Diego Andrade, Manuel Arenaz, Basilio B. Fraguela, Juan Touriño and Ramón Doallo
Computer Architecture Group, University of A Coruña, Spain

The memory hierarchy plays an essential role in the performance of current computers, thus good analysis tools that help predict and understand its behavior are required. Analytical modeling is the ideal base for such tools if its traditional limitations in accuracy and generality of application are overcome. For example, while there has been extensive research on the modeling of codes with regular access patterns, less attention has been paid to the codes with irregular patterns due to the increased difficulty to analyze them. Nevertheless, many important applications exhibit this kind of patterns, and their lack of locality make them more cache-demanding, which makes their study more relevant. In this paper we present an analytical model that can provide fast and accurate predictions of the cache behavior of codes with irregular access patterns. In addition, we describe the integration of the model in a research compiler oriented to automatic kernel recognition in scientific codes. The paper shows how to exploit the powerful information-gathering capabilities provided by the compiler to allow automated modeling of loop-oriented scientific codes.

Back to the Workshop Program