Minimizing memory requirements in rate-optimal schedules

reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. Abstract In this paper we address the problem of minimizing buuer storage requirement in constructing rate-optimal compile-time schedules for multi-rate dataaow graphs. We demonstrate that this problem, called the Minimum Buuer Rate-Optimal (MBRO) scheduling problem, can be formulated as a uniied linear programming problem. A novel feature of our method is that it tries to minimize the memory requirement while simultaneously maximizing the computation rate. We have constructed an experimental testbed which implements our scheduling algorithm as well as (i) the widely used periodic admissible parallel schedules proposed by Lee and Messer-schmitt 12], (ii) the optimal scheduling buuer allocation (OSBA) algorithm of Ning and Gao 15], and (iii) the multi-rate software pipelining (MRSP) algorithm 7]. The experimental results have demonstrated a signiicant improvement in buuer requirements for the MBRO schedules compared to the schedules generated by the other three methods. Compared to block schedules, MBRO schedules perform better in terms of both computation rate and buuer requirements. The average observed improvement in buuer storage is 26% with respect to the MRSP algorithm, 17% with respect to block schedules and 5% with respect to the OSBA formulation.