The theoretical speedup in latency for task execution under fixed workloads as processors increase.
Where:
S = theoretical speedup of the execution of the whole task when enhancements are applied
p = proportion of the program that can be parallelized (0 ≤ p ≤ 1)
n = number of processors
(1−p) = proportion of the program that remains serial
The speedup is fundamentally limited by the serial (I/O) portion of the program.
