Related papers: Improving Latency in a Signal Processing System on…
Interference is emerging as a fundamental bottleneck in many important wireless communication scenarios, including dense cellular networks and cognitive networks with spectrum sharing by multiple service providers. Although multipleantenna…
Memory-bound algorithms show complex performance and energy consumption behavior on multicore processors. We choose the lattice-Boltzmann method (LBM) on an Intel Sandy Bridge cluster as a prototype scenario to investigate if and how…
Driven by great demands on low-latency services of the edge devices (EDs), mobile edge computing (MEC) has been proposed to enable the computing capacities at the edge of the radio access network. However, conventional MEC servers suffer…
Almost in every heavily computation-dependent application, from 6G communication systems to autonomous driving platforms, a large portion of computing should be near to the client side. Edge computing (AI at Edge) in mobile devices is one…
Not only with the large host memory for supporting large scale graph processing, GPU-accelerated heterogeneous architecture can also provide a great potential for high-performance computing. However, few existing heterogeneous systems can…
We propose XPipe, an efficient asynchronous pipeline model parallelism approach for multi-GPU DNN training. XPipe is designed to use multiple GPUs to concurrently and continuously train different parts of a DNN model. To improve GPU…
The rapid growth of LLMs has revolutionized natural language processing and AI analysis, but their increasing size and memory demands present significant challenges. A common solution is to spill over to CPU memory; however, traditional…
Bandwidth-starved multicore chips have become ubiquitous. It is well known that the performance of stencil codes can be improved by temporal blocking, lessening the pressure on the memory interface. We introduce a new pipelined approach…
MPSoCs are gaining popularity because of its potential to solve computationally expensive applications. A multi-core processor combines two or more independent cores (normally a CPU) into a single package composed of a single integrated…
With the increasing adoption of AI applications such as large language models and computer vision AI, the computational demands on AI inference systems are continuously rising, making the enhancement of task processing capacity using…
Over the last few years we have witnessed an exponential growth in the adoption of LoRaWAN as LPWAN technology for IoT. While LoRaWAN offers many advantages, one of its limitations is the paltry data rate. Most IoT applications don't…
The signal processing firmware that has been developed for the Low Frequency Aperture Array component of the Square Kilometre Array is described. The firmware is implemented on a dual FPGA board, that is capable of processing the streams…
While deploying large language models on edge devices promises low-latency and privacy-preserving AI services, it is hindered by limited device resources. Although pipeline parallelism facilitates distributed inference, existing approaches…
Sequential computation is well understood but does not scale well with current technology. Within the next decade, systems will contain large numbers of processors with potentially thousands of processors per chip. Despite this, many…
This article presents an automatic approach to quickly derive a good solution for hardware resource partition and task granularity for task-based parallel applications on heterogeneous many-core architectures. Our approach employs a…
In modern data centers, energy usage represents one of the major factors affecting operational costs. Power capping is a technique that limits the power consumption of individual systems, which allows reducing the overall power demand at…
Wi-Fi provides cost-effective data capacity at hotspots in conjunction with broadband cellular networks. The hotspots are required to capture a large number of users and provide high data rates. Data rates, over the Wi-Fi interface, are…
The application of Transformer-based large models has achieved numerous success in recent years. However, the exponential growth in the parameters of large models introduces formidable memory challenge for edge deployment. Prior works to…
Wireless baseband processing (WBP) is a key element of wireless communications, with a series of signal processing modules to improve data throughput and counter channel fading. Conventional hardware solutions, such as digital signal…
Data and pipeline parallelism are key strategies for scaling neural network training across distributed devices, but their high communication cost necessitates co-located computing clusters with fast interconnects, limiting their…