Related papers: Harnessing Manycore Processors with Distributed Me…

With the emergence of massively parallel processing units, parallelization has become a desirable property for new sequence models. The ability to parallelize the processing of sequences with respect to the sequence length during training…

Spiking Neural Networks (SNNs) are distinguished from Artificial Neural Networks (ANNs) for their complex neuronal dynamics and sparse binary activations (spikes) inspired by the biological neural system. Traditional neuron models use…

Drawing on the intricate structures of the brain, Spiking Neural Networks (SNNs) emerge as a transformative development in artificial intelligence, closely emulating the complex dynamics of biological neural networks. While SNNs show…

As an important class of spiking neural networks (SNNs), recurrent spiking neural networks (RSNNs) possess great computational power and have been widely used for processing sequential data like audio and text. However, most RSNNs suffer…

The Transformer has been an indispensable staple in deep learning. However, for real-life applications, it is very challenging to deploy efficient Transformers due to immense parameters and operations of models. To relieve this burden,…

Existing approaches to train neural networks that use large images require to either crop or down-sample data during pre-processing, use small batch sizes, or split the model across devices mainly due to the prohibitively limited memory…

Processing-In-Memory (PIM) architectures offer a promising approach to accelerate Graph Neural Network (GNN) training and inference. However, various PIM devices such as ReRAM, FeFET, PCM, MRAM, and SRAM exist, with each device offering…

It is a challenging task to train large DNN models on sophisticated GPU platforms with diversified interconnect capabilities. Recently, pipelined training has been proposed as an effective approach for improving device utilization. However,…

Traditional von Neumann architecture based processors become inefficient in terms of energy and throughput as they involve separate processing and memory units, also known as~\textit{memory wall}. The memory wall problem is further…

The employment of high-performance servers and GPU accelerators for training deep neural network models have greatly accelerated recent advances in deep learning (DL). DL frameworks, such as TensorFlow, MXNet, and Caffe2, have emerged to…

Current deep learning (DL) systems rely on a centralized computing paradigm which limits the amount of available training data, increases system latency, and adds privacy and security constraints. On-device learning, enabled by…

The excessive computational requirements of modern artificial neural networks (ANNs) are posing limitations on the machines that can run them. Sparsification of ANNs is often motivated by time, memory and energy savings only during model…

Graph Neural Networks (GNNs) are a computationally efficient method to learn embeddings and classifications on graph data. However, GNN training has low computational intensity, making communication costs the bottleneck for scalability.…

Recurrent neural networks (RNNs) are becoming the de facto solution for speech recognition. RNNs exploit long-term temporal relationships in data by applying repeated, learned transformations. Unlike fully-connected (FC) layers with single…

Recently, there have been increasing demands to construct compact deep architectures to remove unnecessary redundancy and to improve the inference speed. While many recent works focus on reducing the redundancy by eliminating unneeded…

Efficiently scaling deep neural networks across GPU clusters requires navigating complex trade-offs between computational throughput, memory utilization, and synchronization overhead. This paper presents a unified empirical evaluation of…

Recently, a new recurrent neural network (RNN) named the Legendre Memory Unit (LMU) was proposed and shown to achieve state-of-the-art performance on several benchmark datasets. Here we leverage the linear time-invariant (LTI) memory…

Mixed-signal analog/digital circuits emulate spiking neurons and synapses with extremely high energy efficiency, an approach known as "neuromorphic engineering". However, analog circuits are sensitive to process-induced variation among…

Brain-inspired Spiking Neural Networks (SNNs) have the characteristics of event-driven and high energy-efficient, which are different from traditional Artificial Neural Networks (ANNs) when deployed on edge devices such as neuromorphic…

Sequential models, such as Recurrent Neural Networks and Neural Ordinary Differential Equations, have long suffered from slow training due to their inherent sequential nature. For many years this bottleneck has persisted, as many thought…