GDC is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

GDC + VRDC 2019 Session Scheduler

View, browse and sort the ever-growing list of GDC sessions by pass type, track, format, and more! With Session Scheduler, create an account to build your own GDC schedule and access it anywhere, including on the GDC app, once live.

If you've registered for GDC, you can use the same login credentials. Adding a session to your schedule does not guarantee you a seat. Sessions do fill up, so please arrive early to sessions that you would like to attend.

Advanced Graphics Techniques Tutorial: Breaking Down Barriers: An Introduction to GPU Synchronization

Matt Pettineo  (Lead graphics and Engine Programmer, Ready at Dawn)

Location: Room 303, South Hall

Date: Monday, March 18

Time: 4:00 pm - 5:00 pm

Pass Type: All Access, GDC Conference + Summits, GDC Summits - Get your pass now!

Topic: Programming

Format: Tutorial

Tutorials: Advanced Graphics Techniques Tutorial

Vault Recording: Video

The recent wave of "explicit" graphics APIs such as Vulkan and D3D12 require that programmers make use of barriers, events, fences, and other GPU-side synchronization primitives in order to obtain correct results. For programmers new to GPU programming or who are used to other APIs that don't require barriers, it's not at all obvious why barriers are needed or what they're actually doing under the hood. This presentation aims to remove much of the mystery around barriers by explaining how they work on modern PC and console GPU architectures.

Takeaway

Attendees will gain a better understanding of why barriers are necessary, and also what implications they have on GPU utilization and performance. This talk will also explain how barriers and synchronization tie into more complex topics such as submitting commands to multiple hardware queues (AKA Async Compute), and GPU pre-emption.