taichi VS taichi_benchmark

taichi – Productive, portable, and performant GPU programming in Python

ETH Zurich is using it for their physics sim courses, University of Utah is using it for simulations (SIGGRAPH 2022), OPPO (they make smart devices running Android), Kuaishou uses it for liquid and gas simulation on GPUs. Lots of GPU accelerated sim stuff.

https://www.taichi-lang.org/

https://www.researchgate.net/publication/337118128_Taichi_a_...

https://github.com/taichi-dev/taichi

Check our the realease note (https://github.com/taichi-dev/taichi/releases) for more improvements.

I've recently started using Taichi (https://taichi-lang.org/) for numerical codes and the fact it doesn't try to trick you into thinking it's numpy is a nice "feature". ;)

Taichi v1.4.0 is released! See what's new: - Taichi AOT, along with a native Taichi Runtime library: Native applications can now load compiled AOT modules and launch Taichi kernels without a Python interpreter. - Taichi ndarray: An array object that holds contiguous multi-dimensional data to allow easy data exchange with external libraries. - Dynamic index: Use variable indices whenever necessary on all backends without affecting the performance of those matrices with only constant indices. See deprecation and more improvements in the release note.

Oh, then if you're not already tied to any particular VFX software, I might as well recommend Taichi again.

It's an upgrade of a basic version. See changes to the source code here: https://github.com/taichi-dev/taichi/pull/6851

In fact, Taichi's compiler relies on heavy underlying engineering to enable high performance. In the aforementioned code snippet, the summation is actually an atomic operation, which cannot be parallelized and is thus subject to limited operation efficiency. The most commonly used method of parallel computing optimization in vector summation is reduction, which is one of the must-have skills to learn parallel computing. The benchmark report concludes that, thanks to automatic reduction optimization implemented by its compiler, Taichi achieves a performance comparable to manually implemented CUB and way better than Numba.

Sure, here are some benchmarks that could be helpful: https://github.com/taichi-dev/taichi_benchmark

Some are uncertain about Taichi Lang's performance against other frameworks such as CUDA, and would require a comprehensive benchmarking report. Actually, we published a systematic benchmarking report when we released Taichi Lang v1.0.0. Taichi has more or less comparable performance to CUDA. But, for sure, you will have much fewer lines of code with Taichi Lang!