taichi_benchmark VS faster-python-with-taichi

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!

The source code is here. Reaction-diffusion is the third example in the repo, apart from the other two cases where the package speeds up Python code. I also wrote a detailed explanation and you can skip to the third example.

You can refer to the source code of three examples comparing Taichi with Python here.

A shortcut to the source code of the three cases: https://github.com/taichi-dev/faster-python-with-taichi.