63ca93c7d1
This patch renames the `OpenMPIRBuilderConfig` flags to reduce confusion over their meaning. `IsTargetCodegen` becomes `IsGPU`, whereas `IsEmbedded` becomes `IsTargetDevice`. The `-fopenmp-is-device` compiler option is also renamed to `-fopenmp-is-target-device` and the `omp.is_device` MLIR attribute is renamed to `omp.is_target_device`. Getters and setters of all these renamed properties are also updated accordingly. Many unit tests have been updated to use the new names, but an alias for the `-fopenmp-is-device` option is created so that external programs do not stop working after the name change. `IsGPU` is set when the target triple is AMDGCN or NVIDIA PTX, and it is only valid if `IsTargetDevice` is specified as well. `IsTargetDevice` is set by the `-fopenmp-is-target-device` compiler frontend option, which is only added to the OpenMP device invocation for offloading-enabled programs. Differential Revision: https://reviews.llvm.org/D154591
58 lines
2.3 KiB
C++
58 lines
2.3 KiB
C++
// 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
|
|
// REQUIRES: amdgpu-registered-target
|
|
|
|
|
|
// Test target codegen - host bc file has to be created first.
|
|
// 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
|
|
// 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
|
|
|
|
// 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
|
|
// 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
|
|
|
|
// expected-no-diagnostics
|
|
|
|
#ifndef HEADER
|
|
#define HEADER
|
|
|
|
typedef enum omp_allocator_handle_t {
|
|
omp_null_allocator = 0,
|
|
omp_default_mem_alloc = 1,
|
|
omp_large_cap_mem_alloc = 2,
|
|
omp_const_mem_alloc = 3,
|
|
omp_high_bw_mem_alloc = 4,
|
|
omp_low_lat_mem_alloc = 5,
|
|
omp_cgroup_mem_alloc = 6,
|
|
omp_pteam_mem_alloc = 7,
|
|
omp_thread_mem_alloc = 8,
|
|
KMP_ALLOCATOR_MAX_HANDLE = __UINTPTR_MAX__
|
|
} omp_allocator_handle_t;
|
|
|
|
//.
|
|
// CHECK-AMD: @local_a = internal addrspace(3) global [10 x i32] poison, align 4
|
|
//.
|
|
// CHECK-NVIDIA: @local_a = internal addrspace(3) global [10 x i32] poison, align 4
|
|
//.
|
|
int main()
|
|
{
|
|
int N = 10000;
|
|
int *a = new int[N];
|
|
#pragma omp target data map(tofrom:a[:N])
|
|
{
|
|
#pragma omp target teams distribute parallel for
|
|
for(int i = 0; i < N; i++)
|
|
{
|
|
int local_a[10];
|
|
#pragma omp allocate(local_a) allocator(omp_pteam_mem_alloc)
|
|
for(int j = 0; j < 10; j++)
|
|
local_a[j] = a[(i + j) % N];
|
|
a[i] = local_a[0];
|
|
}
|
|
}
|
|
return a[17];
|
|
}
|
|
|
|
#endif
|
|
//// NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
|
|
// CHECK-AMD: {{.*}}
|
|
// CHECK-NVIDIA: {{.*}}
|