Multi-Adapter with Integrated and Discrete GPUs
- 0 Collaborators
Gaming PCs often pair a high-performance CPU with a discrete GPU. Those CPUs often include integrated graphics, usually left idle. This sample provides a recipe to add the power of the integrated GPU to offload work from the discrete GPU. ...learn more
Project status: Under Development
Groups
GDC 2020
Intel Technologies
Intel Integrated Graphics
Overview / Usage
Gaming PCs typically pair a high-performance CPU, great for complicated logic and decision making, with a discrete GPU, great for visuals. Those CPUs often include integrated graphics, usually left idle. We explore cases (async compute & post-processing) where the latest Intel integrated GPUs add significant performance when paired with a discrete GPU.
Methodology / Approach
The sample's foundation is the Microsoft® D3D12 n-body particles sample, which demonstrates using async compute to execute simulation and rendering in parallel on a single GPU.
This sample runs the simulation (compute shader) on the integrated GPU, so the discrete GPU has more room to work on graphics. It adds a copy queue on the discrete GPU to move data from system to discrete-local memory. All 3 stages run in parallel: simulation, copy, and rendering.
With this technique, the potential speedup is a function of how much work can be offloaded from the discrete GPU.
Technologies Used
D3D12, Direct3D12, Multi-Adapter, Cross-Adapter, Async Compute, Copy Queue, Simulation, Particles