Related papers: ChipLight: Cross-Layer Optimization of Chiplet Des…

The evolution from wired system to the wireless environment opens a set of challenge for the improvement of the wireless system performances because of many of their weakness compared to wired networks. To achieve this goal, cross layer…

Split learning (SL) is a collaborative learning framework, which can train an artificial intelligence (AI) model between a device and an edge server by splitting the AI model into a device-side model and a server-side model at a cut layer.…

There is growing interest in integrating high-fidelity visual synthesis capabilities into large language models (LLMs) without compromising their strong reasoning capabilities. Existing methods that directly train LLMs or bridge LLMs and…

Windowed orthogonal frequency-division multiplexing (OFDM) and wavelet OFDM have been proposed as medium access techniques for broadband communications over the power line network by the standard IEEE 1901. Windowed OFDM has been…

Deep neural network-based medical image classifications often use "hard" labels for training, where the probability of the correct category is 1 and those of others are 0. However, these hard targets can drive the networks over-confident…

The explosive growth of Large Language Models (LLMs), such as GPT-4 with 1.8 trillion parameters, demands a fundamental rethinking of data center architecture to ensure scalability, efficiency, and cost-effectiveness. Our work provides a…

GPU systems are increasingly powering modern datacenters at scale. Despite being highly performant, GPU systems can exhibit performance variation at the node and cluster levels. Such performance variation can significantly impact both…

Enhancing performance while reducing costs is the fundamental design philosophy of integrated circuits (ICs). With advancements in packaging technology, interposer-based chiplet architecture has emerged as a promising solution. Chiplet…

Large Language Models (LLMs) have showcased remarkable capabilities surpassing conventional NLP challenges, creating opportunities for use in production use cases. Towards this goal, there is a notable shift to building compound AI systems,…

With the increasing scale of models, the need for efficient distributed training has become increasingly urgent. Recently, many synchronous pipeline parallelism approaches have been proposed to improve training throughput. However, these…

Mixture-of-experts (MoE) has been extensively employed to scale large language models to trillion-plus parameters while maintaining a fixed computational cost. The development of large MoE models in the distributed scenario encounters the…

2.5D integration technology is gaining traction as it copes with the exponentially growing design cost of modern integrated circuits. A crucial part of a 2.5D stacked chip is a low-latency and high-throughput inter-chiplet interconnect…

Training LLMs larger than the aggregated memory of multiple GPUs is increasingly necessary due to the faster growth of LLM sizes compared to GPU memory. To this end, multi-tier host memory or disk offloading techniques are proposed by state…

As integrated circuit (IC) dimensions shrink below the lithographic wavelength, optical lithography faces growing challenges from diffraction and process variability. Model-based optical proximity correction (OPC) and inverse lithography…

The rapid growth of AI and accelerator-driven workloads is forcing a fundamental rethinking of optical interconnect architectures in datacenters. Co-packaged optics and three-dimensional photonic integration have emerged as promising…

Optical interconnects (OIs) based on vertical-cavity surface-emitting lasers (VCSELs) are the main workhorse within data centers, supercomputers, and even vehicles, providing low-cost, high-rate connectivity. VCSELs must operate under…

Multichip systems with memory stacks and various processing chips are at the heart of platform based designs such as servers and embedded systems. Full utilization of the benefits of these integrated multichip systems need a seamless, and…

Nowadays the number of available processing cores within computing nodes which are used in recent clustered environments, are growing up with a rapid rate. Despite this trend, the number of available network interfaces in such computing…

To train modern large DNN models, pipeline parallelism has recently emerged, which distributes the model across GPUs and enables different devices to process different microbatches in pipeline. Earlier pipeline designs allow multiple…

High Performance and Energy Efficiency are critical requirements for Internet of Things (IoT) end-nodes. Exploiting tightly-coupled clusters of programmable processors (CMPs) has recently emerged as a suitable solution to address this…