; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --no_x86_scrub_mem_shuffle
; RUN: llc < %s -mtriple=i686-apple-darwin -mcpu=corei7-avx | FileCheck %s --check-prefixes=CHECK,X86
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx | FileCheck %s --check-prefixes=CHECK,X64

define <4 x i32> @blendvb_fallback_v4i32(<4 x i1> %mask, <4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: blendvb_fallback_v4i32:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vpslld $31, %xmm0, %xmm0
; CHECK-NEXT:    vblendvps %xmm0, %xmm1, %xmm2, %xmm0
; CHECK-NEXT:    ret{{[l|q]}}
  %ret = select <4 x i1> %mask, <4 x i32> %x, <4 x i32> %y
  ret <4 x i32> %ret
}

define <8 x i32> @blendvb_fallback_v8i32(<8 x i1> %mask, <8 x i32> %x, <8 x i32> %y) {
; CHECK-LABEL: blendvb_fallback_v8i32:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vpmovzxwd {{.*#+}} xmm3 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; CHECK-NEXT:    vpslld $31, %xmm3, %xmm3
; CHECK-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
; CHECK-NEXT:    vpslld $31, %xmm0, %xmm0
; CHECK-NEXT:    vinsertf128 $1, %xmm0, %ymm3, %ymm0
; CHECK-NEXT:    vblendvps %ymm0, %ymm1, %ymm2, %ymm0
; CHECK-NEXT:    ret{{[l|q]}}
  %ret = select <8 x i1> %mask, <8 x i32> %x, <8 x i32> %y
  ret <8 x i32> %ret
}

define <8 x float> @blendvb_fallback_v8f32(<8 x i1> %mask, <8 x float> %x, <8 x float> %y) {
; CHECK-LABEL: blendvb_fallback_v8f32:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vpmovzxwd {{.*#+}} xmm3 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; CHECK-NEXT:    vpslld $31, %xmm3, %xmm3
; CHECK-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
; CHECK-NEXT:    vpslld $31, %xmm0, %xmm0
; CHECK-NEXT:    vinsertf128 $1, %xmm0, %ymm3, %ymm0
; CHECK-NEXT:    vblendvps %ymm0, %ymm1, %ymm2, %ymm0
; CHECK-NEXT:    ret{{[l|q]}}
  %ret = select <8 x i1> %mask, <8 x float> %x, <8 x float> %y
  ret <8 x float> %ret
}

declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i32) nounwind readnone

define <4 x float> @insertps_from_vector_load(<4 x float> %a, <4 x float>* nocapture readonly %pb) {
; X86-LABEL: insertps_from_vector_load:
; X86:       ## %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-NEXT:    vinsertps $48, (%eax), %xmm0, %xmm0 ## xmm0 = xmm0[0,1,2],mem[0]
; X86-NEXT:    retl
;
; X64-LABEL: insertps_from_vector_load:
; X64:       ## %bb.0:
; X64-NEXT:    vinsertps $48, (%rdi), %xmm0, %xmm0 ## xmm0 = xmm0[0,1,2],mem[0]
; X64-NEXT:    retq
  %1 = load <4 x float>, <4 x float>* %pb, align 16
  %2 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %1, i32 48)
  ret <4 x float> %2
}

;; Use a non-zero CountS for insertps
define <4 x float> @insertps_from_vector_load_offset(<4 x float> %a, <4 x float>* nocapture readonly %pb) {
; X86-LABEL: insertps_from_vector_load_offset:
; X86:       ## %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-NEXT:    vinsertps $32, 4(%eax), %xmm0, %xmm0 ## xmm0 = xmm0[0,1],mem[0],xmm0[3]
; X86-NEXT:    retl
;
; X64-LABEL: insertps_from_vector_load_offset:
; X64:       ## %bb.0:
; X64-NEXT:    vinsertps $32, 4(%rdi), %xmm0, %xmm0 ## xmm0 = xmm0[0,1],mem[0],xmm0[3]
; X64-NEXT:    retq
  %1 = load <4 x float>, <4 x float>* %pb, align 16
  %2 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %1, i32 96)
  ret <4 x float> %2
}

define <4 x float> @insertps_from_vector_load_offset_2(<4 x float> %a, <4 x float>* nocapture readonly %pb, i64 %index) {
; X86-LABEL: insertps_from_vector_load_offset_2:
; X86:       ## %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT:    shll $4, %ecx
; X86-NEXT:    vinsertps $0, 12(%eax,%ecx), %xmm0, %xmm0 ## xmm0 = mem[0],xmm0[1,2,3]
; X86-NEXT:    retl
;
; X64-LABEL: insertps_from_vector_load_offset_2:
; X64:       ## %bb.0:
; X64-NEXT:    shlq $4, %rsi
; X64-NEXT:    vinsertps $0, 12(%rdi,%rsi), %xmm0, %xmm0 ## xmm0 = mem[0],xmm0[1,2,3]
; X64-NEXT:    retq
  %1 = getelementptr inbounds <4 x float>, <4 x float>* %pb, i64 %index
  %2 = load <4 x float>, <4 x float>* %1, align 16
  %3 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %2, i32 192)
  ret <4 x float> %3
}

define <4 x float> @insertps_from_broadcast_loadf32(<4 x float> %a, float* nocapture readonly %fb, i64 %index) {
; X86-LABEL: insertps_from_broadcast_loadf32:
; X86:       ## %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT:    vinsertps $48, (%ecx,%eax,4), %xmm0, %xmm0 ## xmm0 = xmm0[0,1,2],mem[0]
; X86-NEXT:    retl
;
; X64-LABEL: insertps_from_broadcast_loadf32:
; X64:       ## %bb.0:
; X64-NEXT:    vinsertps $48, (%rdi,%rsi,4), %xmm0, %xmm0 ## xmm0 = xmm0[0,1,2],mem[0]
; X64-NEXT:    retq
  %1 = getelementptr inbounds float, float* %fb, i64 %index
  %2 = load float, float* %1, align 4
  %3 = insertelement <4 x float> undef, float %2, i32 0
  %4 = insertelement <4 x float> %3, float %2, i32 1
  %5 = insertelement <4 x float> %4, float %2, i32 2
  %6 = insertelement <4 x float> %5, float %2, i32 3
  %7 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %6, i32 48)
  ret <4 x float> %7
}

define <4 x float> @insertps_from_broadcast_loadv4f32(<4 x float> %a, <4 x float>* nocapture readonly %b) {
; X86-LABEL: insertps_from_broadcast_loadv4f32:
; X86:       ## %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-NEXT:    vinsertps $48, (%eax), %xmm0, %xmm0 ## xmm0 = xmm0[0,1,2],mem[0]
; X86-NEXT:    retl
;
; X64-LABEL: insertps_from_broadcast_loadv4f32:
; X64:       ## %bb.0:
; X64-NEXT:    vinsertps $48, (%rdi), %xmm0, %xmm0 ## xmm0 = xmm0[0,1,2],mem[0]
; X64-NEXT:    retq
  %1 = load <4 x float>, <4 x float>* %b, align 4
  %2 = extractelement <4 x float> %1, i32 0
  %3 = insertelement <4 x float> undef, float %2, i32 0
  %4 = insertelement <4 x float> %3, float %2, i32 1
  %5 = insertelement <4 x float> %4, float %2, i32 2
  %6 = insertelement <4 x float> %5, float %2, i32 3
  %7 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %6, i32 48)
  ret <4 x float> %7
}

define <4 x float> @insertps_from_broadcast_multiple_use(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x float> %d, float* nocapture readonly %fb, i64 %index) {
; X86-LABEL: insertps_from_broadcast_multiple_use:
; X86:       ## %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT:    vbroadcastss (%ecx,%eax,4), %xmm4
; X86-NEXT:    vblendps {{.*#+}} xmm0 = xmm0[0,1,2],xmm4[3]
; X86-NEXT:    vblendps {{.*#+}} xmm1 = xmm1[0,1,2],xmm4[3]
; X86-NEXT:    vaddps %xmm1, %xmm0, %xmm0
; X86-NEXT:    vblendps {{.*#+}} xmm1 = xmm2[0,1,2],xmm4[3]
; X86-NEXT:    vblendps {{.*#+}} xmm2 = xmm3[0,1,2],xmm4[3]
; X86-NEXT:    vaddps %xmm2, %xmm1, %xmm1
; X86-NEXT:    vaddps %xmm1, %xmm0, %xmm0
; X86-NEXT:    retl
;
; X64-LABEL: insertps_from_broadcast_multiple_use:
; X64:       ## %bb.0:
; X64-NEXT:    vbroadcastss (%rdi,%rsi,4), %xmm4
; X64-NEXT:    vblendps {{.*#+}} xmm0 = xmm0[0,1,2],xmm4[3]
; X64-NEXT:    vblendps {{.*#+}} xmm1 = xmm1[0,1,2],xmm4[3]
; X64-NEXT:    vaddps %xmm1, %xmm0, %xmm0
; X64-NEXT:    vblendps {{.*#+}} xmm1 = xmm2[0,1,2],xmm4[3]
; X64-NEXT:    vblendps {{.*#+}} xmm2 = xmm3[0,1,2],xmm4[3]
; X64-NEXT:    vaddps %xmm2, %xmm1, %xmm1
; X64-NEXT:    vaddps %xmm1, %xmm0, %xmm0
; X64-NEXT:    retq
  %1 = getelementptr inbounds float, float* %fb, i64 %index
  %2 = load float, float* %1, align 4
  %3 = insertelement <4 x float> undef, float %2, i32 0
  %4 = insertelement <4 x float> %3, float %2, i32 1
  %5 = insertelement <4 x float> %4, float %2, i32 2
  %6 = insertelement <4 x float> %5, float %2, i32 3
  %7 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %6, i32 48)
  %8 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %b, <4 x float> %6, i32 48)
  %9 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %c, <4 x float> %6, i32 48)
  %10 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %d, <4 x float> %6, i32 48)
  %11 = fadd <4 x float> %7, %8
  %12 = fadd <4 x float> %9, %10
  %13 = fadd <4 x float> %11, %12
  ret <4 x float> %13
}