Related papers: Switch-Less Dragonfly on Wafers: A Scalable Interc…
Due to the emergence of new paradigms and services such as 5G/6G, IoT, and more, current deployed wired Data Center Networks (DCNs) are not meeting the required performance metrics due to their limited reconfigurability, scalability, and…
The recent rise of electricity generation based on renewable energy sources increases the demand for transmission capacity. Capacity expansion via the upgrade of transmission line capacity, e.g., by conversion to a high-voltage direct…
With the increasing use of renewable generation in power systems, responsive resources will be necessary to support primary frequency control in future low-inertia/under-damped power systems. Flexible loads can provide fast-frequency…
Hyperdimensional computing (HDC) is an emerging computing paradigm that represents, manipulates, and communicates data using very long random vectors (aka hypervectors). Among different hardware platforms capable of executing HDC…
Transformer architectures, particularly Diffusion Transformers (DiTs), have become widely used in diffusion and flow-matching models due to their strong performance compared to convolutional UNets. However, the isotropic design of DiTs…
In chip-to-chip communication, terahertz waves provide a promising approach to achieve high data capacity with improved energy efficiency, effectively bridging the gap between electrical and optical domains. By realizing this potential,…
Modern edge devices increasingly rely on neural networks for intelligent applications. However, conventional digital computing-based edge inference requires substantial memory and energy consumption. In analog radio frequency (RF)…
As the number of cores scales to tens and hundreds, the energy consumption of routers across various types of on-chip networks in chip muiltiprocessors (CMPs) increases significantly. A major source of this energy consumption comes from the…
In this paper, two novel hybrid beamforming methods are proposed to reduce the cost and power consumption of hybrid beamformers with subconnected phase shifter network structure in massive multiple-input multiple-output (MIMO) systems. This…
Putting the DRAM on the same package with a processor enables several times higher memory bandwidth than conventional off-package DRAM. Yet, the latency of in-package DRAM is not appreciably lower than that of off-package DRAM. A promising…
This paper considers the use of routerless networks-on-chip as an alternative on-chip interconnect for multiprocessor systems requiring hard real-time guarantees for inter-processor communication. It presents a novel analytical framework…
Providing resilient network control is a critical concern for deploying Software-Defined Networking (SDN) into Wide-Area Networks (WANs). For performance reasons, a Software-Defined WAN is divided into multiple domains controlled by…
Federated learning (FL) is a promising paradigm that enables collaboratively learning a shared model across massive clients while keeping the training data locally. However, for many existing FL systems, clients need to frequently exchange…
More and more latency-sensitive services and applications are being deployed into the data center. Performance can be limited by the high latency of the network interconnect. Because the conventional network stack is designed not only for…
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…
Data Centers (DCs) are required to be scalable to large data sets so as to accommodate ever increasing demands of resource-limited embedded and mobile devices. Thanks to the availability of recent high data rate millimeter-wave frequency…
When implementing hierarchical federated learning over wireless networks, scalability assurance and the ability to handle both interference and device data heterogeneity are crucial. This work introduces a learning method designed to…
Given the fast growth of intelligent devices, it is expected that a large number of high-stake artificial intelligence (AI) applications, e.g., drones, autonomous cars, tactile robots, will be deployed at the edge of wireless networks in…
Recent neural networks (NNs) with self-attention exhibit competitiveness across different AI domains, but the essential attention mechanism brings massive computation and memory demands. To this end, various sparsity patterns are introduced…
Optical interconnects are already the dominant technology in large-scale data center networks. However, the high optical loss of many optical components coupled with the low efficiency of laser sources result in high aggregate power…