Sam Parker

I'm picking up AtomicRMW for AArch64.

I'm picking up AtomicCas and IaddPairwise for aarch64.

I've also picked up snarrow, unarrow, uunarrow and fvdemote.

I've started on icmp, which doesn't look like it's going to be fun!

I've made a PR for the aarch64 min/max instructions

I never thought bitcasts could be so complicated until I read the clif docs :) It sounds like the standarization of booleans, hopefully enabling storage, is the only thing preventing...

> FWIW, this now seems to fully work: various upstream issues seem to have resolved (e.g. asan on aarch64 works now?), and I'm successfully running fuzz jobs on a Linux/aarch64...

Hi, Arm person here... and I apologize now for really not knowing anything about .net, so please pardon my ignorance! I really like the sound of focusing on the generic...

So, what happens if the compiler decides that sometimes we should use AVX-512 for some operations, but AVX2 for others? Is there enough type information to enable this with `Vector`?...

Fair enough wrt to masking vs leading/trailing, thanks for the clarification. > This would likely end up PGO or data driven in some other fashion. It would default to "Max"...