Welcome
NEW BOOK (FREE) -
Parallel Computing and Programming of Multi-core Systems
(In Hebrew)
https://leanpub.com/multicoreProgramming
My primary research interest is parallel computing and programming. These research areas include portability of high-performance applications, use of advanced-computer architectures, programming methodology, parallel languages and tools for parallel computers, Cloud computing and Ad Hoc networks.
My current research area focuses on two topics: usability of parallel languages and energy efficiency of multi-core and many-core systems.
The aim of the research in the area of usability of parallel languages is to find new ways to make the art of parallel programming easier. Usability of a parallel language is measured by how easy it is to learn how to design, develop, code, test and debug a parallel program by using the language features. Therefore, it directly affects the productivity of software developers. Measuring the usability of contemporary parallel programming languages and libraries by empirical studies is the key to understanding how programmers are thinking, designing, coding and analyzing parallel programs.
Energy efficiency is increasingly critical for multi-core processors and many-core accelerators. In order to increase energy efficiency, chip manufacturers are developing heterogeneous CMP chips and hardware-based power-management techniques to increase power savings. My research is focused on the software side that must be power aware as well. Reducing the parallelism overheads of software systems by developing efficient load-balancing algorithms, low-latency collective communications, fine-grained primitive synchronization, and sophisticated performance optimization techniques directly impacts power consumption. Moreover, smart algorithms that exploit data locality, perform loop unrolling, eliminate iterative loops and recursive algorithms, and use idle-power-friendly programming languages and libraries and auto-tuning based on multi-version algorithms can achieve higher-energy-efficiency applications.
Parallel Computing and Programming of Multi-core Systems
(In Hebrew)
https://leanpub.com/multicoreProgramming
My primary research interest is parallel computing and programming. These research areas include portability of high-performance applications, use of advanced-computer architectures, programming methodology, parallel languages and tools for parallel computers, Cloud computing and Ad Hoc networks.
My current research area focuses on two topics: usability of parallel languages and energy efficiency of multi-core and many-core systems.
The aim of the research in the area of usability of parallel languages is to find new ways to make the art of parallel programming easier. Usability of a parallel language is measured by how easy it is to learn how to design, develop, code, test and debug a parallel program by using the language features. Therefore, it directly affects the productivity of software developers. Measuring the usability of contemporary parallel programming languages and libraries by empirical studies is the key to understanding how programmers are thinking, designing, coding and analyzing parallel programs.
Energy efficiency is increasingly critical for multi-core processors and many-core accelerators. In order to increase energy efficiency, chip manufacturers are developing heterogeneous CMP chips and hardware-based power-management techniques to increase power savings. My research is focused on the software side that must be power aware as well. Reducing the parallelism overheads of software systems by developing efficient load-balancing algorithms, low-latency collective communications, fine-grained primitive synchronization, and sophisticated performance optimization techniques directly impacts power consumption. Moreover, smart algorithms that exploit data locality, perform loop unrolling, eliminate iterative loops and recursive algorithms, and use idle-power-friendly programming languages and libraries and auto-tuning based on multi-version algorithms can achieve higher-energy-efficiency applications.