The evolution of distributed systems for graph neural networks and their origin in graph processing and deep learning: A survey

J Vatter, R Mayer, HA Jacobsen - ACM Computing Surveys, 2023 - dl.acm.org
Graph neural networks (GNNs) are an emerging research field. This specialized deep
neural network architecture is capable of processing graph structured data and bridges the …

FPGA HLS today: successes, challenges, and opportunities

J Cong, J Lau, G Liu, S Neuendorffer, P Pan… - ACM Transactions on …, 2022 - dl.acm.org
The year 2011 marked an important transition for FPGA high-level synthesis (HLS), as it
went from prototy** to deployment. A decade later, in this article, we assess the progress …

A modern primer on processing in memory

O Mutlu, S Ghose, J Gómez-Luna… - … computing: from devices …, 2022 - Springer
Modern computing systems are overwhelmingly designed to move data to computation. This
design choice goes directly against at least three key trends in computing that cause …

Dorylus: Affordable, scalable, and accurate {GNN} training with distributed {CPU} servers and serverless threads

J Thorpe, Y Qiao, J Eyolfson, S Teng, G Hu… - … USENIX Symposium on …, 2021 - usenix.org
A graph neural network (GNN) enables deep learning on structured graph data. There are
two major GNN training obstacles: 1) it relies on high-end servers with many GPUs which …

{LegoOS}: A disseminated, distributed {OS} for hardware resource disaggregation

Y Shan, Y Huang, Y Chen, Y Zhang - 13th USENIX Symposium on …, 2018 - usenix.org
The monolithic server model where a server is the unit of deployment, operation, and failure
is meeting its limits in the face of several recent hardware and application trends. To improve …

Aligraph: A comprehensive graph neural network platform

R Zhu, K Zhao, H Yang, W Lin, C Zhou, B Ai… - arxiv preprint arxiv …, 2019 - arxiv.org
An increasing number of machine learning tasks require dealing with large graph datasets,
which capture rich and complex relationship among potentially billions of elements. Graph …

AWB-GCN: A graph convolutional network accelerator with runtime workload rebalancing

T Geng, A Li, R Shi, C Wu, T Wang, Y Li… - 2020 53rd Annual …, 2020 - ieeexplore.ieee.org
Deep learning systems have been successfully applied to Euclidean data such as images,
video, and audio. In many applications, however, information and their relationships are …

Clipper: A {Low-Latency} online prediction serving system

D Crankshaw, X Wang, G Zhou, MJ Franklin… - … USENIX Symposium on …, 2017 - usenix.org
Clipper: A Low-Latency Online Prediction Serving System Page 1 This paper is included in the
Proceedings of the 14th USENIX Symposium on Networked Systems Design and Implementation …

Snap: A general-purpose network analysis and graph-mining library

J Leskovec, R Sosič - ACM Transactions on Intelligent Systems and …, 2016 - dl.acm.org
Large networks are becoming a widely used abstraction for studying complex systems in a
broad set of disciplines, ranging from social-network analysis to molecular biology and …

Processing data where it makes sense: Enabling in-memory computation

O Mutlu, S Ghose, J Gómez-Luna… - Microprocessors and …, 2019 - Elsevier
Today's systems are overwhelmingly designed to move data to computation. This design
choice goes directly against at least three key trends in systems that cause performance …