Historique | Voir | Annoter | Télécharger (14,16 ko)
Replace *PU by xPU
Add option on Seeds in order to improve // implementations under Threads and MPI
Define the last value of Parallel Rate exploration as the first one if not defined.
Add support for Pthreads and MPI
Replace *PU by xPU to avoid prolems on files.
Modify the "device.type" in order not to crash with POCL implementation.
Change default name of output.
Correct some errors on CUDA implementation.
Transform from Python 2 to Python 3
Identation for XPU parsing.
Improve MPI distribution.
Add MPI and pThreads version to use multiple OpenCL devices.