Understanding the design-space of sparse/dense multiphase GNN dataflows on spatial accelerators
Visualitza/Obre
10.1109/IPDPS53621.2022.00062
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/382086
Tipus de documentText en actes de congrés
Data publicació2022
EditorInstitute of Electrical and Electronics Engineers (IEEE)
Condicions d'accésAccés obert
Tots els drets reservats. Aquesta obra està protegida pels drets de propietat intel·lectual i
industrial corresponents. Sense perjudici de les exempcions legals existents, queda prohibida la seva
reproducció, distribució, comunicació pública o transformació sense l'autorització del titular dels drets
Abstract
Graph Neural Networks (GNNs) have garnered a lot of recent interest because of their success in learning representations from graph-structured data across several critical applications in cloud and HPC. Owing to their unique compute and memory characteristics that come from an interplay between dense and sparse phases of computations, the emergence of recon-figurable dataflow (aka spatial) accelerators offers promise for acceleration by mapping optimized dataflows (i.e., computation order and parallelism) for both phases. The goal of this work is to characterize and understand the design-space of dataflow choices for running GNNs on spatial accelerators in order for mappers or design-space exploration tools to optimize the dataflow based on the workload. Specifically, we propose a taxonomy to describe all possible choices for mapping the dense and sparse phases of GNN inference, spatially and temporally over a spatial accelerator, capturing both the intra-phase dataflow and the inter-phase (pipelined) dataflow. Using this taxonomy, we do deep-dives into the cost and benefits of several dataflows and perform case studies on implications of hardware parameters for dataflows and value of flexibility to support pipelined execution.
CitacióGarg, R. [et al.]. Understanding the design-space of sparse/dense multiphase GNN dataflows on spatial accelerators. A: IEEE International Parallel and Distributed Processing Symposium. "2022 IEEE 36th International Parallel and Distributed Processing Symposium: 30 May-3 June 2022, virtual event: proceedings". Institute of Electrical and Electronics Engineers (IEEE), 2022, p. 571-582. ISBN 978-1-6654-8106-9. DOI 10.1109/IPDPS53621.2022.00062.
ISBN978-1-6654-8106-9
Versió de l'editorhttps://ieeexplore.ieee.org/document/9820725
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
2103.07977.pdf | 3,588Mb | Visualitza/Obre |