Compiler Directed Data Locality Optimization for Multicore Architectures

This paper presents and evaluates a cache hierarchy-aware code parallelization/mapping and scheduling strategy for multicore architectures. Our proposed parallelization/mapping strategy determines a loop iteration-to-core mapping by taking into account the data access pattern of an application and the on-chip cache hierarchy of a target architecture. The goal of this step is to maximize data locality at each level of caches while minimizing the data dependences across the cores. Our scheduling strategy on the other hand determines a schedule for the iterations assigned to each core in the target architecture, with the goal of satisfying all the data dependences in the code (both intra-core and inter-core) and reducing data reuse distances across the cores that share data. We formulate both parallelization/mapping problem and scheduling problem in a linear algebraic framework and solve them using the Farkas Lemma and the Integer Fourier-Motzkin Elimination. To measure the effectiveness of our schemes, we implemented them in a compiler and tested them using eight multithreaded application programs on a multicore machine. Our results show that the proposed mapping scheme reduces cache miss rates at all levels of the cache hierarchy and improves execution time of applications significantly, compared to alternate approaches, and when supported by scheduling, the improvements in cache miss rates and execution time become much larger.