neuronika VS VkFFT

Compare neuronika vs VkFFT and see what are their differences.


Tensors and dynamic neural networks in pure Rust. (by neuronika)


Vulkan/CUDA/HIP/OpenCL Fast Fourier Transform library (by DTolm)
Our great sponsors
  • Scout APM - A developer's best friend. Try free for 14-days
  • Nanos - Run Linux Software Faster and Safer than Linux with Unikernels
  • SaaSHub - Software Alternatives and Reviews
neuronika VkFFT
10 20
562 781
10.9% -
6.9 7.5
12 days ago 3 days ago
Rust C++
Mozilla Public License 2.0 MIT License
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
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.


Posts with mentions or reviews of neuronika. We have used some of these posts to build our list of alternatives and similar projects. The last one was on 2021-11-01.


Posts with mentions or reviews of VkFFT. We have used some of these posts to build our list of alternatives and similar projects. The last one was on 2021-11-15.
  • The AMD โ€œAldebaranโ€ GPU That Won Exascale
    5 projects | | 15 Nov 2021
    Incorrect. Vulkan has compute shaders[1], which are generally usable. Libraries like VkFFT[2] demonstrate basic signal processing in Vulkan. This can certainly be expanded upon, & there are numerous other non-graphical uses.

    There is a Vulkan ML TSG (Technical Subgroup), which is supposed to be working on ML. Even Nvidia is participating, with extensions like VK_NV_cooperative_matrix, which specifically target the ml tensor cores.

    There's people could probably say this better/more specifically, but I'll give it a try: Vulkan is, above all, an general standard for dispatching & orchestrating work usually on a GPU. Right now that work is most of often graphics, but that is far from a limit.

    SYCL is, imo, the opposite of where we need to go. It's the old historical legacy that CUDA has, of writing really dumb ignorant code & hoping the tools can make it run well on a GPU. Vulkan, on the other hand, asks us to consider deeply what near-to-the-metal resources we are going to need, and demands that we define, dispatch, & complete the actual processing engines on the GPU that will do the work. It's a much much much harder task, but it invites in fantastic levels of close optimization & tuning, allows for far more advanced pipelining & possibilities. If the future is good, it should abandon SYCL and CUDA, and bother to get good at Vulkan.




  • VkFFT - GPU Fast Fourier Transform library API guide release
    1 project | | 22 Aug 2021
    1 project | | 22 Aug 2021
    Hello, I am the creator of the VkFFT - GPU Fast Fourier Transform library for Vulkan/CUDA/HIP and OpenCL. In the last update, I have released explicit 50-page documentation on how to use the VkFFT API. It describes all the necessary steps needed to set up the VkFFT library and explains the core design of the VkFFT. This is a very important update, as it should make VkFFT easier to use.
  • VkFFT can now perform Fast Fourier Transforms of arbitrary length
    1 project | | 26 Jul 2021
    For general optimized radix transforms, you might want to check the benchmark plots on GitHub or my Nvidia GTC talk where I describe them in detail.
    1 project | | 25 Jul 2021
    1 project | | 25 Jul 2021
    Performace-wise, VkFFT achieves up to half of the device bandwidth in Bluestein's FFTs, which is up to up to 4x faster on <1MB systems, similar in performance on 1MB-8MB systems and up to 2x faster on big systems than Nvidia's cuFFT. VkFFT is also >5x times faster than AMD's rocFFT for Bluestein's systems. You can check the benchmark and precision scripts on VkFFT's GitHub repo.
  • VkFFT now supports Discrete Cosine Transforms
    2 projects | | 19 Jun 2021
    VkFFT supports convolution calculations - see samples 7, 8 and 9 in the VkFFT repository.
  • VkFFT now supports Discrete Cosine Transforms on GPU
    1 project | | 19 Jun 2021
  • Announcing neuronika 0.1.0, a deep learning framework in Rust
    7 projects | | 15 Jun 2021
    The Vulkan docs online are quite good; if i remember they have "hello world" type tutorials as well. An take a look at something like Vulkan fft that has both Vulkan and opencl backends. Looking at "real" projects will of course tens to obscure the main points, but can be helpful for comparison.
  • Vulkan and HPC
    1 project | | 6 Jun 2021
    It's still pretty niche, honestly. Though is a good counterexample.

What are some alternatives?

When comparing neuronika and VkFFT you can also consider the following projects:

rust-ndarray - ndarray: an N-dimensional array with array views, multidimensional slicing, and efficient operations

wgpu - Safe and portable GPU abstraction in Rust, implementing WebGPU API.

rust-gpu - ๐Ÿ‰ Making Rust a first-class language and ecosystem for GPU code ๐Ÿšง

rustdesk - Yet another remote desktop software

kompute - General purpose GPU compute framework for cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for advanced GPU data processing usecases. Backed by the Linux Foundation.

are-we-learning-yet - How ready is Rust for Machine Learning?

clblast-rs - clblast bindings for rust

conan-center-index - Recipes for the ConanCenter repository

autograph - Machine Learning Library for Rust

sciter-js-sdk - Sciter.JS - Sciter but with QuickJS on board instead of my TIScript

constmuck - Const equivalents of many bytemuck functions, and a few additional const functions.

justrunmydebugger - just run my debugger