Saber Feki
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Saber Feki has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
Ahmed Al-Jarro
Division of Computer, Electrical and Mathematical Sciences and Engineering, University College London, London WC1E 7JE, UK; Photonics Group, Department of Electronic and Electrical Engineering, University College London, London WC1E 7JE, UK
2 shared publicationsEdgar Gabriel
2 shared publications- Hakan Bagci
Computer, Electrical, and Mathematical Science and Engineering Division, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
2 shared publications - Shahzeb Siddiqui
Pfizer Inc. Groton & Labs
2 shared publications Alain Clo
KAUST Research Computing, King Abdullah University of Science and Technology (KAUST), Thuwal, 23955-6900, KSA
1 shared publicationAnis Ben Ishak
Tunis University
1 shared publication
Latest Publications
- Open Access
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 44-54
Balancing Throughput and Energy: Power Provisioning Case Studies for CPU and GPU Workloads
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 44-54
Open AccessBalancing Throughput and Energy: Power Provisioning Case Studies for CPU and GPU Workloads
- 18 April 2015
- Published by Springer Nature
- p. 224-235
Historic Learning Approach for Auto-tuning OpenACC Accelerated Scientific Applications
- 18 April 2015
- Published by Springer Nature
- p. 224-235
Historic Learning Approach for Auto-tuning OpenACC Accelerated Scientific Applications
- 7 September 2014
- Published by EAGE Publications bv
Automatic Performance Tuning of Parallel and Accelerated Seismic Imaging Kernels
- 7 September 2014
- Published by EAGE Publications bv
Automatic Performance Tuning of Parallel and Accelerated Seismic Imaging Kernels
- 17 June 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Propagation Magazine
- Vol. 56 (2) , 265-277
Porting an explicit time-domain volume-integral-equation solver on gpus with openacc [open problems in cem]
Graphics processing units (GPUs) are gradually becoming mainstream in high-performance computing, as their capabilities for enhancing performance of a large spectrum of scientific applications to many fold when compared to multi-core CPUs have been clearly identified and proven. In this paper, implementation and performance-tuning details for porting an explicit marching-on-in-time (MOT)-based time-domain volume-integral-equation (TDVIE) solver onto GPUs are described in detail. To this end, a high-level approach, utilizing the OpenACC directive-based parallel programming model, is used to minimize two often-faced challenges in GPU programming: developer productivity and code portability. The MOT-TDVIE solver code, originally developed for CPUs, is annotated with compiler directives to port it to GPUs in a fashion similar to how OpenMP targets multi-core CPUs. In contrast to CUDA and OpenCL, where significant modifications to CPU-based codes are required, this high-level approach therefore requires minimal changes to the codes. In this work, we make use of two available OpenACC compilers, CAPS and PGI. Our experience reveals that different annotations of the code are required for each of the compilers, due to different interpretations of the fairly new standard by the compiler developers. Both versions of the OpenACC accelerated code achieved significant performance improvements, with up to 30× speedup against the sequential CPU code using recent hardware technology. Moreover, we demonstrated that the GPU-accelerated fully explicit MOT-TDVIE solver leveraged energy-consumption gains of the order of 3× against its CPU counterpart.
- 17 June 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Propagation Magazine
- Vol. 56 (2) , 265-277
Porting an explicit time-domain volume-integral-equation solver on gpus with openacc [open problems in cem]
Graphics processing units (GPUs) are gradually becoming mainstream in high-performance computing, as their capabilities for enhancing performance of a large spectrum of scientific applications to many fold when compared to multi-core CPUs have been clearly identified and proven. In this paper, implementation and performance-tuning details for porting an explicit marching-on-in-time (MOT)-based time-domain volume-integral-equation (TDVIE) solver onto GPUs are described in detail. To this end, a high-level approach, utilizing the OpenACC directive-based parallel programming model, is used to minimize two often-faced challenges in GPU programming: developer productivity and code portability. The MOT-TDVIE solver code, originally developed for CPUs, is annotated with compiler directives to port it to GPUs in a fashion similar to how OpenMP targets multi-core CPUs. In contrast to CUDA and OpenCL, where significant modifications to CPU-based codes are required, this high-level approach therefore requires minimal changes to the codes. In this work, we make use of two available OpenACC compilers, CAPS and PGI. Our experience reveals that different annotations of the code are required for each of the compilers, due to different interpretations of the fairly new standard by the compiler developers. Both versions of the OpenACC accelerated code achieved significant performance improvements, with up to 30× speedup against the sequential CPU code using recent hardware technology. Moreover, we demonstrated that the GPU-accelerated fully explicit MOT-TDVIE solver leveraged energy-consumption gains of the order of 3× against its CPU counterpart.
- 1 July 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 90
Multi-GPU-based acceleration of the explicit time domain volume integral equation solver using MPI-OpenACC
An explicit marching-on-in-time (MOT)-based time-domain volume integral equation (TDVIE) solver has recently been developed for characterizing transient electromagnetic wave interactions on arbitrarily shaped dielectric bodies (A. Al-Jarro et al., IEEE Trans. Antennas Propag., vol. 60, no. 11, 2012). The solver discretizes the spatio-temporal convolutions of the source fields with the background medium's Green function using nodal discretization in space and linear interpolation in time. The Green tensor, which involves second order spatial and temporal derivatives, is computed using finite differences on the temporal and spatial grid. A predictor-corrector algorithm is used to maintain the stability of the MOT scheme. The simplicity of the discretization scheme permits the computation of the discretized spatio-temporal convolutions on the fly during time marching; no “interaction” matrices are pre-computed or stored resulting in a memory efficient scheme. As a result, most often the applicability of this solver to the characterization of wave interactions on electrically large structures is limited by the computation time but not the memory.
- 1 July 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 90
Multi-GPU-based acceleration of the explicit time domain volume integral equation solver using MPI-OpenACC
An explicit marching-on-in-time (MOT)-based time-domain volume integral equation (TDVIE) solver has recently been developed for characterizing transient electromagnetic wave interactions on arbitrarily shaped dielectric bodies (A. Al-Jarro et al., IEEE Trans. Antennas Propag., vol. 60, no. 11, 2012). The solver discretizes the spatio-temporal convolutions of the source fields with the background medium's Green function using nodal discretization in space and linear interpolation in time. The Green tensor, which involves second order spatial and temporal derivatives, is computed using finite differences on the temporal and spatial grid. A predictor-corrector algorithm is used to maintain the stability of the MOT scheme. The simplicity of the discretization scheme permits the computation of the discretized spatio-temporal convolutions on the fly during time marching; no “interaction” matrices are pre-computed or stored resulting in a memory efficient scheme. As a result, most often the applicability of this solver to the characterization of wave interactions on electrically large structures is limited by the computation time but not the memory.
- 1 July 2013
- Published by Elsevier in Quaternary International
- Vol. 302, 199-209
Study of variation in groundwater quality in a coastal aquifer in north-eastern Tunisia using multivariate factor analysis
- 1 July 2013
- Published by Elsevier in Quaternary International
- Vol. 302, 199-209
Study of variation in groundwater quality in a coastal aquifer in north-eastern Tunisia using multivariate factor analysis
- 1 February 2012
- Published by Elsevier in Expert Systems with Applications
- Vol. 39 (3) , 3087-3099
Feature selection using Bayesian and multiclass Support Vector Machines approaches: Application to bank risk prediction
- 1 February 2012
- Published by Elsevier in Expert Systems with Applications
- Vol. 39 (3) , 3087-3099
Feature selection using Bayesian and multiclass Support Vector Machines approaches: Application to bank risk prediction
- 1 October 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 265-274
Incorporating Historic Knowledge into a Communication Library for Self-Optimizing High Performance Computing Applications
Emerging computing systems have a wide variety of hardware and software components influencing the performance of parallel applications, presenting end-users with a (nearly) unique execution environment on each parallel machine. One of the big challenges of High Performance Computing is therefore to develop portable and efficient codes for any execution environment. The Abstract Data and Communication Library (ADCL) is a self-optimizing runtime communication library aiming at providing the highest possible performance for application level communication operations. The library provides for a given communication pattern a large number of implementations and incorporates a runtime selection logic. This selection aims at adaptively choosing the best performing implementation on the current platform and for the given problem. In this paper, we present a recent enhancement to the library which introduces the capability of utilizing information from previous executions in order to minimize the overhead of the runtime selection logic which mainly stems from testing under performing implementations. We introduce the notion of similar problems by using a proximity measure for a given operation. The approach is evaluated for the n-dimensional neighborhood communication for two different network interconnects and for a large range of different problems.
- 1 October 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 265-274
Incorporating Historic Knowledge into a Communication Library for Self-Optimizing High Performance Computing Applications
Emerging computing systems have a wide variety of hardware and software components influencing the performance of parallel applications, presenting end-users with a (nearly) unique execution environment on each parallel machine. One of the big challenges of High Performance Computing is therefore to develop portable and efficient codes for any execution environment. The Abstract Data and Communication Library (ADCL) is a self-optimizing runtime communication library aiming at providing the highest possible performance for application level communication operations. The library provides for a given communication pattern a large number of implementations and incorporates a runtime selection logic. This selection aims at adaptively choosing the best performing implementation on the current platform and for the given problem. In this paper, we present a recent enhancement to the library which introduces the capability of utilizing information from previous executions in order to minimize the overhead of the runtime selection logic which mainly stems from testing under performing implementations. We introduce the notion of similar problems by using a proximity measure for a given operation. The approach is evaluated for the n-dimensional neighborhood communication for two different network interconnects and for a large range of different problems.
- 1 January 2008
- Published by Springer Nature
- p. 210-217
A Tool for Optimizing Runtime Parameters of Open MPI
- 1 January 2008
- Published by Springer Nature
- p. 210-217
A Tool for Optimizing Runtime Parameters of Open MPI