warp

Regarding the section on Python and high-level CUDA, anyone interested should maybe first take a peek at Warp, which I’m guessing is too new to have a book yet. Warp lets you write CUDA kernels directly in Python, and it’s a breeze to get started. https://github.com/nvidia/warp

It is a nice physics engine, it uses Taichi (https://github.com/taichi-dev/taichi) to compile Python code to CUDA/GPU (similar to what Warp Sim does, https://github.com/NVIDIA/warp)

I strongly recommend against using taichi because it doesn't support Python 3.12. Even if they add support now, they have already demonstrated a disinterest in keeping up with Python, unfairly blaming it on Pytorch. Note that Pytorch itself supports 3.12 just fine. If you have an Nvidia CUDA GPU, consider https://github.com/NVIDIA/warp instead.

I would argue that this isn't "normal open source", though it is indeed not locked behind a login on their website. The license (1) is feels very much proprietary, even if the source code is available. (1) https://github.com/NVIDIA/warp/blob/main/LICENSE.md

It being on GitHub doesn't mean it's open-source. https://github.com/NVIDIA/warp?tab=License-1-ov-file#readme Looks more "source available" to me.

I would recommend considering using NanoBind, the follow up of PyBind11 by the same author (Wensel Jakob), and move as much performance critical code to C or C++. https://github.com/wjakob/nanobind If you really care about performance called from Python, consider something like NVIDIA Warp (Preview). Warp jits and runs your code on CUDA or CPU. Although Warp targets physics simulation, geometry processing, and procedural animation, it can be used for other tasks as well. https://github.com/NVIDIA/warp Google Jax is another option, jitting and vectorizing code for TPU, GPU or CPU. https://github.com/google/jax