Hacker News Reader

Comment by elashri | Hacker News Reader

> Python/Numpy: 5360ms (Xeon(R) CPU E5-2698 v4 @ 2.20GHz) CuPy: 10.6ms (A100) MatX: 2.54ms (A100) >

Are they even comparing apples to apples to claim that they see these improvements over NumPy?

> While the code complexity and length are roughly the same, the MatX version shows a 2100x over the Numpy version, and over 4x faster than the CuPy version on the same GPU.

NumPy doesn't use GPU by default unless you use something like Jax [1] to compile NumPy code to run on GPUs. I think more honest comparison will mainly compare MatX running on same CPU like NumPy and for GPU comparison focus to compare vs CuPy.

[1] https://github.com/google/jax

View on HN

This seems like an FFT based benchmark.... I believe NumPy for licensing reasons includes a port of old FFTPACK which is only single threaded. (Py)FFTW or others are surely much faster.

So the test seems to compare one thread of a CPU launched in 2016 running a port of 40year old fortran code to a optimised FFT library on a GPU launched in 2020.

The sample is really designed to show the simplicity of the syntax, and the performance is just a side effect. Where you'll see a bigger performance difference with numPy/cuPy is when kernel fusion happens where MatX is typically able to fuse many things into a single kernel at compile-time and cuPy launches many kernels. If you have a specific type of expression you'd like to compare please let us know.

I agree we should update it given that it's also a very old comparison (2 years now). The cuPy comparison should be fair since it was the same GPU.

I addressed it more here: https://news.ycombinator.com/item?id=37760120

It's very much an apples to oranges comparison, but nevertheless relevant, since NumPy is the defacto baseline for anything numeric in Python.

Not really, for GPU computation, PyTorch, TensorFlow or JAX are the baselines (they are not just for ML stuff). Even for CPU, that's a more relevant comparison.

I agree in principle, but my experience is that researchers writing code just default to NumPy.

I would be curious how it compares to the big names in the field, Eigen, OpenBLAS, Boost, etc.

Hi, those libraries don't have a GPU counterpart, and for matrix multiplication we only support GPU right now.

Reply on news.ycombinator.com