
In a nutshell, this moves our libomptarget code to populate the offload subproject. With this commit, users need to enable the new LLVM/Offload subproject as a runtime in their cmake configuration. No further changes are expected for downstream code. Tests and other components still depend on OpenMP and have also not been renamed. The results below are for a build in which OpenMP and Offload are enabled runtimes. In addition to the pure `git mv`, we needed to adjust some CMake files. Nothing is intended to change semantics. ``` ninja check-offload ``` Works with the X86 and AMDGPU offload tests ``` ninja check-openmp ``` Still works but doesn't build offload tests anymore. ``` ls install/lib ``` Shows all expected libraries, incl. - `libomptarget.devicertl.a` - `libomptarget-nvptx-sm_90.bc` - `libomptarget.rtl.amdgpu.so` -> `libomptarget.rtl.amdgpu.so.18git` - `libomptarget.so` -> `libomptarget.so.18git` Fixes: https://github.com/llvm/llvm-project/issues/75124 --------- Co-authored-by: Saiyedul Islam <Saiyedul.Islam@amd.com>
54 lines
1.2 KiB
C++
54 lines
1.2 KiB
C++
// Unonptimized, we need 24000000 bytes heap
|
|
// RUN: %libomptarget-compilexx-generic
|
|
// RUN: env LIBOMPTARGET_HEAP_SIZE=24000000 \
|
|
// RUN: %libomptarget-run-generic 2>&1 | %fcheck-generic
|
|
// RUN: %libomptarget-compileoptxx-run-and-check-generic
|
|
|
|
#include <iostream>
|
|
|
|
template <typename LOOP_BODY>
|
|
inline void forall(int Begin, int End, LOOP_BODY LoopBody) {
|
|
#pragma omp target parallel for schedule(static)
|
|
for (int I = Begin; I < End; ++I) {
|
|
LoopBody(I);
|
|
}
|
|
}
|
|
|
|
#define N (1000)
|
|
|
|
//
|
|
// Demonstration of the RAJA abstraction using lambdas
|
|
// Requires data mapping onto the target section
|
|
//
|
|
int main() {
|
|
double A[N], B[N], C[N];
|
|
|
|
for (int I = 0; I < N; I++) {
|
|
A[I] = I + 1;
|
|
B[I] = -I;
|
|
C[I] = -9;
|
|
}
|
|
|
|
#pragma omp target data map(tofrom : C[0 : N]) map(to : A[0 : N], B[0 : N])
|
|
{
|
|
forall(0, N, [&](int I) { C[I] += A[I] + B[I]; });
|
|
}
|
|
|
|
int Fail = 0;
|
|
for (int I = 0; I < N; I++) {
|
|
if (C[I] != -8) {
|
|
std::cout << "Failed at " << I << " with val " << C[I] << std::endl;
|
|
Fail = 1;
|
|
}
|
|
}
|
|
|
|
// CHECK: Succeeded
|
|
if (Fail) {
|
|
std::cout << "Failed" << std::endl;
|
|
} else {
|
|
std::cout << "Succeeded" << std::endl;
|
|
}
|
|
|
|
return 0;
|
|
}
|