Petr Penzin

That looks better now :)

Thank you @jan-wassenberg for the write up. I did not mean to take this long to reply. I think this is a good start. > Can apps be encouraged to...

Alright, I started writing this yesterday, but it got really late and now the discussion has moved quite far 😄 I think there is no opposition to add length-agnostic variants...

@lemaitre, good point, thank you! I just opened #12 to track this.

@akirilov-arm @jan-wassenberg how about the same time a week later?

Whether fingerprinting can be avoided entirely depends on how deterministic the behavior is - it might be possible to construct tests which would be able to at least distinguish between...

> @rowan-m See https://github.com/google/XNNPACK/blob/bbf51825bc2b96f691121611e8d1d262f76b8010/src/init.c#L73-L78 @Maratyszcza, is this something you have in mind for this proposal as well? For example, relaxed swizzle can be used in one or the other possible...

> Hello everyone, this is an attempt to formalize flexible vectors in a model that mimics SVE, as an alternative to #21 . The main goal of this PR is...

> Basically, does narrowing concat inputs, or interleave inputs? Does widening selects low/high half or even/odd half? This might not be an issue as there seem to be consensus on...

To set the record straight - while this proposal (the repo) draws inspiration from vector instruction sets, the first goal is to extend WebAssembly support for hardware fixed-width SIMD beyond...