NVIDIA seem to be on a bit of a roll lately when it comes to Linux with a huge new driver release, DLSS for Proton, RTX and DLSS support for Arm on Linux and getting Linux native support added to the DLSS SDK and now they've open sourced a bunch of GameWorks.
Perhaps feeling some pressure from AMD and GPUOpen? Open sourcing their work means many more developers can use them without licensing issues, and so it might pull more towards it instead of going with various tech them AMD currently provides.
Now NVIDIA has released these on GitHub under the MIT license:
- RTXMU - RTX Memory Utility - The NVIDIA RTX Memory Utility (RTXMU) SDK is designed to reduce the coding complexity associated with optimal memory management of acceleration structures. RTXMU provides compaction and suballocation solutions for both DXR and Vulkan Ray Tracing while the client manages synchronization and execution of acceleration structure building. The SDK provides sample implementations of suballocators and compaction managers for both APIs while providing flexibility for the client to implement their own version. More on their blog post.
- NVRHI - NVRHI (NVIDIA Rendering Hardware Interface) is a library that implements a common abstraction layer over multiple graphics APIs (GAPIs): Direct3D 11, Direct3D 12, and Vulkan 1.2. It works on Windows (x64 only) and Linux (x64 and ARM64).
- Donut - Donut is a real-time rendering framework built by NVIDIA DevTech for use in various prototype renderers and code samples. It provides a collection of reusable and somewhat extensible rendering passes that can be put together in an application, and a system for loading a scene and maintaining its component graph. There's also a bunch of Donut Examples developers can use too.
Some you may have missed, popular articles from the last month:
The comments on this article are closed.
4 comments
Nice gesture, but personally i only care if they open source their driver (or at least the blob for reclocking), CUDA or DLSS...
2 Likes, Who?
slaapliedje Jul 20, 2021
Quoting: TermyNice gesture, but personally i only care if they open source their driver (or at least the blob for reclocking), CUDA or DLSS...Kind of seems like a slow process for sure. But I'm not going to be of the 'well why not the driver? screw you nvidia, do the driver!' We should say "This is great, more open source the better. Please consider open sourcing the driver bits.'
Maybe if we ask nicely they'll do it. I think one of the reasons they haven't done it in so long is because, let's be honest, their closed source support has been great, and their cards had been more performant than AMD's for years.
For me, the open source method of having to get the latest drivers are far more annoying than getting nvidia's closed source ones. Usually requiring a kernel update and newer mesa libraries. Things that are not okay if you're shooting for a stable desktop that you can suggest non-technical people use.
0 Likes
Quoting: slaapliedjeMaybe if we ask nicely they'll do it.I suspect that the more they have open source development, the more open source development they'll want to do. It's fundamentally really pragmatic. Baby steps.
1 Likes, Who?
Quoting: CatKillerQuoting: slaapliedjeMaybe if we ask nicely they'll do it.I suspect that the more they have open source development, the more open source development they'll want to do. It's fundamentally really pragmatic. Baby steps.
Seeing that open sourcing something did not kill the company is indeed likely to give more voice to those who prefer open source inside the company.
Now it will also depend on what you want to open source. Kernel/vulkan driver, I think this is the sense of history. But for their money makers, especially those who could be reused by competitors .... More complicated. CUDA, I have doubts, albeit it is not impossible (but one of the core advantage of CUDA is to be nvidia only, as it ends up giving much nicer code compared to more generic approaches until now.) DLSS, I have insanely high doubts for the short and mid term, as they have something fairly unique (the NN and its training set), yet mot that hard to flat out reuse by competitors. As such, the cost of open source is potentially high, whereas the benefit is low.
Conversely, driver opening cost is likely very low (pretty much riskless, only some legal stuff), but potential gain is high (user satisfaction, secure boot, image, and lower maintenance cost). So I have good hope that it will come.
0 Likes
Patreon
PayPal
See more from me