Who is this for?
This Learning Path is for game developers, graphics engineers, and technical leads who understand Arm Neural Technology and want to plan an integration for a mobile game.
What will you learn?
After completing this Learning Path, you'll be able to perform the following tasks:
- Choose the Arm Neural Technology integration route that matches your game and team.
- Plan an Neural Frame Rate Upscaling (NFRU) evaluation using public Arm tools and representative game content.
- Decide when advanced Neural Super Sampling and Denoising (NSSD) exploration with Arm fits your visual goals.
- Use Model Gym, Arm ML Inference Advisor (MLIA), and Streamline to plan model development and validation for neural accelerator (NX).
Prerequisites
Before starting, you'll need the following prerequisites:
- Familiarity with Arm Neural Technology and its NSS, NFRU, and NSSD use cases
- Basic understanding of real-time rendering, motion vectors, temporal techniques, and denoising
- Familiarity with your game’s frame-rate, image-quality, power, and thermal targets
Summary
This summary was drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.
You’ll choose an Arm Neural Technology route for your game’s visual goal and engine. You’ll examine Neural Frame Rate Upscaling (NFRU) inputs and frame pacing, then set pass criteria and test game content. Next, you’ll decide whether NSSD merits experimental exploration with Arm. If a measured gap justifies model work, you’ll use Model Gym, MLIA, and Streamline to assess candidates. You’ll finish with an integration brief separating estimates from device measurements.