In this paper, a new technique is presented for the resource constrain
ed scheduling problem in high level synthesis. This approach works by
successively partitioning the control steps into zones and solving eac
h of them by a 0-1 integer linear programming technique. By specifying
the maximum number of 0-1 variables involved within a zone, the model
can be turned into an optimal ILP scheduling, a list scheduling, or o
ne in between with different speed/quality characteristics. Experiment
s show that better results than those achieved by list scheduling have
been obtained with an acceptable computation overhead.