oneflow VS kompute

We are thrilled to announce the new release of OneFlow,, which is a deep learning framework designed to be user-friendly, scalable and efficient. OneFlow v0.9.0 contains 640 commits. For the full changelog, please check out: https://github.com/Oneflow-Inc/oneflow/releases/tag/v0.9.0.

Found relevant code at https://github.com/Oneflow-Inc/oneflow + all code implementations here

Check out OneFlow on GitHub . We'd love to hear your feedback!

OneFlow URL：https://github.com/Oneflow-Inc/oneflow/

No other options?:) We are developing a new distributed DL framework called OneFlow, which is faster than other frameworks and easier to use. Now it provides more and better PyTorch compatible APIs.

Code for https://arxiv.org/abs/2110.15032 found: https://github.com/Oneflow-Inc/oneflow

This article focuses on what is happening behind the execution of a Tensor in the deep learning framework OneFlow. It takes the operator oneflow.relu as an example to introduce the Interpreter and VM mechanisms that need to be relied on to execute this operator.

This article describes how OneFlow works with MLIR, how to add a graph-level Pass to OneFlow IR, how OneFlow Operations automatically become MLIR Operations, and why OneFlow IR can use MLIR to accelerate computations.

Backpressure mechanism, also known as credit-based flow control, is a classic scheme for network communication flow control problems. Its predecessor is the TCP sliding window. This idea is particularly simple and effective. As we will see in this article, based on the same principles, this idea is applicable to any flow control scheme and is found in the design of many hardware and software systems. In this article, the engineer of OneFlow will tell the chequered history of this simple idea.

The two I know of are IREE and Kompute[1]. I'm not sure how much momentum the latter has, I don't see it referenced much. There's also a growing body of work that uses Vulkan indirectly through WebGPU. This is currently lagging in performance due to lack of subgroups and cooperative matrix mult, but I see that gap closing. There I think wonnx[2] has the most momentum, but I am aware of other efforts.

[1]: https://kompute.cc/

[2]: https://github.com/webonnx/wonnx

Great to see the positive momentum of this framework! Best wishes and upvotes from the Vulkan Kompute team :)

To a first approximation, Kompute[1] is that. It doesn't seem to be catching on, I'm seeing more buzz around WebGPU solutions, including wonnx[2] and more hand-rolled approaches, and IREE[3], the latter of which has a Vulkan back-end.

[1]: https://kompute.cc/

[2]: https://github.com/webonnx/wonnx

[3]: https://github.com/openxla/iree

I look in an example and see similar instructions, stating that the build should be quite simple. But again, it doesn't work. It generates a bunch of folders with Visual Studio stuff, but no executables, no libraries, or anything like that.

I can't figure out how, and there are no tutorials. According to https://kompute.cc/overview/build-system.html I should simply run "cmake -Bbuild". But this doesn't output what I need, and when I look in the Makefile I get the sense that this is more an example Makefile... but then that contradicts the above tutorial.

Kompute is in my opinion good example to take inspiration for abstractions.

Currently, there's a few Vulkan compute frameworks floating around (like Kompute). I would work with those. Kompute simplifies a lot of the biolerplate and seems like you could benefit from using it.

Try Kompute, a project from the Linux foundation. It is quite simple to use, and does not require deep knowledge of graphics API. It’s a bit painful to setup, but it kinda works well (and I have a project going on on it)

This so much.

This makes alot of sense considering the Linux Foundation is also in charge of Kompute which is likely to be the basis of vendor agnostic GPGPU, and thus the basis of vendor agnostic GPU-based machine learning.