Élie Michel 🍪

Research Scientist at @AdobeResearch. PhD in Computer Graphics. Dev of #OpenMfx and Learn #WebGPU C++. Opinions are my own. ⏩

[Élie Michel 🍪 @exppad]

@simplydt @karpathy I think that a good plugin architecture is a relevant way to make a repo "maximally forkable", it does not need to be opposed!

[Élie Michel 🍪 @exppad]

@johndpope @fhahlbohm That 2400 fps is overclaim, it's measured on a degraded version that ignores any sort of transparency. The actual FPS reported in the paper is 97.

[Élie Michel 🍪 @exppad]

@CantBeFaraz @threejs @_Dervishh Very nice! There just seems to be one little glitch here:

[Élie Michel 🍪 @exppad]

@Eng_Hemdi Please stop forgetting to mention that the 2400FPS is *not* rendered with the same quality as the CUDA renderer used for quality comparison! Far from it actually, since there is no transparency at all. It's more an example of graceful degradation imho.

[Élie Michel 🍪 @exppad]

I also gather some related toughts in this appendix of the #LearnWebGPU programming guide:

"Keep in mind lower-end devices" https://t.co/gyomjU3NLp

[Élie Michel 🍪 @exppad]

Is it because researchers only work with recent high end #GPU that everybody has to renew their hardware so fast or is the other way around?

Causality is hard to prove, but the correlation is a fact! And we have plenty more figures to show at our #SIGGRAPH2025 talk next summer!

[Élie Michel 🍪 @exppad]

We're very much interested in your opinion and interpretation of these results!

More info about the upcoming talk:
🔹SIGGRAPH program: https://t.co/0eCv0bN62a
🔹Webpage: https://t.co/D05pUZuSw6

with @emxtyu Octave Crespel @Axel_Paris and @FelixHahnlein

[Élie Michel 🍪 @exppad]

@rvandeghen I definitely understand the will to tease the paper, communication is important, but to my eyes at least it would have more impact if it was more consistent. The 2800FPS figure is fancy for sure, but you want to communicate with researchers, who pay attention to details!

[Élie Michel 🍪 @exppad]

@rvandeghen All right but maybe I still don't fully get it: does the 2400 FPS game engine give the same visual result than the benchmark? The web page presents accuracy figures, it should give the render time that corresponds to this accuracy

[Élie Michel 🍪 @exppad]

@rvandeghen (I don't want to minimize the good work, congrats again, just mean to make things a bit less misleading!)

[Élie Michel 🍪 @exppad]

@rvandeghen Would be nice to report this actual FPS as well in the web page, so that it doesn't steer towards overclaim territory, because you show accuracy comparison with 1 renderer and FPS with a different one.

[Élie Michel 🍪 @exppad]

@janusch_patas (I'm gonna ask on the original author post actually🙂)

[Élie Michel 🍪 @exppad]

@janusch_patas Hey nice work! I'm just a bit puzzled with point (iv): directly compatible w/ existing renderer means there is no sorting, right? So not so much semi-transparent and volumetric effects?

[Élie Michel 🍪 @exppad]

Note that 'naga' is the equivalent tool developed by Firefox. It can easily be installed using cargo (the rust build manager): https://t.co/EWw0tlN3N6

[Élie Michel 🍪 @exppad]

'tint' is the shader compiler developed by Chrome to implement #WebGPU. It has a nice command line interface, but so far there is no official build out...

Wait no more! I share here precompiled binaries of tint CLI: https://t.co/frcOqs9ALw

[Élie Michel 🍪 @exppad]

Important notes:
🔹This rewrite is *WIP*, refer to the main section (w/o "next" in the URL) for further chapters.
🔹This only works with Dawn for now because it is closer to what the v1.0 of WebGPU will be.
🔹The accompagnying code "stepXXX-next" is not up to date yet.

[Élie Michel 🍪 @exppad]

I've just realized something. It makes much more sense to have the "hello triangle" pointing upside down when learning #WebGPU!

👉 The ongoing "Next" rewrite of my guide reached the Hello Triangle chapter 🥳 https://t.co/C1AEC7S6Kj