From the course: Python Parallel and Concurrent Programming Part 2
Join today to access over 22,700 courses taught by industry experts or purchase this course individually.
Measure speedup - Python Tutorial
From the course: Python Parallel and Concurrent Programming Part 2
Measure speedup
- Amdahl's law is great for estimating the speedup that you might achieve by parallelizing a program, but once you've created that parallel program, it can be useful to actually measure its speedup empirically. Speedup is calculated as the ratio of two values, the time it takes for the program to execute sequentially divided by the time it takes to execute in its parallel implementation. That means we'll actually need to take two separate measurements to calculate speedup. First we'll see how long the algorithm takes to execute with a single processor. Now, this doesn't mean just take the parallel version of the program and run it with only one processor, because the parallel program will include additional overhead that isn't necessary to run sequentially. We want to measure the best possible implementation of that algorithm written with sequential execution in mind. - I've got my stopwatch ready. Let's see how fast you can add up these receipts by yourself. - Well, the fastest way…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.