How to Improve Shader Performance by Resolving LDC Divergence
This deep dive into improving shader performance uses Nsight Graphics to profile Diablo® II: Resurrected. Learn about how latency caused by LDC Divergence (a phenomenon where load constant addresses differ within the same warp) can be identified and resolved with help from Nsight Graphics, yielding significant throughput improvements.
Get started with Nsight Graphics today:
- Public version: https://developer.nvidia.com/nsight-graphics
- Pro version: partners reach out to devtools-support@nvidia.com
Check out more resources on Nsight Graphics and optimizing shaders:
- How to use the Shader Profiler:
https://developer.nvidia.com/blog/identifying-shader-limiters-with-the-shader-profiler-in-nvidia-nsight-graphics/
- How to use GPU Trace: https://www.youtube.com/watch?v=g-VarJU6yJ8
- Improving shader performance with SER: https://developer.nvidia.com/blog/improve-shader-performance-and-in-game-frame-rates-with-shader-execution-reordering/
Watch more from this series:
- Building Acceleration Structures Using Async Compute: https://www.youtube.com/watch?v=ctow9…
- Avoiding Stalls and Hitches in DirectX 12: https://www.youtube.com/watch?v=f0a9mN4HQCI
Further resources on NVIDIA Nsight Tools: https://nvda.ws/3GVd8kl