5216a9bfb0
Currently, the AMDGPU plugin did not support the `TARGET_ALLOC_SHARED` allocation kind. We used the fine-grained memory allocator for the "host" alloc when this is most likely not what is intended. Fine-grained memory can be accessed by all agents, so it should be considered shared. This patch removes the use of fine-grained memory for the host allocator. A later patch will add support for this via the `hsa_amd_memory_lock` method. Reviewed By: kevinsala Differential Revision: https://reviews.llvm.org/D143771
30 lines
695 B
C
30 lines
695 B
C
// RUN: %libomptarget-compile-run-and-check-generic
|
|
|
|
#include <omp.h>
|
|
#include <stdio.h>
|
|
|
|
void *llvm_omp_target_alloc_shared(size_t, int);
|
|
void llvm_omp_target_free_shared(void *, int);
|
|
|
|
int main() {
|
|
const int N = 64;
|
|
const int device = omp_get_default_device();
|
|
|
|
int *shared_ptr = llvm_omp_target_alloc_shared(N * sizeof(int), device);
|
|
|
|
#pragma omp target teams distribute parallel for device(device) \
|
|
is_device_ptr(shared_ptr)
|
|
for (int i = 0; i < N; ++i) {
|
|
shared_ptr[i] = 1;
|
|
}
|
|
|
|
int sum = 0;
|
|
for (int i = 0; i < N; ++i)
|
|
sum += shared_ptr[i];
|
|
|
|
llvm_omp_target_free_shared(shared_ptr, device);
|
|
// CHECK: PASS
|
|
if (sum == N)
|
|
printf("PASS\n");
|
|
}
|