In this paper we address the problem of minimizing buffer storage requirement in constructing rate-optimal compile-time schedules for multi-rate dataflow gmphs. We demonstrate that this problem, called the Minimum Buffer Rate-Optimal (MBRO) scheduling problem, can be formulbted as a unified linear programming problem. A novel feature of our method is that it tries to minimize the memory requirement while simultaneously mazimizing the computation rate.We have constructed an ezperimental testbed which implements our scheduling algorithm as well as (i) the widely used periodic admissible parallel schedules proposed by Lee and Messerschmitt [f 21, (ii) the optimal scheduling buffer allocation (OSBA) algorithm of Ning and Gao 1151, and (iii) the multi-rate software pipelining (MRSP) algorithm 171. The ezperimental resultshave demonstrated a significant improvement in buffer requirements for the MBRO schedules compared to the schedule8 generated by the other three methods. Compared to block achedules, MBRO schedulesperform better in terms of both computation rate and buffer requirements. The average observed improvement in buffer storage ia 26% with respect to the MRSP algorithm, 17% with respect to block schedules and 5% with respect to the OSBA formulation.

No abstract