Saturday 11:15 AM–12:00 PM in C01

How GPU Computing literally saved me at work

Abhishek Mungoli

Audience level:
Intermediate

Description

Distributed/Parallel computing is at the heart of new technology. Every company, big or small want to make most of the technology available to them. One such niche technology is GPU computing. Here, I present to you a real-world application on how GPU can save computing efforts and reduce the computation time from 2 days to 20 seconds. Shared is a live application from Retail domain utilizing GPU.

Abstract

Distributed/Parallel computing is at the heart of new technology. Every company, big or small want to make most of the technology available to them. One such niche technology is GPU computing. If used cautiously can save a lot of computing efforts and time across the applications. Business, with the boom in Machine learning/Deep learning techniques, are on the way to leverage this technology in their day to day work. Here, I present to you a real-time application on how GPU can save computing efforts and reduce the computation time from 2 days to 20 seconds. The talk will cover the best case scenarios and use case for the GPU implementing for recommendations at scale. The talk will start with the overview of the problem at hand, comparing CPU and GPU processing time and best fit to utilize GPU for the task in hand or any other scenario.

For those, interested in delving into the detailed code utilized for the same, here’s the link to my blog containing the same, https://medium.com/walmartlabs/how-gpu-computing-literally-saved-me-at-work-fc1dc70f48b6

Subscribe to Receive PyData Updates