Port-arm archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

Re: LSE Atomics

Tobias Nygren <tnn%NetBSD.org@localhost> wrote:
>I don't think defaulting to the common denominator ISA is a good idea
>because big.LITTLE is implemented for battery savings and for that you
>do want to be on the core with hardware accelerated crypto when doing

Maybe we need a slightly higher level API to be able to ask "what
instructions can I use on the current CPU" than the current sysctl.

In the absense of a better API I think I will go with my current
patch to nss, it matches the pattern used elsewhere.

Home | Main Index | Thread Index | Old Index