llvm/test/CodeGen/X86/mmx-arg-passing-x86-64.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+mmx,+sse2 | FileCheck %s --check-prefix=X86-64
;
; On Darwin x86-64, v8i8, v4i16, v2i32 values are passed in XMM[0-7].
; On Darwin x86-64, v1i64 values are passed in 64-bit GPRs.

@g_v8qi = external global <8 x i8>

define void @t3() nounwind  {
; X86-64-LABEL: t3:
; X86-64:       ## %bb.0:
; X86-64-NEXT:    movq _g_v8qi@GOTPCREL(%rip), %rax
; X86-64-NEXT:    movq (%rax), %rdi
; X86-64-NEXT:    xorl %eax, %eax
; X86-64-NEXT:    jmp _pass_v8qi ## TAILCALL
  %tmp3 = load <8 x i8>, ptr @g_v8qi, align 8
  %tmp3a = bitcast <8 x i8> %tmp3 to <1 x i64>
  %tmp4 = tail call i32 (...) @pass_v8qi( <1 x i64> %tmp3a ) nounwind
  ret void
}

define void @t4(<1 x i64> %v1, <1 x i64> %v2) nounwind  {
; X86-64-LABEL: t4:
; X86-64:       ## %bb.0:
; X86-64-NEXT:    movq %rdi, %xmm0
; X86-64-NEXT:    movq %rsi, %xmm1
; X86-64-NEXT:    paddb %xmm0, %xmm1
; X86-64-NEXT:    movq %xmm1, %rdi
; X86-64-NEXT:    xorl %eax, %eax
; X86-64-NEXT:    jmp _pass_v8qi ## TAILCALL
  %v1a = bitcast <1 x i64> %v1 to <8 x i8>
  %v2b = bitcast <1 x i64> %v2 to <8 x i8>
  %tmp3 = add <8 x i8> %v1a, %v2b
  %tmp3a = bitcast <8 x i8> %tmp3 to <1 x i64>
  %tmp4 = tail call i32 (...) @pass_v8qi( <1 x i64> %tmp3a ) nounwind
  ret void
}

define void @t5() nounwind  {
; X86-64-LABEL: t5:
; X86-64:       ## %bb.0:
; X86-64-NEXT:    pushq %rax
; X86-64-NEXT:    xorl %edi, %edi
; X86-64-NEXT:    callq _pass_v1di
; X86-64-NEXT:    popq %rax
; X86-64-NEXT:    retq
  call void @pass_v1di( <1 x i64> zeroinitializer )
  ret void
}

declare i32 @pass_v8qi(...)
declare void @pass_v1di(<1 x i64>)