If an instruction can be completed by a single$-$stage pipeline and it takes $25$ clock cycles to

finish. On the other hand, the instruction can be divided into four sub$-$tasks, each of which can be

carried out by one processing stage.

If sub$-$task $1$ takes $5$ clock cycles, sub$-$task $2$ takes $24$ clock cycles, sub$-$task three takes $15$ clock

cycles and sub$-$task four takes $10$ clock cycles. Use a diagram to illustrate that sub$-$task two will

dominate the overall performance of the system.

If $40$ instructions are being executed, determine the speedup in $\%$ by using the sub$-$task system.