Automatic parallelization: Difference between revisions

Revision as of 10:35, 2 July 2007

Revision as of 00:43, 26 September 2007

Line 39:

Automatic parallelization by compilers or tools is very difficult due to the following reasons:

* dependence analysis is hard for code using indirect addressing, pointers, recursion, indirect function calls.

* while loops hashave unknown number of iterations

* accesses to global resources is difficult to coordinate: memory allocation, I/O, shared variables