GDC is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

View, browse and sort the ever-growing list of sessions by pass type, track, and format. With this Session Viewer, you can view GDC 2023 session details, speakers and share your favorites via social media. You will be able to build your schedule and access it during the show via export or with the Mobile App, once live. Sessions do fill up and seating is first come, first serve, so arrive early to sessions that you would like to attend.

Engine Optimization Powered by Big Data

Vladimir Katchadourian  (Data Scientist, Ubisoft)

Vincent Leclercq  (Lead Programmer, Ubisoft)

Pass Type: All Access Pass, Core Pass

Topic: Production & Team Leadership, Programming

Format: Lecture

Vault Recording: TBD

Audience Level: All

As games grow in complexity and size, the systems they rely on become increasingly difficult to master—and so does their technical optimization. Often handled by experts at the end of a production, the analysis and prioritization of such optimization tasks is a long and tedious job.

To overcome this problem, we developed an automated solution leveraging big data platform. We collect, store, transform, aggregate and make profiling data available to developers through standard analytical dashboards and queryable databases. We also engineered machine learning models to prioritize which system would be the best to optimize.

We were able to reduce the time spent on analysis and prioritization from hours to minutes. Moreover, profiling questions are now more accessible thus it empowers all developers on their system's performance, making profiling concerns not only an expert field.

Takeaway

Attendees will see the benefits of applying big data solutions to technical performance issues on ever bigger and complex games. Also, this set of new technology opens new methods of working on performance optimization such as transforming the analysis and prioritization of issues from hours to minutes and with more accuracy and less bias.

Intended Audience

This is for anyone with an interest in performance optimization. We expect Technical leads, Technical directors and programmers to get the most out of it. Having a good grasp on performance issues in open worlds will help understand our motivation to rely on Big Data and Machine Learning solutions.