Arrow Research search

Author name cluster

Shishir Rai

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers
1 author row

Possible papers

2

TCS Journal 2024 Journal Article

Ordered scheduling in control-flow distributed transactional memory

  • Pavan Poudel
  • Shishir Rai
  • Swapnil Guragain

Consider the control-flow model of transaction execution in a distributed system modeled as a communication graph where shared objects positioned at nodes of the graph are immobile but the transactions accessing the objects send requests to the nodes where objects are located to read/write those objects. The control-flow model offers benefits to applications in which the movement of shared objects is costly due to their sizes and security purposes. In this paper, we study the ordered scheduling problem of committing dependent transactions according to their predefined priorities in this model. The considered problem naturally arises in areas, such as loop parallelization and state-machine-based computing, where producing executions equivalent to a priority order is needed to satisfy certain properties. Specifically, we study ordered scheduling considering two performance metrics fundamental to any distributed system: (i) execution time - total time to commit all the transactions and (ii) communication cost - the total distance traversed in accessing required shared objects. We design scheduling algorithms that are individually or simultaneously efficient for both the metrics and rigorously evaluate them through several benchmarks on random and grid graphs, validating their efficiency. To our best knowledge, this is the first study of ordered scheduling in the control-flow model of distributed transaction execution.

Details DOI

I&C Journal 2022 Journal Article

Load balanced distributed directories

  • Shishir Rai
  • Gokarna Sharma
  • Costas Busch
  • Maurice Herlihy

We present LB-Spiral, a novel distributed directory protocol for shared objects, suitable for large-scale distributed shared memory systems. Each shared object has an owner node that can modify its value. The ownership may change by moving the object from one node to another in response to move requests. The value of an object can be read by other nodes with lookup requests. The distinctive feature of LB-Spiral is that it balances the processing load on nodes in addition to minimizing the communication cost in general network topologies. In contrast, the existing distributed directory protocols for general network topologies only minimize the communication cost. In particular, LB-Spiral achieves poly-log approximation for both load and communication cost in general networks with respect to the problem parameters. Simulation results show that the established theoretical results translate well in practice.

Details DOI
v2026.09.13