; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --no_x86_scrub_sp --no_x86_scrub_mem_shuffle
; RUN: llc -mcpu=generic -mtriple=i686-pc-windows-msvc -mattr=+sse2 < %s | FileCheck %s --check-prefix=MSVC
; RUN: llc -mcpu=generic -mtriple=i686-pc-mingw32 -mattr=+sse2 < %s | FileCheck %s --check-prefix=MINGW

@a = external dso_local global <4 x float>, align 16

define dso_local void @testPastArguments() nounwind {
; MSVC-LABEL: testPastArguments:
; MSVC:       # %bb.0: # %entry
; MSVC-NEXT:    subl $20, %esp
; MSVC-NEXT:    movaps _a, %xmm0
; MSVC-NEXT:    movups %xmm0, 4(%esp)
; MSVC-NEXT:    movl $1, (%esp)
; MSVC-NEXT:    calll _testm128
; MSVC-NEXT:    addl $20, %esp
; MSVC-NEXT:    retl
;
; MINGW-LABEL: testPastArguments:
; MINGW:       # %bb.0: # %entry
; MINGW-NEXT:    pushl %ebp
; MINGW-NEXT:    movl %esp, %ebp
; MINGW-NEXT:    andl $-16, %esp
; MINGW-NEXT:    subl $48, %esp
; MINGW-NEXT:    movaps _a, %xmm0
; MINGW-NEXT:    movaps %xmm0, 16(%esp)
; MINGW-NEXT:    movl $1, (%esp)
; MINGW-NEXT:    calll _testm128
; MINGW-NEXT:    movl %ebp, %esp
; MINGW-NEXT:    popl %ebp
; MINGW-NEXT:    retl
entry:
  %0 = load <4 x float>, <4 x float>* @a, align 16
  %call = tail call i32 (i32, ...) @testm128(i32 1, <4 x float> inreg %0)
  ret void
}

define <4 x i32> @foo(<4 x float> %0, ...) nounwind {
; MSVC-LABEL: foo:
; MSVC:       # %bb.0:
; MSVC-NEXT:    pushl %eax
; MSVC-NEXT:    movaps 8(%esp), %xmm0
; MSVC-NEXT:    movups 24(%esp), %xmm1
; MSVC-NEXT:    cmpltps %xmm1, %xmm0
; MSVC-NEXT:    popl %eax
; MSVC-NEXT:    retl
;
; MINGW-LABEL: foo:
; MINGW:       # %bb.0:
; MINGW-NEXT:    pushl %ebp
; MINGW-NEXT:    movl %esp, %ebp
; MINGW-NEXT:    andl $-16, %esp
; MINGW-NEXT:    subl $16, %esp
; MINGW-NEXT:    movaps 8(%ebp), %xmm0
; MINGW-NEXT:    movups 24(%ebp), %xmm1
; MINGW-NEXT:    cmpltps %xmm1, %xmm0
; MINGW-NEXT:    movl %ebp, %esp
; MINGW-NEXT:    popl %ebp
; MINGW-NEXT:    retl
  %2 = alloca <4 x float>*, align 4
  %3 = bitcast <4 x float>** %2 to i8*
  call void @llvm.lifetime.start.p0i8(i64 4, i8* %3)
  call void @llvm.va_start(i8* %3)
  %4 = load <4 x float>*, <4 x float>** %2, align 4
  %5 = load <4 x float>, <4 x float>* %4, align 4
  %6 = fcmp ogt <4 x float> %5, %0
  %7 = sext <4 x i1> %6 to <4 x i32>
  call void @llvm.lifetime.end.p0i8(i64 4, i8* %3)
  ret <4 x i32> %7
}

define <4 x i32> @bar() nounwind {
; MSVC-LABEL: bar:
; MSVC:       # %bb.0:
; MSVC-NEXT:    subl $32, %esp
; MSVC-NEXT:    movaps {{.*#+}} xmm0 = [5.0E+0,6.0E+0,7.0E+0,8.0E+0]
; MSVC-NEXT:    movaps %xmm0, 16(%esp)
; MSVC-NEXT:    movaps {{.*#+}} xmm0 = [1.0E+0,2.0E+0,3.0E+0,4.0E+0]
; MSVC-NEXT:    movaps %xmm0, (%esp)
; MSVC-NEXT:    calll _foo
; MSVC-NEXT:    addl $32, %esp
; MSVC-NEXT:    retl
;
; MINGW-LABEL: bar:
; MINGW:       # %bb.0:
; MINGW-NEXT:    pushl %ebp
; MINGW-NEXT:    movl %esp, %ebp
; MINGW-NEXT:    andl $-16, %esp
; MINGW-NEXT:    subl $48, %esp
; MINGW-NEXT:    movaps {{.*#+}} xmm0 = [5.0E+0,6.0E+0,7.0E+0,8.0E+0]
; MINGW-NEXT:    movaps %xmm0, 16(%esp)
; MINGW-NEXT:    movaps {{.*#+}} xmm0 = [1.0E+0,2.0E+0,3.0E+0,4.0E+0]
; MINGW-NEXT:    movaps %xmm0, (%esp)
; MINGW-NEXT:    calll _foo
; MINGW-NEXT:    movl %ebp, %esp
; MINGW-NEXT:    popl %ebp
; MINGW-NEXT:    retl
  %1 = tail call <4 x i32> (<4 x float>, ...) @foo(<4 x float> <float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00>, <4 x float> <float 5.000000e+00, float 6.000000e+00, float 7.000000e+00, float 8.000000e+00>)
  ret <4 x i32> %1
}

declare i32 @testm128(i32, ...) nounwind
declare void @llvm.va_start(i8*)
declare void @llvm.lifetime.start.p0i8(i64, i8*)
declare void @llvm.lifetime.end.p0i8(i64, i8*)