@inproceedings{hyatt_agrawal_1998, title={Congestion control in the wormhole-routed torus with clustering and delayed deflection}, volume={1417}, booktitle={Parallel computer routing and communication: Second international workshop, PCRCW 1997, Atlanta, Georgia, USA, June 26-27, 1997. Proceedings. Ed. by Sudhakar Yalamanchili and Jose Duato}, publisher={New York: Springer}, author={Hyatt, C. and Agrawal, D. P.}, year={1998}, pages={33–38} }
 @article{darbha_agrawal_1998, title={Optimal scheduling algorithm for distributed-memory machines}, volume={9}, ISSN={["1045-9219"]}, DOI={10.1109/71.655248}, abstractNote={Task Scheduling is one of the key elements in any distributed-memory machine (DMM), and an efficient algorithm can help reduce the interprocessor communication time. As optimal scheduling of tasks to DMMs is a strong NP-hard problem, many heuristic algorithms have been introduced in the literature. This paper presents a Task Duplication based Scheduling (TDS) algorithm which can schedule directed acyclic graphs (DAGs) with a complexity of O(|V|/sup 2/), where |V| is the number of tasks in the DAG. This algorithm generates an optimal schedule for a class of DAGs which satisfy a simple cost relationship. The performance of the algorithm has been observed by its application to some practical DAGs, and by comparing it with other existing scheduling schemes in terms of the schedule length and algorithm complexity.}, number={1}, journal={IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS}, author={Darbha, S and Agrawal, DP}, year={1998}, month={Jan}, pages={87–95} }
 @article{darbha_agrawal_1997, title={A task duplication based scalable scheduling algorithm for distributed memory systems}, volume={46}, ISSN={["1096-0848"]}, DOI={10.1006/jpdc.1997.1376}, abstractNote={One of the major limitations of distributed memory systems (DMSs) is the high cost for interprocessor communication, which can be minimized by having an efficient task partitioning and scheduling algorithm. It is well known that scheduling the tasks of a directed acyclic graph (DAG) to obtain an optimal solution is a strong NP-hard problem. This paper presents a scalable task duplication based scheduling (STDS) algorithm which can schedule the tasks of a DAG onto the processors of a DMS with a worst case complexity ofO(|V|2), where |V| is the number of nodes of the DAG. This algorithm generates an optimal schedule for DAGs provided a cost relationship is satisfied and if the required number of processors are available. The STDS algorithm generates a schedule for the number of processors available in the system. The performance of the STDS algorithm has been observed by comparing the parallel execution times for practical DAGs with the theoretical lowerbound.}, number={1}, journal={JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING}, author={Darbha, S and Agrawal, DP}, year={1997}, month={Oct}, pages={15–27} }
 @article{park_agrawal_1997, title={Efficient deadlock-free wormhole routing and virtual-channel reduction in shuffle-based networks}, volume={46}, ISSN={["0743-7315"]}, DOI={10.1006/jpdc.1997.1380}, abstractNote={Many aspects of shuffle-based networks have recently been studied by numerous researchers. However, no attention has been paid to deadlock-free wormhole routing algorithms. In this paper, for a set of shuffle-based networks, we introduce a graph-partitioning technique that enables a deadlock-free routing algorithm with fewer virtual channels than the known algorithms. This is achieved for the de Bruijn digraphs which are shown to require a maximum ofm? ?(m? 1)/r? virtual channels per physical channel, wheremis the diameter andris the radix. Algorithms for the generalized de Bruijn graph, the de Bruijn Cube (dBCube) graph and the Shuffle?Exchange network are introduced, and virtual channel requirements are determined. The dBCube graph of size (r,Nb,n) requires a maximum ofm? ?(m? 1)/r? virtual channels for the outcluster channels, and a maximum ofm+ 1 ? ?m/r? virtual channels for the incluster channels in most cases, wherem= ?logrNb?,ris the radix of a generalized de Bruijn graph of sizeNb, andnrepresents the number of dimensions in a binary hypercube. We also show that a maximum ofm? ?(m? 1)/2? virtual channels are required in shuffle-exchange networks with 2mnodes.}, number={2}, journal={JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING}, author={Park, H and Agrawal, DP}, year={1997}, month={Nov}, pages={165–179} }
 @article{kumar_agrawal dharma_1997, title={The shared buffer direct access (SBDA) ATM switch architecture for broadband networks}, volume={12}, number={2}, journal={Computer Systems Science and Engineering}, author={Kumar, S. and Agrawal Dharma, P.}, year={1997}, pages={69–79} }
 @book{proceedings of the 1995 icpp workshop on challenges for parallel processing, august 14, 1995_1995, ISBN={0849326184}, publisher={Boca Raton: CRC Press}, year={1995} }