◆ perf_arch
| struct starpu_perfmodel_arch _starpu_combined_worker::perf_arch |
in case there are different models of the same arch
◆ worker_mask
| uint32_t _starpu_combined_worker::worker_mask |
what is the type of workers ?
◆ worker_size
| int _starpu_combined_worker::worker_size |
◆ memory_node
| unsigned _starpu_combined_worker::memory_node |
which memory node is associated that worker to ?
◆ combined_workerid
◆ hwloc_cpu_set
| hwloc_bitmap_t _starpu_combined_worker::hwloc_cpu_set |
◆ padding
| char _starpu_combined_worker::padding[STARPU_CACHELINE_SIZE] |
Keep this last, to make sure to separate worker data in separate cache lines.
The documentation for this struct was generated from the following file: