September 2008
Intermediate to advanced
280 pages
6h 31m
English
There are two main types of parallel programming architectures—shared memory and message passing.
The term shared memory means exactly that: Multiple CPUs all have access to some common physical memory. Code running on one CPU communicates with code running on the others by reading from and writing to this shared memory, much as threads in a multithreaded application communicate with one another through a shared address space. (Indeed, threaded programming has become the standard way to write application code for shared memory systems.)
By contrast, in a message passing environment, code running on each CPU can only access that CPU's local memory, and it communicates with the others by sending strings of ...
Read now
Unlock full access