From the course: Complete Guide to Parallel and Concurrent Programming in Python

Unlock the full course today

Join today to access over 24,900 courses taught by industry experts.

Mapping

Mapping - Python Tutorial

From the course: Complete Guide to Parallel and Concurrent Programming in Python

Start my 1-month free trial Buy for my team

Mapping

“

- The fourth and final stage of our parallel design process is mapping. And this is where we specify where each of the tasks we established will actually execute. Now, this mapping stage does not apply if you're only using a single-processor system because there's only one place to execute the program, or if you're using a system with automated task scheduling. So if I'm just writing programs to run on a desktop computer, like the examples we've shown you throughout this course, mapping isn't even a consideration. The operating system handles scheduling threads to execute on specific processor cores, so that's out of our hands. Mapping really becomes a factor if you're using a distributed system or specialized hardware with lots of parallel processors for large-scale problems, like in scientific computing applications. The usual goal of a mapping algorithm is to minimize the total execution time of the program, and there are two main strategies to achieve that goal. You can place…

Contents