30min video recording of a Fable gameplay demo, enjoy! www.youtube.com/watch?v=doV0...
Kostas Anagnostou
New Fable trailer just dropped, very proud to be part of this super talented team! www.youtube.com/watch?v=3iW1...
On some GPUs (eg GCN/RDNA) 24bit integer muls/mads are 4x faster than 32bit ones. 24bit instructions are not exposed in HLSL/GLSL but you can encourage the compiler to use the 24bit intrinsics by zeroing the 8 most significant bits, if the range allows it, for faster integer muls/mads.
Floor and Ceil Versus Denormals on CPU and GPU -- new article on my blog
asawicki.info/news_1802_fl...
Agility SDK 1.720-preview has been released with Linear Algebra Matrix support which replaces Cooperative Vectors and WaveMMA for hardware accelerated matrix operations, access to wave threadgroup index, and increased groupshared memory among others.
devblogs.microsoft.com/directx/shad...
ReSTIR PT Enhanced: Algorithmic Advances for Faster and More Robust ReSTIR Path Tracing research.nvidia.com/labs/rtr/pub...
The Minimal Retroreflective Microfacet Model jcgt.org/published/00...
AMD DGF SuperCompression (DGFS) cuts DGF geometry file sizes while preserving exact block reconstruction and enabling fast decode to either DGF blocks or conventional meshlets for cross-device deploym...
Overview Today, we are pleased to announce that Shader Model 6.10 and other features have been officially released with Agility SDK 1.720-preview and complementary DXC 1.10.2605.2. AgilitySDK 1.720-pr...
devblogs.microsoft.com
<p>Algorithms leveraging ReSTIR-style spatiotemporal reuse have recently proliferated, hugely increasing effective sample count for light transport in real-time ray and path tracers. Many papers have ...
Indeed! Used this a while ago to make a 24-bit hash optimized for GPU and got some really really good wins compared to the commonly used version of PCG out there.
The full-rate 24-bit multiply-adds are the real workhorse of it 🧡
www.shadertoy.com/view/l3K3zR
