Siham Tabik

Research Interests

• Developing novel and scalable algorithms for Geographic Information Systems
• Optimizing scientific applications for hybrid and heterogeneous systems including Supercomputers
• Accelerating scientific kernels on GPUs, many-core and multi-core
• Building performance models for specific computation patterns

Selected Publications

• S Tabik, M Peemen, N Guil, H Corporaal.
  Demystifying the 16x16 thread-block for stencils on the GPU
  Concurrency and Computation: Practice and Experience , 27 (18), 5557-5573, 2015. [pdf]
  
  
• A. R. Cervilla, S. Tabik, L. F. Romero.
  Sitting Multiple Observers for Maximum Coverage: An Accurate Approach
  Procedia Computer Science, Volume 51, 2015, Pages 356-365. [pdf]
  
  
• S. Tabik, A.R. Cervilla, E, Zapata, L.F. Romero.
  Efficient Data Structure and Highly Scalable Algorithm for Total-Viewshed Computation
  IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(1):304-310, 2015. [pdf]
  
  
• S Tabik, G. Ortega, E.M. Garzon
  Performance Evaluation of Kernel Fusion BLAS Routines on the GPU: Iterative Solvers as Case Study,
  The Journal of Supercomputing, 2014. [pdf].
  
  
• S. Tabik, L.F. Romero, E. L. Zapata.
  Simultaneous Computation of Total Viewshed on Large High Resolution Grids,
  International Journal of Geographical Information Science, 27(4): 804-814, 2013. [pdf]
  
  
• S Tabik, A Villegas, EL Zapata, LF Romero
  Optimal tilt and orientation maps: a multi-algorithm approach for heterogeneous multicore-GPU systems,
  The Journal of Supercomputing, 1-13, 2013. [pdf]
  
  
• S. Tabik, L.F. Romero, P. Mimica, O. G. Plata, E. L. Zapata
  VLBI-resolution radio-map algorithms: Performance analysis of different levels of data-sharing on multi-socket, multi-core architectures,
  Computer Physics Communications 183(9): 1937-1946, 2012. [pdf]
  
  
• G. Utrera, S. Tabik, J. Corbalan, J. Labarta.
  A Job Scheduling Approach for Multi-core Clusters Based on Virtual Malleability,
  Euro-Par, pp. 191-203, August 27-31, 2012. [pdf]
  
  
• S. Tabik, L.F. Romero, E. L. Zapata.
  High Performance Three-horizon Composition Algorithm for Large Scale Terrains,
  International Journal of Geographical Information Science , Vol. 25, Issue 4, pp. 541-555, 2011. [pdf]
  
  
• A. Navarro, R. Asenjo, S. Tabik, C. Cascaval.
  Analytical Modeling of Pipeline Parallelism. .
  International Conference on Parallel Architectures and Compilation Techniques (PACT'09), pp. 281-290, September 12-16, 2009. [pdf]
  
  
• S. Tabik, L.F. Romero, J. Vias, Emilio L. Zapata.
  Fast Clear-sky Solar Irradiation Computation for Very Large Digital Elevation Models.
  Computer Physics Communications , Vol. 178, Issue 11, pp. 800-808, 2008. [pdf]
  
  
• S. Tabik, L.F. Romero, E.M. Garzon, J.I. Ramos.
  On a Model of Three-dimensional Bursting and its Parallel Implementations.
  Computer Physics Communications , Vol. 178, Issue 7, pp. 471-485, 2008. [pdf]
  
  
• S. Tabik, E.M. Garzon, I. Garcia, J.J. Fernandez.
  High Performance Noise Reduction for Biomedical Multidimensional Data.
  Digital Signal Processing , Vol. 17, Issue 4, pp. 724-736, 2007. [pdf]
  

Software

• An efficient Total-viewshed Software for Linux OS [Download]
  
• Insolator: High Performance GIS-Software for Solar Irradiation Computation [Download]
  Insolator is an open source, high performance software for computing solar energy input that can be collected
  at any point of a terrain represented by a DEM (Digital Elevation Model). It is stable and can be run on distributed
  and or shared memory systems.
  
  Insolator: High Performance GIS-Software for Solar Irradiation Computation under Licence
  Creative Commons Reconocimiento-NoComercial-CompartirIgual 3.0 Unported.
  . www.ac.uma.es.
  
  
• Web appication based in part on Insolator [http]
  This application is available for the area of Malaga.

Technical Reports

S. Tabik, L.F. Romero.
The horizontal error in horizon computation.

---

Dept. Arquitectura de Computadores, UMA

---