The rule, which is an industry term, is named for Fred Pollack, a lead engineer and fellow at Intel.
A generous interpretation of the rule allows for the case in which an ideal device could contain hundreds of low-complexity cores, each operating at very low power and together performing large amounts of (processing) work quickly.
This describes a massively parallel processor array (MPPA), which is currently being used in embedded systems and hardware accelerators.
However, Pollack's Law as originally formulated was considered to be a limit on the performance improvements for single CPUs as the number of transistors increased, as well as for multiprocessor systems.
On the other hand, Pollack's rule implies that microarchitecture advances improve the performance by another √2 ≈ 41%.