tnibler

> but only because of not wanting to spend the effort Which is a totally valid reason of not doing work for free, is it not?

I see, it's not that big of a deal anyway since it's easy to build from source. The Rust library is just basic bindings so not much to go wrong,...

Those are in place though (at least the ones I found, like `rotate` and `flip`), which is different again so that makes three versions of every function: the current one...

What do you think about [something like this](https://play.rust-lang.org/?version=stable&mode=debug&edition=2021&gist=e9b9193eada20d73b7f28e22efcc6abd)? You would only have to implement `op_into` (and in-place versions if possible) and get the rest generated automatically.

Okay, so since there is some interest I'll try and come up with some possible design ideas that can take into account some of the more complex cases and the...

Ok, I have thought about some of these points and hope to flesh them out in a master's thesis, so I'll have some better insights after that hopefully. The `ndarray`...

`mut` functions are in-place though right? That's different than putting the result into a buffer passed in by the caller while keeping the input image unchanged.

It's a huge pain, PPR docs for the last 3 (actually 4 now) generations are missing and AMD support just says they will be released "later". In the meantime I...

Update: seems like there are at least some differences between model 75h and the Zen4 counter mappings in likwid (don't know about 68h), and even a good number of e.g....

That was a misleading way to phrase it, I'm not sure LIKWID is doing anything wrong actually. perf has the [same L3 lookup state events](https://github.com/torvalds/linux/blob/9852d85ec9d492ebef56dc5f229416c925758edc/tools/perf/pmu-events/arch/x86/amdzen4/cache.json#L654) as LIKWID, but they are...