High-performance multi-queue buffers for VLSI communications switches
ISCA '88 Proceedings of the 15th Annual International Symposium on Computer architecture
Achieving 100% throughput in an input-queued switch
INFOCOM'96 Proceedings of the Fifteenth annual joint conference of the IEEE computer and communications societies conference on The conference on computer communications - Volume 1
| Hi-index | 0.00 |
Input Queued switches have been very well studied in the recent past. The Maximum Weight Matching (MWM) algorithm is known to deliver 100% throughput under any admissible traffic. However, MWM is not practical for its high computational complexity O(N3). In this paper, we study a class of approximations to MWM from the point of view of local search. Firstly, we propose a greedy scheduling algorithm called GSA. It has the following features: (a) It is very simple to compute the weight of a neighbor matching. GSA only needs to compute the weight of two swapped edges instead of the weight of all the edges. (b) The computational complexity of GSA is O(c_max), where c_max denotes the maximum number of iterations. Hence we can adjust the value of c_max to achieve low computational complexity. Secondly, we observe that: (a) Local search is well suitable for parallel computing. (b) Each line card of high performance router has at least one processor. Based on the two important observations, we develop the second algorithm PGSA. Compared with GSA, PGSA significantly reduce the number of iterations. Simulation results show that PGSA with three iterations outperforms algorithms in [1] under different switch sizes.