[Bug libgomp/122280] target teams distribute parallel for collapse(2) yields different results in a matmul than separate loops (one with omp target teams distribute the second with omp parallel for) on nvptx target. Clang compiles the code correctly

[schulz.benjamin at googlemail dot com via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=122280

--- Comment #4 from Benjamin Schulz <schulz.benjamin at googlemail dot com> ---
As for the code, setting
  Math_Functions_Policy p1(Math_Functions_Policy::AUTO);
would mean that the code uses a heuristic to decide whether to offload...

For cpu, it would use CPU_ONLY...

As for my comment, the code ran without any errors, I meant, when compiled with
clang. 

On gcc, I got errors, and wrong results, and I dont know why...