Alexey Lastovetsky
"Automatic Assessment of Computer Programs in eLearning Systems",
The 15th Educational Technology Conference of the Irish Learning Technology Association (ILTA), Dublin, Ireland, 29-30 May, 2014.
"High-Level Topology-Oblivious Optimization of MPI Broadcast Algorithms on Extreme-Scale Platforms",
Euro-Par 2014: Parallel Processing Workshops, Vol. 8806 of Lecture Notes in Computer Science, Porto, Portugal, Springer, pp. 413-425, 25-29 August, 2014.
Download: tasus_2014.pdf (280.75 KB)
"Optimal Data Partitioning Shape for Matrix Multiplication on Three Fully Connected Heterogeneous Processors",
12th International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms (HeteroPar'2014), Porto, Portugal, 25 August, 2014.
Download: heteropar2014.pdf (772.84 KB)
"Searching for the Optimal Data Partitioning Shape for Parallel Matrix Matrix Multiplication on 3 Heterogenous Processors",
23rd International Heterogeneity in Computing Workshop (HCW 2014), Phoenix, Arizona, USA, IEEE Computer Society, 19 May, 2014.
Download: HCW-2014-05.pdf (510.38 KB)
"Topology-aware Optimization of Communications for Parallel Matrix Multiplication on Hierarchical Heterogeneous HPC Platforms",
23rd International Heterogeneity in Computing Workshop (HCW 2014), Phoenix, Arizona, USA, IEEE Computer Society, 19 May, 2014.
Download: HCW-2014-09.pdf (294.81 KB)
"Heterogeneous Parallel Computing: from Clusters of Workstations to Hierarchical Hybrid Platforms",
Supercomputing Frontiers and Innovations, vol. 1, issue 3, pp. 70-87, 12/2014.
Download: 32-140-2-PB.pdf (747.18 KB)
"Optimal Partitioning for Parallel Matrix Computation on a Small Number of Abstract Heterogeneous Processors",
School of Computer Science and Informatics, Dublin, University College Dublin, pp. 161, 09/2014.
Abstract
Download: AshleyPhDThesis.pdf (3.22 MB)
"Using Static Code Analysis for Improvement of Programmability and Performance of GridRPC-Based Applications",
School of Computer Science and Informatics, Dublin, University College Dublin, pp. 110, 09/2014.
Abstract
Download: oleg_thesis.pdf (583.17 KB)
"Optimization of Data-Parallel Scientific Applications on Highly Heterogeneous Modern HPC Platforms",
School of Computer Science and Informatics, Dublin, University College Dublin, pp. 142, 08/2014.
Abstract
Download: ziming_thesis.pdf (1.06 MB)
"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)
"Performance-Driven Methods and Tools for Optimization of Collective Communication on Complex Networks",
School of Computer Science and Informatics, Dublin, University College Dublin, pp. 104, 01/2014.
Abstract
Download: KirilDichev-PhD.pdf (1.62 MB)
"Design and optimization of scientific applications for highly heterogeneous and hierarchical HPC platforms using functional computation performance models",
High-Performance Computing on Complex Environments: Wiley, pp. 235-260, 2014.
Download: fpm-complexhpc-web.pdf (634.61 KB)
"FuPerMod: a software tool for the optimization of data-parallel applications on heterogeneous platforms",
The Journal of Supercomputing, vol. 69, issue 1: Springer US, pp. 61- 69, 2014.
Download: fupermod-jos-2014.pdf (276.83 KB)
"Optimization of collective communication for heterogeneous HPC platforms",
High-Performance Computing on Complex Environments: Wiley, pp. 95-114, 2014.
Download: coll-comm-complexhpc2013.pdf (334.71 KB)
"FuPerMod: A Framework for Optimal Data Partitioning for Parallel Scientific Applications on Dedicated Heterogeneous HPC Platforms",
12th International Conference on Parallel Computing Technologies (PaCT-2013), St. Petersburg, Russia, Lecture Notes in Computer Science 7979, Springer, pp. 182-196, 30 Sept - 4 Oct, 2013.
Download: pact2013-fupermod.pdf (367.48 KB)
"Communication Models for Resource Constrained Hierarchical Ethernet Networks",
11th International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms (HeteroPar'2013), Aachen, Germany, Lecture Notes in Computer Science 8374, Springer, pp. 259-269, 26 August, 2013.
Download: hetPar13-final-08.pdf (614.88 KB)
"Efficient and reliable network tomography in heterogeneous networks using BitTorrent broadcasts and clustering algorithms",
Scientific Programming, vol. 21, issue 3-4: IOS Press, pp. 79-92, 12/2013.
Download: sci-pro-2013.pdf (702.01 KB)
"Smart RPC-based computing in Grids and on Clouds",
Large Scale Network-Centric Computing Systems: Wiley-Interscience, pp. 255-290, 11/2013.
Download: smart_rpc_in_grids_and_clouds_final.pdf (403.82 KB)
"Hierarchical Parallel Matrix Multiplication on Large-Scale Distributed Memory Platforms",
42nd International Conference on Parallel Processing (ICPP 2013), Lyon, France, IEEE, pp. 754-762, 1-4 October, 2013.
Download: 06687414.pdf (480.2 KB)
"Heterogeneity in parallel and distributed computing",
Journal of Parallel and Distributed Computing, vol. 73, issue 12, pp. 1523-1524, 2013.
Download: jpdc-2013.pdf (152.05 KB)
"Efficient and Reliable Network Tomography in Heterogeneous Networks Using BitTorrent Broadcasts and Clustering Algorithms",
ACM/IEEE International Conference on High Performance Computing, Networking, Storage and Analysis (SC'12), Salt Lake City, UT, USA, November 11-15, 2012.
Abstract
Download: sc12.pdf (595.58 KB)
"Partitioning for Parallel Matrix-Matrix Multiplication with Heterogeneous Processors: The Optimal Solution",
21st International Heterogeneity in Computing Workshop (HCW 2012), Shanghai, China, IEEE Computer Society, May 21, 2012.
Download: PID2221951.pdf (677.03 KB)
"Using Static Code Analysis to Improve Performance of GridRPC Applications",
9th High-Performance Grid and Cloud Computing Workshop (HPGC 2012), Shanghai, China, IEEE Computer Society, May 21, 2012.
Download: 12.pdf (332.29 KB)
"Column-Based Matrix Partitioning for Parallel Matrix Multiplication on Heterogeneous Processors Based on Functional Performance Models",
9th International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms (HeteroPar'2011) , Bordeaux, France, Lecture Notes in Computer Science 7155, Springer, pp. 450-459, August 29, 2011, 2012.
Download: Matrix_Multiplication_Heterogeneous_full.pdf (310.85 KB)
"MPI vs BitTorrent : Switching Between Large-Message Broadcast Algorithms in the Presence of Bottleneck Links",
10th International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms (HeteroPar'2012), Rhodes Island, Greece, Lecture Notes in Computer Science 7640, Springer, pp. 185-195, August 27, 2012.
Download: Dichev-HeteroPar2012.pdf (204.69 KB)
