In an article published by Intel, the company explains that thanks to advances in path-traced light simulation that means a far more efficient path-traced rendering, Intel is looking into enabling integrated GPUs to run path-tracing in real-time.
Ray tracing has been around since 2018, but it requires considerable processing power to run. Even some top GPUs on the market struggle to run AAA games at a constant 60FPS with ray-tracing graphics enabled.
If Intel can get path tracing to work well on its integrated graphics solutions, it would make light simulation easier to run on discrete GPUs.
The article in question, which you can read here, talks about three new papers focusing on path-traced optimisations that will be presented at SIGGRAPH, EGSR, and HPG by the Intel Graphics Research Organization.
The premise of these three papers is to showcase three new ways to optimise current practices to alleviate and improve GPU performance by reducing the number of calculations required to simulate light bounces.
The first paper presents a new method of computing reflections on a GGX microfacet surface. With this method, materials are reduced to a hemispherical mirror that is substantially more simple to simulate.
The second paper shows a more efficient method of rendering glittery surfaces in a 3D environment. With this new method, the average number of visible glitter from each pixel can be taken into account, which means that the GPU only needs to render the correct amount of visible glitter visible.
The third paper showcases a more efficient method of constructing photo trajectories in different illumination scenarios, known as Markov Chain Mixture Models for Real-Time Direct Illumination.
Using these three techniques, Intel hopes to improve the core aspects of path tracing, including ray tracing, shading, and sampling, which will help improve real-time path tracing performance on integrated GPUs.