This discussion has been locked.
You can no longer post new replies to this discussion. If you have a question you can start a new discussion

Why L1 cache associativity DOUBLED and index method CHANGED from the programmer's point of view?

I'm confused when I see the description of L1 cache:

L1 data memory system:
The L1 data cache is organized as a Virtually Indexed, Physically Tagged (VIPT) cache.


*Note*
In the L1 data memory subsystems, aliases are handled in hardware and from the programmer's point of view, the data cache behaves like an eight-way set associative PIPT cache (for 32KB configurations) and a 16-way set associative PIPT cache (for 64KB configurations).

Few materials are about this mechanism, could someone kind offer me some ideas?

Thanks and have a nice day! :)