Catálogo de publicaciones - revistas

<jats:p>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.</jats:p> <jats:p> Let { <jats:italic>ABC</jats:italic> } <jats:sup> <jats:italic>n</jats:italic> </jats:sup> represent a loop containing operations <jats:italic>A, B, C</jats:italic> that is executed <jats:italic>n</jats: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 { <jats:italic>ABC</jats:italic> } <jats:sup> <jats:italic>n</jats:italic> </jats:sup> is equivalent to <jats:italic>A</jats:italic> { <jats:italic>BCA</jats:italic> } <jats:sup> <jats:italic>n</jats:italic> −1 </jats:sup> <jats:italic>BC</jats:italic> . Although the operations contained in the loop do not change, the operations are from different iterations of the original loop. </jats:p> <jats:p>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.</jats:p>