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?
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. |