Static Graphs for Coding Productivity in OpenACC

Toledo, Leonel; Valero Lara, Pedro; Vetter, Jeffrey; Pena, Antonio

doi:10.1109/HiPC53243.2021.00050

Static Graphs for Coding Productivity in OpenACC

Conference · Wed Dec 01 04:00:00 EST 2021

DOI:https://doi.org/10.1109/HiPC53243.2021.00050· OSTI ID:1883754

Toledo, Leonel ^[1]; ^[2]; ^[2]; Pena, Antonio ^[1]

Barcelona Supercomputing Center
ORNL

The main contribution of this work is to increase the coding productivity for GPU programming by using the concept of Static Graphs. To do so, we have combined the new CUDA Graph API with the OpenACC programming model. We use as test cases a well-known and widely used problems in HPC and AI: the Particle Swarm Optimization. We complement the OpenACC functionality with the use of CUDA Graph, achieving accelerations of more than one order of magnitude, and a performance very close to a reference and optimized CUDA code. Finally, we propose a new specification to incorporate the concept of Static Graphs into the OpenACC specification.

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE; USDOE Office of Science (SC)

DOE Contract Number:: AC05-00OR22725

OSTI ID:: 1883754

Country of Publication:: United States

Language:: English

References (11)

StarPU: a unified platform for task scheduling on heterogeneous multicore architectures Augonnet, Cédric; Thibault, Samuel; Namyst, Raymond Concurrency and Computation: Practice and Experience, Vol. 23, Issue 2 https://doi.org/10.1002/cpe.1631	journal	November 2010
Many-Task Computing on Many-Core Architectures Valero-Lara, Pedro; Nookala, Poornima; Pelayo, Fernando L. Scalable Computing: Practice and Experience, Vol. 17, Issue 1 https://doi.org/10.12694/scpe.v17i1.1148	journal	March 2016
Performance evaluation of unified memory and dynamic parallelism for selected parallel CUDA applications Jarząbek, Łukasz; Czarnul, Paweł The Journal of Supercomputing, Vol. 73, Issue 12 https://doi.org/10.1007/s11227-017-2091-x	journal	June 2017
Tasking in Accelerators: Performance Evaluation Toledo, Leonel; Pena, Antonio J.; Catalan, Sandra 2019 20th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT) https://doi.org/10.1109/PDCAT46702.2019.00034	conference	December 2019
Particle swarm optimization: developments, applications and resources No authors listed Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546) https://doi.org/10.1109/CEC.2001.934374	conference	May 2001
An investigation of Unified Memory Access performance in CUDA Landaverde, Raphael; Coskun, Ayse K. 2014 IEEE High Performance Extreme Computing Conference (HPEC) https://doi.org/10.1109/HPEC.2014.7040988	conference	September 2014
OpenMP to CUDA graphs Yu, Chenle; Royuela, Sara; Quiñones, Eduardo Proceedings of the 23th International Workshop on Software and Compilers for Embedded Systems https://doi.org/10.1145/3378678.3391881	conference	May 2020
Particle swarm optimization Kennedy, J.; Eberhart, R. Proceedings of ICNN'95 - International Conference on Neural Networks https://doi.org/10.1109/ICNN.1995.488968	conference	January 1995
Particle swarm optimization: An overview Poli, Riccardo; Kennedy, James; Blackwell, Tim Swarm Intelligence, Vol. 1, Issue 1 https://doi.org/10.1007/s11721-007-0002-0	journal	August 2007
Analysis in performance and new model for multiple kernels executions on many-core architectures Valero-Lara, Pedro; Pelayo, Fernando L. 2013 IEEE 12th International Conference on Cognitive Informatics and Cognitive Computing https://doi.org/10.1109/ICCI-CC.2013.6622243	conference	July 2013
OmpSs: A PROPOSAL FOR PROGRAMMING HETEROGENEOUS MULTI-CORE ARCHITECTURES Duran, Alejandro; AyguadÉ, Eduard; Badia, Rosa M. Parallel Processing Letters, Vol. 21, Issue 02 https://doi.org/10.1142/S0129626411000151	journal	June 2011

Similar Records

Towards Enhancing Coding Productivity for GPU Programming Using Static Graphs

Journal Article · Tue Apr 19 20:00:00 EDT 2022 · Electronics · OSTI ID:1883753

OpenACC unified programming environment for GPU and FPGA multi-hybrid acceleration

Conference · Wed Jul 01 00:00:00 EDT 2020 · OSTI ID:2000432

OpenACC Unified Programming Environment for Multi-hybrid Acceleration with GPU and FPGA

Conference · Mon May 01 00:00:00 EDT 2023 · OSTI ID:2000272

Static Graphs for Coding Productivity in OpenACC

Citation Formats

References (11)

Similar Records

Related Subjects