"SUARA: A scalable universal allreduce communication algorithm for acceleration of parallel deep learning applications",
Journal of Parallel and Distributed Computing, vol. 183, pp. 15, 01/2024.
Download: jpdc-suara.pdf (2.46 MB)
"A Survey of Communication Performance Models for High-Performance Computing",
ACM Computing Surveys, vol. 51, issue 6: ACM, 01/2019.
"A Survey of Power and Energy Predictive Models in HPC Systems and Applications",
ACM Computing Surveys, vol. 50, issue 3: ACM, 10/2017.
Download: surveypowerenergymodelshpc.pdf (578.85 KB)
"A tool to assess the communication cost of parallel kernels on heterogeneous platforms",
The Journal of Supercomputing, vol. 76: Springer, pp. 4629–4644, 06/2020.
"Topology-Oblivious Optimization of MPI Broadcast Algorithms on Extreme-Scale Platforms",
Simulation Modelling Practice and Theory, vol. 58: Elsevier, pp. 30-39, 11/2015.
Download: simpat2015.pdf (1.63 MB)
"Towards Optimal Matrix Partitioning for Data Parallel Computing on a Hybrid Heterogeneous Server",
IEEE Access, vol. 9: IEEE, pp. 17229 - 17244, 02/2021.
Download: IEEE-Access-09328411.pdf (3.76 MB)
"Design and implementation of self-adaptable parallel algorithms for scientific computing on highly heterogeneous HPC platforms",
arXiv.org, no. arXiv:1109.3074, 09/2011.
Download: 1109.3074.pdf (1.04 MB)
An Efficient Procedure for Building the Functional Performance Model of a Processor,
, 2005.
Download: Cluster2005_perf_model.pdf (268.4 KB)
Experimental Study of Six Different Parallel Matrix-Matrix Multiplication Applications for Heterogeneous Computational Clusters of Multicore Processors,
: School of Computer Science and Informatics, University College Dublin, pp. 47, 02/2009.
Abstract
Download: Parallel_matrix_matrix_mutiplication_multicores.pdf (373.08 KB)
Heterogeneous PBLAS: A Set of Parallel Basic Linear Algebra Subprograms for Heterogeneous Computational Clusters,
: School of Computer Science and Informatics, University College Dublin, pp. 19, 04/2008.
Abstract
Download: UCD-CSI-2008-2-HeteroPBLAS.pdf (111.71 KB)
"How Algorithm Definition Language (ADL) Improves the Performance of SmartGridSolve Applications",
UCD CSI Technical Report 2009-06, Dublin, 07/2009.
Abstract
Download: ucd-csi-2009-06.pdf (162.06 KB)
"Modeling Performance of Many-to-One Collective Communication Operations in Heterogeneous Clusters",
UCD CSI Technical Report 2006-3, 2006.
Download: 1157631827149.pdf (145.83 KB)
"A Non-Intrusive and Incremental Approach to Enabling Direct Communications in RPC-based Grid Programming Systems",
Technical Report UCD-CSI-2005-2, pp. 15, 2006.
Download: ucd-csi-2005-2.pdf (295.56 KB)
SmartGridRPC: The new RPC model for high performance Grid computing,
: University College Dublin, pp. 55, 10/2009.
Download: ucd-csi-2009-10.pdf (1.8 MB)
"Theoretical Results on Optimal Partitoning for Matrix-Matrix Multiplication with Two Processors",
School of Computer Science and Informatics, University College Dublin, no. UCD-CSI-2011-09, 09/2011.
Download: ucd-csi-2011-09.pdf (678.89 KB)
Verifikation der Eigenschaften von kryptographischen Protokollen unter Verwendung von Spin Was ist Model Checking?,
: University of Stuttgart, pp. 1–8, 2005.
"Accurate Component-level Energy Modelling of Parallel Applications on Modern Heterogeneous Hybrid Computing Platforms using System-level Measurements",
School of Computer Science, Dublin, University College Dublin, pp. 198, 12/2020.
Download: thesis-fahad.pdf (3.49 MB)
"Application level energy measurements and models for hybrid platform with accelerators",
School of Computer Science, Dublin, University College Dublin, pp. 165, 05/2018.
Download: thesis.pdf (1.61 MB)
"Communication Performance Models for Heterogeneous Computational Clusters",
School of Computer Science and Informatics, Dublin, University College Dublin, pp. 115, 06/2009.
Download: moflynn-ethesis.pdf (925.45 KB)
"Design and Implementation of Parallel Algorithms for Modern Heterogeneous Platforms Based on the Functional Performance Model",
School of Computer Science and Informatics, Dublin, University College Dublin, pp. 117, 05/2014.
Download: DavidClarke_PhDthesis.pdf (1.22 MB)
"Design and Optimization of OpenFOAM-based CFD Applications for Modern Hybrid and Heterogeneous HPC Platforms",
School of Computer Science and Informatics, Dublin, University College Dublin, pp. 89, 12/2013.
Download: AmaniAlOnazi_Thesis.pdf (2.82 MB)
"Efficient and accurate selection of optimal MPI collective algorithms using analytical performance modelling",
School of Computer Science, Dublin, University College Dublin, pp. 130, 06/2021.
Download: thesis.pdf (2.21 MB)
"Hierarchical Approach to Optimization of MPI Collective Communication Algorithms",
School of Computer Science, Dublin, University College Dublin, pp. 152, 10/2015.
Download: khalid-thesis-oct-2015.pdf (1.1 MB)
"High-Level Data Partitioning for Parallel Computing on Heterogeneous Hierarchical Computational Platforms",
School of Computer Science and Informatics, Dublin, Ireland, University College Dublin, pp. 186, 04/2011.
Download: brett_thesis_final.pdf (4.87 MB)
"HMPI: A Message-Passing Library for Heterogeneous Networks of Computers",
Computer Science Department, Dublin, University College Dublin, pp. 456, 06/2005.
Download: Ravi_thesis.pdf (1.89 MB)

] 

