Optimizing Data-Flow Graphs with min/max, adding and relational operations

During Electronic System-Level (ESL) design, High-Level Synthesis (HLS) tools normally translate the system description to a Control/Data Flow Graph. At this level, several transformations are performed as early as possible to reduce the number and complexity of the data operations. These preliminary transformations (for example, common sub-expression elimination, constant propagation, etc) are typically applied in algebraic expressions with arithmetic operators. This paper presents preliminary transformations that optimize Data-Flow Graphs with relational, maximum/minimum and arithmetic (addition/subtraction) operations. The proposed techniques produce a significant reduction in the number of operations. HLS tools and even software compilers and symbolic algebra packages are not able to generate similar results. The efficiency of the techniques has been evaluated with several modules of real telecommunications standards and their HW implementations show important area reductions and, sometimes, low impact on latency or critical path.