Software pipelining

Utilizing parallelism at the instruction level is an important way to improve performance. Because the time spent in loop execution dominates total execution time, a large body of optimizations focuses on decreasing the time to execute each iteration. Software pipelining is a technique that reforms the loop so that a faster execution rate is realized. Iterations are executed in overlapped fashion to increase parallelism. Let {<italic>ABC</italic>}<supscrpt><italic>n</italic></supscrpt> represent a loop containing operations <italic>A, B, C</italic> that is executed <italic>n</italic> times. Although the operations of a single iteration can be parallelized, more parallelism may be achieved if the entire loop is considered rather than a single iteration. The software pipelining transformation utilizes the fact that a loop {<italic>ABC</italic>}<supscrpt><italic>n</italic></supscrpt> is equivalent to <italic>A</italic>{<italic>BCA</italic>}<supscrpt><italic>n</italic>−1</supscrpt><italic>BC</italic>. Although the operations contained in the loop do not change, the operations are from different iterations of the original loop. Various algorithms for software pipelining exist. A comparison of the alternative methods for software pipelining is presented. The relationships between the methods are explored and possibilities for improvement highlighted.