From WikiChip
Microprocessor Performance
Revision as of 21:10, 4 January 2019 by David (talk | contribs)

The performance of a microprocessor is a measure of its efficiency in terms of the amount of useful work it accomplishes.

Equation

The performance (time-to-execute) of a certain finite workload is the reciprocal of execution time.

Equation upper P proportional-to StartFraction 1 Over upper T Subscript exec Baseline EndFraction left-bracket StartFraction monospace programs Over monospace second EndFraction right-bracket

The total execution time, Equation upper T Subscript exec , required to execute a specific finite program is.

Equation upper T Subscript exec Baseline equals StartFraction monospace IC times monospace CPI Over f EndFraction left-bracket monospace second right-bracket

Where,

Thus, the performance of a microprocessor can also be defined as.

Equation StartLayout 1st Row 1st Column upper P 2nd Column equals StartFraction f Over monospace IC times monospace CPI EndFraction 2nd Row 1st Column Blank 3rd Row 1st Column Blank 2nd Column equals StartFraction monospace IPC times f Over monospace IC EndFraction EndLayout

Note that for the sake of brevity, sometimes the instruction count is omitted when referring to the performance of a fixed portion of code. In other words, when the instruction count is fixed because the program is not being recompiled, it is sometimes omitted from the equation. However, doing this ignores the fact that recompiling code can have a positive impact on performance.