Related papers: Node-Aware Improvements to Allreduce
Analyzing large scale data has emerged as an important activity for many organizations in the past few years. This large scale data analysis is facilitated by the MapReduce programming and execution model and its implementations, most…
Many problems of interest for cyber-physical network systems can be formulated as Mixed-Integer Linear Programs in which the constraints are distributed among the agents. In this paper we propose a distributed algorithmic framework to solve…
Single node failures represent more than 85% of all node failures in the today's large communication networks such as the Internet. Also, these node failures are usually transient. Consequently, having the routing paths globally recomputed…
We present a strongly polynomial-time algorithm to generate bandwidth optimal allgather/reduce-scatter on any network topology, with or without switches. Our algorithm constructs pipeline schedules achieving provably the best possible…
Many ML applications and products train on medium amounts of input data but get bottlenecked in real-time inference. When implementing ML systems, conventional wisdom favors segregating ML code into services queried by product code via…
Multicore systems present on-board memory hierarchies and communication networks that influence performance when executing shared memory parallel codes. Characterising this influence is complex, and understanding the effect of particular…
Major chip manufacturers have all introduced Multithreaded processors. These processors are used for running a variety of workloads. Efficient resource utilization is an important design aspect in such processors. Particularly, it is…
Distributed optimization requires nodes to coordinate, yet full synchronization scales poorly. When $n$ nodes collaborate through $m$ pairwise regularizers, standard methods demand $\mathcal{O}(m)$ communications per iteration. This paper…
Multiple Tensor-Times-Matrix (Multi-TTM) is a key computation in algorithms for computing and operating with the Tucker tensor decomposition, which is frequently used in multidimensional data analysis. We establish communication lower…
Multicast data transfers occur in many distributed systems and applications (e.g. IPTV, Grids, content delivery networks). Because of this, efficient multicast data distribution optimization techniques are required. In the first part of…
The Message Passing Interface (MPI) is the most commonly used application programming interface for process communication on current large-scale parallel systems. Due to the scale and complexity of modern parallel architectures, it is…
When there are multiple node failures in a distributed storage system, regenerating the failed storage nodes individually in a one-by-one manner is suboptimal as far as repair-bandwidth minimization is concerned. If data exchange among the…
The problem of communication among nodes in an \emph{extended network} is considered, where radio power decay and interference are limiting factors. It has been shown previously that, with simple multi-hopping, the achievable total…
Application development for distributed computing "Grids" can benefit from tools that variously hide or enable application-level management of critical aspects of the heterogeneous environment. As part of an investigation of these issues,…
The under exploitation of the available resources risks to be one of the main problems for a computing center. The growing demand of computational power necessarily entails more complex approaches in the management of the computing…
Multiple-input multiple-output (MIMO) systems greatly increase the overall throughput of wireless systems since they are capable of transmitting multiple streams employing the same time-frequency resources. However, this gain requires an…
We consider running-time optimization for band-joins in a distributed system, e.g., the cloud. To balance load across worker machines, input has to be partitioned, which causes duplication. We explore how to resolve this tension between…
The deployment of inference services at the network edge, called edge inference, offloads computation-intensive inference tasks from mobile devices to edge servers, thereby enhancing the former's capabilities and battery lives. In a…
We introduce the fastest known exact algorithm~for~the multiterminal cut problem with k terminals. In particular, we engineer existing as well as new data reduction rules. We use the rules within a branch-and-reduce framework and to boost…
In this paper, we revisit the communication vs. distributed computing trade-off, studied within the framework of MapReduce in [1]. An implicit assumption in the aforementioned work is that each server performs all possible computations on…