Areas of Research Interest
Parallel and distributed algorithms and architectures, real-time systems and applications, heterogeneous computing, reconfigurable computing, and scientific computing.
- Performance evaluation of parallel processing systems and parallel applications.
- High performance reconfigurable computing for cryptographic algorithms.
- Efficient implementations of cryptography on reconfigurable systems
- Performance analysis of reconfigurable architectures.
- Custom and adaptive computing.
- Application-specific parallel architectures.
- Multiprocessor and multi-computer architectures.
- System simulation using fuzzy logic control.
- Application of simulation to engineering education and educational development.
- Higher Education in the MENA region.
- Global issues in Education.
Performance Evaluation of Reconfigurable Computer Architectures
Processors vary from ASICs (Application-specific Integrated Circuits) designed to perform specific predefined operation(s), to general-purpose processors (GPPs) designed to perform a wide range of applications. ASICs make use of the inherent quality of a certain application’s algorithm to provide very high performance. On the other hand, GPPs are designed to execute any application. With that, comes the need of a system that combines the high performance of ASICs and the flexibility of GPPs. This has led to the introduction of reconfigurable computing (RC) that employs both reconfigurable hardware and programmable processors. RC allows the user to configure the hardware through software by defining the hardware resources needed for a certain application. The aim of this research is the mapping of new applications on an RC architecture, which will involve tuning the algorithm, pertaining to the application, to the hardware. The driving force of the above is to optimize the execution performance.
Implementation of Cryptographic Algorithms on High Performance Parallel Architectures
This research explores parallelization of applications in the field of cryptography on parallel architectures. Data security will play a central role in the design of future IT systems and cryptographic engines realized on parallel architectures are a promising option for protecting these systems. Implementation of cryptographic algorithms presents several requirements and challenges and the performance of these algorithms is often crucial. The goal of this research will be to gain insight of the potential that some parallel architectures offer for cryptographic algorithms.
Application of Fuzzy Logic to Performance Evaluation in Parallel Processing Systems
Performance is one of the key factors that need to be taken into account in the design, development, configuration, and tuning of a computer system. Hence, the quantitative evaluation of computer performance (CP) is needed during the entire life cycle of a computer system. The methods that have been used can be divided into three main areas, namely performance measurement, analytic performance modeling, and simulation performance modeling. These methods have been applied across the entire spectrum of computer systems. This research work proposes the introduction of fuzzy logic methodology as an alternative simulation performance modeling technique. This methodology has been successfully used in specific CP application areas including performance evaluation of cache memory and of the arbiters used for multiple-bus multiprocessor systems.
Scheduling of Parallel Tasks onto Modular Parallel Architectures
In either sequential or parallel systems, the architecture is characterized by functional components, the communication topology and facilities, and control structures and mechanisms. However, there are several issues related to parallelization that do not arise in sequential programming. One of the most important issues is task allocation that is the breakdown of the total workload into smaller tasks assigned to different processors, and the proper sequencing of the tasks when some of them are interdependent and cannot be executed simultaneously. To achieve the highest level of performance it is important to ensure that each processor is properly utilized. This process is called load balancing or scheduling and it is considered to be extremely “formidable” to solve. The aim of this research is to develop efficient techniques for mapping and scheduling of parallel tasks onto networks of parallel processors.
Global Issues in Education and Higher Education in the MENA Region
My interest in research in education not only stems from the early days of my research years in the application of simulation to engineering education but also in a more concentrated manner after my appointment as Minister of Education & Higher Education. My research in this area focuses on the investigation of relationships in different fields of higher education. To date, I have worked in different research areas in education with the active and constructivism theories as the theoretical framework of my research in the higher education field. I have also conducted research based on approaches related to women empowerment. My current research focuses primarily on knowledge sharing processes in educational institutions and on the impact of the use of ICT in school and university classrooms. More importantly, I have conducted research on curriculum reform at the school and university scales. I have been also interested in developing methods to assess knowledge sharing and its effects on examining interventions designed to improve different teaching/learning processes. My research is also grounded in the processes of communication, coordination and knowledge-sharing which are of utmost importance. My current research is mainly on curriculum development, teacher professional development, and educational planning with governments and educational institutions in almost all of the Arab countries in the MENA region.