// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5
// RUN: %clang_cc1 -triple nvptx64-nvidia-cuda -emit-llvm -o - %s | FileCheck %s

extern void varargs_simple(int, ...);

// CHECK-LABEL: define dso_local void @foo(
// CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    [[C:%.*]] = alloca i8, align 1
// CHECK-NEXT:    [[S:%.*]] = alloca i16, align 2
// CHECK-NEXT:    [[I:%.*]] = alloca i32, align 4
// CHECK-NEXT:    [[L:%.*]] = alloca i64, align 8
// CHECK-NEXT:    [[F:%.*]] = alloca float, align 4
// CHECK-NEXT:    [[D:%.*]] = alloca double, align 8
// CHECK-NEXT:    [[A:%.*]] = alloca [[STRUCT_ANON:%.*]], align 4
// CHECK-NEXT:    [[V:%.*]] = alloca <4 x i32>, align 16
// CHECK-NEXT:    [[T:%.*]] = alloca [[STRUCT_ANON_0:%.*]], align 1
// CHECK-NEXT:    store i8 1, ptr [[C]], align 1
// CHECK-NEXT:    store i16 1, ptr [[S]], align 2
// CHECK-NEXT:    store i32 1, ptr [[I]], align 4
// CHECK-NEXT:    store i64 1, ptr [[L]], align 8
// CHECK-NEXT:    store float 1.000000e+00, ptr [[F]], align 4
// CHECK-NEXT:    store double 1.000000e+00, ptr [[D]], align 8
// CHECK-NEXT:    [[TMP0:%.*]] = load i8, ptr [[C]], align 1
// CHECK-NEXT:    [[CONV:%.*]] = sext i8 [[TMP0]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = load i16, ptr [[S]], align 2
// CHECK-NEXT:    [[CONV1:%.*]] = sext i16 [[TMP1]] to i32
// CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr [[I]], align 4
// CHECK-NEXT:    [[TMP3:%.*]] = load i64, ptr [[L]], align 8
// CHECK-NEXT:    [[TMP4:%.*]] = load float, ptr [[F]], align 4
// CHECK-NEXT:    [[CONV2:%.*]] = fpext float [[TMP4]] to double
// CHECK-NEXT:    [[TMP5:%.*]] = load double, ptr [[D]], align 8
// CHECK-NEXT:    call void (i32, ...) @varargs_simple(i32 noundef 0, i32 noundef [[CONV]], i32 noundef [[CONV1]], i32 noundef [[TMP2]], i64 noundef [[TMP3]], double noundef [[CONV2]], double noundef [[TMP5]]) #[[ATTR3:[0-9]+]]
// CHECK-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[A]], ptr align 4 @__const.foo.a, i64 12, i1 false)
// CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds nuw [[STRUCT_ANON]], ptr [[A]], i32 0, i32 0
// CHECK-NEXT:    [[TMP7:%.*]] = load i32, ptr [[TMP6]], align 4
// CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds nuw [[STRUCT_ANON]], ptr [[A]], i32 0, i32 1
// CHECK-NEXT:    [[TMP9:%.*]] = load i8, ptr [[TMP8]], align 4
// CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds nuw [[STRUCT_ANON]], ptr [[A]], i32 0, i32 2
// CHECK-NEXT:    [[TMP11:%.*]] = load i32, ptr [[TMP10]], align 4
// CHECK-NEXT:    call void (i32, ...) @varargs_simple(i32 noundef 0, i32 [[TMP7]], i8 [[TMP9]], i32 [[TMP11]]) #[[ATTR3]]
// CHECK-NEXT:    store <4 x i32> splat (i32 1), ptr [[V]], align 16
// CHECK-NEXT:    [[TMP12:%.*]] = load <4 x i32>, ptr [[V]], align 16
// CHECK-NEXT:    call void (i32, ...) @varargs_simple(i32 noundef 0, <4 x i32> noundef [[TMP12]]) #[[ATTR3]]
// CHECK-NEXT:    [[TMP13:%.*]] = getelementptr inbounds nuw [[STRUCT_ANON_0]], ptr [[T]], i32 0, i32 0
// CHECK-NEXT:    [[TMP14:%.*]] = load i8, ptr [[TMP13]], align 1
// CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds nuw [[STRUCT_ANON_0]], ptr [[T]], i32 0, i32 1
// CHECK-NEXT:    [[TMP16:%.*]] = load i8, ptr [[TMP15]], align 1
// CHECK-NEXT:    [[TMP17:%.*]] = getelementptr inbounds nuw [[STRUCT_ANON_0]], ptr [[T]], i32 0, i32 0
// CHECK-NEXT:    [[TMP18:%.*]] = load i8, ptr [[TMP17]], align 1
// CHECK-NEXT:    [[TMP19:%.*]] = getelementptr inbounds nuw [[STRUCT_ANON_0]], ptr [[T]], i32 0, i32 1
// CHECK-NEXT:    [[TMP20:%.*]] = load i8, ptr [[TMP19]], align 1
// CHECK-NEXT:    [[TMP21:%.*]] = getelementptr inbounds nuw [[STRUCT_ANON_0]], ptr [[T]], i32 0, i32 0
// CHECK-NEXT:    [[TMP22:%.*]] = load i8, ptr [[TMP21]], align 1
// CHECK-NEXT:    [[TMP23:%.*]] = getelementptr inbounds nuw [[STRUCT_ANON_0]], ptr [[T]], i32 0, i32 1
// CHECK-NEXT:    [[TMP24:%.*]] = load i8, ptr [[TMP23]], align 1
// CHECK-NEXT:    call void (i32, ...) @varargs_simple(i32 noundef 0, i8 [[TMP14]], i8 [[TMP16]], i8 [[TMP18]], i8 [[TMP20]], i32 noundef 0, i8 [[TMP22]], i8 [[TMP24]]) #[[ATTR3]]
// CHECK-NEXT:    ret void
//
void foo() {
  char c = '\x1';
  short s = 1;
  int i = 1;
  long l = 1;
  float f = 1.f;
  double d = 1.;
  varargs_simple(0, c, s, i, l, f, d);

  struct {int x; char c; int y;} a = {1, '\x1', 1};
  varargs_simple(0, a);

  typedef int __attribute__((ext_vector_type(4))) int4;
  int4 v = {1, 1, 1, 1};
  varargs_simple(0, v);

  struct {char c, d;} t;
  varargs_simple(0, t, t, 0, t);
}

typedef struct {long x; long y;} S;
extern void varargs_complex(S, S, ...);

// CHECK-LABEL: define dso_local void @bar(
// CHECK-SAME: ) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    [[S:%.*]] = alloca [[STRUCT_S:%.*]], align 8
// CHECK-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 8 [[S]], ptr align 8 @__const.bar.s, i64 16, i1 false)
// CHECK-NEXT:    call void (ptr, ptr, ...) @varargs_complex(ptr noundef byval([[STRUCT_S]]) align 8 [[S]], ptr noundef byval([[STRUCT_S]]) align 8 [[S]], i32 noundef 1, i64 noundef 1, double noundef 1.000000e+00) #[[ATTR3]]
// CHECK-NEXT:    ret void
//
void bar() {
  S s = {1l, 1l};
  varargs_complex(s, s, 1, 1l, 1.0);
}