## n instructions execute in n*k cycles on a hypothetical non-pipelined processor with k stages,

## the execution of n instructions on a k-stage pipeline will take k+n-1 cycles, assuming ideal conditions with latency k cycles and throughput 1.

## Speedup = n*k / (k+n-1) = k / (k/n + 1 - 1/n)

## Ideal speedup (n ? infinite) = k

Previous slide | Next slide | Back to first slide | View graphic version |