Related papers: RTNN: The new parallel machine in Zaragoza

Graph Neural Networks (GNNs) have shown success in many real-world applications that involve graph-structured data. Most of the existing single-node GNN training systems are capable of training medium-scale graphs with tens of millions of…

Deep neural networks with large model sizes achieve state-of-the-art results for tasks in computer vision (CV) and natural language processing (NLP). However, these large-scale models are too compute- or memory-intensive for…

Binary Neural Networks (BNNs) are promising to deliver accuracy comparable to conventional deep neural networks at a fraction of the cost in terms of memory and energy. In this paper, we introduce the XNOR Neural Engine (XNE), a fully…

Graph neural networks (GNNs) leverage the connectivity and structure of real-world graphs to learn intricate properties and relationships between nodes. Many real-world graphs exceed the memory capacity of a GPU due to their sheer size, and…

The vision of super computer at every desk can be realized by powerful and highly parallel CPUs or GPUs or APUs. Graphics processors once specialized for the graphics applications only, are now used for the highly computational intensive…

We outline the essential features of a Linux PC cluster which is now being developed at National Taiwan University, and discuss how to optimize its hardware and software for lattice QCD with overlap Dirac quarks. At present, the cluster…

Recurrent Neural Networks (RNNs) are powerful tools for solving sequence-based problems, but their efficacy and execution time are dependent on the size of the network. Following recent work in simplifying these networks with model pruning…

Computer vision on low-power edge devices enables applications including search-and-rescue and security. State-of-the-art computer vision algorithms, such as Deep Neural Networks (DNNs), are too large for inference on low-power edge…

We present a comparative analysis of the maximum performance achieved by the Linpack benchmark on compute intensive hardware publicly available from multiple cloud providers. We study both performance within a single compute node, and…

Deploying mixed-precision neural networks on edge devices is friendly to hardware resources and power consumption. To support fully mixed-precision neural network inference, it is necessary to design flexible hardware accelerators for…

Low-latency, low-power portable recurrent neural network (RNN) accelerators offer powerful inference capabilities for real-time applications such as IoT, robotics, and human-machine interaction. We propose a lightweight Gated Recurrent Unit…

Molecular machines may resolve three distinct bottlenecks of scientific advancement. Nanofactories (Phoenix, 2003) composed of MM may produce atomically perfect products spending negligible amount of energy (Hess, 2004) thus alleviating the…

Synaptic delay has attracted significant attention in neural network dynamics for integrating and processing complex spatiotemporal information. This paper introduces a high-throughput Spiking Neural Network (SNN) processor that supports…

Modern Graphics Processing Units (GPUs) are now considered accelerators for general purpose computation. A tight interaction between the GPU and the interconnection network is the strategy to express the full potential on capability…

Relational databases (RDBs) are ubiquitous in enterprise and real-world applications. Flattening the database poses challenges for deep learning models that rely on fixed-size input representations to capture relational semantics from the…

Today's unrelenting increase in demand for information processing creates the need for novel computing concepts. Reservoir computing is such a concept that lends itself particularly well to photonic hardware implementations. Over recent…

We have repurposed Google Tensor Processing Units (TPUs), application-specific chips developed for machine learning, into large-scale dense linear algebra supercomputers. The TPUs' fast inter-core interconnects (ICI)s, physically…

We introduce a parallelizable simplification of Neural Turing Machine (NTM), referred to as P-NTM, which redesigns the core operations of the original architecture to enable efficient scan-based parallel execution. We evaluate the proposed…

This paper describes maxDNN, a computationally efficient convolution kernel for deep learning with the NVIDIA Maxwell GPU. maxDNN reaches 96.3% computational efficiency on typical deep learning network architectures. The design combines…

This paper introduces the first low-power hardware accelerator for Spiking Transformers, an emerging alternative to traditional artificial neural networks. By modifying the base Spikformer model to use IAND instead of residual addition, the…