In another thread I ask about pyiodide ... is this an answer to use cuda in browser under python?
CuPy – NumPy-compatible matrix library accelerated by CUDA
21–30 of 36 posts
Re: CuPy – NumPy-compatible matrix library accelerated by CUDA
#22In another thread I ask about pyiodide ... is this an answer to use cuda in browser under python?
No, browsers only expose specific Web APIs and CUDA is not one. WebGL doesn't even provide access to compute shaders.
Re: CuPy – NumPy-compatible matrix library accelerated by CUDA
#23Not sure what is the motivation behind this library. There are already several array GPU accelerated array libraries -- PyTorch, TensorFlow, ArrayFire, it even looks like pycuda has a small array class.
Chainer and potentially CuPy (which was extracted from Chainer to be independent) were around before PyTorch as it served as inspiration for PyTorch. I feel like that's a good motivation for diversity in packages and ecosystems regardless of your feelings otherwise. Along with a colleague I used CuPy in first Chainer and then PyTorch for implementing the Quasi-Recurrent Neural Network (QRNN) which at the time was far…
Thanks for the QRNN.
What’s it like working for Socher?
Re: CuPy – NumPy-compatible matrix library accelerated by CUDA
#24Earlier quoted context omitted.
Chainer and potentially CuPy (which was extracted from Chainer to be independent) were around before PyTorch as it served as inspiration for PyTorch. I feel like that's a good motivation for diversity in packages and ecosystems regardless of your feelings otherwise. Along with a colleague I used CuPy in first Chainer and then PyTorch for implementing the Quasi-Recurrent Neural Network (QRNN) which at the time was far…
PyTorch is almost (or even literally?) a fork of chainer, which can be seen when comparing example code. The latter was much more stable than the former for quite some time after PyTorch gained big popularity through Facebook. We have been using chainer for a lot of published NN research projects and only recently moved to PyTorch because students complained that they feel they can't put the more popular framework on…
>PyTorch is almost (or even literally?) a fork of chainer
That's funny, I would have assumed PyTorch to be, like, the python version of Torch?
Re: CuPy – NumPy-compatible matrix library accelerated by CUDA
#25Cool I wish that other libraries like tensorflow could get cudnn installed automatically like this library!
pytorch does the same:
Re: CuPy – NumPy-compatible matrix library accelerated by CUDA
#26I use pandas mostly, rarely dropping down to NumPy. Are there non ML/neural network use cases where this library is meaningfully faster than numpy?
Anything that involves computing dot products on large matrices will be dramatically faster with cupy than numpy (depends on your graphics card of course).
Re: CuPy – NumPy-compatible matrix library accelerated by CUDA
#27Can you use Pandas with it? I'm guessing.. no?
You can try cuDF: https://github.com/rapidsai/cudf
Re: CuPy – NumPy-compatible matrix library accelerated by CUDA
#28I’m working with Numba’s CUDA API and it works well as a drop in replacement for embarrassingly parallel functions.
I've done a fair bit of C++11 for CUDA and I was so happy to throw everything out and switch to Numba. It has some rough edges (like incomprehensible error messages when the type inference goes wrong) but it's been a pleasure overall to work with.
I've done a fair bit of Numba CUDA and I was so happy to throw everything out and switch to C++.
NubaCUDA gave me lots of small problems and a few big ones. The poor support for debug/perf tools and poor integration with other high-level python CUDA code (FFTs in particular) sent me packing, but the number of small problems was excessive in comparison to the size of my code. I had 5 reduced bugs at the bottom of my notebook and two paragraphs of "baggage" at the top to support a tiny little 50LoC kernel: one paragraph for the environment variables and one for patching nubacuda itself for a trivial API incompatibility that hadn't been fixed for the better part of a year. All of this for a tool that provided a diminutive subset of functionality at the intersection of both python and C. I've felt more computational freedom writing BASIC on my TI-83.
CuPy could well have changed that equation!
> incomprehensible error messages when the type inference goes wrong
NumbaCUDA is truly the galaxy-brain of type checking: first it complains loudly so as to force you to provide type information, then it opts to not complain about a mismatch, and then it silently reinterpret_casts a double* to float* behind your back.
I know it's free software and I have no right to complain, but I sure sunk a lot of time into this dead end and regret it.
Spiffy icon though.
Re: CuPy – NumPy-compatible matrix library accelerated by CUDA
#29Earlier quoted context omitted.
PyTorch is almost (or even literally?) a fork of chainer, which can be seen when comparing example code. The latter was much more stable than the former for quite some time after PyTorch gained big popularity through Facebook. We have been using chainer for a lot of published NN research projects and only recently moved to PyTorch because students complained that they feel they can't put the more popular framework on…
>PyTorch is almost (or even literally?) a fork of chainer That's funny, I would have assumed PyTorch to be, like, the python version of Torch?
The PyTorch tensor library was originally basically the Python version of Torch 7. It's now moving closer towards NumPy's API (and farther from Torch 7).
Th autograd library was inspired by Chainer's design and took a lot of concepts (but not code) directly from Chainer. The neural network API is a bit of a hybrid. It's built on top of the autograd library but the layer names, implementations, and some conventions were inherited from Torch 7's NN and cuNN libraries.
(EDIT: and the name "autograd" originates from HIPS autograd library, which I think predates Chainer)
Re: CuPy – NumPy-compatible matrix library accelerated by CUDA
#30Earlier quoted context omitted.
I've done a fair bit of C++11 for CUDA and I was so happy to throw everything out and switch to Numba. It has some rough edges (like incomprehensible error messages when the type inference goes wrong) but it's been a pleasure overall to work with.
I've done a fair bit of Numba CUDA and I was so happy to throw everything out and switch to C++. NubaCUDA gave me lots of small problems and a few big ones. The poor support for debug/perf tools and poor integration with other high-level python CUDA code (FFTs in particular) sent me packing, but the number of small problems was excessive in comparison to the size of my code. I had 5 reduced bugs at the bottom of my n…
What’s the difference of NuMBA CUDA and Pytorch or similar?
If you’re doing custom kernels you should take a look at the Julia library CuArray [1] and generic kernels [2]. I really like that I don’t have to dig into C++ and deal with all of the memory and kernel management.
1: https://github.com/JuliaGPU/CuArrays.jl 2: http://mikeinnes.github.io/2017/08/24/cudanative.html