Related papers: FuxiShuffle: An Adaptive and Resilient Shuffle Ser…
Services hosted in multi-tenant cloud platforms often encounter performance interference due to contention for non-partitionable resources, which in turn causes unpredictable behavior and degradation in application performance. To grapple…
Datalog-based languages are regaining popularity as a powerful abstraction for expressing recursive computations in domains such as program analysis and graph processing. However, existing systems often face a trade-off between efficiency…
Layerwise offloading reduces the GPU memory footprint of large diffusion transformer (DiT) inference by prefetching upcoming layers from host memory, but its effectiveness hinges on hiding prefetch latency behind per-layer computation. This…
Clustering is essential in data analysis and machine learning, but traditional algorithms like $k$-means and Gaussian Mixture Models (GMM) often fail with nonconvex clusters. To address the challenge, we introduce the Flexible Bivariate…
The continuous growth of big data applications with high computational and scalability demands has resulted in increasing popularity of cloud computing. Optimizing the performance and power consumption of cloud resources is therefore…
Edge computing has become increasingly popular across many domains and enterprises. However, given the locality constraint of edges (i.e., only close-by edges are useful), multiplexing diverse workloads becomes challenging. This results in…
Fault-tolerant distributed applications require mechanisms to recover data lost via a process failure. On modern cluster systems it is typically impractical to request replacement resources after such a failure. Therefore, applications have…
Analyzing large datasets with distributed dataflow systems requires the use of clusters. Public cloud providers offer a large variety and quantity of resources that can be used for such clusters. However, picking the appropriate resources…
Massively parallel Fourier transforms are widely used in computational sciences, and specifically in computational fluid dynamics which involves unbounded Poisson problems. In practice the latter is usually the most time-consuming operation…
Due to the distribution of linked data across the web, the methods that process federated queries through a distributed approach are more attractive to the users and have gained more prosperity. In distributed processing of federated…
Inference serving for large language models (LLMs) is the key to unleashing their potential in people's daily lives. However, efficient LLM serving remains challenging today because the requests are inherently heterogeneous and…
Federated Learning (FL) is a machine learning paradigm that safeguards privacy by retaining client data on edge devices. However, optimizing FL in practice can be challenging due to the diverse and heterogeneous nature of the learning…
When using Stochastic Gradient Descent (SGD) for training machine learning models, it is often crucial to provide the model with examples sampled at random from the dataset. However, for large datasets stored in the cloud, random access to…
Load balancing is critical for distributed storage to meet strict service-level objectives (SLOs). It has been shown that a fast cache can guarantee load balancing for a clustered storage system. However, when the system scales out to…
This document presents a vision for a novel AI infrastructure design that has been initially validated through inference simulations on state-of-the-art large language models. Advancements in deep learning and specialized hardware have…
Efficient load balancing is crucial in cloud computing environments to ensure optimal resource utilization, minimize response times, and prevent server overload. Traditional load balancing algorithms, such as round-robin or least…
In this paper, we present a Fragmented Hybrid Cloud (FHC) that provides a unified view of multiple geographically distributed private cloud datacenters. FHC leverages a fragmented usage model in which outsourcing is bi-directional across…
The peculiar congestion patterns in data centers are caused by the bursty and composite nature of traffic, the small bandwidth-delay product, and the tiny switch buffers. It is not practical to modify TCP to adapt to data centers,…
All modern distributed systems list performance and scalability as their core strengths. Given that optimal performance requires carefully selecting configuration options, and typical cluster sizes can range anywhere from 2 to 300 nodes, it…
The potential of Wi-Fi backscatter communications systems is immense, yet challenges such as signal instability and energy constraints impose performance limits. This paper introduces FlexScatter, a Wi-Fi backscatter system using a designed…