AMD platforms have a bug when using struct assignment. this affects algorithms like fill() when used with pairs/tuples. see: https://community.amd.com/thread/166622
| 36 | // |
| 37 | // see: https://community.amd.com/thread/166622 |
| 38 | inline bool bug_in_struct_assignment(const boost::compute::device &device) |
| 39 | { |
| 40 | return boost::compute::detail::is_amd_device(device); |
| 41 | } |
| 42 | |
| 43 | // clEnqueueSVMMemcpy() operation does not work on AMD devices. This affects |
| 44 | // copy() algorithm. This bug was fixed in AMD drivers for Windows. |
no test coverage detected