Optimising your game AFTER it ships
Talkat GCAP 2022: Ambition · on Tuesday, 2022-10-04· at 12:00· Room 109, 1 Convention Centre Place South Wharf, Victoria 3006·
summary
A live-game performance pipeline is built: clients send sampled subframe times to a global collector, data lands in Data Bricks/Tableau and triggers alerts; long-term storage shows gradual drift across two years and a 24‑release/year cadence. Debug tools include replay playback plus GPU profiling (GPA) to find a tessellated trail causing ~10ms on specific frames, per-game RPD files (quantized medians, ~2MB raw) for triage, and aggregated PassMark buckets to compare hardware-equivalent cohorts.
AI-written summary · about
chapters (14)
- 0:00Introduction
- 3:12Player feedback issues
- 7:49Performance degradation types
- 12:24Automating detection
- 15:56Analyzing real-world data
- 20:15Benchmark aggregation
- 26:40Visualizing trends with Tableau
- 29:11Root causes of slowdowns
- 32:22Triage player issues
- 38:27Collecting breadcrumbs
- 40:10Server-side metrics
- 43:21Iterative optimization
- 44:47Summary
- 45:29Q&A
related talks
01h 03mMonitoring Performance on Massive Games.
36mDebug, Analyze and Optimize Games with Intel Tools
25mSuperstar Session: How to Spot Performance Problems that Gamers Hate & Even Major Studios Often Miss
42mMaximizing Your Game's Performance in Unreal Engine
58mUE4 Performance and Profiling
01h 03mMaximizing Your Game's Performance in Unreal Engine
28mOptimizing and Profiling UI Performance
41mGoing into the New Era: Galaxy GameDev - Updates, Secrets and Leaks