clang/test/OpenMP/target_team_variable_codegen.cpp

   1 // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --check-globals --prefix-filecheck-ir-name _ --global-value-regex "llvm.compiler.used" "_[0-9a-zA-Z]+A[0-9a-zA-Z]+pi[0-9a-zA-Z]+" "_[0-9a-zA-Z]+anotherPi" --version 2
   2 // REQUIRES: amdgpu-registered-target
   3
   4
   5 // Test target codegen - host bc file has to be created first.
   6 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm-bc %s -o %t-ppc-host-amd.bc
   7 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple amdgcn-amd-amdhsa -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm %s -fopenmp-target-debug -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host-amd.bc -o - | FileCheck %s --check-prefix=CHECK-AMD
   8
   9 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host-nvidia.bc
  10 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-unknown-unknown -emit-llvm %s -fopenmp-target-debug -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host-nvidia.bc -o - | FileCheck %s --check-prefix=CHECK-NVIDIA
  11
  12 // expected-no-diagnostics
  13
  14 #ifndef HEADER
  15 #define HEADER
  16
  17 typedef enum omp_allocator_handle_t {
  18   omp_null_allocator = 0,
  19   omp_default_mem_alloc = 1,
  20   omp_large_cap_mem_alloc = 2,
  21   omp_const_mem_alloc = 3,
  22   omp_high_bw_mem_alloc = 4,
  23   omp_low_lat_mem_alloc = 5,
  24   omp_cgroup_mem_alloc = 6,
  25   omp_pteam_mem_alloc = 7,
  26   omp_thread_mem_alloc = 8,
  27   KMP_ALLOCATOR_MAX_HANDLE = __UINTPTR_MAX__
  28 } omp_allocator_handle_t;
  29
  30 int main()
  31 {
  32         int N = 10000;
  33         int *a = new int[N];
  34 #pragma omp target data map(tofrom:a[:N])
  35         {
  36 #pragma omp target teams distribute parallel for
  37     for(int i = 0; i < N; i++)
  38     {
  39       int local_a[10];
  40 #pragma omp allocate(local_a) allocator(omp_pteam_mem_alloc)
  41       for(int j = 0; j < 10; j++)
  42                     local_a[j] = a[(i + j) % N];
  43       a[i] = local_a[0];
  44     }
  45         }
  46   return a[17];
  47 }
  48
  49 #endif
  50 //// NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
  51 // CHECK-AMD: {{.*}}
  52 // CHECK-NVIDIA: {{.*}}