A scheduling algorithm based on data modality for high-level synthesis

One of the critical steps in high level synthesis is to determine the particular scheduling algorithm that will assign behavioral operations to control states. A new scheduling algorithm called Syntax Oriented Scheduling (SOS) for high level synthesis is presented. It can determine an appropriate scheduling algorithm and minimize the number of states required using data modality and dependency conditions extracted from the behavioral code, taking into account resource constraint in each control state. The proposed algorithm identifies a set of conditions which force a state transition in the control circuit. Given this framework, the remaining transitions can be found and the operations are scheduled into appropriate states using focused local processing only.<
>