Related papers: Optimizing Tail Latency in Commodity Datacenters u…
Distributed storage systems often employ erasure codes to achieve high data reliability while attaining space efficiency. Such storage systems are known to be susceptible to long tails in response time. It has been shown that in modern…
Distributed optimization has become the default training paradigm in modern machine learning due to the growing scale of models and datasets. To mitigate communication overhead, local updates are often applied before global aggregation,…
The choice of feedback mechanism between delay and packet loss has long been a point of contention in TCP congestion control. This has partly been resolved, as it has become increasingly evident that delay based methods are needed to…
Latency Based Tiling provides a systems based approach to deriving approximate tiling solution that maximizes locality while maintaining a fast compile time. The method uses triangular loops to characterize miss ratio scaling of a machine…
In this paper, we study the problem of reducing the delay of downloading data from cloud storage systems by leveraging multiple parallel threads, assuming that the data has been encoded and stored in the clouds using fixed rate forward…
The performance and behavior of large-scale distributed applications is highly influenced by network properties such as latency, bandwidth, packet loss, and jitter. For instance, an engineer might need to answer questions such as: What is…
This paper presents a cross-layer approach for optimizing the delay performance of a multiuser diversity system with heterogeneous block-fading channels and a delay-sensitive bursty-traffic. We consider the downlink of a time-slotted…
Typically, serverless functions rely on remote storage services for managing state, which can result in increased latency and network communication overhead. In a dynamic environment such as the 3D (Edge-Cloud-Space) Compute Continuum,…
Miniaturized satellites are currently not considered suitable for critical, high-priority, and complex multi-phased missions, due to their low reliability. As hardware-side fault tolerance (FT) solutions designed for larger spacecraft can…
Parameter-Efficient Fine-Tuning (PEFT) is widely applied as the backend of fine-tuning APIs for large language model (LLM) customization in datacenters. Service providers deploy separate instances for individual PEFT tasks, giving rise to…
Cloud database systems, particularly their middleware and query execution layers, use sorting as a core operation in query processing, indexing and join execution. Distribution-dependence and limited parallelism are key issues inherent in…
Neural networks have been successfully applied in various resource-constrained edge devices, where usually central processing units (CPUs) instead of graphics processing units exist due to limited power availability. State-of-the-art…
Attention mechanisms underpin the success of large language models (LLMs), yet their substantial computational and memory overhead poses challenges for optimizing efficiency and performance. A critical bottleneck arises as KV cache and…
Most load balancing techniques implemented in current data centers tend to rely on a mapping from packets to server IP addresses through a hash value calculated from the flow five-tuple. The hash calculation allows extremely fast packet…
Deploying deep models in real-world scenarios entails a number of challenges, including computational efficiency and real-world (e.g., long-tailed) data distributions. We address the combined challenge of learning long-tailed distributions…
Short text clustering has been popularly studied for its significance in mining valuable insights from many short texts. In this paper, we focus on the federated short text clustering (FSTC) problem, i.e., clustering short texts that are…
Load Balancing plays a vital role in modern data centers to distribute traffic among instances of network functions or services. State-of-the-art load balancers such as Silkroad dispatch traffic obliviously without considering the real-time…
Cloud Computing is the delivery of computing resources which includes servers, storage, databases, networking, software, analytics, and intelligence over the internet to offer faster innovation, flexible resources, and economies of scale.…
We consider transport layer approaches for achieving high rate, low delay communication over edge paths where the bottleneck is an 802.11ac WLAN. We first show that by regulating send rate so as to maintain a target aggregation level it is…
Product bundling aims to organize a set of thematically related items into a combined bundle for shipment facilitation and item promotion. To increase the exposure of fresh or overstocked products, sellers typically bundle these items with…