Enzyme
Rust-CUDA
Our great sponsors
Enzyme | Rust-CUDA | |
---|---|---|
16 | 37 | |
1,133 | 2,816 | |
2.9% | 3.9% | |
9.6 | 0.0 | |
7 days ago | 5 months ago | |
LLVM | Rust | |
GNU General Public License v3.0 or later | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Enzyme
-
Show HN: Port of OpenAI's Whisper model in C/C++
https://ispc.github.io/ispc.html
For the auto-differentiation when I need performance or memory, I currently use tapenade ( http://tapenade.inria.fr:8080/tapenade/index.jsp ) and/or manually written gradient when I need to fuse some kernel, but Enzyme ( https://enzyme.mit.edu/ ) is also very promising.
MPI for parallelization across machines.
-
Do you consider making a physics engine (for RL) worth it?
For autodiff, we are currently working again on publishing a new Enzyme (https://enzyme.mit.edu) Frontend for Rust which can also handle pure Rust types, first version should be done in ~ a week.
-
What is a really cool thing you would want to write in Rust but don't have enough time, energy or bravery for?
Have you taken a look at enzymeAD? There is a group porting it to rust.
-
The Julia language has a number of correctness flaws
Enzyme dev here, so take everything I say as being a bit biased:
While, by design Enzyme is able to run very fast by operating within the compiler (see https://proceedings.neurips.cc/paper/2020/file/9332c513ef44b... for details) -- it aggressively prioritizes correctness. Of course that doesn't mean that there aren't bugs (we're only human and its a large codebase [https://github.com/EnzymeAD/Enzyme], especially if you're trying out newly-added features).
Notably, this is where the current rough edges for Julia users are -- Enzyme will throw an error saying it couldn't prove correctness, rather than running (there is a flag for "making a best guess, but that's off by default"). The exception to this is garbage collection, for which you can either run a static analysis, or stick to the "officially supported" subset of Julia that Enzyme specifies.
Incidentally, this is also where being a cross-language tool is really nice -- namely we can see edge cases/bug reports from any LLVM-based language (C/C++, Fortran, Swift, Rust, Python, Julia, etc). So far the biggest code we've handled (and verified correctness for) was O(1million) lines of LLVM from some C++ template hell.
I will also add that while I absolutely love (and will do everything I can to support) Enzyme being used throughout arbitrary Julia code: in addition to exposing a nice user-facing interface for custom rules in the Enzyme Julia bindings like Chris mentioned, some Julia-specific features (such as full garbage collection support) also need handling in Enzyme.jl, before Enzyme can be considered an "all Julia AD" framework. We are of course working on all of these things (and the more the merrier), but there's only a finite amount of time in the day. [^]
[^] Incidentally, this is in contrast to say C++/Fortran/Swift/etc, where Enzyme has much closer to whole-language coverage than Julia -- this isn't anything against GC/Julia/etc, but we just have things on our todo list.
-
Jax vs. Julia (Vs PyTorch)
Idk, Enzyme is pretty next gen, all the way down to LLVM code.
-
What's everyone working on this week (7/2022)?
I'm working on merging my build-tool for (oxide)-enzyme into Enzyme itself. Also looking into improving the documentation.
-
Trade-Offs in Automatic Differentiation: TensorFlow, PyTorch, Jax, and Julia
that seems one of the points of enzyme[1], which was mentioned in the article.
[1] - https://enzyme.mit.edu/
being able in effect do interprocedural cross language analysis seems awesome.
-
Enzyme: towards state-of-the-art AutoDiff in Rust
Enzyme is an LLVM (incubator) project, which performs automatic differentiation of LLVM-IR code. Here is an introduction to AutoDiff, which was recommended by @DoogoMiercoles in an earlier post. You can also try it online, if you know some C/C++: https://enzyme.mit.edu/explorer.
-
Oxide-Enzyme: Integrating LLVM's Static Automatic Differentiation Plugin
To give a little bit of context here, this is a Rust frontend for Enzyme itself, which is a leading Auto-Diff tool. The key advantage is that unlike most of the existing tools it does generate gradient functions after applying a lot of (LLVM's) optimizations, which leads to very efficient gradients (benchmarks here: https://enzyme.mit.edu/). Working on LLVM level also allows it to work across language barriers. Finally it is also the first AD library to support generic AMD-HIP / NVIDIA-CUDA code and works also with OpenMP and MPI. https://c.wsmoses.com/papers/EnzymeGPU.pdf I have intentions to add rayon support, since that is more likely to be used on our Rust side :)
-
Cerebras’ New Monster AI Chip Adds 1.4T Transistors
The answer is an API, like NNAPI. AD is a frontend concern and doesn't really matter to accelerators.
For AD, I am bullish for Enzyme, which does AD on LLVM IR, avoiding deep compiler integration: https://enzyme.mit.edu/
Rust-CUDA
-
[Media] Anyone try writing a ray tracer with rust? It's pretty fun!
Source code [here](https://github.com/ihawn/RTracer) if anyone is interested in taking a look or giving feedback. As a side question, does anyone have any general advise on getting GPU compute working with rust? I tried [this project](https://github.com/Rust-GPU/Rust-CUDA) but had a bunch of issues (And it doesn't look like an active repo anyways)
- [Rust] État de GPGPU en 2022
- Which crate for CUDA in Rust?
-
Announcing cudarc and fully GPU accelerated dfdx: ergonomic deep learning ENTIRELY in rust, now with CUDA support and tensors with mixed compile and runtime dimensions!
Be warned, NON_BLOCKING streams do not fully synchronize with sync host to device copies. They are not guaranteed to actually finish by the time they return. Meaning its possible to initiate a copy, then initiate a kernel launch, and have the copy be unfinished by the time the kernel is launched. This caused so many confusing bugs that i personally decided to stop using NON_BLOCKING altogether in rust-cuda. https://github.com/Rust-GPU/Rust-CUDA/issues/15
-
In which circumstances is C++ better than Rust?
- Cuda is not doing by FFI linking, instead is compiling CUDA code natively in Rust https://github.com/Rust-GPU/Rust-CUDA and even if it not complete as the C++ SDK is more than a toy
- I learned 7 programming languages so you don't have to
-
GNU Octave
Given your criteria, you might want to consider (modern) C++.
* Fast - in many cases faster than Rust, although the difference is inconsequential relative to Python-to-Rust improvement I guess.
* _Really_ utilize CUDA, OpenCL, Vulcan etc. Specifically, Rust GPU is limited in its supported features, see: https://github.com/Rust-GPU/Rust-CUDA/blob/master/guide/src/... ...
* Host-side use of CUDA is at least as nice, and probably nicer, than what you'll get with Rust. That is, provided you use my own Modern C++ wrappers for the CUDA APIs: https://github.com/eyalroz/cuda-api-wrappers/ :-) ... sorry for the shameless self-plug.
* ... which brings me to another point: Richer offering of libraries for various needs than Rust, for you to possibly utilize.
* Easier to share than Rust. A target system is less likely to have an appropriate version of Rust and the surrounding ecosystem.
There are downsides, of course, but I was just applying your criteria.
-
Your average rustafarians
Technically, yes. There are crates for OpenCL and CUDA, although official ROCm support does not exist yet.
-
My negative views on Rust
Also you might not be aware but you can write cuda in rust now also https://github.com/Rust-GPU/Rust-CUDA
-
Non graphical computing on GPU
On the other hand CUDA is optimized to death and very good. Documentation and codes examples are everywhere (in C++ at least) but it is one more piece of software to install/configure and interact with from Rust. I don't know if Rust-CUDA is good or not. It's a WIP but the development seems stalled at this point (no commit since July)
What are some alternatives?
rust-gpu - 🐉 Making Rust a first-class language and ecosystem for GPU shaders 🚧
wgpu - Cross-platform, safe, pure-rust graphics api.
rust-ndarray - ndarray: an N-dimensional array with array views, multidimensional slicing, and efficient operations
Zygote.jl - 21st century AD
Flux.jl - Relax! Flux is the ML library that doesn't make you tensor
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
Lux.jl - Explicitly Parameterized Neural Networks in Julia
CUDA.jl - CUDA programming in Julia.
linfa - A Rust machine learning framework.
faust - Functional programming language for signal processing and sound synthesis
zygote - Explorations in area of programming languages: concepts, typing, formal verification
GLSL - GLSL Shading Language Issue Tracker