Re:Show HN: I've made a Monte-Carlo raytracer for glTF scene...
by pjmlp on Thursday December 26, 2024 @03:05PM
(#42517389)
WebGPU projects that don't provide browser examples are kind of strange, then better use Vulkan or whatever.
[ Parent
| on HN ]
Re:Show HN: I've made a Monte-Carlo raytracer for glTF scene...
by lisyarus on Thursday December 26, 2024 @03:33PM
(#42517576)
See my answer to artemonster above.
Re:Show HN: I've made a Monte-Carlo raytracer for glTF scene...
by sspiff on Friday December 27, 2024 @02:32AM
(#42520545)
WegGPU is a way nicer HAL if you're not an experienced graphics engineer. So even if you only target desktops, it's a valid choice.
On the web, WebGPU is only supported by Chrome-based browser engines at this point, and a lot of software developers us Firefox (and don't really like encouraging a browser monoculture), so it doesn't make a ton of sense to target browser based WebGPU for some people at this point.
Re:Show HN: I've made a Monte-Carlo raytracer for glTF scene...
by lisyarus on Friday December 27, 2024 @06:17AM
(#42521375)
It's not as much about experience as it is about trade-offs. I've worked a lot with Vulkan and it's an incredible API, but when you're working alone and you don't have the goal of squeezing 250% performance out of your GPU on dozens of different GPU architectures, your performance becomes pretty much independent of a specific graphics API (unless your API doesn't support some stuff like multi-draw-indirect, etc).
Re:Show HN: I've made a Monte-Carlo raytracer for glTF scene...
by pjmlp on Friday December 27, 2024 @06:19AM
(#42521385)
The answer is middleware engine, all of them with much nicer tooling available, without the constraints of a browser sandboxing design, for 2017 graphics APIs minimum common denominator.