This. For folks who regularly write simd/vmx/etc, this is a fairly straightforward PR, and one that uses very common patterns to achieve better parallelism.
It's still cool nonetheless, but not a particularly great test of DeepSeek vs. alternatives.
That is what I am struggling to understand about the hype. I regularly use them to generate new simd. Other than a few edge cases (issues around handling of nan values, order of argument for corresponding ops, availability of new avx512f intrinsics), they are pretty good at converting. The names of very intrinsics are very similar from simd to another.
The very self-explanatory nature of the intrinsics names and having similar apis from simd to another makes this somewhat expected result given what they can already accomplish.
I do have to say, that before knowing what was Simd it was all black magic to me. Now, I've had to get how it works for my thesis, on a very shallow level, and I have to say it's much less black magic than before, although I wouldn't be able to write Simd code
Deepseek r1 is not exactly better than the alternatives. It is, however, open as in open weight and requires much less resources. This is what’s disruptive about it.
It's still cool nonetheless, but not a particularly great test of DeepSeek vs. alternatives.