Guillaume Boissé

@[email protected]
678 Followers
94 Following
69 Posts
Lead graphics programmer @AMD, previously SIE R&D. Demoscene w/ Exist. Opinions are my own.
Bloghttps://gboisse.github.io
Guillaume BoisséNov 21
GPUOpenNov 20

Capsaicin is not just for tacos, it's also our developer rendering framework!

v1.3 is out now:

🌶️ Added heat with GI-1.2, which includes multiple-bounce indirect lighting.
🌶️ HDR support with spicier tone mapping.

And much, much more: https://gpuopen.com/learn/gi-1-2-multibounce-indirect-rendering/?utm_source=mastodon&utm_medium=social&utm_campaign=capsaicin

Introducing AMD GI-1.2 with multibounce indirect real-time rendering - AMD GPUOpen

AMD GI-1.2, our real-time Global Illumination solution, is available now as part of the AMD Capsaicin Framework v1.3.

Guillaume BoisséNov 5
New blog post! Behind the scenes of some of the techniques involved in making our last PC demo 💫 https://gboisse.github.io/posts/this-is-us/
Guillaume BoisséOct 16
GPUOpenOct 16

Get up to speed with our latest advanced graphics research:

📝 GATE (Geometry-Aware Trained Encoding) for neural rendering.
📝 Real-time procedural GPU tree generation.
📝 Neural Visibility Cache for real-time light sampling.

📥 Download the papers: https://gpuopen.com/learn/publications/?utm_source=mastodon&utm_medium=social&utm_campaign=research

Show threadGuillaume BoisséAug 27, 2025
Performance is quite decent even at the highest quality settings; 120us for specular (and ~20us for diffuse):
Guillaume BoisséAug 27, 2025
Been wanting to implement that fast GGX-based convolution for glossy reflection probes for quite a while and finally made some time for it:) https://research.activision.com/publications/archives/fast-filtering-of-reflection-probes
Guillaume BoisséMar 6, 2025
GPUOpenMar 6, 2025

🚀 Today is #AMD #RDNA 4 day! To celebrate, we've got new content on GPUOpen:

🔥 Machine-readable ISA for RDNA 3.5/4
🔥 #opensource Interactive Streaming SDK
🔥 Updates to AMF + Capsaicin

Find out more: https://gpuopen.com/learn/new_content_released_on_gpuopen_for_amd_rdna_4_on-shelf_day/?utm_source=mastodon&utm_medium=social&utm_campaign=rdna4

New content released on GPUOpen for AMD RDNA™ 4 on-shelf day

Learn about our updates on GPUOpen to support the release of AMD RDNA 4, plus other new content!

AMD GPUOpen
Guillaume BoisséJan 14, 2025
Testing the fluid sim. with object collision:)
Guillaume BoisséJan 10, 2025
Re-wrote my acceleration structure for neighbourhood search based on some insight from @vassvik and got significant speedups on large fluid simulations:) Here’s ~1/2 million particles ✨
Show threadGuillaume BoisséJan 10, 2025
Here’s the original thread on pre-loading the 3D tile into LDS: https://bsky.app/profile/vassvik.bsky.social/post/3lb6j2wnmtk2k
Morten Vassvik (@vassvik.bsky.social)

The core idea is to take the 10x10x10 footprint accessed by all threads in the workgroup and split it into chunks, and then fetch these chunks cooperatively in a way that efficiently aligns with subgroup boundaries in such a way that we don't introduce divergence, and then store to shared memory

Bluesky Social
Guillaume BoisséOct 28, 2024
GPUOpenOct 28, 2024

🎇 We're excited to share more of our latest #raytracing #research in our latest blog! 🎇

➡️ Read about our new neural denoising and supersampling technique, where we aim to achieve real-time #pathtracing 🔥

Find out how on GPUOpen ⤵️

https://gpuopen.com/learn/neural_supersampling_and_denoising_for_real-time_path_tracing/?utm_source=mastodon&utm_medium=social&utm_campaign=nssd

Neural Supersampling and Denoising for Real-time Path Tracing - AMD GPUOpen

Read our research for a neural denoising and supersampling technique, with the aim of achieving real-time path tracing.