; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_52 -mattr=+ptx64 | FileCheck %s
; RUN: %if ptxas-isa-6.4 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_52 -mattr=+ptx64 | %ptxas-verify %}

target triple = "nvptx64-nvidia-cuda"

%struct.S = type { i8 }
%struct.U = type { i64 }

@ptr = external global ptr, align 8

define internal i32 @foo() {
; CHECK-LABEL: foo(
; CHECK:       {
; CHECK-NEXT:    .local .align 1 .b8 __local_depot0[2];
; CHECK-NEXT:    .reg .b64 %SP;
; CHECK-NEXT:    .reg .b64 %SPL;
; CHECK-NEXT:    .reg .b16 %rs<2>;
; CHECK-NEXT:    .reg .b32 %r<2>;
; CHECK-NEXT:    .reg .b64 %rd<4>;
; CHECK-EMPTY:
; CHECK-NEXT:  // %bb.0: // %entry
; CHECK-NEXT:    mov.b64 %SPL, __local_depot0;
; CHECK-NEXT:    cvta.local.u64 %SP, %SPL;
; CHECK-NEXT:    ld.global.b64 %rd1, [ptr];
; CHECK-NEXT:    { // callseq 0, 0
; CHECK-NEXT:    .param .align 1 .b8 param0[1];
; CHECK-NEXT:    .param .b64 param1;
; CHECK-NEXT:    .param .b32 retval0;
; CHECK-NEXT:    add.u64 %rd2, %SP, 0;
; CHECK-NEXT:    st.param.b64 [param1], %rd2;
; CHECK-NEXT:    add.u64 %rd3, %SPL, 1;
; CHECK-NEXT:    ld.local.b8 %rs1, [%rd3];
; CHECK-NEXT:    st.param.b8 [param0], %rs1;
; CHECK-NEXT:    prototype_0 : .callprototype (.param .b32 _) _ (.param .align 1 .b8 _[1], .param .b64 _);
; CHECK-NEXT:    call (retval0), %rd1, (param0, param1), prototype_0;
; CHECK-NEXT:    ld.param.b32 %r1, [retval0];
; CHECK-NEXT:    } // callseq 0
; CHECK-NEXT:    st.param.b32 [func_retval0], %r1;
; CHECK-NEXT:    ret;
entry:
  %s = alloca %struct.S, align 1
  %agg.tmp = alloca %struct.S, align 1
  %0 = load ptr, ptr @ptr, align 8
  %call = call i32 %0(ptr byval(%struct.S) align 1 %agg.tmp, ptr noundef %s)
  ret i32 %call
}

define internal i32 @bar() {
; CHECK-LABEL: bar(
; CHECK:         // @bar
; CHECK-NEXT:  {
; CHECK-NEXT:    .local .align 8 .b8 __local_depot1[16];
; CHECK-NEXT:    .reg .b64 %SP;
; CHECK-NEXT:    .reg .b64 %SPL;
; CHECK-NEXT:    .reg .b32 %r<2>;
; CHECK-NEXT:    .reg .b64 %rd<5>;
; CHECK-EMPTY:
; CHECK-NEXT:  // %bb.0: // %entry
; CHECK-NEXT:    mov.b64 %SPL, __local_depot1;
; CHECK-NEXT:    cvta.local.u64 %SP, %SPL;
; CHECK-NEXT:    ld.global.b64 %rd1, [ptr];
; CHECK-NEXT:    { // callseq 1, 0
; CHECK-NEXT:    .param .align 8 .b8 param0[8];
; CHECK-NEXT:    .param .b64 param1;
; CHECK-NEXT:    .param .b32 retval0;
; CHECK-NEXT:    add.u64 %rd2, %SP, 0;
; CHECK-NEXT:    st.param.b64 [param1], %rd2;
; CHECK-NEXT:    add.u64 %rd3, %SPL, 8;
; CHECK-NEXT:    ld.local.b64 %rd4, [%rd3];
; CHECK-NEXT:    st.param.b64 [param0], %rd4;
; CHECK-NEXT:    prototype_1 : .callprototype (.param .b32 _) _ (.param .align 8 .b8 _[8], .param .b64 _);
; CHECK-NEXT:    call (retval0), %rd1, (param0, param1), prototype_1;
; CHECK-NEXT:    ld.param.b32 %r1, [retval0];
; CHECK-NEXT:    } // callseq 1
; CHECK-NEXT:    st.param.b32 [func_retval0], %r1;
; CHECK-NEXT:    ret;
entry:
  %s = alloca %struct.U, align 8
  %agg.tmp = alloca %struct.U, align 8
  %0 = load ptr, ptr @ptr, align 8
  %call = call noundef i32 %0(ptr byval(%struct.U) align 8 %agg.tmp, ptr %s)
  ret i32 %call
}