Single Instruction, Multiple Data (SIMD) is a technique that allows you to run multiple parallel computations on data via a single instruction.
This is an important optimization technique in many areas that have highly parallelizable workflows. For example in image processing you have situations where you want to apply the same function to every pixel in an image, this would be a case where SIMD could provide a very substantial performance improvement.
You want to deal with bulk data from your Python program. You realise that looping over every cell of a huge array from your Python code would be silly. You also would like the convenience of many kinds of canned routine to transform your data easily and efficiently. Enter NumPy!Published on September 16th, 2018 by Nick Downing.