The implementation of the algorithm could be made in the near future using FPGAs with higher-capacity or allowing asynchronous interconnectivity between
asynchronous logic blocks, the above must be accompanied by the use of tools with greatest ability to synthesize and to adapt asynchronous digital circuits.
They often use the properties of asynchronous logic for high performance (high speed, low power, robustness, etc.).
The PLB architecture has been designed to be a good trade-off between the efficient resource management and the high flexibility required to be style-independent (many asynchronous logic styles exist: 4-phase, 2-phase logic, e.g., and different data encoding: for instance the 1-of-n data encoding).
As shown in Figure 5, the LE outputs are fed back to the LE inputs through multiplexers in order to ensure the implementation of memory elements that are commonly used in asynchronous logic such as Muller C-elements.
This is why the Muller element (or C-element) is extensively used in asynchronous logic and is considered as the fundamental component on which is based the 4-phase and 2-phase asynchronous protocols implementation.
The LUTs are able to implement functions with memorization which are required for asynchronous logic.
Asynchronous logic requires implementing protocols between communicating modules, which basically consists in computing an acknowledgment signal.
A netlist that contains "reconvergent paths"--nodes where a path with fewer pipeline stages (shorter path) reconverges with a path with more pipeline stages (longer path)--leads to slow speed of operation for
asynchronous logic. In that case, data in the shorter path arrive earlier to the node and have to wait for data in the longer path to propagate forward.