English
Related papers

Related papers: Mitigating GIL Bottlenecks in Edge AI Systems

200 papers

We present SPDL (Scalable and Performant Data Loading), an open-source, framework-agnostic library designed for efficiently loading array data to GPU. Data loading is often a bottleneck in AI applications, and is challenging to optimize…

Python's Global Interpreter Lock prevents execution on more than one CPU core at the same time, even when multiple threads are used. However, starting with Python 3.13 an experimental build allows disabling the GIL. While prior work has…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-06 José Daniel Montoya Salazar

As Large Language Models (LLMs) transition from research environments to production deployments, evaluating their performance against strict Service Level Objectives (SLOs) has become critical. However, current evaluation methodologies…

Artificial Intelligence · Computer Science 2026-05-27 Ashok Chandrasekar , Jason Kramberger

The surging development of Artificial Intelligence-Generated Content (AIGC) marks a transformative era of the content creation and production. Edge servers promise attractive benefits, e.g., reduced service delay and backhaul traffic load,…

Machine Learning · Computer Science 2024-09-10 Yuxin Liang , Peng Yang , Yuanyuan He , Feng Lyu

The rapid growth of end-user AI applications, such as computer vision and generative AI, has led to immense data and processing demands often exceeding user devices' capabilities. Edge AI addresses this by offloading computation to the…

Machine Learning · Computer Science 2024-11-05 Juan Marcelo Parra-Ullauri , Oscar Dilley , Hari Madhukumar , Dimitra Simeonidou

GPUs are critical for compute-intensive applications, yet emerging workloads such as recommender systems, graph analytics, and data analytics often exceed GPU memory capacity. Existing solutions allow GPUs to use CPU DRAM or SSDs as…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-27 Zhuoping Yang , Jinming Zhuang , Xingzhen Chen , Alex K. Jones , Peipei Zhou

6G's AI native vision of embedding advance intelligence in the network while bringing it closer to the user requires a systematic evaluation of Generative AI (GenAI) models on edge devices. Rapidly emerging solutions based on Open RAN…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-28 Zeinab Nezami , Maryam Hafeez , Karim Djemame , Syed Ali Raza Zaidi

Benefiting from expanding cloud infrastructure, deep neural networks (DNNs) today have increasingly high performance when trained in the cloud. Researchers spend months of effort competing for an extra few percentage points of model…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-01-19 Hang Qiu , Ioanna Vavelidou , Jian Li , Evgenya Pergament , Pete Warden , Sandeep Chinchali , Zain Asgar , Sachin Katti

Currently, the generative model has garnered considerable attention due to its application in addressing the challenge of scarcity of abnormal samples in the industrial Internet of Things (IoT). However, challenges persist regarding the…

Networking and Internet Architecture · Computer Science 2024-05-07 Siyuan Li , Xi Lin , Hansong Xu , Kun Hua , Xiaomin Jin , Gaolei Li , Jianhua Li

Large Language Model (LLM) inference requires substantial computational resources, yet CPU-based inference remains essential for democratizing AI due to the widespread availability of CPUs compared to specialized accelerators. However,…

Hardware Architecture · Computer Science 2025-10-01 Jingyao Zhang , Jaewoo Park , Jongeun Lee , Elaheh Sadredini

An increasing number of mobile applications rely on Machine Learning (ML) routines for analyzing data. Executing such tasks at the user devices saves the energy spent on transmitting and processing large data volumes at distant…

Networking and Internet Architecture · Computer Science 2022-01-11 Apostolos Galanopoulos , George Iosifidis , Theodoros Salonidis , Douglas J. Leith

Enterprise IT support is constrained by heterogeneous devices, evolving policies, and long-tail failure modes that are difficult to resolve centrally. We present VIGIL, an edge-extended agentic AI system that deploys desktop-resident agents…

Application tail latency is a key metric for many services, with high latencies being linked directly to loss of revenue. Modern deeply-nested micro-service architectures exacerbate tail latencies, increasing the likelihood of users…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-07-17 Andrew Jeffery , Chris Jensen , Richard Mortier

Modern edge AI applications increasingly rely on microservice architectures that integrate both AI services and conventional microservices into complex request chains with stringent latency requirements. Effectively orchestrating these…

Networking and Internet Architecture · Computer Science 2026-03-10 Chen Yang , Jin Zheng , Yang Zhuolin , Lai Pan , Zhang Xiao , Hu Menglan , Yin Haiyan

The development of large-scale foundation models, particularly Large Language Models (LLMs), is constrained by significant computational and memory bottlenecks. These challenges elevate throughput optimization from a mere engineering task…

Machine Learning · Computer Science 2026-03-31 Mayank Jha

Compound AI (cAI) systems chain multiple AI models to solve complex problems. cAI systems are typically composed of deep neural networks (DNNs), transformers, and large language models (LLMs), exhibiting a high degree of computational…

Multiagent Systems · Computer Science 2025-07-02 Zain Taufique , Aman Vyas , Antonio Miele , Pasi Liljeberg , Anil Kanduri

Edge intelligence enables AI inference at the network edge, co-located with or near the radio access network, rather than in centralized clouds or on mobile devices. It targets low-latency, resource-constrained applications with large data…

Networking and Internet Architecture · Computer Science 2026-01-26 Jaume Anguera Peris , Joakim Jaldén

Existing research has identified three structural performance bottlenecks in AI research agents: (1) synchronous single-GPU execution constrains sample throughput, limiting the benefit of search; (2) a generalization gap where…

Edge computing and IoT applications are severely constrained by limited hardware resource. This makes memory consuming DNN frameworks not applicable to edge computing. Simple algorithms such as direct convolution are finding their way in…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-10-17 Xianwei Cheng , Hui Zhao , Mahmut Kandemir , Saraju Mohanty , Beilei Jiang

In the realm of edge computing, the increasing demand for high Quality of Service (QoS), particularly in dynamic multimedia streaming applications (e.g., Augmented Reality/Virtual Reality and online gaming), has prompted the need for…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-12-29 Cheng Zhang , Yinuo Deng , Hailiang Zhao , Tianlv Chen , Shuiguang Deng
‹ Prev 1 2 3 10 Next ›