Related papers: DaphneSched: A Scheduler for Integrated Data Analy…

Data engineering pipelines are a widespread way to provide high-quality data for all kinds of data science applications. However, numerous challenges still remain in the composition and operation of such pipelines. Data engineering…

The exponential growth in the size and complexity of Large Language Models (LLMs) has introduced unprecedented challenges in their deployment and operational management. Traditional MLOps approaches often fail to efficiently handle the…

Data and pipeline parallelism are key strategies for scaling neural network training across distributed devices, but their high communication cost necessitates co-located computing clusters with fast interconnects, limiting their…

Shared resource interference is observed by applications as dynamic performance asymmetry. Prior art has developed approaches to reduce the impact of performance asymmetry mainly at the operating system and architectural levels. In this…

Pipeline is a fundamental parallel programming pattern. Mainstream pipeline programming frameworks count on data abstractions to perform pipeline scheduling. This design is convenient for data-centric pipeline applications but inefficient…

Multi-party computing (MPC) has been gaining popularity as a secure computing model over the past few years. However, prior works have demonstrated that MPC protocols still pay substantial performance penalties compared to plaintext,…

Integrated energy systems (IESs) are complex systems consisting of diverse operating units spanning multiple domains. To address its operational challenges, we propose a physics-informed hybrid time-series neural network (NN) surrogate to…

Industry 4.0 is concerned with sustainable development constraints. In this context, we propose a multi-agent architecture, named EasySched, aiming at elaborating predictive and reactive scheduling as the result of a coordination between…

As deep neural networks (DNNs) are being applied to a wide range of edge intelligent applications, it is critical for edge inference platforms to have both high-throughput and low-latency at the same time. Such edge platforms with multiple…

Domain-specific systems-on-chip (DSSoCs) aim at bridging the gap between application-specific integrated circuits (ASICs) and general-purpose processors. Traditional operating system (OS) schedulers can undermine the potential of DSSoCs…

Operating a distributed data stream processing workload efficiently at scale is hard. The operator of the workload must parallelize and lay out tasks of the workload with resources that match the requirement of target data rate. The…

On-device Deep Neural Network (DNN) training has been recognized as crucial for privacy-preserving machine learning at the edge. However, the intensive training workload and limited onboard computing resources pose significant challenges to…

We propose XPipe, an efficient asynchronous pipeline model parallelism approach for multi-GPU DNN training. XPipe is designed to use multiple GPUs to concurrently and continuously train different parts of a DNN model. To improve GPU…

Data processing frameworks such as Apache Beam and Apache Spark are used for a wide range of applications, from logs analysis to data preparation for DNN training. It is thus unsurprising that there has been a large amount of work on…

Scaling data volume and diversity is critical for generalizing embodied intelligence. While synthetic data generation offers a scalable alternative to expensive physical data acquisition, existing pipelines remain fragmented and…

Efficiently optimizing multi-model inference pipelines for fast, accurate, and cost-effective inference is a crucial challenge in machine learning production systems, given their tight end-to-end latency requirements. To simplify the…

In recent years, to sustain the resource-intensive computational needs for training deep neural networks (DNNs), it is widely accepted that exploiting the parallelism in large-scale computing clusters is critical for the efficient…

This paper presents a dynamic, adaptive, and scalable framework for simulating task scheduling on the edge of the Internet of Things called "SchEdge". This simulator is designed to be highly configurable to reflect the detailed…

Increasing scale and heterogeneity in data centers have led to the development of federated clusters such as KubeFed, Hydra, and Pigeon, that federate individual data center clusters. In our work, we introduce Megha, a novel decentralized…

Deep research agents, which synthesize information across diverse sources, are significantly constrained by the sequential nature of reasoning. This bottleneck results in high latency, poor runtime adaptability, and inefficient resource…