A Multi-VC Dynamically Shared Buffer with Prefetch for Network on Chip

In this paper, we propose a novel multi-VC dynamically shared buffer named DAMQ-PF for network on chip to decrease the memory and area requirement of statically allocating shared buffer among multiple virtual channels (VC). A small prefetch buffer is used for each VC to store data read from the shared buffer in advance. The same mechanism is also used in the implementation of idle address list. By so doing, we implement continuous and concurrent reading and writing of the shared buffer without delay. A fair credit management method is also proposed to avoid a single VC occupying the shared buffer exclusively. Analyses and tests show that DAMQ-PF achieves high buffer utilization, low write and read delay and high throughput which satisfies the performance requirement of NoC based on flit switch very well.