llvm/clang/test/CodeGen/nvptx_attributes.c

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --check-attributes --check-globals
// RUN: %clang_cc1 -triple nvptx64-nvidia-cuda -target-cpu sm_61 -emit-llvm %s -o - | FileCheck %s

// CHECK: Function Attrs: noinline nounwind optnone
// CHECK-LABEL: define {{[^@]+}}@foo
// CHECK-SAME: (ptr noundef [[RET:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[RET_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT:    store ptr [[RET]], ptr [[RET_ADDR]], align 8
// CHECK-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[RET_ADDR]], align 8
// CHECK-NEXT:    store i32 1, ptr [[TMP0]], align 4
// CHECK-NEXT:    ret void
__attribute__((nvptx_kernel)) void foo(int *ret) {
  *ret = 1;
}

// CHECK: !0 = !{ptr @foo, !"kernel", i32 1}