This 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.
|Session Name:||Low-Level Shader Optimization for Next-Gen and DX11|
|Company Name(s):||Avalanche Studios|
|Track / Format:||Programming|
|Overview:||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.|