You've been logged out of GDC Vault since the maximum users allowed for this account has been reached. To access Members Only content on GDC Vault, please log out of GDC Vault from the computer which last accessed this account.

Click here to find out about GDC Vault Membership options for more users.


The Number One Educational Resource for the Game Industry

Session Name: Real-Time ML Inference for Mobile Gaming (Presented by Arm)
Speaker(s): Pavel Rudko
Company Name(s): Arm
Track / Format: Programming

Did you know free users get access to 30% of content from the last 2 years?

Get your team full access to the most up to date GDC content

Overview: Machine learning-based solutions promise to advance mobile gaming and are becoming more and more popular in the game industry. This includes AR and future use cases, like graphics quality improvements. However, in order to do this efficiently, inference needs to be in real-time. This presents compute challenges, as the device is busy with the graphics which further limits computational resources. Therefore, selecting the right neural network model, inference framework and pipeline-specific optimizations are crucial.In this talk, Arm will explore the state of real-time inference on mobile and how different neural networks can be used for gaming.

Game Developers Conference 2021

Pavel Rudko


free content