相关论文: Improving Latency in a Signal Processing System on…

The use of multicore optical fibers is now recognized as one of the most promising methods to implement the space-division multiplexing techniques required to overcome the impending capacity limit of conventional single-mode optical fibers.…

Hardware specialization is becoming a key enabler of energyefficient performance. Future systems will be increasingly heterogeneous, integrating multiple specialized and programmable accelerators, each with different memory demands.…

Among hardware accelerators for deep-learning inference, data flow implementations offer low latency and high throughput capabilities. In these architectures, each neuron is mapped to a dedicated hardware unit, making them well-suited for…

Reasoning-based end-to-end (E2E) autonomous driving has recently emerged as a promising approach to improving the interpretability of driving decisions as it can generate human-readable reasoning together with predicted trajectories. Such…

Despite being a relatively new communication technology, Low-Power Wide Area Networks (LPWANs) have shown their suitability to empower a major part of Internet of Things applications. Nonetheless, most LPWAN solutions are built on star…

This paper presents PipeBoost, a low-latency LLM serving system for multi-GPU (serverless) clusters, which can rapidly launch inference services in response to bursty requests without preemptively over-provisioning GPUs. Many LLM inference…

Multi-connectivity is emerging as promising solution to provide reliable communications and seamless connectivity at the millimeter-wave frequency range. Due to the obstacles that cause frequent interruptions at such high frequency range,…

Deploying large language models (LLMs) for online inference is often constrained by limited GPU memory, particularly due to the growing KV cache during auto-regressive decoding. Hybrid GPU-CPU execution has emerged as a promising solution…

Electronic-photonic integrated circuits (EPICs) offer transformative potential for next-generation high-performance AI but require interdisciplinary advances across devices, circuits, architecture, and design automation. The complexity of…

MIMO mobile systems, with a large number of antennas at the base-station side, enable the concurrent transmission of multiple, spatially separated information streams and, therefore, enable improved network throughput and connectivity both…

Typically, a memory request from a processor may need to go through many intermediate interconnect routers, directory node, owner node, etc before it is finally serviced. Current multiprocessors do not give preference to any particular…

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…

Efficient implementations of parallel applications on heterogeneous hybrid architectures require a careful balance between computations and communications with accelerator devices. Even if most of the communication time can be overlapped by…

Ubiquitous multicore processors nowadays rely on an integrated packet-switched network for cores to exchange and share data. The performance of these intra-chip networks is a key determinant of the processor speed and, at high core counts,…

With more devices connected, delays and jitter at the WiFi hop become more prevalent, and correct functioning during network congestion becomes more important. However, two important performance issues prevent modern WiFi from reaching its…

In the realm of Large Language Model (LLM) inference, the inherent structure of transformer models coupled with the multi-GPU tensor parallelism strategy leads to a sequential execution of computation and communication. This results in…

By provisioning inference offloading services, edge inference drives the rapid growth of AI applications at network edge. However, how to reduce the inference latency remains a significant challenge. To address this issue, we develop a…

Over the last decade the relative latency of access to shared memory by multicore increased as wire resistance dominated latency and low wire density layout pushed multiport memories farther away from their ports. Various techniques were…

Large model inference is shifting from cloud to edge due to concerns about the privacy of user interaction data. However, edge devices often struggle with limited computing power, memory, and bandwidth, requiring collaboration across…

The increasing variety of input data and complexity of tasks that are handled by the devices of internet of things (IoT) environments require solutions that consider the limited hardware and computation power of the edge devices. Complex…