Graphics processing units (GPUs) can improve deep neural network inference throughput via batch processing, where multiple tasks are concurrently processed. We focus on novel scenarios that the energy-constrained mobile devices offload to an edge server with GPU. The task is partitioned into sub-tasks for a finer granularity of offloading and scheduling, user energy consumption minimization pro...

There currently exist a number of excellent techniques to capture, register, and blend digital panoramas. However, the problem is treated as an automated batch process, which can take several minutes to produce a panorama. Unfortunately, many of the algorithms involved are prone to errors and/or artifacts and may require meticulous tuning to achieve high quality results. This not only requires ...

In this paper, we consider an integrated scheduling problem of production and distribution for manufacturers. In the production part, the batch-processing machines have fixed capacity and the jobs have arbitrary sizes and processing times. Jobs in a batch can be processed together, provided that the total size of the jobs in the batch does not exceed the machine capacity. The processing time of...

We consider a single batch machine on-line scheduling problem with jobs arriving over time. A batch processing machine can handle up to B jobs simultaneously as a batch, and the processing time for a batch is equal to the longest processing time among the jobs in it. Each job becomes available at its arrival time, which is not known in advance, and its characteristics, such as processing time a...

WebLicht is a workflow engine that gives researchers access to well-inhabited space of natural language processing tools can be combined into tool chains perform complex analyses. In this paper, we present WebLicht-Batch, web-based interface WebLicht's chainer back-end. WebLicht-Batch helps users automatically feed large input data, or data multiple files WebLicht. It disassembles smaller, more...

In the parallel batch schedulingmodel, a group of jobs can be scheduled together as a batch while the processing time of this batch is the greatest processing time among its members; in the model of scheduling with rejection, any job can be rejected with a corresponding penalty cost added to the objective value. In this paper, we present a PTAS for the combined model of the above two scheduling...

Title of dissertation: Pig Squeal: Bridging Batch and Stream Processing Using Incremental Updates James Holmes Lampton, Jr., Doctor of Philosophy, 2015 Dissertation directed by: Professor Ashok Agrawala Department of Computer Science As developers shift from batch MapReduce to stream processing for better latency, they are faced with the dilemma of changing tools and maintaining multiple code b...

With the growing need of processing “big data” in real time, modern streaming processing systems should be able to operate at the cloud scale. This imposes challenges to building large scale stream processing systems. First, processing tasks should be efficiently distributed to worker nodes with small overhead. Second, streaming data processing should be highly available, despite that failures ...

While cluster computing frameworks are continuously evolving to provide real-time data analysis capabilities, Apache Spark has managed to be at the forefront of big data analytics for being a unified framework for both, batch and stream data processing. However, recent studies on micro-architectural characterization of in-memory data analytics are limited to only batch processing workloads. We ...