Related papers: Scalable data concentrator with baseline interconn…

While neural network quantization effectively reduces the cost of matrix multiplications, aggressive quantization can expose non-matrix-multiply operations as significant performance and resource bottlenecks on embedded systems. Addressing…

The OpenFlow-based SDN is widely studied to better network performance through planning fine-grained paths. However, being designed to configure path hop-by-hop, it faces the scalability issue that both the flow table overhead and path…

With increasing data and model complexities, the time required to train neural networks has become prohibitively large. To address the exponential rise in training time, users are turning to data parallel neural networks (DPNN) to utilize…

Data loading can dominate deep neural network training time on large-scale systems. We present a comprehensive study on accelerating data loading performance in large-scale distributed training. We first identify performance and scalability…

FPGAs have become emerging computing infrastructures for accelerating applications in datacenters. Meanwhile, high-level synthesis (HLS) tools have been proposed to ease the programming of FPGAs. Even with HLS, irregular data-intensive…

Binarized neural networks (BNNs) are gaining interest in the deep learning community due to their significantly lower computational and memory cost. They are particularly well suited to reconfigurable logic devices, which contain an…

Domain Adaptation (DA) aims to leverage the knowledge learned from a source domain with ample labeled data to a target domain with unlabeled data only. Most existing studies on DA contribute to learning domain-invariant feature…

With the increasing physical event rate and number of electronic channels, traditional readout scheme meets the challenge of improving readout speed caused by the limited bandwidth of crate backplane. In this paper, a high-speed data…

The XENON1T liquid xenon time projection chamber is the most sensitive detector built to date for the measurement of direct interactions of weakly interacting massive particles with normal matter. The data acquisition system (DAQ) is…

Modern DAQ systems typically use the FPGA-based PCIe cards to concentrate and deliver the data to a computer used as an entry node of the data processing network. This paper presents a QEMU-based methodology for the co-development of the…

An online resource scheduling framework is proposed for minimizing the sum of weighted task latency for all the Internet of things (IoT) users, by optimizing offloading decision, transmission power and resource allocation in the large-scale…

Distribution network reconfiguration (DNR) has proved to be an economical and effective way to improve the reliability of distribution systems. As optimal network configuration depends on system operating states (e.g., loads at each node),…

Data assimilation (DA) is integrated with machine learning in order to perform entirely data-driven online state estimation. To achieve this, recurrent neural networks (RNNs) are implemented as surrogate models to replace key components of…

The exponential emergence of Field Programmable Gate Array (FPGA) has accelerated the research of hardware implementation of Deep Neural Network (DNN). Among all DNN processors, domain specific architectures, such as, Google's Tensor…

The data acquisition system (DAQ) of the future Cherenkov Telescope Array (CTA) must be ef- ficient, modular and robust to be able to cope with the very large data rate of up to 550 Gbps coming from many telescopes with different…

Systolic Array (SA) architectures are well suited for accelerating matrix multiplications through the use of a pipelined array of Processing Elements (PEs) communicating with local connections and pre-orchestrated data movements. Even…

Multi-head attention layers, as used in the Transformer neural sequence model, are a powerful alternative to RNNs for moving information across and between sequences. While training these layers is generally fast and simple, due to…

Many studies have been conducted to improve the efficiency of Transformer from quadric to linear. Among them, the low-rank-based methods aim to learn the projection matrices to compress the sequence length. However, the projection matrices…

Multimodal stacks that mix ViTs, CNNs, GNNs, and transformer NLP strain embedded platforms because their compute/memory patterns diverge and hard real-time targets leave little slack. TRINE is a single-bitstream FPGA accelerator and…

This paper presents a distributed beamforming framework for a constellation of airborne platform stations (APSs) in a massive Multiple-Input and Multiple-Output (MIMO) non-terrestrial network (NTN) that targets the downlink sum-rate…