Review of A Data Locality Optimizing Algorithm

What problem did the paper address? Who is the intended audience? The big picture problem is how can we improve program performance given the large latency between the processor and memory. The audience is compiler researchers and writers because they are focusing on an existing compilation technique called tiling, which was developed to avoid memory access latency . The paper addresses the problem that not all loops are initially tileable. Specifically they answer the question, what combination of loop permutation, skewing, and reversal (unimodular transformations) should be used to make a loop tileable in a way that will improve data locality? The problem is hard. Just finding a legal set of unimodular transformations is exponential in the number of loops [SD90].