| ▲ | eigenspace 2 days ago | ||||||||||||||||||||||
Intel E-cores are basically a different microarchitecture. They often support different instruction sets than their P-cores, have different "instructions-per-clock" rates (IPC), and all sorts of other major differences. They're just very different things, and those differences are responsible for most of the bad reputation that E-cores have. AMD's dense-cores are the same microarchitecture, have the same IPC, use all the same instruction sets. The only real difference between them and regular AMD cores is that their dense cores have less cache, and lower peak clocks. | |||||||||||||||||||||||
| ▲ | zozbot234 2 days ago | parent | next [-] | ||||||||||||||||||||||
There's nothing wrong with E-cores though, their bad reputation is quite undeserved. They pack a lot of compute in tiny area and power constraints compared to P-cores. They're probably not the optimal choice for a single-thread workload, but that's an entirely different matter. | |||||||||||||||||||||||
| |||||||||||||||||||||||
| ▲ | tester756 2 days ago | parent | prev [-] | ||||||||||||||||||||||
>They often support different instruction sets than their P-cores Do they? I thought it caused very significant problems (when there's switch between E and P core) and they avoided it But I cannot find anything about it | |||||||||||||||||||||||
| |||||||||||||||||||||||