4 x i32> @test_x86_avx_cvt_pd2dq_256(<4 x double> %a0) {
; AVX-LABEL: test_x86_avx_cvt_pd2dq_256:
; AVX:       # %bb.0:
; AVX-NEXT:    vcvtpd2dq %ymm0, %xmm0 # encoding: [0xc5,0xff,0xe6,0xc0]
; AVX-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_cvt_pd2dq_256:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vcvtpd2dq %ymm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xff,0xe6,0xc0]
; AVX512VL-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <4 x i32> @llvm.x86.avx.cvt.pd2dq.256(<4 x double> %a0) ; <<4 x i32>> [#uses=1]
  ret <4 x i32> %res
}
declare <4 x i32> @llvm.x86.avx.cvt.pd2dq.256(<4 x double>) nounwind readnone


define <8 x i32> @test_x86_avx_cvt_ps2dq_256(<8 x float> %a0) {
; AVX-LABEL: test_x86_avx_cvt_ps2dq_256:
; AVX:       # %bb.0:
; AVX-NEXT:    vcvtps2dq %ymm0, %ymm0 # encoding: [0xc5,0xfd,0x5b,0xc0]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_cvt_ps2dq_256:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vcvtps2dq %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x5b,0xc0]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <8 x i32> @llvm.x86.avx.cvt.ps2dq.256(<8 x float> %a0) ; <<8 x i32>> [#uses=1]
  ret <8 x i32> %res
}
declare <8 x i32> @llvm.x86.avx.cvt.ps2dq.256(<8 x float>) nounwind readnone


define <4 x i32> @test_x86_avx_cvtt_pd2dq_256(<4 x double> %a0) {
; AVX-LABEL: test_x86_avx_cvtt_pd2dq_256:
; AVX:       # %bb.0:
; AVX-NEXT:    vcvttpd2dq %ymm0, %xmm0 # encoding: [0xc5,0xfd,0xe6,0xc0]
; AVX-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_cvtt_pd2dq_256:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vcvttpd2dq %ymm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xe6,0xc0]
; AVX512VL-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <4 x i32> @llvm.x86.avx.cvtt.pd2dq.256(<4 x double> %a0) ; <<4 x i32>> [#uses=1]
  ret <4 x i32> %res
}
declare <4 x i32> @llvm.x86.avx.cvtt.pd2dq.256(<4 x double>) nounwind readnone


define <8 x i32> @test_x86_avx_cvtt_ps2dq_256(<8 x float> %a0) {
; AVX-LABEL: test_x86_avx_cvtt_ps2dq_256:
; AVX:       # %bb.0:
; AVX-NEXT:    vcvttps2dq %ymm0, %ymm0 # encoding: [0xc5,0xfe,0x5b,0xc0]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_cvtt_ps2dq_256:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vcvttps2dq %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfe,0x5b,0xc0]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <8 x i32> @llvm.x86.avx.cvtt.ps2dq.256(<8 x float> %a0) ; <<8 x i32>> [#uses=1]
  ret <8 x i32> %res
}
declare <8 x i32> @llvm.x86.avx.cvtt.ps2dq.256(<8 x float>) nounwind readnone


define <8 x float> @test_x86_avx_dp_ps_256(<8 x float> %a0, <8 x float> %a1) {
; CHECK-LABEL: test_x86_avx_dp_ps_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vdpps $7, %ymm1, %ymm0, %ymm0 # encoding: [0xc4,0xe3,0x7d,0x40,0xc1,0x07]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float> %a0, <8 x float> %a1, i8 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>, i8) nounwind readnone


define <4 x double> @test_x86_avx_hadd_pd_256(<4 x double> %a0, <4 x double> %a1) {
; CHECK-LABEL: test_x86_avx_hadd_pd_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vhaddpd %ymm1, %ymm0, %ymm0 # encoding: [0xc5,0xfd,0x7c,0xc1]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <4 x double> @llvm.x86.avx.hadd.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
  ret <4 x double> %res
}
declare <4 x double> @llvm.x86.avx.hadd.pd.256(<4 x double>, <4 x double>) nounwind readnone


define <8 x float> @test_x86_avx_hadd_ps_256(<8 x float> %a0, <8 x float> %a1) {
; CHECK-LABEL: test_x86_avx_hadd_ps_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vhaddps %ymm1, %ymm0, %ymm0 # encoding: [0xc5,0xff,0x7c,0xc1]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
  ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float>, <8 x float>) nounwind readnone


define <4 x double> @test_x86_avx_hsub_pd_256(<4 x double> %a0, <4 x double> %a1) {
; CHECK-LABEL: test_x86_avx_hsub_pd_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vhsubpd %ymm1, %ymm0, %ymm0 # encoding: [0xc5,0xfd,0x7d,0xc1]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <4 x double> @llvm.x86.avx.hsub.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
  ret <4 x double> %res
}
declare <4 x double> @llvm.x86.avx.hsub.pd.256(<4 x double>, <4 x double>) nounwind readnone


define <8 x float> @test_x86_avx_hsub_ps_256(<8 x float> %a0, <8 x float> %a1) {
; CHECK-LABEL: test_x86_avx_hsub_ps_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vhsubps %ymm1, %ymm0, %ymm0 # encoding: [0xc5,0xff,0x7d,0xc1]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <8 x float> @llvm.x86.avx.hsub.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
  ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.hsub.ps.256(<8 x float>, <8 x float>) nounwind readnone


define <32 x i8> @test_x86_avx_ldu_dq_256(i8* %a0) {
; X86-LABEL: test_x86_avx_ldu_dq_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vlddqu (%eax), %ymm0 # encoding: [0xc5,0xff,0xf0,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_x86_avx_ldu_dq_256:
; X64:       # %bb.0:
; X64-NEXT:    vlddqu (%rdi), %ymm0 # encoding: [0xc5,0xff,0xf0,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %res = call <32 x i8> @llvm.x86.avx.ldu.dq.256(i8* %a0) ; <<32 x i8>> [#uses=1]
  ret <32 x i8> %res
}
declare <32 x i8> @llvm.x86.avx.ldu.dq.256(i8*) nounwind readonly


define <2 x double> @test_x86_avx_maskload_pd(i8* %a0, <2 x i64> %mask) {
; X86-LABEL: test_x86_avx_maskload_pd:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vmaskmovpd (%eax), %xmm0, %xmm0 # encoding: [0xc4,0xe2,0x79,0x2d,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_x86_avx_maskload_pd:
; X64:       # %bb.0:
; X64-NEXT:    vmaskmovpd (%rdi), %xmm0, %xmm0 # encoding: [0xc4,0xe2,0x79,0x2d,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %res = call <2 x double> @llvm.x86.avx.maskload.pd(i8* %a0, <2 x i64> %mask) ; <<2 x double>> [#uses=1]
  ret <2 x double> %res
}
declare <2 x double> @llvm.x86.avx.maskload.pd(i8*, <2 x i64>) nounwind readonly


define <4 x double> @test_x86_avx_maskload_pd_256(i8* %a0, <4 x i64> %mask) {
; X86-LABEL: test_x86_avx_maskload_pd_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vmaskmovpd (%eax), %ymm0, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x2d,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_x86_avx_maskload_pd_256:
; X64:       # %bb.0:
; X64-NEXT:    vmaskmovpd (%rdi), %ymm0, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x2d,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %res = call <4 x double> @llvm.x86.avx.maskload.pd.256(i8* %a0, <4 x i64> %mask) ; <<4 x double>> [#uses=1]
  ret <4 x double> %res
}
declare <4 x double> @llvm.x86.avx.maskload.pd.256(i8*, <4 x i64>) nounwind readonly


define <4 x float> @test_x86_avx_maskload_ps(i8* %a0, <4 x i32> %mask) {
; X86-LABEL: test_x86_avx_maskload_ps:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vmaskmovps (%eax), %xmm0, %xmm0 # encoding: [0xc4,0xe2,0x79,0x2c,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_x86_avx_maskload_ps:
; X64:       # %bb.0:
; X64-NEXT:    vmaskmovps (%rdi), %xmm0, %xmm0 # encoding: [0xc4,0xe2,0x79,0x2c,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %res = call <4 x float> @llvm.x86.avx.maskload.ps(i8* %a0, <4 x i32> %mask) ; <<4 x float>> [#uses=1]
  ret <4 x float> %res
}
declare <4 x float> @llvm.x86.avx.maskload.ps(i8*, <4 x i32>) nounwind readonly


define <8 x float> @test_x86_avx_maskload_ps_256(i8* %a0, <8 x i32> %mask) {
; X86-LABEL: test_x86_avx_maskload_ps_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vmaskmovps (%eax), %ymm0, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x2c,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_x86_avx_maskload_ps_256:
; X64:       # %bb.0:
; X64-NEXT:    vmaskmovps (%rdi), %ymm0, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x2c,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %res = call <8 x float> @llvm.x86.avx.maskload.ps.256(i8* %a0, <8 x i32> %mask) ; <<8 x float>> [#uses=1]
  ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.maskload.ps.256(i8*, <8 x i32>) nounwind readonly


define void @test_x86_avx_maskstore_pd(i8* %a0, <2 x i64> %mask, <2 x double> %a2) {
; X86-LABEL: test_x86_avx_maskstore_pd:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vmaskmovpd %xmm1, %xmm0, (%eax) # encoding: [0xc4,0xe2,0x79,0x2f,0x08]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_x86_avx_maskstore_pd:
; X64:       # %bb.0:
; X64-NEXT:    vmaskmovpd %xmm1, %xmm0, (%rdi) # encoding: [0xc4,0xe2,0x79,0x2f,0x0f]
; X64-NEXT:    retq # encoding: [0xc3]
  call void @llvm.x86.avx.maskstore.pd(i8* %a0, <2 x i64> %mask, <2 x double> %a2)
  ret void
}
declare void @llvm.x86.avx.maskstore.pd(i8*, <2 x i64>, <2 x double>) nounwind


define void @test_x86_avx_maskstore_pd_256(i8* %a0, <4 x i64> %mask, <4 x double> %a2) {
; X86-LABEL: test_x86_avx_maskstore_pd_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vmaskmovpd %ymm1, %ymm0, (%eax) # encoding: [0xc4,0xe2,0x7d,0x2f,0x08]
; X86-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_x86_avx_maskstore_pd_256:
; X64:       # %bb.0:
; X64-NEXT:    vmaskmovpd %ymm1, %ymm0, (%rdi) # encoding: [0xc4,0xe2,0x7d,0x2f,0x0f]
; X64-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT:    retq # encoding: [0xc3]
  call void @llvm.x86.avx.maskstore.pd.256(i8* %a0, <4 x i64> %mask, <4 x double> %a2)
  ret void
}
declare void @llvm.x86.avx.maskstore.pd.256(i8*, <4 x i64>, <4 x double>) nounwind


define void @test_x86_avx_maskstore_ps(i8* %a0, <4 x i32> %mask, <4 x float> %a2) {
; X86-LABEL: test_x86_avx_maskstore_ps:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vmaskmovps %xmm1, %xmm0, (%eax) # encoding: [0xc4,0xe2,0x79,0x2e,0x08]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_x86_avx_maskstore_ps:
; X64:       # %bb.0:
; X64-NEXT:    vmaskmovps %xmm1, %xmm0, (%rdi) # encoding: [0xc4,0xe2,0x79,0x2e,0x0f]
; X64-NEXT:    retq # encoding: [0xc3]
  call void @llvm.x86.avx.maskstore.ps(i8* %a0, <4 x i32> %mask, <4 x float> %a2)
  ret void
}
declare void @llvm.x86.avx.maskstore.ps(i8*, <4 x i32>, <4 x float>) nounwind


define void @test_x86_avx_maskstore_ps_256(i8* %a0, <8 x i32> %mask, <8 x float> %a2) {
; X86-LABEL: test_x86_avx_maskstore_ps_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vmaskmovps %ymm1, %ymm0, (%eax) # encoding: [0xc4,0xe2,0x7d,0x2e,0x08]
; X86-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_x86_avx_maskstore_ps_256:
; X64:       # %bb.0:
; X64-NEXT:    vmaskmovps %ymm1, %ymm0, (%rdi) # encoding: [0xc4,0xe2,0x7d,0x2e,0x0f]
; X64-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT:    retq # encoding: [0xc3]
  call void @llvm.x86.avx.maskstore.ps.256(i8* %a0, <8 x i32> %mask, <8 x float> %a2)
  ret void
}
declare void @llvm.x86.avx.maskstore.ps.256(i8*, <8 x i32>, <8 x float>) nounwind


define <4 x double> @test_x86_avx_max_pd_256(<4 x double> %a0, <4 x double> %a1) {
; AVX-LABEL: test_x86_avx_max_pd_256:
; AVX:       # %bb.0:
; AVX-NEXT:    vmaxpd %ymm1, %ymm0, %ymm0 # encoding: [0xc5,0xfd,0x5f,0xc1]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_max_pd_256:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vmaxpd %ymm1, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x5f,0xc1]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <4 x double> @llvm.x86.avx.max.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
  ret <4 x double> %res
}
declare <4 x double> @llvm.x86.avx.max.pd.256(<4 x double>, <4 x double>) nounwind readnone


define <8 x float> @test_x86_avx_max_ps_256(<8 x float> %a0, <8 x float> %a1) {
; AVX-LABEL: test_x86_avx_max_ps_256:
; AVX:       # %bb.0:
; AVX-NEXT:    vmaxps %ymm1, %ymm0, %ymm0 # encoding: [0xc5,0xfc,0x5f,0xc1]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_max_ps_256:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vmaxps %ymm1, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfc,0x5f,0xc1]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <8 x float> @llvm.x86.avx.max.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
  ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.max.ps.256(<8 x float>, <8 x float>) nounwind readnone


define <4 x double> @test_x86_avx_min_pd_256(<4 x double> %a0, <4 x double> %a1) {
; AVX-LABEL: test_x86_avx_min_pd_256:
; AVX:       # %bb.0:
; AVX-NEXT:    vminpd %ymm1, %ymm0, %ymm0 # encoding: [0xc5,0xfd,0x5d,0xc1]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_min_pd_256:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vminpd %ymm1, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x5d,0xc1]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <4 x double> @llvm.x86.avx.min.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
  ret <4 x double> %res
}
declare <4 x double> @llvm.x86.avx.min.pd.256(<4 x double>, <4 x double>) nounwind readnone


define <8 x float> @test_x86_avx_min_ps_256(<8 x float> %a0, <8 x float> %a1) {
; AVX-LABEL: test_x86_avx_min_ps_256:
; AVX:       # %bb.0:
; AVX-NEXT:    vminps %ymm1, %ymm0, %ymm0 # encoding: [0xc5,0xfc,0x5d,0xc1]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_min_ps_256:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vminps %ymm1, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfc,0x5d,0xc1]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <8 x float> @llvm.x86.avx.min.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
  ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.min.ps.256(<8 x float>, <8 x float>) nounwind readnone


define i32 @test_x86_avx_movmsk_pd_256(<4 x double> %a0) {
; CHECK-LABEL: test_x86_avx_movmsk_pd_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovmskpd %ymm0, %eax # encoding: [0xc5,0xfd,0x50,0xc0]
; CHECK-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.movmsk.pd.256(<4 x double> %a0) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.movmsk.pd.256(<4 x double>) nounwind readnone


define i32 @test_x86_avx_movmsk_ps_256(<8 x float> %a0) {
; CHECK-LABEL: test_x86_avx_movmsk_ps_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovmskps %ymm0, %eax # encoding: [0xc5,0xfc,0x50,0xc0]
; CHECK-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.movmsk.ps.256(<8 x float> %a0) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.movmsk.ps.256(<8 x float>) nounwind readnone


define i32 @test_x86_avx_ptestc_256(<4 x i64> %a0, <4 x i64> %a1) {
; CHECK-LABEL: test_x86_avx_ptestc_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
; CHECK-NEXT:    vptest %ymm1, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x17,0xc1]
; CHECK-NEXT:    setb %al # encoding: [0x0f,0x92,0xc0]
; CHECK-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.ptestc.256(<4 x i64> %a0, <4 x i64> %a1) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.ptestc.256(<4 x i64>, <4 x i64>) nounwind readnone


define i32 @test_x86_avx_ptestnzc_256(<4 x i64> %a0, <4 x i64> %a1) {
; CHECK-LABEL: test_x86_avx_ptestnzc_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
; CHECK-NEXT:    vptest %ymm1, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x17,0xc1]
; CHECK-NEXT:    seta %al # encoding: [0x0f,0x97,0xc0]
; CHECK-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.ptestnzc.256(<4 x i64> %a0, <4 x i64> %a1) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.ptestnzc.256(<4 x i64>, <4 x i64>) nounwind readnone


define i32 @test_x86_avx_ptestz_256(<4 x i64> %a0, <4 x i64> %a1) {
; CHECK-LABEL: test_x86_avx_ptestz_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
; CHECK-NEXT:    vptest %ymm1, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x17,0xc1]
; CHECK-NEXT:    sete %al # encoding: [0x0f,0x94,0xc0]
; CHECK-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a0, <4 x i64> %a1) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.ptestz.256(<4 x i64>, <4 x i64>) nounwind readnone


define <8 x float> @test_x86_avx_rcp_ps_256(<8 x float> %a0) {
; CHECK-LABEL: test_x86_avx_rcp_ps_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vrcpps %ymm0, %ymm0 # encoding: [0xc5,0xfc,0x53,0xc0]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <8 x float> @llvm.x86.avx.rcp.ps.256(<8 x float> %a0) ; <<8 x float>> [#uses=1]
  ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.rcp.ps.256(<8 x float>) nounwind readnone


define <4 x double> @test_x86_avx_round_pd_256(<4 x double> %a0) {
; AVX-LABEL: test_x86_avx_round_pd_256:
; AVX:       # %bb.0:
; AVX-NEXT:    vroundpd $7, %ymm0, %ymm0 # encoding: [0xc4,0xe3,0x7d,0x09,0xc0,0x07]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_round_pd_256:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vroundpd $7, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x7d,0x09,0xc0,0x07]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <4 x double> @llvm.x86.avx.round.pd.256(<4 x double> %a0, i32 7) ; <<4 x double>> [#uses=1]
  ret <4 x double> %res
}
declare <4 x double> @llvm.x86.avx.round.pd.256(<4 x double>, i32) nounwind readnone


define <8 x float> @test_x86_avx_round_ps_256(<8 x float> %a0) {
; AVX-LABEL: test_x86_avx_round_ps_256:
; AVX:       # %bb.0:
; AVX-NEXT:    vroundps $7, %ymm0, %ymm0 # encoding: [0xc4,0xe3,0x7d,0x08,0xc0,0x07]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_round_ps_256:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vroundps $7, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x7d,0x08,0xc0,0x07]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <8 x float> @llvm.x86.avx.round.ps.256(<8 x float> %a0, i32 7) ; <<8 x float>> [#uses=1]
  ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.round.ps.256(<8 x float>, i32) nounwind readnone


define <8 x float> @test_x86_avx_rsqrt_ps_256(<8 x float> %a0) {
; CHECK-LABEL: test_x86_avx_rsqrt_ps_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vrsqrtps %ymm0, %ymm0 # encoding: [0xc5,0xfc,0x52,0xc0]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <8 x float> @llvm.x86.avx.rsqrt.ps.256(<8 x float> %a0) ; <<8 x float>> [#uses=1]
  ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.rsqrt.ps.256(<8 x float>) nounwind readnone

define <2 x double> @test_x86_avx_vpermilvar_pd(<2 x double> %a0, <2 x i64> %a1) {
; AVX-LABEL: test_x86_avx_vpermilvar_pd:
; AVX:       # %bb.0:
; AVX-NEXT:    vpermilpd %xmm1, %xmm0, %xmm0 # encoding: [0xc4,0xe2,0x79,0x0d,0xc1]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_vpermilvar_pd:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vpermilpd %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x0d,0xc1]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <2 x double> @llvm.x86.avx.vpermilvar.pd(<2 x double> %a0, <2 x i64> %a1) ; <<2 x double>> [#uses=1]
  ret <2 x double> %res
}
declare <2 x double> @llvm.x86.avx.vpermilvar.pd(<2 x double>, <2 x i64>) nounwind readnone


define <4 x double> @test_x86_avx_vpermilvar_pd_256(<4 x double> %a0, <4 x i64> %a1) {
; AVX-LABEL: test_x86_avx_vpermilvar_pd_256:
; AVX:       # %bb.0:
; AVX-NEXT:    vpermilpd %ymm1, %ymm0, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x0d,0xc1]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_vpermilvar_pd_256:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vpermilpd %ymm1, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x0d,0xc1]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double> %a0, <4 x i64> %a1) ; <<4 x double>> [#uses=1]
  ret <4 x double> %res
}
declare <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double>, <4 x i64>) nounwind readnone

define <4 x double> @test_x86_avx_vpermilvar_pd_256_2(<4 x double> %a0) {
; AVX-LABEL: test_x86_avx_vpermilvar_pd_256_2:
; AVX:       # %bb.0:
; AVX-NEXT:    vpermilpd $9, %ymm0, %ymm0 # encoding: [0xc4,0xe3,0x7d,0x05,0xc0,0x09]
; AVX-NEXT:    # ymm0 = ymm0[1,0,2,3]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_vpermilvar_pd_256_2:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vpermilpd $9, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x7d,0x05,0xc0,0x09]
; AVX512VL-NEXT:    # ymm0 = ymm0[1,0,2,3]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double> %a0, <4 x i64> <i64 2, i64 0, i64 0, i64 2>) ; <<4 x double>> [#uses=1]
  ret <4 x double> %res
}

define <4 x float> @test_x86_avx_vpermilvar_ps(<4 x float> %a0, <4 x i32> %a1) {
; AVX-LABEL: test_x86_avx_vpermilvar_ps:
; AVX:       # %bb.0:
; AVX-NEXT:    vpermilps %xmm1, %xmm0, %xmm0 # encoding: [0xc4,0xe2,0x79,0x0c,0xc1]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_vpermilvar_ps:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vpermilps %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x0c,0xc1]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float> %a0, <4 x i32> %a1) ; <<4 x float>> [#uses=1]
  ret <4 x float> %res
}
define <4 x float> @test_x86_avx_vpermilvar_ps_load(<4 x float> %a0, <4 x i32>* %a1) {
; X86-AVX-LABEL: test_x86_avx_vpermilvar_ps_load:
; X86-AVX:       # %bb.0:
; X86-AVX-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-AVX-NEXT:    vpermilps (%eax), %xmm0, %xmm0 # encoding: [0xc4,0xe2,0x79,0x0c,0x00]
; X86-AVX-NEXT:    retl # encoding: [0xc3]
;
; X86-AVX512VL-LABEL: test_x86_avx_vpermilvar_ps_load:
; X86-AVX512VL:       # %bb.0:
; X86-AVX512VL-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-AVX512VL-NEXT:    vpermilps (%eax), %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x0c,0x00]
; X86-AVX512VL-NEXT:    retl # encoding: [0xc3]
;
; X64-AVX-LABEL: test_x86_avx_vpermilvar_ps_load:
; X64-AVX:       # %bb.0:
; X64-AVX-NEXT:    vpermilps (%rdi), %xmm0, %xmm0 # encoding: [0xc4,0xe2,0x79,0x0c,0x07]
; X64-AVX-NEXT:    retq # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: test_x86_avx_vpermilvar_ps_load:
; X64-AVX512VL:       # %bb.0:
; X64-AVX512VL-NEXT:    vpermilps (%rdi), %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x0c,0x07]
; X64-AVX512VL-NEXT:    retq # encoding: [0xc3]
  %a2 = load <4 x i32>, <4 x i32>* %a1
  %res = call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float> %a0, <4 x i32> %a2) ; <<4 x float>> [#uses=1]
  ret <4 x float> %res
}
declare <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float>, <4 x i32>) nounwind readnone


define <8 x float> @test_x86_avx_vpermilvar_ps_256(<8 x float> %a0, <8 x i32> %a1) {
; AVX-LABEL: test_x86_avx_vpermilvar_ps_256:
; AVX:       # %bb.0:
; AVX-NEXT:    vpermilps %ymm1, %ymm0, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x0c,0xc1]
; AVX-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
;
; AVX512VL-LABEL: test_x86_avx_vpermilvar_ps_256:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vpermilps %ymm1, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x0c,0xc1]
; AVX512VL-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float> %a0, <8 x i32> %a1) ; <<8 x float>> [#uses=1]
  ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float>, <8 x i32>) nounwind readnone


define i32 @test_x86_avx_vtestc_pd(<2 x double> %a0, <2 x double> %a1) {
; CHECK-LABEL: test_x86_avx_vtestc_pd:
; CHECK:       # %bb.0:
; CHECK-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
; CHECK-NEXT:    vtestpd %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x79,0x0f,0xc1]
; CHECK-NEXT:    setb %al # encoding: [0x0f,0x92,0xc0]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.vtestc.pd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.vtestc.pd(<2 x double>, <2 x double>) nounwind readnone


define i32 @test_x86_avx_vtestc_pd_256(<4 x double> %a0, <4 x double> %a1) {
; CHECK-LABEL: test_x86_avx_vtestc_pd_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
; CHECK-NEXT:    vtestpd %ymm1, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x0f,0xc1]
; CHECK-NEXT:    setb %al # encoding: [0x0f,0x92,0xc0]
; CHECK-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.vtestc.pd.256(<4 x double> %a0, <4 x double> %a1) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.vtestc.pd.256(<4 x double>, <4 x double>) nounwind readnone


define i32 @test_x86_avx_vtestc_ps(<4 x float> %a0, <4 x float> %a1) {
; CHECK-LABEL: test_x86_avx_vtestc_ps:
; CHECK:       # %bb.0:
; CHECK-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
; CHECK-NEXT:    vtestps %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x79,0x0e,0xc1]
; CHECK-NEXT:    setb %al # encoding: [0x0f,0x92,0xc0]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.vtestc.ps(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.vtestc.ps(<4 x float>, <4 x float>) nounwind readnone


define i32 @test_x86_avx_vtestc_ps_256(<8 x float> %a0, <8 x float> %a1) {
; CHECK-LABEL: test_x86_avx_vtestc_ps_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
; CHECK-NEXT:    vtestps %ymm1, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x0e,0xc1]
; CHECK-NEXT:    setb %al # encoding: [0x0f,0x92,0xc0]
; CHECK-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.vtestc.ps.256(<8 x float> %a0, <8 x float> %a1) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.vtestc.ps.256(<8 x float>, <8 x float>) nounwind readnone


define i32 @test_x86_avx_vtestnzc_pd(<2 x double> %a0, <2 x double> %a1) {
; CHECK-LABEL: test_x86_avx_vtestnzc_pd:
; CHECK:       # %bb.0:
; CHECK-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
; CHECK-NEXT:    vtestpd %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x79,0x0f,0xc1]
; CHECK-NEXT:    seta %al # encoding: [0x0f,0x97,0xc0]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.vtestnzc.pd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.vtestnzc.pd(<2 x double>, <2 x double>) nounwind readnone


define i32 @test_x86_avx_vtestnzc_pd_256(<4 x double> %a0, <4 x double> %a1) {
; CHECK-LABEL: test_x86_avx_vtestnzc_pd_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
; CHECK-NEXT:    vtestpd %ymm1, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x0f,0xc1]
; CHECK-NEXT:    seta %al # encoding: [0x0f,0x97,0xc0]
; CHECK-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.vtestnzc.pd.256(<4 x double> %a0, <4 x double> %a1) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.vtestnzc.pd.256(<4 x double>, <4 x double>) nounwind readnone


define i32 @test_x86_avx_vtestnzc_ps(<4 x float> %a0, <4 x float> %a1) {
; CHECK-LABEL: test_x86_avx_vtestnzc_ps:
; CHECK:       # %bb.0:
; CHECK-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
; CHECK-NEXT:    vtestps %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x79,0x0e,0xc1]
; CHECK-NEXT:    seta %al # encoding: [0x0f,0x97,0xc0]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.vtestnzc.ps(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.vtestnzc.ps(<4 x float>, <4 x float>) nounwind readnone


define i32 @test_x86_avx_vtestnzc_ps_256(<8 x float> %a0, <8 x float> %a1) {
; CHECK-LABEL: test_x86_avx_vtestnzc_ps_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
; CHECK-NEXT:    vtestps %ymm1, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x0e,0xc1]
; CHECK-NEXT:    seta %al # encoding: [0x0f,0x97,0xc0]
; CHECK-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.vtestnzc.ps.256(<8 x float> %a0, <8 x float> %a1) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.vtestnzc.ps.256(<8 x float>, <8 x float>) nounwind readnone


define i32 @test_x86_avx_vtestz_pd(<2 x double> %a0, <2 x double> %a1) {
; CHECK-LABEL: test_x86_avx_vtestz_pd:
; CHECK:       # %bb.0:
; CHECK-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
; CHECK-NEXT:    vtestpd %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x79,0x0f,0xc1]
; CHECK-NEXT:    sete %al # encoding: [0x0f,0x94,0xc0]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.vtestz.pd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.vtestz.pd(<2 x double>, <2 x double>) nounwind readnone


define i32 @test_x86_avx_vtestz_pd_256(<4 x double> %a0, <4 x double> %a1) {
; CHECK-LABEL: test_x86_avx_vtestz_pd_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
; CHECK-NEXT:    vtestpd %ymm1, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x0f,0xc1]
; CHECK-NEXT:    sete %al # encoding: [0x0f,0x94,0xc0]
; CHECK-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.vtestz.pd.256(<4 x double> %a0, <4 x double> %a1) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.vtestz.pd.256(<4 x double>, <4 x double>) nounwind readnone


define i32 @test_x86_avx_vtestz_ps(<4 x float> %a0, <4 x float> %a1) {
; CHECK-LABEL: test_x86_avx_vtestz_ps:
; CHECK:       # %bb.0:
; CHECK-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
; CHECK-NEXT:    vtestps %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x79,0x0e,0xc1]
; CHECK-NEXT:    sete %al # encoding: [0x0f,0x94,0xc0]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.vtestz.ps(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.vtestz.ps(<4 x float>, <4 x float>) nounwind readnone


define i32 @test_x86_avx_vtestz_ps_256(<8 x float> %a0, <8 x float> %a1) {
; CHECK-LABEL: test_x86_avx_vtestz_ps_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
; CHECK-NEXT:    vtestps %ymm1, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x0e,0xc1]
; CHECK-NEXT:    sete %al # encoding: [0x0f,0x94,0xc0]
; CHECK-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call i32 @llvm.x86.avx.vtestz.ps.256(<8 x float> %a0, <8 x float> %a1) ; <i32> [#uses=1]
  ret i32 %res
}
declare i32 @llvm.x86.avx.vtestz.ps.256(<8 x float>, <8 x float>) nounwind readnone


define void @test_x86_avx_vzeroall() {
; CHECK-LABEL: test_x86_avx_vzeroall:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vzeroall # encoding: [0xc5,0xfc,0x77]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  call void @llvm.x86.avx.vzeroall()
  ret void
}
declare void @llvm.x86.avx.vzeroall() nounwind


define void @test_x86_avx_vzeroupper() {
; CHECK-LABEL: test_x86_avx_vzeroupper:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  call void @llvm.x86.avx.vzeroupper()
  ret void
}
declare void @llvm.x86.avx.vzeroupper() nounwind

define void @movnt_dq(i8* %p, <2 x i64> %a1) nounwind {
; X86-AVX-LABEL: movnt_dq:
; X86-AVX:       # %bb.0:
; X86-AVX-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-AVX-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1 # encoding: [0xc5,0xf1,0x76,0xc9]
; X86-AVX-NEXT:    vpsubq %xmm1, %xmm0, %xmm0 # encoding: [0xc5,0xf9,0xfb,0xc1]
; X86-AVX-NEXT:    vmovntdq %ymm0, (%eax) # encoding: [0xc5,0xfd,0xe7,0x00]
; X86-AVX-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-AVX-NEXT:    retl # encoding: [0xc3]
;
; X86-AVX512VL-LABEL: movnt_dq:
; X86-AVX512VL:       # %bb.0:
; X86-AVX512VL-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-AVX512VL-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1 # encoding: [0xc5,0xf1,0x76,0xc9]
; X86-AVX512VL-NEXT:    vpsubq %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfb,0xc1]
; X86-AVX512VL-NEXT:    vmovntdq %ymm0, (%eax) # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xe7,0x00]
; X86-AVX512VL-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-AVX512VL-NEXT:    retl # encoding: [0xc3]
;
; X64-AVX-LABEL: movnt_dq:
; X64-AVX:       # %bb.0:
; X64-AVX-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1 # encoding: [0xc5,0xf1,0x76,0xc9]
; X64-AVX-NEXT:    vpsubq %xmm1, %xmm0, %xmm0 # encoding: [0xc5,0xf9,0xfb,0xc1]
; X64-AVX-NEXT:    vmovntdq %ymm0, (%rdi) # encoding: [0xc5,0xfd,0xe7,0x07]
; X64-AVX-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-AVX-NEXT:    retq # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: movnt_dq:
; X64-AVX512VL:       # %bb.0:
; X64-AVX512VL-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1 # encoding: [0xc5,0xf1,0x76,0xc9]
; X64-AVX512VL-NEXT:    vpsubq %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfb,0xc1]
; X64-AVX512VL-NEXT:    vmovntdq %ymm0, (%rdi) # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xe7,0x07]
; X64-AVX512VL-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-AVX512VL-NEXT:    retq # encoding: [0xc3]
  %a2 = add <2 x i64> %a1, <i64 1, i64 1>
  %a3 = shufflevector <2 x i64> %a2, <2 x i64> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
  tail call void @llvm.x86.avx.movnt.dq.256(i8* %p, <4 x i64> %a3) nounwind
  ret void
}
declare void @llvm.x86.avx.movnt.dq.256(i8*, <4 x i64>) nounwind

define void @movnt_ps(i8* %p, <8 x float> %a) nounwind {
; X86-AVX-LABEL: movnt_ps:
; X86-AVX:       # %bb.0:
; X86-AVX-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-AVX-NEXT:    vmovntps %ymm0, (%eax) # encoding: [0xc5,0xfc,0x2b,0x00]
; X86-AVX-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-AVX-NEXT:    retl # encoding: [0xc3]
;
; X86-AVX512VL-LABEL: movnt_ps:
; X86-AVX512VL:       # %bb.0:
; X86-AVX512VL-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-AVX512VL-NEXT:    vmovntps %ymm0, (%eax) # EVEX TO VEX Compression encoding: [0xc5,0xfc,0x2b,0x00]
; X86-AVX512VL-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-AVX512VL-NEXT:    retl # encoding: [0xc3]
;
; X64-AVX-LABEL: movnt_ps:
; X64-AVX:       # %bb.0:
; X64-AVX-NEXT:    vmovntps %ymm0, (%rdi) # encoding: [0xc5,0xfc,0x2b,0x07]
; X64-AVX-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-AVX-NEXT:    retq # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: movnt_ps:
; X64-AVX512VL:       # %bb.0:
; X64-AVX512VL-NEXT:    vmovntps %ymm0, (%rdi) # EVEX TO VEX Compression encoding: [0xc5,0xfc,0x2b,0x07]
; X64-AVX512VL-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-AVX512VL-NEXT:    retq # encoding: [0xc3]
  tail call void @llvm.x86.avx.movnt.ps.256(i8* %p, <8 x float> %a) nounwind
  ret void
}
declare void @llvm.x86.avx.movnt.ps.256(i8*, <8 x float>) nounwind

define void @movnt_pd(i8* %p, <4 x double> %a1) nounwind {
  ; add operation forces the execution domain.
; X86-AVX-LABEL: movnt_pd:
; X86-AVX:       # %bb.0:
; X86-AVX-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-AVX-NEXT:    vxorpd %xmm1, %xmm1, %xmm1 # encoding: [0xc5,0xf1,0x57,0xc9]
; X86-AVX-NEXT:    vaddpd %ymm1, %ymm0, %ymm0 # encoding: [0xc5,0xfd,0x58,0xc1]
; X86-AVX-NEXT:    vmovntpd %ymm0, (%eax) # encoding: [0xc5,0xfd,0x2b,0x00]
; X86-AVX-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-AVX-NEXT:    retl # encoding: [0xc3]
;
; X86-AVX512VL-LABEL: movnt_pd:
; X86-AVX512VL:       # %bb.0:
; X86-AVX512VL-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-AVX512VL-NEXT:    vxorpd %xmm1, %xmm1, %xmm1 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0x57,0xc9]
; X86-AVX512VL-NEXT:    vaddpd %ymm1, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x58,0xc1]
; X86-AVX512VL-NEXT:    vmovntpd %ymm0, (%eax) # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x2b,0x00]
; X86-AVX512VL-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-AVX512VL-NEXT:    retl # encoding: [0xc3]
;
; X64-AVX-LABEL: movnt_pd:
; X64-AVX:       # %bb.0:
; X64-AVX-NEXT:    vxorpd %xmm1, %xmm1, %xmm1 # encoding: [0xc5,0xf1,0x57,0xc9]
; X64-AVX-NEXT:    vaddpd %ymm1, %ymm0, %ymm0 # encoding: [0xc5,0xfd,0x58,0xc1]
; X64-AVX-NEXT:    vmovntpd %ymm0, (%rdi) # encoding: [0xc5,0xfd,0x2b,0x07]
; X64-AVX-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-AVX-NEXT:    retq # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: movnt_pd:
; X64-AVX512VL:       # %bb.0:
; X64-AVX512VL-NEXT:    vxorpd %xmm1, %xmm1, %xmm1 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0x57,0xc9]
; X64-AVX512VL-NEXT:    vaddpd %ymm1, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x58,0xc1]
; X64-AVX512VL-NEXT:    vmovntpd %ymm0, (%rdi) # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x2b,0x07]
; X64-AVX512VL-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-AVX512VL-NEXT:    retq # encoding: [0xc3]
  %a2 = fadd <4 x double> %a1, <double 0x0, double 0x0, double 0x0, double 0x0>
  tail call void @llvm.x86.avx.movnt.pd.256(i8* %p, <4 x double> %a2) nounwind
  ret void
}
declare void @llvm.x86.avx.movnt.pd.256(i8*, <4 x double>) nounwind


; Check for pclmulqdq
define <2 x i64> @test_x86_pclmulqdq(<2 x i64> %a0, <2 x i64> %a1) {
; CHECK-LABEL: test_x86_pclmulqdq:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vpclmulqdq $0, %xmm1, %xmm0, %xmm0 # encoding: [0xc4,0xe3,0x79,0x44,0xc1,0x00]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %res = call <2 x i64> @llvm.x86.pclmulqdq(<2 x i64> %a0, <2 x i64> %a1, i8 0) ; <<2 x i64>> [#uses=1]
  ret <2 x i64> %res
}
declare <2 x i64> @llvm.x86.pclmulqdq(<2 x i64>, <2 x i64>, i8) nounwind readnone