llvm-project/llvm/test/CodeGen/X86/avx2-vbroadcast.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-apple-darwin -mattr=+avx2 | FileCheck %s --check-prefix=CHECK --check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx2 | FileCheck %s --check-prefix=CHECK --check-prefix=X64

define <16 x i8> @BB16(i8* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: BB16:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vpbroadcastb (%eax), %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: BB16:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vpbroadcastb (%rdi), %xmm0
; X64-NEXT:    retq
entry:
  %q = load i8, i8* %ptr, align 4
  %q0 = insertelement <16 x i8> undef, i8 %q, i32 0
  %q1 = insertelement <16 x i8> %q0, i8 %q, i32 1
  %q2 = insertelement <16 x i8> %q1, i8 %q, i32 2
  %q3 = insertelement <16 x i8> %q2, i8 %q, i32 3
  %q4 = insertelement <16 x i8> %q3, i8 %q, i32 4
  %q5 = insertelement <16 x i8> %q4, i8 %q, i32 5
  %q6 = insertelement <16 x i8> %q5, i8 %q, i32 6
  %q7 = insertelement <16 x i8> %q6, i8 %q, i32 7
  %q8 = insertelement <16 x i8> %q7, i8 %q, i32 8
  %q9 = insertelement <16 x i8> %q8, i8 %q, i32 9
  %qa = insertelement <16 x i8> %q9, i8 %q, i32 10
  %qb = insertelement <16 x i8> %qa, i8 %q, i32 11
  %qc = insertelement <16 x i8> %qb, i8 %q, i32 12
  %qd = insertelement <16 x i8> %qc, i8 %q, i32 13
  %qe = insertelement <16 x i8> %qd, i8 %q, i32 14
  %qf = insertelement <16 x i8> %qe, i8 %q, i32 15
  ret <16 x i8> %qf
}

define <32 x i8> @BB32(i8* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: BB32:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vpbroadcastb (%eax), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: BB32:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vpbroadcastb (%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %q = load i8, i8* %ptr, align 4
  %q0 = insertelement <32 x i8> undef, i8 %q, i32 0
  %q1 = insertelement <32 x i8> %q0, i8 %q, i32 1
  %q2 = insertelement <32 x i8> %q1, i8 %q, i32 2
  %q3 = insertelement <32 x i8> %q2, i8 %q, i32 3
  %q4 = insertelement <32 x i8> %q3, i8 %q, i32 4
  %q5 = insertelement <32 x i8> %q4, i8 %q, i32 5
  %q6 = insertelement <32 x i8> %q5, i8 %q, i32 6
  %q7 = insertelement <32 x i8> %q6, i8 %q, i32 7
  %q8 = insertelement <32 x i8> %q7, i8 %q, i32 8
  %q9 = insertelement <32 x i8> %q8, i8 %q, i32 9
  %qa = insertelement <32 x i8> %q9, i8 %q, i32 10
  %qb = insertelement <32 x i8> %qa, i8 %q, i32 11
  %qc = insertelement <32 x i8> %qb, i8 %q, i32 12
  %qd = insertelement <32 x i8> %qc, i8 %q, i32 13
  %qe = insertelement <32 x i8> %qd, i8 %q, i32 14
  %qf = insertelement <32 x i8> %qe, i8 %q, i32 15

  %q20 = insertelement <32 x i8> %qf, i8 %q,  i32 16
  %q21 = insertelement <32 x i8> %q20, i8 %q, i32 17
  %q22 = insertelement <32 x i8> %q21, i8 %q, i32 18
  %q23 = insertelement <32 x i8> %q22, i8 %q, i32 19
  %q24 = insertelement <32 x i8> %q23, i8 %q, i32 20
  %q25 = insertelement <32 x i8> %q24, i8 %q, i32 21
  %q26 = insertelement <32 x i8> %q25, i8 %q, i32 22
  %q27 = insertelement <32 x i8> %q26, i8 %q, i32 23
  %q28 = insertelement <32 x i8> %q27, i8 %q, i32 24
  %q29 = insertelement <32 x i8> %q28, i8 %q, i32 25
  %q2a = insertelement <32 x i8> %q29, i8 %q, i32 26
  %q2b = insertelement <32 x i8> %q2a, i8 %q, i32 27
  %q2c = insertelement <32 x i8> %q2b, i8 %q, i32 28
  %q2d = insertelement <32 x i8> %q2c, i8 %q, i32 29
  %q2e = insertelement <32 x i8> %q2d, i8 %q, i32 30
  %q2f = insertelement <32 x i8> %q2e, i8 %q, i32 31
  ret <32 x i8> %q2f
}

define <8 x i16> @W16(i16* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: W16:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vpbroadcastw (%eax), %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: W16:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vpbroadcastw (%rdi), %xmm0
; X64-NEXT:    retq
entry:
  %q = load i16, i16* %ptr, align 4
  %q0 = insertelement <8 x i16> undef, i16 %q, i32 0
  %q1 = insertelement <8 x i16> %q0, i16 %q, i32 1
  %q2 = insertelement <8 x i16> %q1, i16 %q, i32 2
  %q3 = insertelement <8 x i16> %q2, i16 %q, i32 3
  %q4 = insertelement <8 x i16> %q3, i16 %q, i32 4
  %q5 = insertelement <8 x i16> %q4, i16 %q, i32 5
  %q6 = insertelement <8 x i16> %q5, i16 %q, i32 6
  %q7 = insertelement <8 x i16> %q6, i16 %q, i32 7
  ret <8 x i16> %q7
}

define <16 x i16> @WW16(i16* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: WW16:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vpbroadcastw (%eax), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: WW16:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vpbroadcastw (%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %q = load i16, i16* %ptr, align 4
  %q0 = insertelement <16 x i16> undef, i16 %q, i32 0
  %q1 = insertelement <16 x i16> %q0, i16 %q, i32 1
  %q2 = insertelement <16 x i16> %q1, i16 %q, i32 2
  %q3 = insertelement <16 x i16> %q2, i16 %q, i32 3
  %q4 = insertelement <16 x i16> %q3, i16 %q, i32 4
  %q5 = insertelement <16 x i16> %q4, i16 %q, i32 5
  %q6 = insertelement <16 x i16> %q5, i16 %q, i32 6
  %q7 = insertelement <16 x i16> %q6, i16 %q, i32 7
  %q8 = insertelement <16 x i16> %q7, i16 %q, i32 8
  %q9 = insertelement <16 x i16> %q8, i16 %q, i32 9
  %qa = insertelement <16 x i16> %q9, i16 %q, i32 10
  %qb = insertelement <16 x i16> %qa, i16 %q, i32 11
  %qc = insertelement <16 x i16> %qb, i16 %q, i32 12
  %qd = insertelement <16 x i16> %qc, i16 %q, i32 13
  %qe = insertelement <16 x i16> %qd, i16 %q, i32 14
  %qf = insertelement <16 x i16> %qe, i16 %q, i32 15
  ret <16 x i16> %qf
}

define <4 x i32> @D32(i32* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: D32:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vbroadcastss (%eax), %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: D32:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vbroadcastss (%rdi), %xmm0
; X64-NEXT:    retq
entry:
  %q = load i32, i32* %ptr, align 4
  %q0 = insertelement <4 x i32> undef, i32 %q, i32 0
  %q1 = insertelement <4 x i32> %q0, i32 %q, i32 1
  %q2 = insertelement <4 x i32> %q1, i32 %q, i32 2
  %q3 = insertelement <4 x i32> %q2, i32 %q, i32 3
  ret <4 x i32> %q3
}

define <8 x i32> @DD32(i32* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: DD32:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vbroadcastss (%eax), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: DD32:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vbroadcastss (%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %q = load i32, i32* %ptr, align 4
  %q0 = insertelement <8 x i32> undef, i32 %q, i32 0
  %q1 = insertelement <8 x i32> %q0, i32 %q, i32 1
  %q2 = insertelement <8 x i32> %q1, i32 %q, i32 2
  %q3 = insertelement <8 x i32> %q2, i32 %q, i32 3
  %q4 = insertelement <8 x i32> %q3, i32 %q, i32 4
  %q5 = insertelement <8 x i32> %q4, i32 %q, i32 5
  %q6 = insertelement <8 x i32> %q5, i32 %q, i32 6
  %q7 = insertelement <8 x i32> %q6, i32 %q, i32 7
  ret <8 x i32> %q7
}

define <2 x i64> @Q64(i64* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: Q64:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    movl (%eax), %ecx
; X32-NEXT:    movl 4(%eax), %eax
; 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:    retl
;
; X64-LABEL: Q64:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vpbroadcastq (%rdi), %xmm0
; X64-NEXT:    retq
entry:
  %q = load i64, i64* %ptr, align 4
  %q0 = insertelement <2 x i64> undef, i64 %q, i32 0
  %q1 = insertelement <2 x i64> %q0, i64 %q, i32 1
  ret <2 x i64> %q1
}

define <4 x i64> @QQ64(i64* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: QQ64:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    movl (%eax), %ecx
; X32-NEXT:    movl 4(%eax), %eax
; 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:    retl
;
; X64-LABEL: QQ64:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vbroadcastsd (%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %q = load i64, i64* %ptr, align 4
  %q0 = insertelement <4 x i64> undef, i64 %q, i32 0
  %q1 = insertelement <4 x i64> %q0, i64 %q, i32 1
  %q2 = insertelement <4 x i64> %q1, i64 %q, i32 2
  %q3 = insertelement <4 x i64> %q2, i64 %q, i32 3
  ret <4 x i64> %q3
}

define <8 x i16> @broadcast_mem_v4i16_v8i16(<4 x i16>* %ptr) {
; X32-LABEL: broadcast_mem_v4i16_v8i16:
; X32:       ## BB#0:
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; X32-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
; X32-NEXT:    retl
;
; X64-LABEL: broadcast_mem_v4i16_v8i16:
; X64:       ## BB#0:
; X64-NEXT:    vpbroadcastq (%rdi), %xmm0
; X64-NEXT:    retq
  %load = load <4 x i16>, <4 x i16>* %ptr
  %shuf = shufflevector <4 x i16> %load, <4 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
  ret <8 x i16> %shuf
}

define <16 x i16> @broadcast_mem_v4i16_v16i16(<4 x i16>* %ptr) {
; X32-LABEL: broadcast_mem_v4i16_v16i16:
; X32:       ## BB#0:
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vpmovzxwd {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; X32-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; X32-NEXT:    vpbroadcastq %xmm0, %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: broadcast_mem_v4i16_v16i16:
; X64:       ## BB#0:
; X64-NEXT:    vpmovzxwd {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; X64-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; X64-NEXT:    vpbroadcastq %xmm0, %ymm0
; X64-NEXT:    retq
  %load = load <4 x i16>, <4 x i16>* %ptr
  %shuf = shufflevector <4 x i16> %load, <4 x i16> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
  ret <16 x i16> %shuf
}

; FIXME: Pointer adjusted broadcasts

define <16 x i8> @load_splat_16i8_16i8_1111111111111111(<16 x i8>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_16i8_16i8_1111111111111111:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vpbroadcastb 1(%eax), %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_16i8_16i8_1111111111111111:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vpbroadcastb 1(%rdi), %xmm0
; X64-NEXT:    retq
entry:
  %ld = load <16 x i8>, <16 x i8>* %ptr
  %ret = shufflevector <16 x i8> %ld, <16 x i8> undef, <16 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
  ret <16 x i8> %ret
}

define <32 x i8> @load_splat_32i8_16i8_11111111111111111111111111111111(<16 x i8>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_32i8_16i8_11111111111111111111111111111111:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vpbroadcastb 1(%eax), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_32i8_16i8_11111111111111111111111111111111:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vpbroadcastb 1(%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %ld = load <16 x i8>, <16 x i8>* %ptr
  %ret = shufflevector <16 x i8> %ld, <16 x i8> undef, <32 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
  ret <32 x i8> %ret
}

define <32 x i8> @load_splat_32i8_32i8_11111111111111111111111111111111(<32 x i8>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_32i8_32i8_11111111111111111111111111111111:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vpbroadcastb 1(%eax), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_32i8_32i8_11111111111111111111111111111111:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vpbroadcastb 1(%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %ld = load <32 x i8>, <32 x i8>* %ptr
  %ret = shufflevector <32 x i8> %ld, <32 x i8> undef, <32 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
  ret <32 x i8> %ret
}

define <8 x i16> @load_splat_8i16_8i16_11111111(<8 x i16>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_8i16_8i16_11111111:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vpbroadcastw 2(%eax), %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_8i16_8i16_11111111:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vpbroadcastw 2(%rdi), %xmm0
; X64-NEXT:    retq
entry:
  %ld = load <8 x i16>, <8 x i16>* %ptr
  %ret = shufflevector <8 x i16> %ld, <8 x i16> undef, <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
  ret <8 x i16> %ret
}

define <16 x i16> @load_splat_16i16_8i16_1111111111111111(<8 x i16>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_16i16_8i16_1111111111111111:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vpbroadcastw 2(%eax), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_16i16_8i16_1111111111111111:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vpbroadcastw 2(%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %ld = load <8 x i16>, <8 x i16>* %ptr
  %ret = shufflevector <8 x i16> %ld, <8 x i16> undef, <16 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
  ret <16 x i16> %ret
}

define <16 x i16> @load_splat_16i16_16i16_1111111111111111(<16 x i16>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_16i16_16i16_1111111111111111:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vpbroadcastw 2(%eax), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_16i16_16i16_1111111111111111:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vpbroadcastw 2(%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %ld = load <16 x i16>, <16 x i16>* %ptr
  %ret = shufflevector <16 x i16> %ld, <16 x i16> undef, <16 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
  ret <16 x i16> %ret
}

define <4 x i32> @load_splat_4i32_4i32_1111(<4 x i32>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_4i32_4i32_1111:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vbroadcastss 4(%eax), %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_4i32_4i32_1111:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vbroadcastss 4(%rdi), %xmm0
; X64-NEXT:    retq
entry:
  %ld = load <4 x i32>, <4 x i32>* %ptr
  %ret = shufflevector <4 x i32> %ld, <4 x i32> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
  ret <4 x i32> %ret
}

define <8 x i32> @load_splat_8i32_4i32_33333333(<4 x i32>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_8i32_4i32_33333333:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vbroadcastss 12(%eax), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_8i32_4i32_33333333:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vbroadcastss 12(%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %ld = load <4 x i32>, <4 x i32>* %ptr
  %ret = shufflevector <4 x i32> %ld, <4 x i32> undef, <8 x i32> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3>
  ret <8 x i32> %ret
}

define <8 x i32> @load_splat_8i32_8i32_55555555(<8 x i32>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_8i32_8i32_55555555:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vbroadcastss 20(%eax), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_8i32_8i32_55555555:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vbroadcastss 20(%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %ld = load <8 x i32>, <8 x i32>* %ptr
  %ret = shufflevector <8 x i32> %ld, <8 x i32> undef, <8 x i32> <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
  ret <8 x i32> %ret
}

define <4 x float> @load_splat_4f32_4f32_1111(<4 x float>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_4f32_4f32_1111:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vbroadcastss 4(%eax), %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_4f32_4f32_1111:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vbroadcastss 4(%rdi), %xmm0
; X64-NEXT:    retq
entry:
  %ld = load <4 x float>, <4 x float>* %ptr
  %ret = shufflevector <4 x float> %ld, <4 x float> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
  ret <4 x float> %ret
}

define <8 x float> @load_splat_8f32_4f32_33333333(<4 x float>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_8f32_4f32_33333333:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vbroadcastss 12(%eax), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_8f32_4f32_33333333:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vbroadcastss 12(%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %ld = load <4 x float>, <4 x float>* %ptr
  %ret = shufflevector <4 x float> %ld, <4 x float> undef, <8 x i32> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3>
  ret <8 x float> %ret
}

define <8 x float> @load_splat_8f32_8f32_55555555(<8 x float>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_8f32_8f32_55555555:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vbroadcastss 20(%eax), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_8f32_8f32_55555555:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vbroadcastss 20(%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %ld = load <8 x float>, <8 x float>* %ptr
  %ret = shufflevector <8 x float> %ld, <8 x float> undef, <8 x i32> <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
  ret <8 x float> %ret
}

define <2 x i64> @load_splat_2i64_2i64_1111(<2 x i64>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_2i64_2i64_1111:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_2i64_2i64_1111:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vpbroadcastq 8(%rdi), %xmm0
; X64-NEXT:    retq
entry:
  %ld = load <2 x i64>, <2 x i64>* %ptr
  %ret = shufflevector <2 x i64> %ld, <2 x i64> undef, <2 x i32> <i32 1, i32 1>
  ret <2 x i64> %ret
}

define <4 x i64> @load_splat_4i64_2i64_1111(<2 x i64>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_4i64_2i64_1111:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vbroadcastsd 8(%eax), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_4i64_2i64_1111:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vbroadcastsd 8(%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %ld = load <2 x i64>, <2 x i64>* %ptr
  %ret = shufflevector <2 x i64> %ld, <2 x i64> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
  ret <4 x i64> %ret
}

define <4 x i64> @load_splat_4i64_4i64_2222(<4 x i64>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_4i64_4i64_2222:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vbroadcastsd 16(%eax), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_4i64_4i64_2222:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vbroadcastsd 16(%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %ld = load <4 x i64>, <4 x i64>* %ptr
  %ret = shufflevector <4 x i64> %ld, <4 x i64> undef, <4 x i32> <i32 2, i32 2, i32 2, i32 2>
  ret <4 x i64> %ret
}

define <2 x double> @load_splat_2f64_2f64_1111(<2 x double>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_2f64_2f64_1111:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_2f64_2f64_1111:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
; X64-NEXT:    retq
entry:
  %ld = load <2 x double>, <2 x double>* %ptr
  %ret = shufflevector <2 x double> %ld, <2 x double> undef, <2 x i32> <i32 1, i32 1>
  ret <2 x double> %ret
}

define <4 x double> @load_splat_4f64_2f64_1111(<2 x double>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_4f64_2f64_1111:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vbroadcastsd 8(%eax), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_4f64_2f64_1111:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vbroadcastsd 8(%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %ld = load <2 x double>, <2 x double>* %ptr
  %ret = shufflevector <2 x double> %ld, <2 x double> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
  ret <4 x double> %ret
}

define <4 x double> @load_splat_4f64_4f64_2222(<4 x double>* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: load_splat_4f64_4f64_2222:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vbroadcastsd 16(%eax), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: load_splat_4f64_4f64_2222:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vbroadcastsd 16(%rdi), %ymm0
; X64-NEXT:    retq
entry:
  %ld = load <4 x double>, <4 x double>* %ptr
  %ret = shufflevector <4 x double> %ld, <4 x double> undef, <4 x i32> <i32 2, i32 2, i32 2, i32 2>
  ret <4 x double> %ret
}

; make sure that we still don't support broadcast double into 128-bit vector
; this used to crash
define <2 x double> @I(double* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: I:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X32-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
; X32-NEXT:    retl
;
; X64-LABEL: I:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
; X64-NEXT:    retq
entry:
  %q = load double, double* %ptr, align 4
  %vecinit.i = insertelement <2 x double> undef, double %q, i32 0
  %vecinit2.i = insertelement <2 x double> %vecinit.i, double %q, i32 1
  ret <2 x double> %vecinit2.i
}

define <8 x i32> @V111(<8 x i32> %in) nounwind uwtable readnone ssp {
; X32-LABEL: V111:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    vpbroadcastd LCPI29_0, %ymm1
; X32-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: V111:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vpbroadcastd {{.*}}(%rip), %ymm1
; X64-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; X64-NEXT:    retq
entry:
  %g = add <8 x i32> %in, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
  ret <8 x i32> %g
}

define <8 x float> @V113(<8 x float> %in) nounwind uwtable readnone ssp {
; X32-LABEL: V113:
; X32:       ## BB#0: ## %entry
; X32-NEXT:    vbroadcastss LCPI30_0, %ymm1
; X32-NEXT:    vaddps %ymm1, %ymm0, %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: V113:
; X64:       ## BB#0: ## %entry
; X64-NEXT:    vbroadcastss {{.*}}(%rip), %ymm1
; X64-NEXT:    vaddps %ymm1, %ymm0, %ymm0
; X64-NEXT:    retq
entry:
  %g = fadd <8 x float> %in, <float 0xbf80000000000000, float 0xbf80000000000000, float 0xbf80000000000000, float 0xbf80000000000000, float 0xbf80000000000000, float 0xbf80000000000000, float 0xbf80000000000000, float 0xbf80000000000000>
  ret <8 x float> %g
}

define <4 x float> @_e2(float* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: _e2:
; X32:       ## BB#0:
; X32-NEXT:    vbroadcastss LCPI31_0, %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: _e2:
; X64:       ## BB#0:
; X64-NEXT:    vbroadcastss {{.*}}(%rip), %xmm0
; X64-NEXT:    retq
  %vecinit.i = insertelement <4 x float> undef, float        0xbf80000000000000, i32 0
  %vecinit2.i = insertelement <4 x float> %vecinit.i, float  0xbf80000000000000, i32 1
  %vecinit4.i = insertelement <4 x float> %vecinit2.i, float 0xbf80000000000000, i32 2
  %vecinit6.i = insertelement <4 x float> %vecinit4.i, float 0xbf80000000000000, i32 3
  ret <4 x float> %vecinit6.i
}

define <8 x i8> @_e4(i8* %ptr) nounwind uwtable readnone ssp {
; X32-LABEL: _e4:
; X32:       ## BB#0:
; X32-NEXT:    vmovaps {{.*#+}} xmm0 = [52,52,52,52,52,52,52,52]
; X32-NEXT:    retl
;
; X64-LABEL: _e4:
; X64:       ## BB#0:
; X64-NEXT:    vmovaps {{.*#+}} xmm0 = [52,52,52,52,52,52,52,52]
; X64-NEXT:    retq
  %vecinit0.i = insertelement <8 x i8> undef, i8       52, i32 0
  %vecinit1.i = insertelement <8 x i8> %vecinit0.i, i8 52, i32 1
  %vecinit2.i = insertelement <8 x i8> %vecinit1.i, i8 52, i32 2
  %vecinit3.i = insertelement <8 x i8> %vecinit2.i, i8 52, i32 3
  %vecinit4.i = insertelement <8 x i8> %vecinit3.i, i8 52, i32 4
  %vecinit5.i = insertelement <8 x i8> %vecinit4.i, i8 52, i32 5
  %vecinit6.i = insertelement <8 x i8> %vecinit5.i, i8 52, i32 6
  %vecinit7.i = insertelement <8 x i8> %vecinit6.i, i8 52, i32 7
  ret <8 x i8> %vecinit7.i
}

define void @crash() nounwind alwaysinline {
; X32-LABEL: crash:
; X32:       ## BB#0: ## %WGLoopsEntry
; X32-NEXT:    xorl %eax, %eax
; X32-NEXT:    testb %al, %al
; X32-NEXT:    je LBB33_1
; X32-NEXT:  ## BB#2: ## %ret
; X32-NEXT:    retl
; X32-NEXT:    .p2align 4, 0x90
; X32-NEXT:  LBB33_1: ## %footer349VF
; X32-NEXT:    ## =>This Inner Loop Header: Depth=1
; X32-NEXT:    jmp LBB33_1
;
; X64-LABEL: crash:
; X64:       ## BB#0: ## %WGLoopsEntry
; X64-NEXT:    xorl %eax, %eax
; X64-NEXT:    testb %al, %al
; X64-NEXT:    je LBB33_1
; X64-NEXT:  ## BB#2: ## %ret
; X64-NEXT:    retq
; X64-NEXT:    .p2align 4, 0x90
; X64-NEXT:  LBB33_1: ## %footer349VF
; X64-NEXT:    ## =>This Inner Loop Header: Depth=1
; X64-NEXT:    jmp LBB33_1
WGLoopsEntry:
  br i1 undef, label %ret, label %footer329VF

footer329VF:
  %A.0.inVF = fmul float undef, 6.553600e+04
  %B.0.in407VF = fmul <8 x float> undef, <float 6.553600e+04, float 6.553600e+04, float 6.553600e+04, float 6.553600e+04, float 6.553600e+04, float 6.553600e+04, float 6.553600e+04, float 6.553600e+04>
  %A.0VF = fptosi float %A.0.inVF to i32
  %B.0408VF = fptosi <8 x float> %B.0.in407VF to <8 x i32>
  %0 = and <8 x i32> %B.0408VF, <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
  %1 = and i32 %A.0VF, 65535
  %temp1098VF = insertelement <8 x i32> undef, i32 %1, i32 0
  %vector1099VF = shufflevector <8 x i32> %temp1098VF, <8 x i32> undef, <8 x i32> zeroinitializer
  br i1 undef, label %preload1201VF, label %footer349VF

preload1201VF:
  br label %footer349VF

footer349VF:
  %2 = mul nsw <8 x i32> undef, %0
  %3 = mul nsw <8 x i32> undef, %vector1099VF
  br label %footer329VF

ret:
  ret void
}

define <8 x i32> @_inreg0(i32 %scalar) nounwind uwtable readnone ssp {
; X32-LABEL: _inreg0:
; X32:       ## BB#0:
; X32-NEXT:    vbroadcastss {{[0-9]+}}(%esp), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: _inreg0:
; X64:       ## BB#0:
; X64-NEXT:    vmovd %edi, %xmm0
; X64-NEXT:    vbroadcastss %xmm0, %ymm0
; X64-NEXT:    retq
  %in = insertelement <8 x i32> undef, i32 %scalar, i32 0
  %wide = shufflevector <8 x i32> %in, <8 x i32> undef, <8 x i32> zeroinitializer
  ret <8 x i32> %wide
}

define <8 x float> @_inreg1(float %scalar) nounwind uwtable readnone ssp {
; X32-LABEL: _inreg1:
; X32:       ## BB#0:
; X32-NEXT:    vbroadcastss {{[0-9]+}}(%esp), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: _inreg1:
; X64:       ## BB#0:
; X64-NEXT:    vbroadcastss %xmm0, %ymm0
; X64-NEXT:    retq
  %in = insertelement <8 x float> undef, float %scalar, i32 0
  %wide = shufflevector <8 x float> %in, <8 x float> undef, <8 x i32> zeroinitializer
  ret <8 x float> %wide
}

define <4 x float> @_inreg2(float %scalar) nounwind uwtable readnone ssp {
; X32-LABEL: _inreg2:
; X32:       ## BB#0:
; X32-NEXT:    vbroadcastss {{[0-9]+}}(%esp), %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: _inreg2:
; X64:       ## BB#0:
; X64-NEXT:    vbroadcastss %xmm0, %xmm0
; X64-NEXT:    retq
  %in = insertelement <4 x float> undef, float %scalar, i32 0
  %wide = shufflevector <4 x float> %in, <4 x float> undef, <4 x i32> zeroinitializer
  ret <4 x float> %wide
}

define <4 x double> @_inreg3(double %scalar) nounwind uwtable readnone ssp {
; X32-LABEL: _inreg3:
; X32:       ## BB#0:
; X32-NEXT:    vbroadcastsd {{[0-9]+}}(%esp), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: _inreg3:
; X64:       ## BB#0:
; X64-NEXT:    vbroadcastsd %xmm0, %ymm0
; X64-NEXT:    retq
  %in = insertelement <4 x double> undef, double %scalar, i32 0
  %wide = shufflevector <4 x double> %in, <4 x double> undef, <4 x i32> zeroinitializer
  ret <4 x double> %wide
}

define   <8 x float> @_inreg8xfloat(<8 x float> %a) {
; X32-LABEL: _inreg8xfloat:
; X32:       ## BB#0:
; X32-NEXT:    vbroadcastss %xmm0, %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: _inreg8xfloat:
; X64:       ## BB#0:
; X64-NEXT:    vbroadcastss %xmm0, %ymm0
; X64-NEXT:    retq
  %b = shufflevector <8 x float> %a, <8 x float> undef, <8 x i32> zeroinitializer
  ret <8 x float> %b
}

define   <4 x float> @_inreg4xfloat(<4 x float> %a) {
; X32-LABEL: _inreg4xfloat:
; X32:       ## BB#0:
; X32-NEXT:    vbroadcastss %xmm0, %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: _inreg4xfloat:
; X64:       ## BB#0:
; X64-NEXT:    vbroadcastss %xmm0, %xmm0
; X64-NEXT:    retq
  %b = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> zeroinitializer
  ret <4 x float> %b
}

define   <16 x i16> @_inreg16xi16(<16 x i16> %a) {
; X32-LABEL: _inreg16xi16:
; X32:       ## BB#0:
; X32-NEXT:    vpbroadcastw %xmm0, %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: _inreg16xi16:
; X64:       ## BB#0:
; X64-NEXT:    vpbroadcastw %xmm0, %ymm0
; X64-NEXT:    retq
  %b = shufflevector <16 x i16> %a, <16 x i16> undef, <16 x i32> zeroinitializer
  ret <16 x i16> %b
}

define   <8 x i16> @_inreg8xi16(<8 x i16> %a) {
; X32-LABEL: _inreg8xi16:
; X32:       ## BB#0:
; X32-NEXT:    vpbroadcastw %xmm0, %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: _inreg8xi16:
; X64:       ## BB#0:
; X64-NEXT:    vpbroadcastw %xmm0, %xmm0
; X64-NEXT:    retq
  %b = shufflevector <8 x i16> %a, <8 x i16> undef, <8 x i32> zeroinitializer
  ret <8 x i16> %b
}

define   <4 x i64> @_inreg4xi64(<4 x i64> %a) {
; X32-LABEL: _inreg4xi64:
; X32:       ## BB#0:
; X32-NEXT:    vbroadcastsd %xmm0, %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: _inreg4xi64:
; X64:       ## BB#0:
; X64-NEXT:    vbroadcastsd %xmm0, %ymm0
; X64-NEXT:    retq
  %b = shufflevector <4 x i64> %a, <4 x i64> undef, <4 x i32> zeroinitializer
  ret <4 x i64> %b
}

define   <2 x i64> @_inreg2xi64(<2 x i64> %a) {
; X32-LABEL: _inreg2xi64:
; X32:       ## BB#0:
; X32-NEXT:    vpbroadcastq %xmm0, %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: _inreg2xi64:
; X64:       ## BB#0:
; X64-NEXT:    vpbroadcastq %xmm0, %xmm0
; X64-NEXT:    retq
  %b = shufflevector <2 x i64> %a, <2 x i64> undef, <2 x i32> zeroinitializer
  ret <2 x i64> %b
}

define   <4 x double> @_inreg4xdouble(<4 x double> %a) {
; X32-LABEL: _inreg4xdouble:
; X32:       ## BB#0:
; X32-NEXT:    vbroadcastsd %xmm0, %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: _inreg4xdouble:
; X64:       ## BB#0:
; X64-NEXT:    vbroadcastsd %xmm0, %ymm0
; X64-NEXT:    retq
  %b = shufflevector <4 x double> %a, <4 x double> undef, <4 x i32> zeroinitializer
  ret <4 x double> %b
}

define   <2 x double> @_inreg2xdouble(<2 x double> %a) {
; X32-LABEL: _inreg2xdouble:
; X32:       ## BB#0:
; X32-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
; X32-NEXT:    retl
;
; X64-LABEL: _inreg2xdouble:
; X64:       ## BB#0:
; X64-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
; X64-NEXT:    retq
  %b = shufflevector <2 x double> %a, <2 x double> undef, <2 x i32> zeroinitializer
  ret <2 x double> %b
}

define   <8 x i32> @_inreg8xi32(<8 x i32> %a) {
; X32-LABEL: _inreg8xi32:
; X32:       ## BB#0:
; X32-NEXT:    vbroadcastss %xmm0, %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: _inreg8xi32:
; X64:       ## BB#0:
; X64-NEXT:    vbroadcastss %xmm0, %ymm0
; X64-NEXT:    retq
  %b = shufflevector <8 x i32> %a, <8 x i32> undef, <8 x i32> zeroinitializer
  ret <8 x i32> %b
}

define   <4 x i32> @_inreg4xi32(<4 x i32> %a) {
; X32-LABEL: _inreg4xi32:
; X32:       ## BB#0:
; X32-NEXT:    vbroadcastss %xmm0, %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: _inreg4xi32:
; X64:       ## BB#0:
; X64-NEXT:    vbroadcastss %xmm0, %xmm0
; X64-NEXT:    retq
  %b = shufflevector <4 x i32> %a, <4 x i32> undef, <4 x i32> zeroinitializer
  ret <4 x i32> %b
}

define   <32 x i8> @_inreg32xi8(<32 x i8> %a) {
; X32-LABEL: _inreg32xi8:
; X32:       ## BB#0:
; X32-NEXT:    vpbroadcastb %xmm0, %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: _inreg32xi8:
; X64:       ## BB#0:
; X64-NEXT:    vpbroadcastb %xmm0, %ymm0
; X64-NEXT:    retq
  %b = shufflevector <32 x i8> %a, <32 x i8> undef, <32 x i32> zeroinitializer
  ret <32 x i8> %b
}

define   <16 x i8> @_inreg16xi8(<16 x i8> %a) {
; X32-LABEL: _inreg16xi8:
; X32:       ## BB#0:
; X32-NEXT:    vpbroadcastb %xmm0, %xmm0
; X32-NEXT:    retl
;
; X64-LABEL: _inreg16xi8:
; X64:       ## BB#0:
; X64-NEXT:    vpbroadcastb %xmm0, %xmm0
; X64-NEXT:    retq
  %b = shufflevector <16 x i8> %a, <16 x i8> undef, <16 x i32> zeroinitializer
  ret <16 x i8> %b
}

; These tests check that a vbroadcast instruction is used when we have a splat
; formed from a concat_vectors (via the shufflevector) of two BUILD_VECTORs
; (via the insertelements).

define <8 x float> @splat_concat1(float %f) {
; X32-LABEL: splat_concat1:
; X32:       ## BB#0:
; X32-NEXT:    vbroadcastss {{[0-9]+}}(%esp), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: splat_concat1:
; X64:       ## BB#0:
; X64-NEXT:    vbroadcastss %xmm0, %ymm0
; X64-NEXT:    retq
  %1 = insertelement <4 x float> undef, float %f, i32 0
  %2 = insertelement <4 x float> %1, float %f, i32 1
  %3 = insertelement <4 x float> %2, float %f, i32 2
  %4 = insertelement <4 x float> %3, float %f, i32 3
  %5 = shufflevector <4 x float> %4, <4 x float> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
  ret <8 x float> %5
}

define <8 x float> @splat_concat2(float %f) {
; X32-LABEL: splat_concat2:
; X32:       ## BB#0:
; X32-NEXT:    vbroadcastss {{[0-9]+}}(%esp), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: splat_concat2:
; X64:       ## BB#0:
; X64-NEXT:    vbroadcastss %xmm0, %ymm0
; X64-NEXT:    retq
  %1 = insertelement <4 x float> undef, float %f, i32 0
  %2 = insertelement <4 x float> %1, float %f, i32 1
  %3 = insertelement <4 x float> %2, float %f, i32 2
  %4 = insertelement <4 x float> %3, float %f, i32 3
  %5 = insertelement <4 x float> undef, float %f, i32 0
  %6 = insertelement <4 x float> %5, float %f, i32 1
  %7 = insertelement <4 x float> %6, float %f, i32 2
  %8 = insertelement <4 x float> %7, float %f, i32 3
  %9 = shufflevector <4 x float> %4, <4 x float> %8, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  ret <8 x float> %9
}

define <4 x double> @splat_concat3(double %d) {
; X32-LABEL: splat_concat3:
; X32:       ## BB#0:
; X32-NEXT:    vbroadcastsd {{[0-9]+}}(%esp), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: splat_concat3:
; X64:       ## BB#0:
; X64-NEXT:    vbroadcastsd %xmm0, %ymm0
; X64-NEXT:    retq
  %1 = insertelement <2 x double> undef, double %d, i32 0
  %2 = insertelement <2 x double> %1, double %d, i32 1
  %3 = shufflevector <2 x double> %2, <2 x double> undef, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
  ret <4 x double> %3
}

define <4 x double> @splat_concat4(double %d) {
; X32-LABEL: splat_concat4:
; X32:       ## BB#0:
; X32-NEXT:    vbroadcastsd {{[0-9]+}}(%esp), %ymm0
; X32-NEXT:    retl
;
; X64-LABEL: splat_concat4:
; X64:       ## BB#0:
; X64-NEXT:    vbroadcastsd %xmm0, %ymm0
; X64-NEXT:    retq
  %1 = insertelement <2 x double> undef, double %d, i32 0
  %2 = insertelement <2 x double> %1, double %d, i32 1
  %3 = insertelement <2 x double> undef, double %d, i32 0
  %4 = insertelement <2 x double> %3, double %d, i32 1
  %5 = shufflevector <2 x double> %2, <2 x double> %4, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  ret <4 x double> %5
}

; Test cases for <rdar://problem/16074331>.
; Instruction selection for broacast instruction fails if
; the load cannot be folded into the broadcast.
; This happens if the load has initial one use but other uses are
; created later, or if selection DAG cannot prove that folding the
; load will not create a cycle in the DAG.
; Those test cases exerce the latter.

; CHECK-LABEL: isel_crash_16b
; CHECK: vpbroadcastb {{[^,]+}}, %xmm{{[0-9]+}}
; CHECK: ret
define void @isel_crash_16b(i8* %cV_R.addr) {
eintry:
  %__a.addr.i = alloca <2 x i64>, align 16
  %__b.addr.i = alloca <2 x i64>, align 16
  %vCr = alloca <2 x i64>, align 16
  store <2 x i64> zeroinitializer, <2 x i64>* %vCr, align 16
  %tmp = load <2 x i64>, <2 x i64>* %vCr, align 16
  %tmp2 = load i8, i8* %cV_R.addr, align 4
  %splat.splatinsert = insertelement <16 x i8> undef, i8 %tmp2, i32 0
  %splat.splat = shufflevector <16 x i8> %splat.splatinsert, <16 x i8> undef, <16 x i32> zeroinitializer
  %tmp3 = bitcast <16 x i8> %splat.splat to <2 x i64>
  store <2 x i64> %tmp, <2 x i64>* %__a.addr.i, align 16
  store <2 x i64> %tmp3, <2 x i64>* %__b.addr.i, align 16
  ret void
}

; CHECK-LABEL: isel_crash_32b
; CHECK: vpbroadcastb {{[^,]+}}, %ymm{{[0-9]+}}
; CHECK: ret
define void @isel_crash_32b(i8* %cV_R.addr) {
eintry:
  %__a.addr.i = alloca <4 x i64>, align 16
  %__b.addr.i = alloca <4 x i64>, align 16
  %vCr = alloca <4 x i64>, align 16
  store <4 x i64> zeroinitializer, <4 x i64>* %vCr, align 16
  %tmp = load <4 x i64>, <4 x i64>* %vCr, align 16
  %tmp2 = load i8, i8* %cV_R.addr, align 4
  %splat.splatinsert = insertelement <32 x i8> undef, i8 %tmp2, i32 0
  %splat.splat = shufflevector <32 x i8> %splat.splatinsert, <32 x i8> undef, <32 x i32> zeroinitializer
  %tmp3 = bitcast <32 x i8> %splat.splat to <4 x i64>
  store <4 x i64> %tmp, <4 x i64>* %__a.addr.i, align 16
  store <4 x i64> %tmp3, <4 x i64>* %__b.addr.i, align 16
  ret void
}

; CHECK-LABEL: isel_crash_8w
; CHECK: vpbroadcastw {{[^,]+}}, %xmm{{[0-9]+}}
; CHECK: ret
define void @isel_crash_8w(i16* %cV_R.addr) {
entry:
  %__a.addr.i = alloca <2 x i64>, align 16
  %__b.addr.i = alloca <2 x i64>, align 16
  %vCr = alloca <2 x i64>, align 16
  store <2 x i64> zeroinitializer, <2 x i64>* %vCr, align 16
  %tmp = load <2 x i64>, <2 x i64>* %vCr, align 16
  %tmp2 = load i16, i16* %cV_R.addr, align 4
  %splat.splatinsert = insertelement <8 x i16> undef, i16 %tmp2, i32 0
  %splat.splat = shufflevector <8 x i16> %splat.splatinsert, <8 x i16> undef, <8 x i32> zeroinitializer
  %tmp3 = bitcast <8 x i16> %splat.splat to <2 x i64>
  store <2 x i64> %tmp, <2 x i64>* %__a.addr.i, align 16
  store <2 x i64> %tmp3, <2 x i64>* %__b.addr.i, align 16
  ret void
}

; CHECK-LABEL: isel_crash_16w
; CHECK: vpbroadcastw {{[^,]+}}, %ymm{{[0-9]+}}
; CHECK: ret
define void @isel_crash_16w(i16* %cV_R.addr) {
eintry:
  %__a.addr.i = alloca <4 x i64>, align 16
  %__b.addr.i = alloca <4 x i64>, align 16
  %vCr = alloca <4 x i64>, align 16
  store <4 x i64> zeroinitializer, <4 x i64>* %vCr, align 16
  %tmp = load <4 x i64>, <4 x i64>* %vCr, align 16
  %tmp2 = load i16, i16* %cV_R.addr, align 4
  %splat.splatinsert = insertelement <16 x i16> undef, i16 %tmp2, i32 0
  %splat.splat = shufflevector <16 x i16> %splat.splatinsert, <16 x i16> undef, <16 x i32> zeroinitializer
  %tmp3 = bitcast <16 x i16> %splat.splat to <4 x i64>
  store <4 x i64> %tmp, <4 x i64>* %__a.addr.i, align 16
  store <4 x i64> %tmp3, <4 x i64>* %__b.addr.i, align 16
  ret void
}

; CHECK-LABEL: isel_crash_4d
; CHECK: vbroadcastss {{[^,]+}}, %xmm{{[0-9]+}}
; CHECK: ret
define void @isel_crash_4d(i32* %cV_R.addr) {
entry:
  %__a.addr.i = alloca <2 x i64>, align 16
  %__b.addr.i = alloca <2 x i64>, align 16
  %vCr = alloca <2 x i64>, align 16
  store <2 x i64> zeroinitializer, <2 x i64>* %vCr, align 16
  %tmp = load <2 x i64>, <2 x i64>* %vCr, align 16
  %tmp2 = load i32, i32* %cV_R.addr, align 4
  %splat.splatinsert = insertelement <4 x i32> undef, i32 %tmp2, i32 0
  %splat.splat = shufflevector <4 x i32> %splat.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
  %tmp3 = bitcast <4 x i32> %splat.splat to <2 x i64>
  store <2 x i64> %tmp, <2 x i64>* %__a.addr.i, align 16
  store <2 x i64> %tmp3, <2 x i64>* %__b.addr.i, align 16
  ret void
}

; CHECK-LABEL: isel_crash_8d
; CHECK: vbroadcastss {{[^,]+}}, %ymm{{[0-9]+}}
; CHECK: ret
define void @isel_crash_8d(i32* %cV_R.addr) {
eintry:
  %__a.addr.i = alloca <4 x i64>, align 16
  %__b.addr.i = alloca <4 x i64>, align 16
  %vCr = alloca <4 x i64>, align 16
  store <4 x i64> zeroinitializer, <4 x i64>* %vCr, align 16
  %tmp = load <4 x i64>, <4 x i64>* %vCr, align 16
  %tmp2 = load i32, i32* %cV_R.addr, align 4
  %splat.splatinsert = insertelement <8 x i32> undef, i32 %tmp2, i32 0
  %splat.splat = shufflevector <8 x i32> %splat.splatinsert, <8 x i32> undef, <8 x i32> zeroinitializer
  %tmp3 = bitcast <8 x i32> %splat.splat to <4 x i64>
  store <4 x i64> %tmp, <4 x i64>* %__a.addr.i, align 16
  store <4 x i64> %tmp3, <4 x i64>* %__b.addr.i, align 16
  ret void
}

; X64-LABEL: isel_crash_2q
; X64: vpbroadcastq {{[^,]+}}, %xmm{{[0-9]+}}
; X64: ret
define void @isel_crash_2q(i64* %cV_R.addr) {
entry:
  %__a.addr.i = alloca <2 x i64>, align 16
  %__b.addr.i = alloca <2 x i64>, align 16
  %vCr = alloca <2 x i64>, align 16
  store <2 x i64> zeroinitializer, <2 x i64>* %vCr, align 16
  %tmp = load <2 x i64>, <2 x i64>* %vCr, align 16
  %tmp2 = load i64, i64* %cV_R.addr, align 4
  %splat.splatinsert = insertelement <2 x i64> undef, i64 %tmp2, i32 0
  %splat.splat = shufflevector <2 x i64> %splat.splatinsert, <2 x i64> undef, <2 x i32> zeroinitializer
  store <2 x i64> %tmp, <2 x i64>* %__a.addr.i, align 16
  store <2 x i64> %splat.splat, <2 x i64>* %__b.addr.i, align 16
  ret void
}

; X64-LABEL: isel_crash_4q
; X64: vbroadcastsd {{[^,]+}}, %ymm{{[0-9]+}}
; X64: ret
define void @isel_crash_4q(i64* %cV_R.addr) {
eintry:
  %__a.addr.i = alloca <4 x i64>, align 16
  %__b.addr.i = alloca <4 x i64>, align 16
  %vCr = alloca <4 x i64>, align 16
  store <4 x i64> zeroinitializer, <4 x i64>* %vCr, align 16
  %tmp = load <4 x i64>, <4 x i64>* %vCr, align 16
  %tmp2 = load i64, i64* %cV_R.addr, align 4
  %splat.splatinsert = insertelement <4 x i64> undef, i64 %tmp2, i32 0
  %splat.splat = shufflevector <4 x i64> %splat.splatinsert, <4 x i64> undef, <4 x i32> zeroinitializer
  store <4 x i64> %tmp, <4 x i64>* %__a.addr.i, align 16
  store <4 x i64> %splat.splat, <4 x i64>* %__b.addr.i, align 16
  ret void
}