Stimpack: An Adaptive Rendering Optimization System for Scalable Cloud Gaming
summary
Stimpack adaptively lowers or raises server-side rendering quality based on network-driven compression so GPU cycles go where they change perceived frames, using a compression-aware efficiency metric. Implementation is a game plugin plus a runtime optimizer tested with Unreal Engine scenes (moderate and intense), up to six concurrent users, real 4G/LTE traces, and blind AB user studies. Results show up to 24% higher service quality, 2x user capacity versus high-quality baseline.
AI-written summary · about
chapters (11)
- 0:00Stimpack and cloud gaming
- 1:01Edge-cloud scalability dilemma
- 2:25Network-aware rendering opportunity
- 4:07GPU sharing impact on FPS
- 5:09Stimpack's three pillars
- 6:35Stimpack architecture workflow
- 8:01Evaluation setup details
- 9:03Scalability and FPS results
- 11:09User study on experience
- 12:57Real-world network adaptability
- 14:23Stimpack impact summary
related talks
16mHigh-density Mobile Cloud Gaming on Edge SoC Clusters
42mMaximizing Your Game's Performance in Unreal Engine
16mThree Steps to Generate Unimaginable Scale for Cloud Gaming
52mOptimising your game AFTER it ships
20mOptimizing assets for graphics heavy Web Applicatoins: tips and tricks from the game dev background
49mOn Demand Texture streaming - How we made all our Cod's fit on one PS4
21mLeaving the lag behind
18mVulkanized: Mobile Game Optimization Techniques