[HN Gopher] VectorWare - from creators of `rust-GPU` and `rust-C...
___________________________________________________________________
VectorWare - from creators of `rust-GPU` and `rust-CUDA`
Author : ashvardanian
Score : 67 points
Date : 2025-10-23 15:41 UTC (7 hours ago)
(HTM) web link (www.vectorware.com)
(TXT) w3m dump (www.vectorware.com)
| billconan wrote:
| after reading this page, I still don't know what gpu native ware
| they want to work on.
|
| > If you look at existing GPU applications, their software
| implementations aren't truly GPU-native. Instead, they are
| architected as traditional CPU software with a GPU add-on.
|
| I feel that this is due to the current hardware architecture, not
| the fault of software.
| LegNeato wrote:
| We have some demos coming in the next couple weeks. The
| hardware is there, the software isn't!
| zozbot234 wrote:
| What does this mean for the rust-gpu and rust-cuda projects
| themselves? Will they go unmaintained now that the creators are
| running a business?
|
| (Don't miss the "Pedantic mode" switch on the linked page, it
| adds relevant and detailed footnotes to the blog post.)
| LegNeato wrote:
| We are investing in them and they form the basis of what we are
| doing. That being said, we are also exploring other technical
| avenues with different tradeoffs...we don't want to assume a
| solution merely because we are familiar with them.
| wrs wrote:
| Be sure to turn on "pedantic mode" to get the footnotes that make
| this make more sense. Some examples of what this means by
| "applications" would help. I don't _think_ the prediction here is
| that Excel 's main event loop is going to run on the GPU, but I
| can see that its calculation engine might.
| LegNeato wrote:
| More software than you think can run fully on the GPU,
| especially with datacenter cards. We'll be sharing some demos
| in the coming weeks.
| simonask wrote:
| With current GPU architectures, this seems unlikely. Like, you
| would need a _ton_ of cells with almost perfectly aligned
| inputs before even the DMA bus roundtrip is worth it.
|
| We're talking at least hundreds of thousands of cells,
| depending on the calculation, or at least a number that will
| make the UI very sad long before you'll see a slowdown from
| calculation.
|
| Databases, on the other hand...
| zozbot234 wrote:
| There isn't always a DMA roundtrip; unified memory is a
| thing. But programming for the GPU is _very_ awkward at a
| systems level. Even with unified memory, there is generally
| no real equivalent to _virtual_ memory or mmap() so you have
| to shuffle your working set in and out of VRAM by hand anyway
| (i.e. backing and residency is managed explicitly, even with
| "sparse" allocation api's that might otherwise be expected to
| ease some of the work). Better GPU drivers may be enough to
| mitigate this, along with broad-based standardization of some
| current vendor-specific extensions (it's not clear that real
| HW changes are needed) but this creates a very real
| limitation in the scale of software (including the AI kind)
| you can realistically run on any given device.
| the__alchemist wrote:
| `rust-GPU` and `rust-CUDA` fall in the category to me of "Rust is
| great, let's build the X ecosystem in rust". Meanwhile, it's been
| in a broken and dormant state for years. There was a
| leadership/dev change recently, (Are the creators of VectorWare
| the creators of Rust-CUDA, or the new leaders?), and more
| activity. I haven't tried since.
|
| If you have a Rust application or library and want to use the
| GPU, these approaches are comparatively smooth: -
| WGPU: Great for 3D graphics - Ash and other Vulkan
| bindings: Low-level graphics bindings - Cudarc: Nice API
| for running CUDA kernels.
|
| I am using WGPU and Cudarc for structural biology + molecular
| dynamics computations, and they work well.
|
| Rust - CUDA feels like lots-of-PR, but not as good of a toolkit
| as these quieter alternatives. What would be cool for them to
| deliver, and I think is in their objectives: Cross-API
| abstractions, so you could, for example, write code that runs on
| Vulkan Compute in addition to CUDA.
|
| Something else that would be cool: High-level bindings to cuFFT
| and vkFFT. You can FFI them currently, but that's not ideal. (Not
| too bad to impl though, if you're familiar with FFI syntax and
| the `cc` crate)
| LegNeato wrote:
| Yes, it is all these folks getting together and getting
| resources to push those projects to the next level:
| https://www.vectorware.com/team/
|
| wgpu, ash, and cudarc are great. We're focusing on the actual
| code that runs on the GPU in Rust, and we work with those
| projects. We have cust in rust-cuda, but that existed before
| cudarc and we have been seriously discussing just killing it in
| favor of cudarc.
| jjallen wrote:
| +1 for cudarc. I've been using it for a couple of years now and
| has worked great. I'm using it for financial markets
| backtesting.
| LegNeato wrote:
| Pedantic note: rust-cuda was created by
| https://github.com/RDambrosio016 and he is not currently involved
| in VectorWare. rust-gpu was created by the folks at embark
| software. We are the current maintainers of both.
|
| We didn't post this or the title, we would never claim we created
| the projects from scratch.
| ashvardanian wrote:
| My bad! "contributors" is more accurate, but HN doesn't allow
| editing titles, sadly :(
| LegNeato wrote:
| No worries, just wanted to correct it for folks. Thanks for
| posting!
| kibwen wrote:
| HN allows the submitter to edit the title, at least it did
| last time I checked.
| Keyframe wrote:
| _folks at embark software_
|
| seems like embark has disembarked from Rust and support for it
| altogether
| LegNeato wrote:
| One of the founders here, feel free to ask whatever. We
| purposefully didn't put much technical detail in the post as it
| is an announcement post (other people posted it here, we didn't).
| jiehong wrote:
| Sounds interesting.
|
| But, languages like Java or python simply lack even programming
| constructs to program on GPUs easily.
|
| No standardised ISA on GPUs also mean compilers can't really
| provide a translation layer.
|
| Let's hope things get better over time!
| binarymax wrote:
| Python has decorators which can be used to add sugar to methods
| for things like true parallelization. For example, see
| modal.com's Python snippets.
|
| https://modal.com/docs/examples/batched_whisper
| LegNeato wrote:
| You might be interested in a previous blog post where we showed
| one codebase running on many types of GPUs: https://rust-
| gpu.github.io/blog/2025/07/25/rust-on-every-gpu...
___________________________________________________________________
(page generated 2025-10-23 23:01 UTC)