Abstract
The process of calculations control in reconfigurable computing systems characterized by the time constraints of both the applications solved and the functional and structural organization of the system is investigated. As part of this, the method is modified and mathematically substantiated for determining the time intervals of tasks. The proposed modification to the analysis of tasks acceleration index allows to evaluate the unproductive time expenditure taking into account the FPGA hardware limitations in the computer algorithms mapping to the reconfigurable computing structure. The method of providing time parameters of service quality in the reconfigurable computing system that provides given application runtime by determining the amount of unproductive time-consuming reconfiguration and the choice of optimal service discipline for each task in terms of time and existing hardware limitations was proposed. The use of the proposed method of determining the time intervals, which the implementation of the method is based on determining the sequence of tasks for which the target architecture of the computer system is effective and the use of additional mechanisms to reduce overhead does not speed up calculations within the advertised time requirements. Application of the proposed method allows to determine and optimize the impact of space limitations the reconfiguration time and reduce the number of rejections of tasks in the dynamic mapping of task flows to the reconfigurable computational structure. The formalization of the method for determining the time intervals of tasks was developed, for which the optimal boundaries of the effective use of the proposed facilities in terms of the adequacy of the offered application time limits to the limits of the reconfigurable computer system were defined and justified. The proposed tools can be used in modern high-performance reconfigurable computing systems during solving the problems of control of various technical and management processes and implementation of multidimensional calculations in complex information systems.
Highlights
A paradigm of the solution of wide classes of tasks is the modern trends of development of reconfigurable computing systems, including the tasks that require strict time restrictions of run time, including real-time tasks
Reconfigurable systems are characterized by particular functional and hardware limitations caused by the use of reprogrammed components – FPGAs
The processes that occur in dynamically reconfigurable computing systems and that stipulate problems with Quality of Service (QoS) [1], considering hardware constraints of FPGA, are the object of research in this work
Summary
A paradigm of the solution of wide classes of tasks is the modern trends of development of reconfigurable computing systems, including the tasks that require strict time restrictions of run time, including real-time tasks. Reconfigurable computing systems are characterized by existence of constant structure and variable – as a set of computing nodes, whose structure can be rebuilt According to this definition, reconfigurable systems are characterized by particular functional and hardware limitations caused by the use of reprogrammed components – FPGAs (field programmable gate arrays). The traditional methods for providing QoS, developed for fixed computing systems arent effective for such systems, considering functional restrictions caused by delays in the process of dynamic creation of computing structure and spatial restrictions of FPGAs. Known methods of the accounting of these time delays can’t be effectively used within time restrictions of the run applications because of impossibility to evaluate their volume for implementation of the computation control optimization
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
