We finally got our buildbot added (to staging, at least) so we want to start running L0 tests in CI. We need `check-offload` to pass though, so XFAIL everything failing. There's a couple `UNSUPPORTED` as well, those are for sporadic fails. Also make set the `gpu` and `intelgpu` LIT variables when testing the `spirv64-intel` triple. We have no DeviceRTL yet so basically everything fails, but we manage to get ``` Total Discovered Tests: 432 Unsupported : 169 (39.12%) Passed : 67 (15.51%) Expectedly Failed: 196 (45.37%) ``` We still don't build the level zero plugin by default and these tests don't run unless the plugin was built, so this has no effect on most builds. --------- Signed-off-by: Nick Sarnie <nick.sarnie@intel.com>
39 lines
1013 B
C
39 lines
1013 B
C
// RUN: %libomptarget-compile-generic && %libomptarget-run-generic
|
|
// RUN: %libomptarget-compileopt-generic && %libomptarget-run-generic
|
|
// XFAIL: intelgpu
|
|
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
|
|
int main() {
|
|
long unsigned *DP = 0;
|
|
int N = 32;
|
|
int Threads = 64;
|
|
int Teams = 10;
|
|
|
|
// Allocate ~160 KiB on the device.
|
|
#pragma omp target map(from : DP)
|
|
DP = (long unsigned *)malloc(sizeof(long unsigned) * N * Threads * Teams);
|
|
|
|
#pragma omp target teams distribute parallel for num_teams(Teams) \
|
|
thread_limit(Threads) is_device_ptr(DP)
|
|
for (int i = 0; i < Threads * Teams; ++i) {
|
|
for (int j = 0; j < N; ++j) {
|
|
DP[i * N + j] = i + j;
|
|
}
|
|
}
|
|
|
|
long unsigned s = 0;
|
|
#pragma omp target teams distribute parallel for num_teams(Teams) \
|
|
thread_limit(Threads) reduction(+ : s)
|
|
for (int i = 0; i < Threads * Teams; ++i) {
|
|
for (int j = 0; j < N; ++j) {
|
|
s += DP[i * N + j];
|
|
}
|
|
}
|
|
|
|
// CHECK: Sum: 6860800
|
|
printf("Sum: %li\n", s);
|
|
return 0;
|
|
}
|