MPI
If you are reading this book, you likely are interested in large computational problems. But what if your problem is too big or takes too long to solve even on a system equipped with one or more Intel Xeon® PhiTM coprocessors? Frequently the answer is a cluster: multiple systems, or nodes, connected together by a fast network and used cooperatively to solve a single problem. One major difference between programming for a single system and a cluster is that each cluster node has a separate memory space. Unlike multiple threads running in a shared memory space, communication between disjoint memory spaces usually requires the programmer to make explicit communication calls. These explicit communications occur via messages and the ...
Get Intel Xeon Phi Coprocessor High Performance Programming now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
