; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_20 -verify-machineinstrs | FileCheck %s
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_20 | %ptxas-verify %}

target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"

declare i8 @llvm.nvvm.ldu.global.i.i8.p0(ptr, i32)

define i8 @foo(ptr %a) {
; CHECK-LABEL: foo(
; CHECK:       {
; CHECK-NEXT:    .reg .b16 %rs<2>;
; CHECK-NEXT:    .reg .b32 %r<2>;
; CHECK-NEXT:    .reg .b64 %rd<2>;
; CHECK-EMPTY:
; CHECK-NEXT:  // %bb.0:
; CHECK-NEXT:    ld.param.b64 %rd1, [foo_param_0];
; CHECK-NEXT:    ldu.global.b8 %rs1, [%rd1];
; CHECK-NEXT:    cvt.u32.u16 %r1, %rs1;
; CHECK-NEXT:    st.param.b32 [func_retval0], %r1;
; CHECK-NEXT:    ret;
  %val = tail call i8 @llvm.nvvm.ldu.global.i.i8.p0(ptr %a, i32 4)
  ret i8 %val
}