Loop fission

Abstract: In the past decade, processor speed has become significantly faster than memory speed. Small, fast cache memories are designed to overcome this discrepancy, but they are only effective when programs exhibit data locality. In the this article, we present compiler optimizations to improve data locality based on a simple yet accurate cost model. The model computes both temporal and spatial reuse of cache lines to find desirable loop organizations. The cost model drives the application of compound transformations consisting of loop permutation, loop fusion, loop distribution, and loop reversal. To validate our optimization strategy, we implemented our algorithms and ran experiments on a large collection of scientific programs and kernels. Experiments illustrate that for kernels our model and algorithm can select and achieve the best loop structure for a nest. For over 30 complete applications, we executed the original and transformed versions and simulated cache hit rates. We collected statistics about the inherent characteristics of these programs and our ability to improve their data locality. To our knowledge, these studies are the first of such breadth and depth. We found performance improvements were difficult to achieve bacause benchmark programs typically have high hit rates even for small data caches; however, our optimizations significanty improved several programs.

Abstract: 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 {ABC}n represent a loop containing operations A, B, C that is executed n 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 {ABC}n is equivalent to A{BCA}n−1BC. 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.

Abstract: Parallelizing compilers promise to exploit the parallelism available in a given program, particularly parallelism that is too low-level or irregular to be expressed by hand in an algorithm. However, existing parallelization techniques do not handle loops in a satisfactory manner. Fine-grain (instruction level) parallelization, or compaction, captures irregular parallelism inside a loop body but does not exploit parallelism across loop iterations. Coarser methods, such as doacross [9], sacrifice irregular forms of parallelism in favor of pipelining iterations (software pipelining). Both of these approaches often yield suboptimal speedups even under the best conditions-when resources are plentiful and processors are synchronous. In this paper we present a new technique bridging the gap between fine-and coarse-grain loop parallelization, allowing the exploitation of parallelism inside and across loop iterations. Furthermore, we show that, given a loop and a set of dependencies between its statements, the execution schedule obtained by our transformation is time optimal: no transformation of the loop based on the given data-dependencies can yield a shorter running time for that loop.