Related papers: Characterizing Network Requirements for GPU API Re…

As data being produced by IoT applications continues to explode, there is a growing need to bring computing power closer to the source of the data to meet the response time, power dissipation and cost goals of performance-critical…

The Bandwidth Problem seeks for a simultaneous permutation of the rows and columns of the adjacency matrix of a graph such that all nonzero entries are as close as possible to the main diagonal. This work focuses on investigating novel…

The attention layer, a core component of Transformer-based LLMs, brings out inefficiencies in current GPU systems due to its low operational intensity and the substantial memory requirements of KV caches. We propose a High-bandwidth…

In recent years, deep neural networks (DNNs), have yielded strong results on a wide range of applications. Graphics Processing Units (GPUs) have been one key enabling factor leading to the current popularity of DNNs. However, despite…

The concept of a softwarized network leveraging technologies such as SDN and NFV comes with different merits such as decreased Operational Expenses (OPEX) and less dependency on underlying hardware components. With the amount of increased…

Collocating deep learning training tasks improves GPU utilization but risks resource contention, severe slowdowns, and out-of-memory (OOM) failures. Accurate memory estimation is essential for robust collocation, and GPU utilization…

Many well-known, real-world problems involve dynamic data which describe the relationship among the entities. Hypergraphs are powerful combinatorial structures that are frequently used to model such data. For many of today's data-centric…

The rapid growth of memory and computation requirements of large language models (LLMs) has outpaced the development of hardware, hindering people who lack large-scale high-end GPUs from training or deploying LLMs. However, consumer-level…

GPUs are broadly used in I/O-intensive big data applications. Prior works demonstrate the benefits of using GPU-side file system layer, GPUfs, to improve the GPU performance and programmability in such workloads. However, GPUfs fails to…

Energy-efficiency is a key concern for neural network applications. To alleviate this issue, hardware acceleration using FPGAs or GPUs can provide better energy-efficiency than general-purpose processors. However, further improvement of the…

With more scientific fields relying on neural networks (NNs) to process data incoming at extreme throughputs and latencies, it is crucial to develop NNs with all their parameters stored on-chip. In many of these applications, there is not…

In this paper, we study an unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) architecture, in which a UAV roaming around the area may serve as a computing server to help user equipment (UEs) compute their tasks or act as a…

Graph Convolutional Networks (GCNs) are increasingly adopted in large-scale graph-based recommender systems. Training GCN requires the minibatch generator traversing graphs and sampling the sparsely located neighboring nodes to obtain their…

Multi-GPU nodes are increasingly common in the rapidly evolving landscape of exascale supercomputers. On these systems, GPUs on the same node are connected through dedicated networks, with bandwidths up to a few terabits per second.…

Simulation speed matters for neuroscientific research: this includes not only how quickly the simulated model time of a large-scale spiking neuronal network progresses, but also how long it takes to instantiate the network model in computer…

Edge Computing exploits computational capabilities deployed at the very edge of the network to support applications with low latency requirements. Such capabilities can reside in small embedded devices that integrate dedicated hardware --…

GPUs are essential to accelerating the latency-sensitive deep neural network (DNN) inference workloads in cloud datacenters. To fully utilize GPU resources, spatial sharing of GPUs among co-located DNN inference workloads becomes…

Artificial Intelligence (AI) workloads drive a rapid expansion of high-performance computing (HPC) infrastructures and increase their power and energy demands towards a critical level. AI benchmarks representing state-of-the art workloads…

As recurrent neural networks become larger and deeper, training times for single networks are rising into weeks or even months. As such there is a significant incentive to improve the performance and scalability of these networks. While…

Graphics Processing Units (GPUs) leverage massive parallelism and large memory bandwidth to support high-performance computing applications, such as multimedia rendering, crypto-mining, deep learning, and natural language processing. These…