; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
; RUN: llc -verify-machineinstrs -stop-before=ppc-vsx-copy -vec-extabi \
; RUN:     -mcpu=pwr7  -mtriple powerpc64-ibm-aix-xcoff < %s | \
; RUN: FileCheck %s

; Testing passing a vector <4 x i32> through ellipses of a variadic function.
define <4 x i32> @callee(i32 signext %count, ...) {
  ; CHECK-LABEL: name: callee
  ; CHECK: bb.0.entry:
  ; CHECK:   liveins: $x4, $x5, $x6, $x7, $x8, $x9, $x10
  ; CHECK:   [[COPY:%[0-9]+]]:g8rc = COPY $x10
  ; CHECK:   [[COPY1:%[0-9]+]]:g8rc = COPY $x9
  ; CHECK:   [[COPY2:%[0-9]+]]:g8rc = COPY $x8
  ; CHECK:   [[COPY3:%[0-9]+]]:g8rc = COPY $x7
  ; CHECK:   [[COPY4:%[0-9]+]]:g8rc = COPY $x6
  ; CHECK:   [[COPY5:%[0-9]+]]:g8rc = COPY $x5
  ; CHECK:   [[COPY6:%[0-9]+]]:g8rc = COPY $x4
  ; CHECK:   STD [[COPY6]], 0, %fixed-stack.0 :: (store (s64) into %fixed-stack.0)
  ; CHECK:   STD [[COPY5]], 8, %fixed-stack.0 :: (store (s64) into %fixed-stack.0 + 8)
  ; CHECK:   STD [[COPY4]], 16, %fixed-stack.0 :: (store (s64))
  ; CHECK:   STD [[COPY3]], 24, %fixed-stack.0 :: (store (s64))
  ; CHECK:   STD [[COPY2]], 32, %fixed-stack.0 :: (store (s64))
  ; CHECK:   STD [[COPY1]], 40, %fixed-stack.0 :: (store (s64))
  ; CHECK:   STD [[COPY]], 48, %fixed-stack.0 :: (store (s64))
  ; CHECK:   LIFETIME_START %stack.0.arg_list
  ; CHECK:   [[ADDI8_:%[0-9]+]]:g8rc = ADDI8 %fixed-stack.0, 0
  ; CHECK:   STD killed [[ADDI8_]], 0, %stack.0.arg_list :: (store (s64) into %ir.0)
  ; CHECK:   [[ADDI8_1:%[0-9]+]]:g8rc = ADDI8 %fixed-stack.0, 15
  ; CHECK:   [[RLDICR:%[0-9]+]]:g8rc = RLDICR killed [[ADDI8_1]], 0, 59
  ; CHECK:   [[LXVW4X:%[0-9]+]]:vsrc = LXVW4X $zero8, killed [[RLDICR]] :: (load (s128) from %ir.4)
  ; CHECK:   LIFETIME_END %stack.0.arg_list
  ; CHECK:   $v2 = COPY [[LXVW4X]]
  ; CHECK:   BLR8 implicit $lr8, implicit $rm, implicit $v2
entry:
  %arg_list = alloca i8*, align 8
  %0 = bitcast i8** %arg_list to i8*
  call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull %0)
  call void @llvm.va_start(i8* nonnull %0)
  %argp.cur = load i8*, i8** %arg_list, align 8
  %1 = ptrtoint i8* %argp.cur to i64
  %2 = add i64 %1, 15
  %3 = and i64 %2, -16
  %argp.cur.aligned = inttoptr i64 %3 to i8*
  %argp.next = getelementptr inbounds i8, i8* %argp.cur.aligned, i64 16
  store i8* %argp.next, i8** %arg_list, align 8
  %4 = inttoptr i64 %3 to <4 x i32>*
  %5 = load <4 x i32>, <4 x i32>* %4, align 16
  call void @llvm.va_end(i8* nonnull %0)
  call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull %0)
  ret <4 x i32> %5
}

declare void @llvm.lifetime.start.p0i8(i64 immarg, i8* nocapture)

declare void @llvm.va_start(i8*)

declare void @llvm.va_end(i8*)

declare void @llvm.lifetime.end.p0i8(i64 immarg, i8* nocapture)