GPU Library Utilities

From: Matt Borland (matt_at_[hidden])
Date: 2024-08-07 12:47:41

By popular demand Boost.Math has begun adding support for CUDA (NVCC and NVRTC) and SYCL. Unfortunately to use all of these platforms you can not really use std:: as CUDA has utilities (e.g. <type_traits>) in cuda::std::, containers (e.g. tuple) in thrust:: and mathematical functions in the global namespace. There are also completely missing features like <limits>. To work with this we have started creating new headers that implement these features and workarounds such as:

1) limits: https://github.com/boostorg/math/blob/develop/include/boost/math/tools/numeric_limits.hpp

2) Tuple: https://github.com/boostorg/math/blob/develop/include/boost/math/tools/tuple.hpp

3) General configuration: https://github.com/boostorg/math/blob/develop/include/boost/math/tools/config.hpp#L666

Now in the code base for example instead of using std::pair you use boost::math::pair which aliases to either thrust::pair or std::pair depending on context.

As we continue to build out this support we know we are going to create more headers for compatibility, and feature completeness. I thought these could be useful to other libraries so I asked John Maddock about adding copies of them to Boost.Config. He said that's not an unreasonable home for them, but I should consult the ML. My questions then are:

1) Would these utilities be useful to you?
2) If yes, do you think that Boost.Config is the right home for them?

I posted a similar question on Slack yesterday and Joaquin suggested Boost.Compute. I don't think that's the right fit because these would be out of scope, the library is extremely heavy, and it's been over 5 years since the last commit from a maintainer. I would also rather not propose and go through review on a Boost.GPU_Utils, but with sufficient demand it could be worth the effort.

Please let us know what you think, and thanks for your time.

Matt