Dynamic path distribution method and system applicable to network on chip

Abstract

The invention discloses a dynamic path distribution method and system applicable to a network on a chip. The method is characterized in that bandwidth occupancy conditions and fault information of each routing unit in the network on chip are collected in real time, and routing paths with communication tasks are regulated dynamically in accordance with network states, so that the routing paths can avoid congestion and fault links. The distribution system comprises a receiving controller, a fault management module, a communication task management module, a node sequential recording module, a path mapping module, a path management module and a sending controller. According to the distribution method and system, the routing paths with the communication tasks can be optimized under the condition that link congestion and permanent faults occur on the network on chip, the network loads can be balanced, the blocking rate of data packets can be reduced, and the performances can be improved under the condition of the link congestion and fault.

Description

Technical field [0001] The invention relates to a dynamic path allocation method and system applied to an on-chip network, which is applied to the field of integrated circuits, in particular to the field of design of interconnection networks on an integrated circuit. Background technique [0002] With the maturity and further development of deep submicron VLSI process technology, the design of SoC (System on Chip, system on chip) is facing severe problems, which are mainly manifested in three aspects: the synchronization problem of connection delay and global clock , Structural problems such as limited address space and the inability to support parallel communication of multiple groups of devices, as well as system expansion problems. In order to solve the problems encountered in SoC design, some European research institutions put forward the concept of NoC (Network on Chip, Network on Chip) in 2000. Its core idea is to transplant computer network technology into chip design and ...

AI Technical Summary

Problems solved by technology

[0004] a) When the network load is heavy, local link congestion is likely to occur, resulting in the failure of real-time responses to communication requests on some critical paths;

[0005] b) The network load distribution is uneven; in a certain area of ​​the network, the data flow is too large, and the delay of the data packet is unacceptable, and at the same time, the communication nodes in some areas of the network are idle, and the utilization rate of the network link is too low;

[0006] c) When there is a faulty node in the network or some nodes are temporarily disabled, resulting in an increase in the number of congested links, the communication performance will be greatly reduced

Images