Now, you are given $3$ processors $A,B,C,$ and $5$ benchmark programs $P1$ to $P5.$ The following summarizes

the run time of these programs in the $3$ processors. In all cases, both the raw CPU times $($in seconds$)$

Consider the $3$ programs $P,Q$ and $R$ running in processor A and $B$ with the following number of

instructions:

HINT: use a spreadsheet program to help with answering this question.

A$\mathrm{.}1\mathrm{.}1$ What is the average CPI of programP,$Q,R,$ when executed on processor A and $B?$

A$\mathrm{.}1\mathrm{.}2$ Processor A runs at $1\mathrm{.}5GHz$ while processor $B$ runs at $1\mathrm{.}2GHz,$ double the clock rate. Consider

only the $3$ programs $P,Q$ and $R$ individually, which processor results in higher performance, and by

how much?

A$\mathrm{.}1\mathrm{.}3$ When considering all three programs as a whole, which processor is faster? On average $($geometric

mean$),$ how much faster is the faster processor?

A$\mathrm{.}1\mathrm{.}4$ You are allowed to improve the speed of only $1$ of the three instruction types $($ALU$,$ Branch$/$Jump$,$

Load$/$Store$)$ of the slower processor. Assuming the clock frequency remains unchanged, what is the

maximum speedup possible when using the total runtime $($not geometric mean$)$ for the three programs?

A$\mathrm{.}1\mathrm{.}5$ If the geometric mean of speedup between the processors among the $3$ programs were to measure

how good a processor is$,$ would that affect your choice of instruction class to improve on$?$ If so$,$ how does

it affect your answer? If not, explain why it doesn't matter whether total runtime or geometric mean is

used?