SwePub - search: WFRF:(Sahin Cagri)

Enumeration	Reference	Cover	Find
1.	Sari, Alparslan, et al. (author) Designing a Distributed Multi-agent System for Compiler Optimization 2021 In: 2021 Zooming Innovation in Consumer Technologies Conference, ZINC 2021. ; , s. 269-274 Conference paper (peer-reviewed)abstract This paper explores the run time performance improvements using different GCC optimization flags in program compilation. As multi-core microprocessor systems replacing legacy single-core ones, tremendous effort is needed to address to optimize the associated compilers for newly designed architectures in order to suit them for running parallel programming on multiple cores. Therefore, the aim of this paper is to address this challenge by designing an optimum distributed multi-agent system to perform compiler optimization. A multi-agent framework is adopted to utilize random and genetic algorithm-based search algorithm to find the best GCC optimization flags for a given program. The framework is highly scalable and can be extended with distributed system concept to perform code compilation in parallel to find the best-optimized code sequence in a short amount of time. The initial performance results have promising indicators which clearly show that the performance improvement is achieved.

Sari, Alparslan, et al. (author)
Designing a Distributed Multi-agent System for Compiler Optimization
2021
In: 2021 Zooming Innovation in Consumer Technologies Conference, ZINC 2021. ; , s. 269-274
Conference paper (peer-reviewed)abstract
- This paper explores the run time performance improvements using different GCC optimization flags in program compilation. As multi-core microprocessor systems replacing legacy single-core ones, tremendous effort is needed to address to optimize the associated compilers for newly designed architectures in order to suit them for running parallel programming on multiple cores. Therefore, the aim of this paper is to address this challenge by designing an optimum distributed multi-agent system to perform compiler optimization. A multi-agent framework is adopted to utilize random and genetic algorithm-based search algorithm to find the best GCC optimization flags for a given program. The framework is highly scalable and can be extended with distributed system concept to perform code compilation in parallel to find the best-optimized code sequence in a short amount of time. The initial performance results have promising indicators which clearly show that the performance improvement is achieved.

Träfflista för sökning "WFRF:(Sahin Cagri) "