test/Fir/CUDA/cuda-register-func.fir

// RUN: fir-opt --cuf-add-constructor %s | FileCheck %s

module attributes {dlti.dl_spec = #dlti.dl_spec<#dlti.dl_entry<!llvm.ptr, dense<64> : vector<4xi64>>, #dlti.dl_entry<!llvm.ptr<271>, dense<32> : vector<4xi64>>, #dlti.dl_entry<!llvm.ptr<270>, dense<32> : vector<4xi64>>, #dlti.dl_entry<f128, dense<128> : vector<2xi64>>, #dlti.dl_entry<f64, dense<64> : vector<2xi64>>, #dlti.dl_entry<f80, dense<128> : vector<2xi64>>, #dlti.dl_entry<f16, dense<16> : vector<2xi64>>, #dlti.dl_entry<i32, dense<32> : vector<2xi64>>, #dlti.dl_entry<i16, dense<16> : vector<2xi64>>, #dlti.dl_entry<i128, dense<128> : vector<2xi64>>, #dlti.dl_entry<i8, dense<8> : vector<2xi64>>, #dlti.dl_entry<!llvm.ptr<272>, dense<64> : vector<4xi64>>, #dlti.dl_entry<i64, dense<64> : vector<2xi64>>, #dlti.dl_entry<i1, dense<8> : vector<2xi64>>, #dlti.dl_entry<"dlti.endianness", "little">, #dlti.dl_entry<"dlti.stack_alignment", 128 : i64>>, fir.defaultkind = "a1c4d8i4l4r4", fir.kindmap = "", gpu.container_module, llvm.data_layout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128", llvm.ident = "flang version 20.0.0 (https://github.com/llvm/llvm-project.git cae351f3453a0a26ec8eb2ddaf773c24a29d929e)", llvm.target_triple = "x86_64-unknown-linux-gnu"} {
  gpu.module @cuda_device_mod {
    gpu.func @_QPsub_device1() kernel {
      gpu.return
    }
    gpu.func @_QPsub_device2(%arg0: !fir.ref<f32>) kernel {
      gpu.return
    }
  }
}

// CHECK-LABEL: llvm.func internal @__cudaFortranConstructor()
// CHECK: %[[MOD_HANDLE:.*]] = cuf.register_module @cuda_device_mod -> !llvm.ptr
// CHECK: cuf.register_kernel @cuda_device_mod::@_QPsub_device1(%[[MOD_HANDLE]] : !llvm.ptr)
// CHECK: cuf.register_kernel @cuda_device_mod::@_QPsub_device2(%[[MOD_HANDLE]] : !llvm.ptr)