Choose a language:


|    Programming

As new platforms emerge and existing platforms evolve, programmers face an ever increasing challenge to produce games that capture the attention of the public and the media. The Programming Track focuses on these challenges and the opportunities presented by next and current generation development including: mature consoles, new handhelds, a highly competitive sales environment, and increased demand for very high production values in games.

Arrow Search for all Programming Track sessions


Scaling from Mobile to High-End PCs: The Tech of Broken Age
Oliver Franzke (Double Fine Productions)
Bringing the beautiful and lively world of Broken Age simultaneously to five different platforms ranging from older mobile devices to state-of-the-art PCs was a great challenge. This talk will describe the key decisions made to achieve the necessary scalability, and will detail the authoring process of flexible 2D characters and parallaxing environments, the data build pipeline, as well as run-time techniques such as advanced 2D lighting and shadows. Several practical solutions for maximizing rendering performance on mobile GPUs as well as other challenges associated with mobile/PC cross-platform game development will be presented in detail.
Engine Postmortem of inFAMOUS: Second Son
Adrian Bentley (Sucker Punch Productions)
Have you ever wanted to make an urban open world super hero game? Push boundaries on emotive cutscenes? Render awesome particle effects? Or maybe you just want to make your game really cool on the PS4? In this talk, we'll describe how Sucker Punch designed the inFAMOUS Second Son engine to take advantage of the power of the PS4. We'll cover our threading approach, its pros and cons, how we made content easier to tweak and create, and how we utilized compute and the PS4's GPU to achieve new levels of visual fidelity.
Modeling AI Perception and Awareness in Splinter Cell: Blacklist
Martin Walsh (Ubisoft)
With many recent games incorporating stealth elements and more meaningful AI interactions, gamers expect more from AI perception models than a simple vision cone and hearing radius. They expect realistic vision and hearing, but they also expect social, environmental and contextual awareness; in other words, they expect the AI to sense and react the way a human would to a large range of stimuli in a large variety of situations. But having realistic perception and behavior is not enough, players need clear feedback to understand the model and the current state of the AI. In this session, Martin will describe the models we used on Splinter Cell Blacklist, the reason for using them, issues we ran into, and our overall strategy for giving consistent feedback to the player while maintaining realism.highly-parallel GPU.
Low-Level Shader Optimization for Next-Gen and DX11
Emil Persson (Avalanche Studios)
This lecture will go through examples to show how high-level shading constructs map to the underlying hardware assembly instructions, as well as intrinsics for accessing special GPU instruction. Modern shader features such as integer math, doubles, branching and compute will be discussed. Numerous low-level optimization tricks will be covered, illustrating the benefits of a close-to-the-metal mindset while writing shaders in high-level languages. The main focus is on GCN, the GPU architecture powering next-gen consoles, as well as recent AMD GPUs for PC, but generic optimizations applicable to any modern GPU will also be discussed.
The Infamous: Second Son Particle System Architecture
Bill Rockenbeck (Sucker Punch Productions)
Particle effects play a central role in Infamous: Second Son, with superpowers including "smoke" and "neon." Particle systems are authored in a powerful, text-based expression language which provides great flexibility for effect artists to create complex behavior. This language is compiled into PSSL and run on the asynchronous compute queues of the PlayStation 4 GPU. This talk will describe the particle system runtime and authoring environment, with numerous examples of how simple features can be combined to create interesting effects. We will also describe our solutions to various challenges that arose when trying to run efficiently on the highly-parallel GPU.
UBM Tech