Related papers: FlashCommunication V2: Bit Splitting and Spike Res…
Fully Homomorphic Encryption (FHE) facilitates secure computations on encrypted data but imposes significant demands on memory bandwidth and computational power. While current FHE accelerators focus on optimizing computation, they often…
Recent years have seen several new directions in the design of sparse control of cyber-physical systems (CPSs) driven by the objective of reducing communication cost. One common assumption made in these designs is that the communication…
It is often said that one of the biggest limitations on computer performance is memory bandwidth (i.e."the memory wall problem"). In this position paper, I argue that if historical trends in computing evolution (where growth in available…
Distributed Quantum Computing (DQC) enables scalability by interconnecting multiple QPUs. Among various DQC implementations, quantum data centers (QDCs), which utilize reconfigurable optical switch networks to link QPUs across different…
Optical interconnects are the most promising solution to address the data-movement bottleneck in data centers. Silicon microdisks, benefiting from their compact footprint, low energy consumption, and wavelength division multiplexing (WDM)…
Speculative decoding has become the standard approach for accelerating Large Language Model (LLM) inference. It exploits a lossless draft-then-verify procedure to circumvent the latency of autoregressive decoding, achieving impressive…
The practical applications based on recurrent spiking neurons are limited due to their non-trivial learning algorithms. The temporal nature of spiking neurons is more favorable for hardware implementation where signals can be represented in…
In-network computing techniques, exemplified by NVLink SHARP (NVLS), offer a promising approach to addressing the communication bottlenecks in LLM inference by offloading collective operations such as All-Reduce to switches. However, the…
For multiuser MISO systems with bounded uncertainties in the Channel State Information (CSI), we consider two classical robust design problems: maximizing the minimum rate subject to a transmit power constraint, and power minimization under…
Joint pushing and caching is recognized as an efficient remedy to the problem of spectrum scarcity incurred by tremendous mobile data traffic. In this paper, by exploiting storage resources at end users and predictability of user demand…
Communication has become a first-order bottleneck in large-cale GPU workloads, and existing distributed compilers address it mainly by overlapping whole compute and communication kernels at the stream level. This coarse granularity incurs…
In federated learning (FL), a machine learning model is trained on multiple nodes in a decentralized manner, while keeping the data local and not shared with other nodes. However, FL requires the nodes to also send information on the model…
Multimode silicon photonics, leveraging mode-division multiplexing technologies, offers significant potential to increase capacity of large-scale multiprocessing systems for on-chip optical interconnects. These technologies have…
Attention mechanisms, primarily designed to capture pairwise correlations between words, have become the backbone of machine learning, expanding beyond natural language processing into other domains. This growth in adaptation comes at the…
Neuromorphic computing, inspired by biological neural systems, has emerged as a promising approach for ultra-energy-efficient data processing by leveraging analog neuron structures and spike-based computation. However, its application in…
Covert communication is the undetected transmission of sensitive information over a communication channel. In wireless communication systems, channel impairments such as signal fading present challenges in the effective implementation and…
Recent literature including our past work provide analysis and solutions for using (i) erasure coding, (ii) parallelism, or (iii) variable slicing/chunking (i.e., dividing an object of a specific size into a variable number of smaller…
The packet type (PT)-based framework~\cite{zhang2026taming} provides a systematic and principled approach to designing device-to-device (D2D) coded caching schemes that achieve reduced \sbp while preserving the optimal communication rate.…
Transformers, while revolutionary, face challenges due to their demanding computational cost and large data movement. To address this, we propose HyFlexPIM, a novel mixed-signal processing-in-memory (PIM) accelerator for inference that…
Federated Learning (FL) is an innovative distributed machine learning paradigm that enables multiple parties to collaboratively train a model without sharing their raw data, thereby preserving data privacy. Communication efficiency concerns…