Re:Ara: A 1 GHz+ Scalable and Energy-Efficient RISC-V Vector...
by pjscott on Friday June 07, 2019 @07:28PM
(#20129523)
I checked the latency and throughput of the SSE4 POPCNT and LZCNT instructions on a bunch of microarchitectures [1], and can't think of any way to get that kind of performance with a combination of simpler instructions. These are occasionally very useful operations, and I really do want them to be fast.
[1] https://www.agner.org/optimize/instruction_tables.pdf