Is there a software optimization guide for Ampere cores? I’ve gotten some code working, but I have no idea what to expect in terms of how expensive instructions are? Even a bare “throughput and latency” table similar to what ARM puts out for (say) the A75 would be very helpful.
Today there is material from our customer connect site which is available to system owners.
In the future we do want to populate more open information. Let me check out the throughput and latency table for ARM – good pointer.