LLMORE: A Framework for Data Mapping and Architecture Analysis

We outline our recent efforts in developing MIT Lincoln Laboratory’s Mapping and Optimization Runtime Environment (LLMORE). The LLMORE framework consists of several components that together estimate and optimize performance critical sections of an application. This framework can be used to improve the performance of parallel applications and as an important tool for analyzing different hardware architectures. In this paper, we describe the use cases that have driven the development of LLMORE. We also give two concrete examples of how LLMORE can be used to improve the parallel performance of a numerical operation and characterize the power efficiency of numerical algorithms and computer architectures.