Related papers: ZipLine: In-Network Compression at Line Speed

In GPU-accelerated data analytics, the overhead of data transfer from CPU to GPU becomes a performance bottleneck when the data scales beyond GPU memory capacity due to the limited PCIe bandwidth. Data compression has come to rescue for…

Packet trimming is a primitive that has been proposed for datacenter networks: to minimize latency, switches run small queues; when the queue overflows, rather than dropping packets the switch trims off the packet payload and either…

Communication has emerged as a critical bottleneck in the distributed training of large language models (LLMs). While numerous approaches have been proposed to reduce communication overhead, the potential of lossless compression has…

In environments with energy and processing constraints, such as sensor networks and embedded devices, sending raw information over wireless networks can be costly. In order to reduce the amount of transmitted data and ultimately save…

Compression algorithms reduce the redundancy in data representation to decrease the storage required for that data. Data compression offers an attractive approach to reducing communication costs by using available bandwidth effectively.…

With the growth of model sizes and the scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these. While there is a vast model compression literature deleting parts of…

As a core component in modern data centers, key-value cache provides high-throughput and low-latency services for high-speed data processing. The effectiveness of a key-value cache relies on its ability of accommodating the needed data.…

Serverless computing is a popular cloud deployment paradigm where developers implement applications as workflows of functions that invoke each other. Cloud providers automatically scale function instances on demand and forward workflow…

In the past few years, lossy compression has been widely applied in the field of wireless sensor networks (WSN), where energy efficiency is a crucial concern due to the constrained nature of the transmission devices. Often, the common…

Internet of Things (IoT) devices and applications are generating and communicating vast quantities of data, and the rate of data collection is increasing rapidly. These high communication volumes are challenging for energy-constrained,…

Fast data synchronization in wireless ad hoc networks is a challenging and critical problem. It is fundamental for efficient information fusion, control and decision in distributed systems. Previously, distributed data synchronization was…

Deep learning has been used in a wide range of areas and made a huge breakthrough. With the ever-increasing model size and train-ing data volume, distributed deep learning emerges which utilizes a cluster to train a model in parallel.…

With the advent of edge computing, data generated by end devices can be pre-processed before transmission, possibly saving transmission time and energy. On the other hand, data processing itself incurs latency and energy consumption,…

We study two approaches to distributed compressed sensing for in-network data compression and signal reconstruction at a sink in a wireless sensor network where sensors are placed on a straight line. Communication to the sink is considered…

This paper investigates hardware-based memory compression designs to increase the memory bandwidth. When lines are compressible, the hardware can store multiple lines in a single memory location, and retrieve all these lines in a single…

Thanks to the rapid proliferation of connected devices, sensor-generated time series constitute a large and growing portion of the world's data. Often, this data is collected from distributed, resource-constrained devices and centralized at…

Edge devices demand low energy consumption, cost and small form factor. To efficiently deploy convolutional neural network (CNN) models on edge device, energy-aware model compression becomes extremely important. However, existing work did…

A sequential fronthaul network, referred to as radio stripes, is a promising fronthaul topology of cell-free MIMO systems. In this setup, a single cable suffices to connect access points (APs) to a central processor (CP). Thus, radio…

Wavelets are well known for data compression, yet have rarely been applied to the compression of neural networks. This paper shows how the fast wavelet transform can be used to compress linear layers in neural networks. Linear layers still…

Network slicing has emerged as an integral concept in 5G, aiming to partition the physical network infrastructure into isolated slices, customized for specific applications. We theoretically formulate the key performance metrics of an…