test/CodeGen/X86/avx512vl-intrinsics-fast-isel.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -fast-isel -mtriple=i386-unknown-unknown -mattr=+avx512f,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=X32
; RUN: llc < %s -fast-isel -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=X64

; NOTE: This should use IR equivalent to what is generated by clang/test/CodeGen/avx512vl-builtins.c

define <2 x i64> @test_mm_mask_set1_epi32(<2 x i64> %__O, i8 zeroext %__M)  {
; X32-LABEL: test_mm_mask_set1_epi32:
; X32:       # BB#0: # %entry
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpbroadcastd {{\.LCPI.*}}, %xmm0 {%k1}
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_mask_set1_epi32:
; X64:       # BB#0: # %entry
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vpbroadcastd {{.*}}(%rip), %xmm0 {%k1}
; X64-NEXT:    retq
entry:
  %0 = bitcast <2 x i64> %__O to <4 x i32>
  %1 = bitcast i8 %__M to <8 x i1>
  %extract.i = shufflevector <8 x i1> %1, <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %2 = select <4 x i1> %extract.i, <4 x i32> <i32 5, i32 5, i32 5, i32 5>, <4 x i32> %0
  %3 = bitcast <4 x i32> %2 to <2 x i64>
  ret <2 x i64> %3
}

define <2 x i64> @test_mm_maskz_set1_epi32(i8 zeroext %__M) {
; X32-LABEL: test_mm_maskz_set1_epi32:
; X32:       # BB#0: # %entry
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpbroadcastd {{\.LCPI.*}}, %xmm0 {%k1} {z}
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_maskz_set1_epi32:
; X64:       # BB#0: # %entry
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vpbroadcastd {{.*}}(%rip), %xmm0 {%k1} {z}
; X64-NEXT:    retq
entry:
  %0 = bitcast i8 %__M to <8 x i1>
  %extract.i = shufflevector <8 x i1> %0, <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %1 = select <4 x i1> %extract.i, <4 x i32> <i32 5, i32 5, i32 5, i32 5>, <4 x i32> zeroinitializer
  %2 = bitcast <4 x i32> %1 to <2 x i64>
  ret <2 x i64> %2
}

define <4 x i64> @test_mm256_mask_set1_epi32(<4 x i64> %__O, i8 zeroext %__M)  {
; X32-LABEL: test_mm256_mask_set1_epi32:
; X32:       # BB#0: # %entry
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpbroadcastd {{\.LCPI.*}}, %ymm0 {%k1}
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_mask_set1_epi32:
; X64:       # BB#0: # %entry
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vpbroadcastd {{.*}}(%rip), %ymm0 {%k1}
; X64-NEXT:    retq
entry:
  %0 = bitcast <4 x i64> %__O to <8 x i32>
  %1 = bitcast i8 %__M to <8 x i1>
  %2 = select <8 x i1> %1, <8 x i32> <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>, <8 x i32> %0
  %3 = bitcast <8 x i32> %2 to <4 x i64>
  ret <4 x i64> %3
}

define <4 x i64> @test_mm256_maskz_set1_epi32(i8 zeroext %__M)  {
; X32-LABEL: test_mm256_maskz_set1_epi32:
; X32:       # BB#0: # %entry
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpbroadcastd {{\.LCPI.*}}, %ymm0 {%k1} {z}
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_maskz_set1_epi32:
; X64:       # BB#0: # %entry
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vpbroadcastd {{.*}}(%rip), %ymm0 {%k1} {z}
; X64-NEXT:    retq
entry:
  %0 = bitcast i8 %__M to <8 x i1>
  %1 = select <8 x i1> %0, <8 x i32> <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>, <8 x i32> zeroinitializer
  %2 = bitcast <8 x i32> %1 to <4 x i64>
  ret <4 x i64> %2
}

define <2 x i64> @test_mm_mask_set1_epi64(<2 x i64> %__O, i8 zeroext %__M, i64 %__A)  {
; X32-LABEL: test_mm_mask_set1_epi64:
; X32:       # BB#0: # %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    movb {{[0-9]+}}(%esp), %cl
; X32-NEXT:    vmovd %eax, %xmm1
; X32-NEXT:    vpbroadcastb %xmm1, %xmm1
; X32-NEXT:    kmovw %ecx, %k1
; X32-NEXT:    vmovdqa64 %xmm1, %xmm0 {%k1}
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_mask_set1_epi64:
; X64:       # BB#0: # %entry
; X64-NEXT:    vmovd %esi, %xmm1
; X64-NEXT:    vpbroadcastb %xmm1, %xmm1
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vmovdqa64 %xmm1, %xmm0 {%k1}
; X64-NEXT:    retq
entry:
  %conv.i = trunc i64 %__A to i8
  %vecinit.i.i = insertelement <16 x i8> undef, i8 %conv.i, i32 0
  %vecinit15.i.i = shufflevector <16 x i8> %vecinit.i.i, <16 x i8> undef, <16 x i32> zeroinitializer
  %0 = bitcast <16 x i8> %vecinit15.i.i to <2 x i64>
  %1 = bitcast i8 %__M to <8 x i1>
  %extract.i = shufflevector <8 x i1> %1, <8 x i1> undef, <2 x i32> <i32 0, i32 1>
  %2 = select <2 x i1> %extract.i, <2 x i64> %0, <2 x i64> %__O
  ret <2 x i64> %2
}

define <2 x i64> @test_mm_maskz_set1_epi64(i8 zeroext %__M, i64 %__A)  {
; X32-LABEL: test_mm_maskz_set1_epi64:
; X32:       # BB#0: # %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    movb {{[0-9]+}}(%esp), %cl
; X32-NEXT:    vmovd %eax, %xmm0
; X32-NEXT:    vpbroadcastb %xmm0, %xmm0
; X32-NEXT:    kmovw %ecx, %k1
; X32-NEXT:    vmovdqa64 %xmm0, %xmm0 {%k1} {z}
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_maskz_set1_epi64:
; X64:       # BB#0: # %entry
; X64-NEXT:    vmovd %esi, %xmm0
; X64-NEXT:    vpbroadcastb %xmm0, %xmm0
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vmovdqa64 %xmm0, %xmm0 {%k1} {z}
; X64-NEXT:    retq
entry:
  %conv.i = trunc i64 %__A to i8
  %vecinit.i.i = insertelement <16 x i8> undef, i8 %conv.i, i32 0
  %vecinit15.i.i = shufflevector <16 x i8> %vecinit.i.i, <16 x i8> undef, <16 x i32> zeroinitializer
  %0 = bitcast <16 x i8> %vecinit15.i.i to <2 x i64>
  %1 = bitcast i8 %__M to <8 x i1>
  %extract.i = shufflevector <8 x i1> %1, <8 x i1> undef, <2 x i32> <i32 0, i32 1>
  %2 = select <2 x i1> %extract.i, <2 x i64> %0, <2 x i64> zeroinitializer
  ret <2 x i64> %2
}


define <4 x i64> @test_mm256_mask_set1_epi64(<4 x i64> %__O, i8 zeroext %__M, i64 %__A) {
; X32-LABEL: test_mm256_mask_set1_epi64:
; X32:       # BB#0: # %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT:    movb {{[0-9]+}}(%esp), %dl
; X32-NEXT:    vmovd %ecx, %xmm1
; X32-NEXT:    vpinsrd $1, %eax, %xmm1, %xmm1
; X32-NEXT:    vpinsrd $2, %ecx, %xmm1, %xmm1
; X32-NEXT:    vpinsrd $3, %eax, %xmm1, %xmm1
; X32-NEXT:    vinserti128 $1, %xmm1, %ymm1, %ymm1
; X32-NEXT:    kmovw %edx, %k1
; X32-NEXT:    vmovdqa64 %ymm1, %ymm0 {%k1}
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_mask_set1_epi64:
; X64:       # BB#0: # %entry
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vpbroadcastq %rsi, %ymm0 {%k1}
; X64-NEXT:    retq
entry:
  %vecinit.i.i = insertelement <4 x i64> undef, i64 %__A, i32 0
  %vecinit3.i.i = shufflevector <4 x i64> %vecinit.i.i, <4 x i64> undef, <4 x i32> zeroinitializer
  %0 = bitcast i8 %__M to <8 x i1>
  %extract.i = shufflevector <8 x i1> %0, <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %1 = select <4 x i1> %extract.i, <4 x i64> %vecinit3.i.i, <4 x i64> %__O
  ret <4 x i64> %1
}

define <4 x i64> @test_mm256_maskz_set1_epi64(i8 zeroext %__M, i64 %__A)  {
; X32-LABEL: test_mm256_maskz_set1_epi64:
; X32:       # BB#0: # %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT:    movb {{[0-9]+}}(%esp), %dl
; X32-NEXT:    vmovd %ecx, %xmm0
; X32-NEXT:    vpinsrd $1, %eax, %xmm0, %xmm0
; X32-NEXT:    vpinsrd $2, %ecx, %xmm0, %xmm0
; X32-NEXT:    vpinsrd $3, %eax, %xmm0, %xmm0
; X32-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
; X32-NEXT:    kmovw %edx, %k1
; X32-NEXT:    vmovdqa64 %ymm0, %ymm0 {%k1} {z}
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_maskz_set1_epi64:
; X64:       # BB#0: # %entry
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vpbroadcastq %rsi, %ymm0 {%k1} {z}
; X64-NEXT:    retq
entry:
  %vecinit.i.i = insertelement <4 x i64> undef, i64 %__A, i32 0
  %vecinit3.i.i = shufflevector <4 x i64> %vecinit.i.i, <4 x i64> undef, <4 x i32> zeroinitializer
  %0 = bitcast i8 %__M to <8 x i1>
  %extract.i = shufflevector <8 x i1> %0, <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %1 = select <4 x i1> %extract.i, <4 x i64> %vecinit3.i.i, <4 x i64> zeroinitializer
  ret <4 x i64> %1
}

define <2 x i64> @test_mm_broadcastd_epi32(<2 x i64> %a0) {
; X32-LABEL: test_mm_broadcastd_epi32:
; X32:       # BB#0:
; X32-NEXT:    vbroadcastss %xmm0, %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_broadcastd_epi32:
; X64:       # BB#0:
; X64-NEXT:    vbroadcastss %xmm0, %xmm0
; X64-NEXT:    retq
  %arg0 = bitcast <2 x i64> %a0 to <4 x i32>
  %res0 = shufflevector <4 x i32> %arg0, <4 x i32> undef, <4 x i32> zeroinitializer
  %res1 = bitcast <4 x i32> %res0 to <2 x i64>
  ret <2 x i64> %res1
}

define <2 x i64> @test_mm_mask_broadcastd_epi32(<2 x i64> %a0, i8 %a1, <2 x i64> %a2) {
; X32-LABEL: test_mm_mask_broadcastd_epi32:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpbroadcastd %xmm1, %xmm0 {%k1}
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_mask_broadcastd_epi32:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vpbroadcastd %xmm1, %xmm0 {%k1}
; X64-NEXT:    retq
  %trn1 = trunc i8 %a1 to i4
  %arg0 = bitcast <2 x i64> %a0 to <4 x i32>
  %arg1 = bitcast i4 %trn1 to <4 x i1>
  %arg2 = bitcast <2 x i64> %a2 to <4 x i32>
  %res0 = shufflevector <4 x i32> %arg2, <4 x i32> undef, <4 x i32> zeroinitializer
  %res1 = select <4 x i1> %arg1, <4 x i32> %res0, <4 x i32> %arg0
  %res2 = bitcast <4 x i32> %res1 to <2 x i64>
  ret <2 x i64> %res2
}

define <2 x i64> @test_mm_maskz_broadcastd_epi32(i8 %a0, <2 x i64> %a1) {
; X32-LABEL: test_mm_maskz_broadcastd_epi32:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpbroadcastd %xmm0, %xmm0 {%k1} {z}
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_maskz_broadcastd_epi32:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vpbroadcastd %xmm0, %xmm0 {%k1} {z}
; X64-NEXT:    retq
  %trn0 = trunc i8 %a0 to i4
  %arg0 = bitcast i4 %trn0 to <4 x i1>
  %arg1 = bitcast <2 x i64> %a1 to <4 x i32>
  %res0 = shufflevector <4 x i32> %arg1, <4 x i32> undef, <4 x i32> zeroinitializer
  %res1 = select <4 x i1> %arg0, <4 x i32> %res0, <4 x i32> zeroinitializer
  %res2 = bitcast <4 x i32> %res1 to <2 x i64>
  ret <2 x i64> %res2
}

define <4 x i64> @test_mm256_broadcastd_epi32(<2 x i64> %a0) {
; X32-LABEL: test_mm256_broadcastd_epi32:
; X32:       # BB#0:
; X32-NEXT:    vbroadcastss %xmm0, %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_broadcastd_epi32:
; X64:       # BB#0:
; X64-NEXT:    vbroadcastss %xmm0, %ymm0
; X64-NEXT:    retq
  %arg0 = bitcast <2 x i64> %a0 to <4 x i32>
  %res0 = shufflevector <4 x i32> %arg0, <4 x i32> undef, <8 x i32> zeroinitializer
  %res1 = bitcast <8 x i32> %res0 to <4 x i64>
  ret <4 x i64> %res1
}

define <4 x i64> @test_mm256_mask_broadcastd_epi32(<4 x i64> %a0, i8 %a1, <2 x i64> %a2) {
; X32-LABEL: test_mm256_mask_broadcastd_epi32:
; X32:       # BB#0:
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpbroadcastd %xmm1, %ymm0 {%k1}
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_mask_broadcastd_epi32:
; X64:       # BB#0:
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vpbroadcastd %xmm1, %ymm0 {%k1}
; X64-NEXT:    retq
  %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
  %arg1 = bitcast i8 %a1 to <8 x i1>
  %arg2 = bitcast <2 x i64> %a2 to <4 x i32>
  %res0 = shufflevector <4 x i32> %arg2, <4 x i32> undef, <8 x i32> zeroinitializer
  %res1 = select <8 x i1> %arg1, <8 x i32> %res0, <8 x i32> %arg0
  %res2 = bitcast <8 x i32> %res1 to <4 x i64>
  ret <4 x i64> %res2
}

define <4 x i64> @test_mm256_maskz_broadcastd_epi32(i8 %a0, <2 x i64> %a1) {
; X32-LABEL: test_mm256_maskz_broadcastd_epi32:
; X32:       # BB#0:
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpbroadcastd %xmm0, %ymm0 {%k1} {z}
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_maskz_broadcastd_epi32:
; X64:       # BB#0:
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vpbroadcastd %xmm0, %ymm0 {%k1} {z}
; X64-NEXT:    retq
  %arg0 = bitcast i8 %a0 to <8 x i1>
  %arg1 = bitcast <2 x i64> %a1 to <4 x i32>
  %res0 = shufflevector <4 x i32> %arg1, <4 x i32> undef, <8 x i32> zeroinitializer
  %res1 = select <8 x i1> %arg0, <8 x i32> %res0, <8 x i32> zeroinitializer
  %res2 = bitcast <8 x i32> %res1 to <4 x i64>
  ret <4 x i64> %res2
}

define <2 x i64> @test_mm_broadcastq_epi64(<2 x i64> %a0) {
; X32-LABEL: test_mm_broadcastq_epi64:
; X32:       # BB#0:
; X32-NEXT:    vpbroadcastq %xmm0, %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_broadcastq_epi64:
; X64:       # BB#0:
; X64-NEXT:    vpbroadcastq %xmm0, %xmm0
; X64-NEXT:    retq
  %res = shufflevector <2 x i64> %a0, <2 x i64> undef, <2 x i32> zeroinitializer
  ret <2 x i64> %res
}

define <2 x i64> @test_mm_mask_broadcastq_epi64(<2 x i64> %a0, i8 %a1, <2 x i64> %a2) {
; X32-LABEL: test_mm_mask_broadcastq_epi64:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $3, %al
; X32-NEXT:    movb %al, {{[0-9]+}}(%esp)
; X32-NEXT:    movzbl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpbroadcastq %xmm1, %xmm0 {%k1}
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_mask_broadcastq_epi64:
; X64:       # BB#0:
; X64-NEXT:    andb $3, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vpbroadcastq %xmm1, %xmm0 {%k1}
; X64-NEXT:    retq
  %trn1 = trunc i8 %a1 to i2
  %arg1 = bitcast i2 %trn1 to <2 x i1>
  %res0 = shufflevector <2 x i64> %a2, <2 x i64> undef, <2 x i32> zeroinitializer
  %res1 = select <2 x i1> %arg1, <2 x i64> %res0, <2 x i64> %a0
  ret <2 x i64> %res1
}

define <2 x i64> @test_mm_maskz_broadcastq_epi64(i8 %a0, <2 x i64> %a1) {
; X32-LABEL: test_mm_maskz_broadcastq_epi64:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $3, %al
; X32-NEXT:    movb %al, {{[0-9]+}}(%esp)
; X32-NEXT:    movzbl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpbroadcastq %xmm0, %xmm0 {%k1} {z}
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_maskz_broadcastq_epi64:
; X64:       # BB#0:
; X64-NEXT:    andb $3, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vpbroadcastq %xmm0, %xmm0 {%k1} {z}
; X64-NEXT:    retq
  %trn0 = trunc i8 %a0 to i2
  %arg0 = bitcast i2 %trn0 to <2 x i1>
  %res0 = shufflevector <2 x i64> %a1, <2 x i64> undef, <2 x i32> zeroinitializer
  %res1 = select <2 x i1> %arg0, <2 x i64> %res0, <2 x i64> zeroinitializer
  ret <2 x i64> %res1
}

define <4 x i64> @test_mm256_broadcastq_epi64(<2 x i64> %a0) {
; X32-LABEL: test_mm256_broadcastq_epi64:
; X32:       # BB#0:
; X32-NEXT:    vbroadcastsd %xmm0, %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_broadcastq_epi64:
; X64:       # BB#0:
; X64-NEXT:    vbroadcastsd %xmm0, %ymm0
; X64-NEXT:    retq
  %res = shufflevector <2 x i64> %a0, <2 x i64> undef, <4 x i32> zeroinitializer
  ret <4 x i64> %res
}

define <4 x i64> @test_mm256_mask_broadcastq_epi64(<4 x i64> %a0, i8 %a1, <2 x i64> %a2) {
; X32-LABEL: test_mm256_mask_broadcastq_epi64:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpbroadcastq %xmm1, %ymm0 {%k1}
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_mask_broadcastq_epi64:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vpbroadcastq %xmm1, %ymm0 {%k1}
; X64-NEXT:    retq
  %trn1 = trunc i8 %a1 to i4
  %arg1 = bitcast i4 %trn1 to <4 x i1>
  %res0 = shufflevector <2 x i64> %a2, <2 x i64> undef, <4 x i32> zeroinitializer
  %res1 = select <4 x i1> %arg1, <4 x i64> %res0, <4 x i64> %a0
  ret <4 x i64> %res1
}

define <4 x i64> @test_mm256_maskz_broadcastq_epi64(i8 %a0, <2 x i64> %a1) {
; X32-LABEL: test_mm256_maskz_broadcastq_epi64:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpbroadcastq %xmm0, %ymm0 {%k1} {z}
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_maskz_broadcastq_epi64:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vpbroadcastq %xmm0, %ymm0 {%k1} {z}
; X64-NEXT:    retq
  %trn0 = trunc i8 %a0 to i4
  %arg0 = bitcast i4 %trn0 to <4 x i1>
  %res0 = shufflevector <2 x i64> %a1, <2 x i64> undef, <4 x i32> zeroinitializer
  %res1 = select <4 x i1> %arg0, <4 x i64> %res0, <4 x i64> zeroinitializer
  ret <4 x i64> %res1
}

define <2 x double> @test_mm_broadcastsd_pd(<2 x double> %a0) {
; X32-LABEL: test_mm_broadcastsd_pd:
; X32:       # BB#0:
; X32-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_broadcastsd_pd:
; X64:       # BB#0:
; X64-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
; X64-NEXT:    retq
  %res = shufflevector <2 x double> %a0, <2 x double> undef, <2 x i32> zeroinitializer
  ret <2 x double> %res
}

define <2 x double> @test_mm_mask_broadcastsd_pd(<2 x double> %a0, i8 %a1, <2 x double> %a2) {
; X32-LABEL: test_mm_mask_broadcastsd_pd:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $3, %al
; X32-NEXT:    movb %al, {{[0-9]+}}(%esp)
; X32-NEXT:    movzbl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vmovddup {{.*#+}} xmm0 {%k1} = xmm1[0,0]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_mask_broadcastsd_pd:
; X64:       # BB#0:
; X64-NEXT:    andb $3, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vmovddup {{.*#+}} xmm0 {%k1} = xmm1[0,0]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a1 to i2
  %arg1 = bitcast i2 %trn1 to <2 x i1>
  %res0 = shufflevector <2 x double> %a2, <2 x double> undef, <2 x i32> zeroinitializer
  %res1 = select <2 x i1> %arg1, <2 x double> %res0, <2 x double> %a0
  ret <2 x double> %res1
}

define <2 x double> @test_mm_maskz_broadcastsd_pd(i8 %a0, <2 x double> %a1) {
; X32-LABEL: test_mm_maskz_broadcastsd_pd:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $3, %al
; X32-NEXT:    movb %al, {{[0-9]+}}(%esp)
; X32-NEXT:    movzbl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vmovddup {{.*#+}} xmm0 {%k1} {z} = xmm0[0,0]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_maskz_broadcastsd_pd:
; X64:       # BB#0:
; X64-NEXT:    andb $3, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vmovddup {{.*#+}} xmm0 {%k1} {z} = xmm0[0,0]
; X64-NEXT:    retq
  %trn0 = trunc i8 %a0 to i2
  %arg0 = bitcast i2 %trn0 to <2 x i1>
  %res0 = shufflevector <2 x double> %a1, <2 x double> undef, <2 x i32> zeroinitializer
  %res1 = select <2 x i1> %arg0, <2 x double> %res0, <2 x double> zeroinitializer
  ret <2 x double> %res1
}

define <4 x double> @test_mm256_broadcastsd_pd(<2 x double> %a0) {
; X32-LABEL: test_mm256_broadcastsd_pd:
; X32:       # BB#0:
; X32-NEXT:    vbroadcastsd %xmm0, %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_broadcastsd_pd:
; X64:       # BB#0:
; X64-NEXT:    vbroadcastsd %xmm0, %ymm0
; X64-NEXT:    retq
  %res = shufflevector <2 x double> %a0, <2 x double> undef, <4 x i32> zeroinitializer
  ret <4 x double> %res
}

define <4 x double> @test_mm256_mask_broadcastsd_pd(<4 x double> %a0, i8 %a1, <2 x double> %a2) {
; X32-LABEL: test_mm256_mask_broadcastsd_pd:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vbroadcastsd %xmm1, %ymm0 {%k1}
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_mask_broadcastsd_pd:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vbroadcastsd %xmm1, %ymm0 {%k1}
; X64-NEXT:    retq
  %trn1 = trunc i8 %a1 to i4
  %arg1 = bitcast i4 %trn1 to <4 x i1>
  %res0 = shufflevector <2 x double> %a2, <2 x double> undef, <4 x i32> zeroinitializer
  %res1 = select <4 x i1> %arg1, <4 x double> %res0, <4 x double> %a0
  ret <4 x double> %res1
}

define <4 x double> @test_mm256_maskz_broadcastsd_pd(i8 %a0, <2 x double> %a1) {
; X32-LABEL: test_mm256_maskz_broadcastsd_pd:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vbroadcastsd %xmm0, %ymm0 {%k1} {z}
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_maskz_broadcastsd_pd:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vbroadcastsd %xmm0, %ymm0 {%k1} {z}
; X64-NEXT:    retq
  %trn0 = trunc i8 %a0 to i4
  %arg0 = bitcast i4 %trn0 to <4 x i1>
  %res0 = shufflevector <2 x double> %a1, <2 x double> undef, <4 x i32> zeroinitializer
  %res1 = select <4 x i1> %arg0, <4 x double> %res0, <4 x double> zeroinitializer
  ret <4 x double> %res1
}

define <4 x float> @test_mm_broadcastss_ps(<4 x float> %a0) {
; X32-LABEL: test_mm_broadcastss_ps:
; X32:       # BB#0:
; X32-NEXT:    vbroadcastss %xmm0, %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_broadcastss_ps:
; X64:       # BB#0:
; X64-NEXT:    vbroadcastss %xmm0, %xmm0
; X64-NEXT:    retq
  %res = shufflevector <4 x float> %a0, <4 x float> undef, <4 x i32> zeroinitializer
  ret <4 x float> %res
}

define <4 x float> @test_mm_mask_broadcastss_ps(<4 x float> %a0, i8 %a1, <4 x float> %a2) {
; X32-LABEL: test_mm_mask_broadcastss_ps:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vbroadcastss %xmm1, %xmm0 {%k1}
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_mask_broadcastss_ps:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vbroadcastss %xmm1, %xmm0 {%k1}
; X64-NEXT:    retq
  %trn1 = trunc i8 %a1 to i4
  %arg1 = bitcast i4 %trn1 to <4 x i1>
  %res0 = shufflevector <4 x float> %a2, <4 x float> undef, <4 x i32> zeroinitializer
  %res1 = select <4 x i1> %arg1, <4 x float> %res0, <4 x float> %a0
  ret <4 x float> %res1
}

define <4 x float> @test_mm_maskz_broadcastss_ps(i8 %a0, <4 x float> %a1) {
; X32-LABEL: test_mm_maskz_broadcastss_ps:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vbroadcastss %xmm0, %xmm0 {%k1} {z}
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_maskz_broadcastss_ps:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vbroadcastss %xmm0, %xmm0 {%k1} {z}
; X64-NEXT:    retq
  %trn0 = trunc i8 %a0 to i4
  %arg0 = bitcast i4 %trn0 to <4 x i1>
  %res0 = shufflevector <4 x float> %a1, <4 x float> undef, <4 x i32> zeroinitializer
  %res1 = select <4 x i1> %arg0, <4 x float> %res0, <4 x float> zeroinitializer
  ret <4 x float> %res1
}

define <8 x float> @test_mm256_broadcastss_ps(<4 x float> %a0) {
; X32-LABEL: test_mm256_broadcastss_ps:
; X32:       # BB#0:
; X32-NEXT:    vbroadcastss %xmm0, %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_broadcastss_ps:
; X64:       # BB#0:
; X64-NEXT:    vbroadcastss %xmm0, %ymm0
; X64-NEXT:    retq
  %res = shufflevector <4 x float> %a0, <4 x float> undef, <8 x i32> zeroinitializer
  ret <8 x float> %res
}

define <8 x float> @test_mm256_mask_broadcastss_ps(<8 x float> %a0, i8 %a1, <4 x float> %a2) {
; X32-LABEL: test_mm256_mask_broadcastss_ps:
; X32:       # BB#0:
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vbroadcastss %xmm1, %ymm0 {%k1}
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_mask_broadcastss_ps:
; X64:       # BB#0:
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vbroadcastss %xmm1, %ymm0 {%k1}
; X64-NEXT:    retq
  %arg1 = bitcast i8 %a1 to <8 x i1>
  %res0 = shufflevector <4 x float> %a2, <4 x float> undef, <8 x i32> zeroinitializer
  %res1 = select <8 x i1> %arg1, <8 x float> %res0, <8 x float> %a0
  ret <8 x float> %res1
}

define <8 x float> @test_mm256_maskz_broadcastss_ps(i8 %a0, <4 x float> %a1) {
; X32-LABEL: test_mm256_maskz_broadcastss_ps:
; X32:       # BB#0:
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vbroadcastss %xmm0, %ymm0 {%k1} {z}
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_maskz_broadcastss_ps:
; X64:       # BB#0:
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vbroadcastss %xmm0, %ymm0 {%k1} {z}
; X64-NEXT:    retq
  %arg0 = bitcast i8 %a0 to <8 x i1>
  %res0 = shufflevector <4 x float> %a1, <4 x float> undef, <8 x i32> zeroinitializer
  %res1 = select <8 x i1> %arg0, <8 x float> %res0, <8 x float> zeroinitializer
  ret <8 x float> %res1
}

define <2 x double> @test_mm_movddup_pd(<2 x double> %a0) {
; X32-LABEL: test_mm_movddup_pd:
; X32:       # BB#0:
; X32-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_movddup_pd:
; X64:       # BB#0:
; X64-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
; X64-NEXT:    retq
  %res = shufflevector <2 x double> %a0, <2 x double> undef, <2 x i32> zeroinitializer
  ret <2 x double> %res
}

define <2 x double> @test_mm_mask_movddup_pd(<2 x double> %a0, i8 %a1, <2 x double> %a2) {
; X32-LABEL: test_mm_mask_movddup_pd:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $3, %al
; X32-NEXT:    movb %al, {{[0-9]+}}(%esp)
; X32-NEXT:    movzbl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vmovddup {{.*#+}} xmm0 {%k1} = xmm1[0,0]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_mask_movddup_pd:
; X64:       # BB#0:
; X64-NEXT:    andb $3, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vmovddup {{.*#+}} xmm0 {%k1} = xmm1[0,0]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a1 to i2
  %arg1 = bitcast i2 %trn1 to <2 x i1>
  %res0 = shufflevector <2 x double> %a2, <2 x double> undef, <2 x i32> zeroinitializer
  %res1 = select <2 x i1> %arg1, <2 x double> %res0, <2 x double> %a0
  ret <2 x double> %res1
}

define <2 x double> @test_mm_maskz_movddup_pd(i8 %a0, <2 x double> %a1) {
; X32-LABEL: test_mm_maskz_movddup_pd:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $3, %al
; X32-NEXT:    movb %al, {{[0-9]+}}(%esp)
; X32-NEXT:    movzbl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vmovddup {{.*#+}} xmm0 {%k1} {z} = xmm0[0,0]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_maskz_movddup_pd:
; X64:       # BB#0:
; X64-NEXT:    andb $3, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vmovddup {{.*#+}} xmm0 {%k1} {z} = xmm0[0,0]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a0 to i2
  %arg0 = bitcast i2 %trn1 to <2 x i1>
  %res0 = shufflevector <2 x double> %a1, <2 x double> undef, <2 x i32> zeroinitializer
  %res1 = select <2 x i1> %arg0, <2 x double> %res0, <2 x double> zeroinitializer
  ret <2 x double> %res1
}

define <4 x double> @test_mm256_movddup_pd(<4 x double> %a0) {
; X32-LABEL: test_mm256_movddup_pd:
; X32:       # BB#0:
; X32-NEXT:    vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_movddup_pd:
; X64:       # BB#0:
; X64-NEXT:    vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]
; X64-NEXT:    retq
  %res = shufflevector <4 x double> %a0, <4 x double> undef, <4 x i32> <i32 0, i32 0, i32 2, i32 2>
  ret <4 x double> %res
}

define <4 x double> @test_mm256_mask_movddup_pd(<4 x double> %a0, i8 %a1, <4 x double> %a2) {
; X32-LABEL: test_mm256_mask_movddup_pd:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vmovddup {{.*#+}} ymm0 {%k1} = ymm1[0,0,2,2]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_mask_movddup_pd:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vmovddup {{.*#+}} ymm0 {%k1} = ymm1[0,0,2,2]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a1 to i4
  %arg1 = bitcast i4 %trn1 to <4 x i1>
  %res0 = shufflevector <4 x double> %a2, <4 x double> undef, <4 x i32> <i32 0, i32 0, i32 2, i32 2>
  %res1 = select <4 x i1> %arg1, <4 x double> %res0, <4 x double> %a0
  ret <4 x double> %res1
}

define <4 x double> @test_mm256_maskz_movddup_pd(i8 %a0, <4 x double> %a1) {
; X32-LABEL: test_mm256_maskz_movddup_pd:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vmovddup {{.*#+}} ymm0 {%k1} {z} = ymm0[0,0,2,2]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_maskz_movddup_pd:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vmovddup {{.*#+}} ymm0 {%k1} {z} = ymm0[0,0,2,2]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a0 to i4
  %arg0 = bitcast i4 %trn1 to <4 x i1>
  %res0 = shufflevector <4 x double> %a1, <4 x double> undef, <4 x i32> <i32 0, i32 0, i32 2, i32 2>
  %res1 = select <4 x i1> %arg0, <4 x double> %res0, <4 x double> zeroinitializer
  ret <4 x double> %res1
}

define <4 x float> @test_mm_movehdup_ps(<4 x float> %a0) {
; X32-LABEL: test_mm_movehdup_ps:
; X32:       # BB#0:
; X32-NEXT:    vmovshdup {{.*#+}} xmm0 = xmm0[1,1,3,3]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_movehdup_ps:
; X64:       # BB#0:
; X64-NEXT:    vmovshdup {{.*#+}} xmm0 = xmm0[1,1,3,3]
; X64-NEXT:    retq
  %res = shufflevector <4 x float> %a0, <4 x float> undef, <4 x i32> <i32 1, i32 1, i32 3, i32 3>
  ret <4 x float> %res
}

define <4 x float> @test_mm_mask_movehdup_ps(<4 x float> %a0, i8 %a1, <4 x float> %a2) {
; X32-LABEL: test_mm_mask_movehdup_ps:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vmovshdup {{.*#+}} xmm0 {%k1} = xmm1[1,1,3,3]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_mask_movehdup_ps:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vmovshdup {{.*#+}} xmm0 {%k1} = xmm1[1,1,3,3]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a1 to i4
  %arg1 = bitcast i4 %trn1 to <4 x i1>
  %res0 = shufflevector <4 x float> %a2, <4 x float> undef, <4 x i32> <i32 1, i32 1, i32 3, i32 3>
  %res1 = select <4 x i1> %arg1, <4 x float> %res0, <4 x float> %a0
  ret <4 x float> %res1
}

define <4 x float> @test_mm_maskz_movehdup_ps(i8 %a0, <4 x float> %a1) {
; X32-LABEL: test_mm_maskz_movehdup_ps:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vmovshdup {{.*#+}} xmm0 {%k1} {z} = xmm0[1,1,3,3]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_maskz_movehdup_ps:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vmovshdup {{.*#+}} xmm0 {%k1} {z} = xmm0[1,1,3,3]
; X64-NEXT:    retq
  %trn0 = trunc i8 %a0 to i4
  %arg0 = bitcast i4 %trn0 to <4 x i1>
  %res0 = shufflevector <4 x float> %a1, <4 x float> undef, <4 x i32> <i32 1, i32 1, i32 3, i32 3>
  %res1 = select <4 x i1> %arg0, <4 x float> %res0, <4 x float> zeroinitializer
  ret <4 x float> %res1
}

define <8 x float> @test_mm256_movehdup_ps(<8 x float> %a0) {
; X32-LABEL: test_mm256_movehdup_ps:
; X32:       # BB#0:
; X32-NEXT:    vmovshdup {{.*#+}} ymm0 = ymm0[1,1,3,3,5,5,7,7]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_movehdup_ps:
; X64:       # BB#0:
; X64-NEXT:    vmovshdup {{.*#+}} ymm0 = ymm0[1,1,3,3,5,5,7,7]
; X64-NEXT:    retq
  %res = shufflevector <8 x float> %a0, <8 x float> undef, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 5, i32 5, i32 7, i32 7>
  ret <8 x float> %res
}

define <8 x float> @test_mm256_mask_movehdup_ps(<8 x float> %a0, i8 %a1, <8 x float> %a2) {
; X32-LABEL: test_mm256_mask_movehdup_ps:
; X32:       # BB#0:
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vmovshdup {{.*#+}} ymm0 {%k1} = ymm1[1,1,3,3,5,5,7,7]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_mask_movehdup_ps:
; X64:       # BB#0:
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vmovshdup {{.*#+}} ymm0 {%k1} = ymm1[1,1,3,3,5,5,7,7]
; X64-NEXT:    retq
  %arg1 = bitcast i8 %a1 to <8 x i1>
  %res0 = shufflevector <8 x float> %a2, <8 x float> undef, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 5, i32 5, i32 7, i32 7>
  %res1 = select <8 x i1> %arg1, <8 x float> %res0, <8 x float> %a0
  ret <8 x float> %res1
}

define <8 x float> @test_mm256_maskz_movehdup_ps(i8 %a0, <8 x float> %a1) {
; X32-LABEL: test_mm256_maskz_movehdup_ps:
; X32:       # BB#0:
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vmovshdup {{.*#+}} ymm0 {%k1} {z} = ymm0[1,1,3,3,5,5,7,7]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_maskz_movehdup_ps:
; X64:       # BB#0:
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vmovshdup {{.*#+}} ymm0 {%k1} {z} = ymm0[1,1,3,3,5,5,7,7]
; X64-NEXT:    retq
  %arg0 = bitcast i8 %a0 to <8 x i1>
  %res0 = shufflevector <8 x float> %a1, <8 x float> undef, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 5, i32 5, i32 7, i32 7>
  %res1 = select <8 x i1> %arg0, <8 x float> %res0, <8 x float> zeroinitializer
  ret <8 x float> %res1
}

define <4 x float> @test_mm_moveldup_ps(<4 x float> %a0) {
; X32-LABEL: test_mm_moveldup_ps:
; X32:       # BB#0:
; X32-NEXT:    vmovsldup {{.*#+}} xmm0 = xmm0[0,0,2,2]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_moveldup_ps:
; X64:       # BB#0:
; X64-NEXT:    vmovsldup {{.*#+}} xmm0 = xmm0[0,0,2,2]
; X64-NEXT:    retq
  %res = shufflevector <4 x float> %a0, <4 x float> undef, <4 x i32> <i32 0, i32 0, i32 2, i32 2>
  ret <4 x float> %res
}

define <4 x float> @test_mm_mask_moveldup_ps(<4 x float> %a0, i8 %a1, <4 x float> %a2) {
; X32-LABEL: test_mm_mask_moveldup_ps:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vmovsldup {{.*#+}} xmm0 {%k1} = xmm1[0,0,2,2]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_mask_moveldup_ps:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vmovsldup {{.*#+}} xmm0 {%k1} = xmm1[0,0,2,2]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a1 to i4
  %arg1 = bitcast i4 %trn1 to <4 x i1>
  %res0 = shufflevector <4 x float> %a2, <4 x float> undef, <4 x i32> <i32 0, i32 0, i32 2, i32 2>
  %res1 = select <4 x i1> %arg1, <4 x float> %res0, <4 x float> %a0
  ret <4 x float> %res1
}

define <4 x float> @test_mm_maskz_moveldup_ps(i8 %a0, <4 x float> %a1) {
; X32-LABEL: test_mm_maskz_moveldup_ps:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vmovsldup {{.*#+}} xmm0 {%k1} {z} = xmm0[0,0,2,2]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_maskz_moveldup_ps:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vmovsldup {{.*#+}} xmm0 {%k1} {z} = xmm0[0,0,2,2]
; X64-NEXT:    retq
  %trn0 = trunc i8 %a0 to i4
  %arg0 = bitcast i4 %trn0 to <4 x i1>
  %res0 = shufflevector <4 x float> %a1, <4 x float> undef, <4 x i32> <i32 0, i32 0, i32 2, i32 2>
  %res1 = select <4 x i1> %arg0, <4 x float> %res0, <4 x float> zeroinitializer
  ret <4 x float> %res1
}

define <8 x float> @test_mm256_moveldup_ps(<8 x float> %a0) {
; X32-LABEL: test_mm256_moveldup_ps:
; X32:       # BB#0:
; X32-NEXT:    vmovsldup {{.*#+}} ymm0 = ymm0[0,0,2,2,4,4,6,6]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_moveldup_ps:
; X64:       # BB#0:
; X64-NEXT:    vmovsldup {{.*#+}} ymm0 = ymm0[0,0,2,2,4,4,6,6]
; X64-NEXT:    retq
  %res = shufflevector <8 x float> %a0, <8 x float> undef, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
  ret <8 x float> %res
}

define <8 x float> @test_mm256_mask_moveldup_ps(<8 x float> %a0, i8 %a1, <8 x float> %a2) {
; X32-LABEL: test_mm256_mask_moveldup_ps:
; X32:       # BB#0:
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vmovsldup {{.*#+}} ymm0 {%k1} = ymm1[0,0,2,2,4,4,6,6]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_mask_moveldup_ps:
; X64:       # BB#0:
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vmovsldup {{.*#+}} ymm0 {%k1} = ymm1[0,0,2,2,4,4,6,6]
; X64-NEXT:    retq
  %arg1 = bitcast i8 %a1 to <8 x i1>
  %res0 = shufflevector <8 x float> %a2, <8 x float> undef, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
  %res1 = select <8 x i1> %arg1, <8 x float> %res0, <8 x float> %a0
  ret <8 x float> %res1
}

define <8 x float> @test_mm256_maskz_moveldup_ps(i8 %a0, <8 x float> %a1) {
; X32-LABEL: test_mm256_maskz_moveldup_ps:
; X32:       # BB#0:
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vmovsldup {{.*#+}} ymm0 {%k1} {z} = ymm0[0,0,2,2,4,4,6,6]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_maskz_moveldup_ps:
; X64:       # BB#0:
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vmovsldup {{.*#+}} ymm0 {%k1} {z} = ymm0[0,0,2,2,4,4,6,6]
; X64-NEXT:    retq
  %arg0 = bitcast i8 %a0 to <8 x i1>
  %res0 = shufflevector <8 x float> %a1, <8 x float> undef, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
  %res1 = select <8 x i1> %arg0, <8 x float> %res0, <8 x float> zeroinitializer
  ret <8 x float> %res1
}

define <4 x i64> @test_mm256_permutex_epi64(<4 x i64> %a0) {
; X32-LABEL: test_mm256_permutex_epi64:
; X32:       # BB#0:
; X32-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[3,0,0,0]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_permutex_epi64:
; X64:       # BB#0:
; X64-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[3,0,0,0]
; X64-NEXT:    retq
  %res = shufflevector <4 x i64> %a0, <4 x i64> undef, <4 x i32> <i32 3, i32 0, i32 0, i32 0>
  ret <4 x i64> %res
}

define <4 x i64> @test_mm256_mask_permutex_epi64(<4 x i64> %a0, i8 %a1, <4 x i64> %a2) {
; X32-LABEL: test_mm256_mask_permutex_epi64:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpermq {{.*#+}} ymm0 {%k1} = ymm1[1,0,0,0]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_mask_permutex_epi64:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vpermq {{.*#+}} ymm0 {%k1} = ymm1[1,0,0,0]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a1 to i4
  %arg1 = bitcast i4 %trn1 to <4 x i1>
  %res0 = shufflevector <4 x i64> %a2, <4 x i64> undef, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
  %res1 = select <4 x i1> %arg1, <4 x i64> %res0, <4 x i64> %a0
  ret <4 x i64> %res1
}

define <4 x i64> @test_mm256_maskz_permutex_epi64(i8 %a0, <4 x i64> %a1) {
; X32-LABEL: test_mm256_maskz_permutex_epi64:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpermq {{.*#+}} ymm0 {%k1} {z} = ymm0[1,0,0,0]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_maskz_permutex_epi64:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vpermq {{.*#+}} ymm0 {%k1} {z} = ymm0[1,0,0,0]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a0 to i4
  %arg0 = bitcast i4 %trn1 to <4 x i1>
  %res0 = shufflevector <4 x i64> %a1, <4 x i64> undef, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
  %res1 = select <4 x i1> %arg0, <4 x i64> %res0, <4 x i64> zeroinitializer
  ret <4 x i64> %res1
}

define <4 x double> @test_mm256_permutex_pd(<4 x double> %a0) {
; X32-LABEL: test_mm256_permutex_pd:
; X32:       # BB#0:
; X32-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[3,0,0,0]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_permutex_pd:
; X64:       # BB#0:
; X64-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[3,0,0,0]
; X64-NEXT:    retq
  %res = shufflevector <4 x double> %a0, <4 x double> undef, <4 x i32> <i32 3, i32 0, i32 0, i32 0>
  ret <4 x double> %res
}

define <4 x double> @test_mm256_mask_permutex_pd(<4 x double> %a0, i8 %a1, <4 x double> %a2) {
; X32-LABEL: test_mm256_mask_permutex_pd:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpermpd {{.*#+}} ymm0 {%k1} = ymm1[1,0,0,0]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_mask_permutex_pd:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vpermpd {{.*#+}} ymm0 {%k1} = ymm1[1,0,0,0]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a1 to i4
  %arg1 = bitcast i4 %trn1 to <4 x i1>
  %res0 = shufflevector <4 x double> %a2, <4 x double> undef, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
  %res1 = select <4 x i1> %arg1, <4 x double> %res0, <4 x double> %a0
  ret <4 x double> %res1
}

define <4 x double> @test_mm256_maskz_permutex_pd(i8 %a0, <4 x double> %a1) {
; X32-LABEL: test_mm256_maskz_permutex_pd:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vpermpd {{.*#+}} ymm0 {%k1} {z} = ymm0[1,0,0,0]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_maskz_permutex_pd:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vpermpd {{.*#+}} ymm0 {%k1} {z} = ymm0[1,0,0,0]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a0 to i4
  %arg0 = bitcast i4 %trn1 to <4 x i1>
  %res0 = shufflevector <4 x double> %a1, <4 x double> undef, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
  %res1 = select <4 x i1> %arg0, <4 x double> %res0, <4 x double> zeroinitializer
  ret <4 x double> %res1
}

define <2 x double> @test_mm_shuffle_pd(<2 x double> %a0, <2 x double> %a1) {
; X32-LABEL: test_mm_shuffle_pd:
; X32:       # BB#0:
; X32-NEXT:    vunpckhpd {{.*#+}} xmm0 = xmm0[1],xmm1[1]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_shuffle_pd:
; X64:       # BB#0:
; X64-NEXT:    vunpckhpd {{.*#+}} xmm0 = xmm0[1],xmm1[1]
; X64-NEXT:    retq
  %res = shufflevector <2 x double> %a0, <2 x double> %a1, <2 x i32> <i32 1, i32 3>
  ret <2 x double> %res
}

define <2 x double> @test_mm_mask_shuffle_pd(<2 x double> %a0, i8 %a1, <2 x double> %a2, <2 x double> %a3) {
; X32-LABEL: test_mm_mask_shuffle_pd:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $3, %al
; X32-NEXT:    movb %al, {{[0-9]+}}(%esp)
; X32-NEXT:    movzbl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vunpckhpd {{.*#+}} xmm0 {%k1} = xmm1[1],xmm2[1]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_mask_shuffle_pd:
; X64:       # BB#0:
; X64-NEXT:    andb $3, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vunpckhpd {{.*#+}} xmm0 {%k1} = xmm1[1],xmm2[1]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a1 to i2
  %arg1 = bitcast i2 %trn1 to <2 x i1>
  %res0 = shufflevector <2 x double> %a2, <2 x double> %a3, <2 x i32> <i32 1, i32 3>
  %res1 = select <2 x i1> %arg1, <2 x double> %res0, <2 x double> %a0
  ret <2 x double> %res1
}

define <2 x double> @test_mm_maskz_shuffle_pd(i8 %a0, <2 x double> %a1, <2 x double> %a2) {
; X32-LABEL: test_mm_maskz_shuffle_pd:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $3, %al
; X32-NEXT:    movb %al, {{[0-9]+}}(%esp)
; X32-NEXT:    movzbl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vunpckhpd {{.*#+}} xmm0 {%k1} {z} = xmm0[1],xmm1[1]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_maskz_shuffle_pd:
; X64:       # BB#0:
; X64-NEXT:    andb $3, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vunpckhpd {{.*#+}} xmm0 {%k1} {z} = xmm0[1],xmm1[1]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a0 to i2
  %arg0 = bitcast i2 %trn1 to <2 x i1>
  %res0 = shufflevector <2 x double> %a1, <2 x double> %a2, <2 x i32> <i32 1, i32 3>
  %res1 = select <2 x i1> %arg0, <2 x double> %res0, <2 x double> zeroinitializer
  ret <2 x double> %res1
}

define <4 x double> @test_mm256_shuffle_pd(<4 x double> %a0, <4 x double> %a1) {
; X32-LABEL: test_mm256_shuffle_pd:
; X32:       # BB#0:
; X32-NEXT:    vshufpd {{.*#+}} ymm0 = ymm0[1],ymm1[1],ymm0[2],ymm1[2]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_shuffle_pd:
; X64:       # BB#0:
; X64-NEXT:    vshufpd {{.*#+}} ymm0 = ymm0[1],ymm1[1],ymm0[2],ymm1[2]
; X64-NEXT:    retq
  %res = shufflevector <4 x double> %a0, <4 x double> %a1, <4 x i32> <i32 1, i32 5, i32 2, i32 6>
  ret <4 x double> %res
}

define <4 x double> @test_mm256_mask_shuffle_pd(<4 x double> %a0, i8 %a1, <4 x double> %a2, <4 x double> %a3) {
; X32-LABEL: test_mm256_mask_shuffle_pd:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vshufpd {{.*#+}} ymm0 {%k1} = ymm1[1],ymm2[1],ymm1[2],ymm2[2]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_mask_shuffle_pd:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vshufpd {{.*#+}} ymm0 {%k1} = ymm1[1],ymm2[1],ymm1[2],ymm2[2]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a1 to i4
  %arg1 = bitcast i4 %trn1 to <4 x i1>
  %res0 = shufflevector <4 x double> %a2, <4 x double> %a3, <4 x i32> <i32 1, i32 5, i32 2, i32 6>
  %res1 = select <4 x i1> %arg1, <4 x double> %res0, <4 x double> %a0
  ret <4 x double> %res1
}

define <4 x double> @test_mm256_maskz_shuffle_pd(i8 %a0, <4 x double> %a1, <4 x double> %a2) {
; X32-LABEL: test_mm256_maskz_shuffle_pd:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vshufpd {{.*#+}} ymm0 {%k1} {z} = ymm0[1],ymm1[1],ymm0[2],ymm1[2]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_maskz_shuffle_pd:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vshufpd {{.*#+}} ymm0 {%k1} {z} = ymm0[1],ymm1[1],ymm0[2],ymm1[2]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a0 to i4
  %arg0 = bitcast i4 %trn1 to <4 x i1>
  %res0 = shufflevector <4 x double> %a1, <4 x double> %a2, <4 x i32> <i32 1, i32 5, i32 2, i32 6>
  %res1 = select <4 x i1> %arg0, <4 x double> %res0, <4 x double> zeroinitializer
  ret <4 x double> %res1
}

define <4 x float> @test_mm_shuffle_ps(<4 x float> %a0, <4 x float> %a1) {
; X32-LABEL: test_mm_shuffle_ps:
; X32:       # BB#0:
; X32-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,0]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_shuffle_ps:
; X64:       # BB#0:
; X64-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,0]
; X64-NEXT:    retq
  %res = shufflevector <4 x float> %a0, <4 x float> %a1, <4 x i32> <i32 0, i32 1, i32 4, i32 4>
  ret <4 x float> %res
}

define <4 x float> @test_mm_mask_shuffle_ps(<4 x float> %a0, i8 %a1, <4 x float> %a2, <4 x float> %a3) {
; X32-LABEL: test_mm_mask_shuffle_ps:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vshufps {{.*#+}} xmm0 {%k1} = xmm1[0,1],xmm2[0,0]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_mask_shuffle_ps:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vshufps {{.*#+}} xmm0 {%k1} = xmm1[0,1],xmm2[0,0]
; X64-NEXT:    retq
  %trn1 = trunc i8 %a1 to i4
  %arg1 = bitcast i4 %trn1 to <4 x i1>
  %res0 = shufflevector <4 x float> %a2, <4 x float> %a3, <4 x i32> <i32 0, i32 1, i32 4, i32 4>
  %res1 = select <4 x i1> %arg1, <4 x float> %res0, <4 x float> %a0
  ret <4 x float> %res1
}

define <4 x float> @test_mm_maskz_shuffle_ps(i8 %a0, <4 x float> %a1, <4 x float> %a2) {
; X32-LABEL: test_mm_maskz_shuffle_ps:
; X32:       # BB#0:
; X32-NEXT:    pushl %eax
; X32-NEXT:    .cfi_def_cfa_offset 8
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    andb $15, %al
; X32-NEXT:    movb %al, (%esp)
; X32-NEXT:    movzbl (%esp), %eax
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vshufps {{.*#+}} xmm0 {%k1} {z} = xmm0[0,1],xmm1[0,0]
; X32-NEXT:    popl %eax
; X32-NEXT:    retl
;
; X64-LABEL: test_mm_maskz_shuffle_ps:
; X64:       # BB#0:
; X64-NEXT:    andb $15, %dil
; X64-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
; X64-NEXT:    movzbl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT:    kmovw %eax, %k1
; X64-NEXT:    vshufps {{.*#+}} xmm0 {%k1} {z} = xmm0[0,1],xmm1[0,0]
; X64-NEXT:    retq
  %trn0 = trunc i8 %a0 to i4
  %arg0 = bitcast i4 %trn0 to <4 x i1>
  %res0 = shufflevector <4 x float> %a1, <4 x float> %a2, <4 x i32> <i32 0, i32 1, i32 4, i32 4>
  %res1 = select <4 x i1> %arg0, <4 x float> %res0, <4 x float> zeroinitializer
  ret <4 x float> %res1
}

define <8 x float> @test_mm256_shuffle_ps(<8 x float> %a0, <8 x float> %a1) {
; X32-LABEL: test_mm256_shuffle_ps:
; X32:       # BB#0:
; X32-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,1],ymm1[0,0],ymm0[4,5],ymm1[4,4]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_shuffle_ps:
; X64:       # BB#0:
; X64-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,1],ymm1[0,0],ymm0[4,5],ymm1[4,4]
; X64-NEXT:    retq
  %res = shufflevector <8 x float> %a0, <8 x float> %a1, <8 x i32> <i32 0, i32 1, i32 8, i32 8, i32 4, i32 5, i32 12, i32 12>
  ret <8 x float> %res
}

define <8 x float> @test_mm256_mask_shuffle_ps(<8 x float> %a0, i8 %a1, <8 x float> %a2, <8 x float> %a3) {
; X32-LABEL: test_mm256_mask_shuffle_ps:
; X32:       # BB#0:
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vshufps {{.*#+}} ymm0 {%k1} = ymm1[0,1],ymm2[0,0],ymm1[4,5],ymm2[4,4]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_mask_shuffle_ps:
; X64:       # BB#0:
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vshufps {{.*#+}} ymm0 {%k1} = ymm1[0,1],ymm2[0,0],ymm1[4,5],ymm2[4,4]
; X64-NEXT:    retq
  %arg1 = bitcast i8 %a1 to <8 x i1>
  %res0 = shufflevector <8 x float> %a2, <8 x float> %a3, <8 x i32> <i32 0, i32 1, i32 8, i32 8, i32 4, i32 5, i32 12, i32 12>
  %res1 = select <8 x i1> %arg1, <8 x float> %res0, <8 x float> %a0
  ret <8 x float> %res1
}

define <8 x float> @test_mm256_maskz_shuffle_ps(i8 %a0, <8 x float> %a1, <8 x float> %a2) {
; X32-LABEL: test_mm256_maskz_shuffle_ps:
; X32:       # BB#0:
; X32-NEXT:    movb {{[0-9]+}}(%esp), %al
; X32-NEXT:    kmovw %eax, %k1
; X32-NEXT:    vshufps {{.*#+}} ymm0 {%k1} {z} = ymm0[0,1],ymm1[0,0],ymm0[4,5],ymm1[4,4]
; X32-NEXT:    retl
;
; X64-LABEL: test_mm256_maskz_shuffle_ps:
; X64:       # BB#0:
; X64-NEXT:    kmovw %edi, %k1
; X64-NEXT:    vshufps {{.*#+}} ymm0 {%k1} {z} = ymm0[0,1],ymm1[0,0],ymm0[4,5],ymm1[4,4]
; X64-NEXT:    retq
  %arg0 = bitcast i8 %a0 to <8 x i1>
  %res0 = shufflevector <8 x float> %a1, <8 x float> %a2, <8 x i32> <i32 0, i32 1, i32 8, i32 8, i32 4, i32 5, i32 12, i32 12>
  %res1 = select <8 x i1> %arg0, <8 x float> %res0, <8 x float> zeroinitializer
  ret <8 x float> %res1
}

!0 = !{i32 1}