d5d836635c
We are planning on making LTO the default compilation mode for offloading. In order to make sure it works we should run these tests on the test suite. AMDGPU already uses the LTO compilation path for its linking, but in LTO mode it also links the static library late. Performing LTO requires the static library to be built, if we make the change this will be a hard requirement and the old bitcode library will go away. This means users will need to use either a two-step build or a runtimes build for libomptarget. Reviewed By: JonChesterfield Differential Revision: https://reviews.llvm.org/D127512
44 lines
869 B
C++
44 lines
869 B
C++
// RUN: %libomptarget-compilexx-run-and-check-generic
|
|
|
|
// UNSUPPORTED: x86_64-pc-linux-gnu
|
|
// UNSUPPORTED: x86_64-pc-linux-gnu-oldDriver
|
|
// UNSUPPORTED: x86_64-pc-linux-gnu-LTO
|
|
|
|
#include <cassert>
|
|
#include <iostream>
|
|
|
|
int main(int argc, char *argv[]) {
|
|
constexpr const int num_threads = 64, N = 128;
|
|
int array[num_threads] = {0};
|
|
|
|
#pragma omp parallel for
|
|
for (int i = 0; i < num_threads; ++i) {
|
|
int tmp[N];
|
|
|
|
for (int j = 0; j < N; ++j) {
|
|
tmp[j] = i;
|
|
}
|
|
|
|
#pragma omp target teams distribute parallel for map(tofrom : tmp)
|
|
for (int j = 0; j < N; ++j) {
|
|
tmp[j] += j;
|
|
}
|
|
|
|
for (int j = 0; j < N; ++j) {
|
|
array[i] += tmp[j];
|
|
}
|
|
}
|
|
|
|
// Verify
|
|
for (int i = 0; i < num_threads; ++i) {
|
|
const int ref = (0 + N - 1) * N / 2 + i * N;
|
|
assert(array[i] == ref);
|
|
}
|
|
|
|
std::cout << "PASS\n";
|
|
|
|
return 0;
|
|
}
|
|
|
|
// CHECK: PASS
|