Related papers: Trevor: Automatic configuration and scaling of str…
The rapid scaling of Large Language Models (LLMs) has pushed training workloads far beyond the limits of single-node analysis, demanding a deeper understanding of how these models behave across large-scale, multi-GPU systems. In this paper,…
When IP-packet processing is unconditionally carried out on behalf of an operating system kernel thread, processing systems can experience overload in high incoming traffic scenarios. This is especially worrying for embedded real-time…
With rapidly increasing distributed deep learning workloads in large-scale data centers, efficient distributed deep learning framework strategies for resource allocation and workload scheduling have become the key to high-performance deep…
Apart from forming the backbone of compiler optimization, static dataflow analysis has been widely applied in a vast variety of applications, such as bug detection, privacy analysis, program comprehension, etc. Despite its importance,…
Orchestrating service-oriented workflows is typically based on a design model that routes both data and control through a single point - the centralised workflow engine. This causes scalability problems that include the unnecessary…
Machines learning techniques plays a preponderant role in dealing with massive amount of data and are employed in almost every possible domain. Building a high quality machine learning model to be deployed in production is a challenging…
As the artificial intelligence community advances into the era of large models with billions of parameters, distributed training and inference have become essential. While various parallelism strategies-data, model, sequence, and…
Obtaining optimal data transfer performance is of utmost importance to today's data-intensive distributed applications and wide-area data replication services. Doing so necessitates effectively utilizing available network bandwidth and…
We study scheduling control of parallel processing networks in which some resources need to simultaneously collaborate to perform some activities and some resources multitask. Resource collaboration and multitasking give rise to…
We introduce a new framework for distributed computing that extends and refines the standard master-worker approach of scheduling multi-threaded computations. In this framework, there are different roles: a supervisor, a source, a target,…
With increasingly more computation being shifted to the edge of the network, monitoring of critical infrastructures, such as intermediate processing nodes in autonomous driving, is further complicated due to the typically…
With the simultaneous rise of energy costs and demand for cloud computing, efficient control of data centers becomes crucial. In the data center control problem, one needs to plan at every time step how many servers to switch on or off in…
In today's typical industrial environments, the computation of the data distribution schedules is highly centralised. Typically, a central entity configures the data forwarding paths so as to guarantee low delivery delays between data…
This paper presents a case for exploiting the synergy of dedicated and opportunistic network resources in a distributed hosting platform for data stream processing applications. Our previous studies have demonstrated the benefits of…
Orchestrating centralised service-oriented workflows presents significant scalability challenges that include: the consumption of network bandwidth, degradation of performance, and single points of failure. This paper presents a high-level…
We present a dataflow model for modelling parallel Unix shell pipelines. To accurately capture the semantics of complex Unix pipelines, the dataflow model is order-aware, i.e., the order in which a node in the dataflow graph consumes inputs…
A parallel computer system is a collection of processing elements that communicate and cooperate to solve large computational problems efficiently. To achieve this, at first the large computational problem is partitioned into several tasks…
The problem of packet scheduling for traffic streams with target outflow profiles traversing input queued switches is formulated in this paper. Target outflow profiles specify the desirable inter-departure times of packets leaving the…
What is a systematic way to efficiently apply a wide spectrum of advanced ML programs to industrial scale problems, using Big Models (up to 100s of billions of parameters) on Big Data (up to terabytes or petabytes)? Modern parallelization…
The relevant features for a machine learning task may arrive as one or more continuous streams of data. Serving machine learning models over streams of data creates a number of interesting systems challenges in managing data routing,…