; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=x86_64-pc-linux -mattr=mmx < %s | FileCheck %s

; MMX packed sub opcodes were wrongly marked as commutative.
; This test checks that the operands of packed sub instructions are
; never interchanged by the "Two-Address instruction pass".

declare { i64, double } @getFirstParam()
declare { i64, double } @getSecondParam()

define i64 @test_psubb() {
; CHECK-LABEL: test_psubb:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rbx
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset %rbx, -16
; CHECK-NEXT:    callq getFirstParam
; CHECK-NEXT:    movq %rax, %rbx
; CHECK-NEXT:    callq getSecondParam
; CHECK-NEXT:    movq %rbx, %mm0
; CHECK-NEXT:    movq %rax, %mm1
; CHECK-NEXT:    psubb %mm1, %mm0
; CHECK-NEXT:    movq %mm0, %rax
; CHECK-NEXT:    popq %rbx
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
entry:
  %call = tail call { i64, double } @getFirstParam()
  %0 = extractvalue { i64, double } %call, 0
  %call2 = tail call { i64, double } @getSecondParam()
  %1 = extractvalue { i64, double } %call2, 0
  %__m1.0.insert.i = insertelement <1 x i64> undef, i64 %0, i32 0
  %__m2.0.insert.i = insertelement <1 x i64> undef, i64 %1, i32 0
  %2 = bitcast <1 x i64> %__m1.0.insert.i to <8 x i8>
  %3 = bitcast <8 x i8> %2 to x86_mmx
  %4 = bitcast <1 x i64> %__m2.0.insert.i to <8 x i8>
  %5 = bitcast <8 x i8> %4 to x86_mmx
  %6 = tail call x86_mmx @llvm.x86.mmx.psub.b(x86_mmx %3, x86_mmx %5) nounwind
  %7 = bitcast x86_mmx %6 to <8 x i8>
  %8 = bitcast <8 x i8> %7 to <1 x i64>
  %retval.0.extract.i15 = extractelement <1 x i64> %8, i32 0
  ret i64 %retval.0.extract.i15
}

define i64 @test_psubw() {
; CHECK-LABEL: test_psubw:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rbx
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset %rbx, -16
; CHECK-NEXT:    callq getFirstParam
; CHECK-NEXT:    movq %rax, %rbx
; CHECK-NEXT:    callq getSecondParam
; CHECK-NEXT:    movq %rbx, %mm0
; CHECK-NEXT:    movq %rax, %mm1
; CHECK-NEXT:    psubw %mm1, %mm0
; CHECK-NEXT:    movq %mm0, %rax
; CHECK-NEXT:    popq %rbx
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
entry:
  %call = tail call { i64, double } @getFirstParam()
  %0 = extractvalue { i64, double } %call, 0
  %call2 = tail call { i64, double } @getSecondParam()
  %1 = extractvalue { i64, double } %call2, 0
  %__m1.0.insert.i = insertelement <1 x i64> undef, i64 %0, i32 0
  %__m2.0.insert.i = insertelement <1 x i64> undef, i64 %1, i32 0
  %2 = bitcast <1 x i64> %__m1.0.insert.i to <4 x i16>
  %3 = bitcast <4 x i16> %2 to x86_mmx
  %4 = bitcast <1 x i64> %__m2.0.insert.i to <4 x i16>
  %5 = bitcast <4 x i16> %4 to x86_mmx
  %6 = tail call x86_mmx @llvm.x86.mmx.psub.w(x86_mmx %3, x86_mmx %5) nounwind
  %7 = bitcast x86_mmx %6 to <4 x i16>
  %8 = bitcast <4 x i16> %7 to <1 x i64>
  %retval.0.extract.i15 = extractelement <1 x i64> %8, i32 0
  ret i64 %retval.0.extract.i15
}

define i64 @test_psubd() {
; CHECK-LABEL: test_psubd:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rbx
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset %rbx, -16
; CHECK-NEXT:    callq getFirstParam
; CHECK-NEXT:    movq %rax, %rbx
; CHECK-NEXT:    callq getSecondParam
; CHECK-NEXT:    movq %rbx, %mm0
; CHECK-NEXT:    movq %rax, %mm1
; CHECK-NEXT:    psubd %mm1, %mm0
; CHECK-NEXT:    movq %mm0, %rax
; CHECK-NEXT:    popq %rbx
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
entry:
  %call = tail call { i64, double } @getFirstParam()
  %0 = extractvalue { i64, double } %call, 0
  %call2 = tail call { i64, double } @getSecondParam()
  %1 = extractvalue { i64, double } %call2, 0
  %__m1.0.insert.i = insertelement <1 x i64> undef, i64 %0, i32 0
  %__m2.0.insert.i = insertelement <1 x i64> undef, i64 %1, i32 0
  %2 = bitcast <1 x i64> %__m1.0.insert.i to <2 x i32>
  %3 = bitcast <2 x i32> %2 to x86_mmx
  %4 = bitcast <1 x i64> %__m2.0.insert.i to <2 x i32>
  %5 = bitcast <2 x i32> %4 to x86_mmx
  %6 = tail call x86_mmx @llvm.x86.mmx.psub.d(x86_mmx %3, x86_mmx %5) nounwind
  %7 = bitcast x86_mmx %6 to <2 x i32>
  %8 = bitcast <2 x i32> %7 to <1 x i64>
  %retval.0.extract.i15 = extractelement <1 x i64> %8, i32 0
  ret i64 %retval.0.extract.i15
}

define i64 @test_psubsb() {
; CHECK-LABEL: test_psubsb:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rbx
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset %rbx, -16
; CHECK-NEXT:    callq getFirstParam
; CHECK-NEXT:    movq %rax, %rbx
; CHECK-NEXT:    callq getSecondParam
; CHECK-NEXT:    movq %rbx, %mm0
; CHECK-NEXT:    movq %rax, %mm1
; CHECK-NEXT:    psubsb %mm1, %mm0
; CHECK-NEXT:    movq %mm0, %rax
; CHECK-NEXT:    popq %rbx
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
entry:
  %call = tail call { i64, double } @getFirstParam()
  %0 = extractvalue { i64, double } %call, 0
  %call2 = tail call { i64, double } @getSecondParam()
  %1 = extractvalue { i64, double } %call2, 0
  %__m1.0.insert.i = insertelement <1 x i64> undef, i64 %0, i32 0
  %__m2.0.insert.i = insertelement <1 x i64> undef, i64 %1, i32 0
  %2 = bitcast <1 x i64> %__m1.0.insert.i to <8 x i8>
  %3 = bitcast <8 x i8> %2 to x86_mmx
  %4 = bitcast <1 x i64> %__m2.0.insert.i to <8 x i8>
  %5 = bitcast <8 x i8> %4 to x86_mmx
  %6 = tail call x86_mmx @llvm.x86.mmx.psubs.b(x86_mmx %3, x86_mmx %5) nounwind
  %7 = bitcast x86_mmx %6 to <8 x i8>
  %8 = bitcast <8 x i8> %7 to <1 x i64>
  %retval.0.extract.i15 = extractelement <1 x i64> %8, i32 0
  ret i64 %retval.0.extract.i15
}

define i64 @test_psubswv() {
; CHECK-LABEL: test_psubswv:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rbx
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset %rbx, -16
; CHECK-NEXT:    callq getFirstParam
; CHECK-NEXT:    movq %rax, %rbx
; CHECK-NEXT:    callq getSecondParam
; CHECK-NEXT:    movq %rbx, %mm0
; CHECK-NEXT:    movq %rax, %mm1
; CHECK-NEXT:    psubsw %mm1, %mm0
; CHECK-NEXT:    movq %mm0, %rax
; CHECK-NEXT:    popq %rbx
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
entry:
  %call = tail call { i64, double } @getFirstParam()
  %0 = extractvalue { i64, double } %call, 0
  %call2 = tail call { i64, double } @getSecondParam()
  %1 = extractvalue { i64, double } %call2, 0
  %__m1.0.insert.i = insertelement <1 x i64> undef, i64 %0, i32 0
  %__m2.0.insert.i = insertelement <1 x i64> undef, i64 %1, i32 0
  %2 = bitcast <1 x i64> %__m1.0.insert.i to <4 x i16>
  %3 = bitcast <4 x i16> %2 to x86_mmx
  %4 = bitcast <1 x i64> %__m2.0.insert.i to <4 x i16>
  %5 = bitcast <4 x i16> %4 to x86_mmx
  %6 = tail call x86_mmx @llvm.x86.mmx.psubs.w(x86_mmx %3, x86_mmx %5) nounwind
  %7 = bitcast x86_mmx %6 to <4 x i16>
  %8 = bitcast <4 x i16> %7 to <1 x i64>
  %retval.0.extract.i15 = extractelement <1 x i64> %8, i32 0
  ret i64 %retval.0.extract.i15
}

define i64 @test_psubusbv() {
; CHECK-LABEL: test_psubusbv:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rbx
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset %rbx, -16
; CHECK-NEXT:    callq getFirstParam
; CHECK-NEXT:    movq %rax, %rbx
; CHECK-NEXT:    callq getSecondParam
; CHECK-NEXT:    movq %rbx, %mm0
; CHECK-NEXT:    movq %rax, %mm1
; CHECK-NEXT:    psubusb %mm1, %mm0
; CHECK-NEXT:    movq %mm0, %rax
; CHECK-NEXT:    popq %rbx
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
entry:
  %call = tail call { i64, double } @getFirstParam()
  %0 = extractvalue { i64, double } %call, 0
  %call2 = tail call { i64, double } @getSecondParam()
  %1 = extractvalue { i64, double } %call2, 0
  %__m1.0.insert.i = insertelement <1 x i64> undef, i64 %0, i32 0
  %__m2.0.insert.i = insertelement <1 x i64> undef, i64 %1, i32 0
  %2 = bitcast <1 x i64> %__m1.0.insert.i to <8 x i8>
  %3 = bitcast <8 x i8> %2 to x86_mmx
  %4 = bitcast <1 x i64> %__m2.0.insert.i to <8 x i8>
  %5 = bitcast <8 x i8> %4 to x86_mmx
  %6 = tail call x86_mmx @llvm.x86.mmx.psubus.b(x86_mmx %3, x86_mmx %5) nounwind
  %7 = bitcast x86_mmx %6 to <8 x i8>
  %8 = bitcast <8 x i8> %7 to <1 x i64>
  %retval.0.extract.i15 = extractelement <1 x i64> %8, i32 0
  ret i64 %retval.0.extract.i15
}

define i64 @test_psubuswv() {
; CHECK-LABEL: test_psubuswv:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rbx
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset %rbx, -16
; CHECK-NEXT:    callq getFirstParam
; CHECK-NEXT:    movq %rax, %rbx
; CHECK-NEXT:    callq getSecondParam
; CHECK-NEXT:    movq %rbx, %mm0
; CHECK-NEXT:    movq %rax, %mm1
; CHECK-NEXT:    psubusw %mm1, %mm0
; CHECK-NEXT:    movq %mm0, %rax
; CHECK-NEXT:    popq %rbx
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
entry:
  %call = tail call { i64, double } @getFirstParam()
  %0 = extractvalue { i64, double } %call, 0
  %call2 = tail call { i64, double } @getSecondParam()
  %1 = extractvalue { i64, double } %call2, 0
  %__m1.0.insert.i = insertelement <1 x i64> undef, i64 %0, i32 0
  %__m2.0.insert.i = insertelement <1 x i64> undef, i64 %1, i32 0
  %2 = bitcast <1 x i64> %__m1.0.insert.i to <4 x i16>
  %3 = bitcast <4 x i16> %2 to x86_mmx
  %4 = bitcast <1 x i64> %__m2.0.insert.i to <4 x i16>
  %5 = bitcast <4 x i16> %4 to x86_mmx
  %6 = tail call x86_mmx @llvm.x86.mmx.psubus.w(x86_mmx %3, x86_mmx %5) nounwind
  %7 = bitcast x86_mmx %6 to <4 x i16>
  %8 = bitcast <4 x i16> %7 to <1 x i64>
  %retval.0.extract.i15 = extractelement <1 x i64> %8, i32 0
  ret i64 %retval.0.extract.i15
}

declare x86_mmx @llvm.x86.mmx.psubus.w(x86_mmx, x86_mmx) nounwind readnone

declare x86_mmx @llvm.x86.mmx.psubus.b(x86_mmx, x86_mmx) nounwind readnone

declare x86_mmx @llvm.x86.mmx.psubs.w(x86_mmx, x86_mmx) nounwind readnone

declare x86_mmx @llvm.x86.mmx.psubs.b(x86_mmx, x86_mmx) nounwind readnone

declare x86_mmx @llvm.x86.mmx.psub.d(x86_mmx, x86_mmx) nounwind readnone

declare x86_mmx @llvm.x86.mmx.psub.w(x86_mmx, x86_mmx) nounwind readnone

declare x86_mmx @llvm.x86.mmx.psub.b(x86_mmx, x86_mmx) nounwind readnone