-
[show abstract]
[hide abstract]
ABSTRACT: In the recent years, major CPU designers have shifted from ramping up clock speeds to add on-chip multi-core processors. Algorithms and applications must be tuned to allow multi-core processors to exploit their inherent parallelism. An experiment is carried out with data mining (DM) algorithms, to explore the potential of quad-core hardware architecture with OpenMP API (application programming interface). The concept of memory mapped files is widely supported by most of the modern operating systems. Performance of memory mapped files on multi-core processor is also explored. In this experiment, a popular clustering algorithm k-means with serial versions and parallel versions are used. The later is experimented with static and dynamic threads of OpenMP. Memory utilization of k-means algorithm is also analyzed. Experimental results with both simulated and real data demonstrate the scalability of our implementation and effective utilization of parallel hardware, which is beneficial to data mining (DM) problems, which involves large data sets. The capacity of RAM (random access memory) affects the mmap() performance.
Methods and Models in Computer Science, 2009. ICM2CS 2009. Proceeding of International Conference on; 01/2010
-
[show abstract]
[hide abstract]
ABSTRACT: Increased availability of Multi-Core processors is forcing us to redesignalgorithms and applications so as to exploit the availablecomputational power from multiple cores. It is not un-common toemploy memory mapping of files in applications involving hugeI/O bandwidth to improve the response/service times. This papermainly focuses on performance of memory mapped files on Multi-Core processors. Experiments are carried out with k-meansalgorithm, a popular Data mining (DM) clustering algorithm, toexplore the potential of Multi-Core hardware under OpenMP APIand POSIX threads. Observations are made both with static anddynamic threads of OpenMP. Experiments are also conductedwith both simulated and real data sets. Experiments indicate thatmemory mapping of files gives considerable benefit on Multi-Core processors also. In addition, the benefit increased withincreased physical memory size. Also, the benefit of memorymapping with the selected algorithm is increasing with number ofcores.
International Journal of Computer Applications. 01/2010;
-
[show abstract]
[hide abstract]
ABSTRACT: The concept of memory mapped files is widely supported by most of the modern operating systems. A study is carried out with computationally intensive applications such as data mining, to see the benefit of this concept over the conventional file I/O which calls standard library function fread(). Experiments are carried out in memory mapping with both simulated and real data. The observations indicated that the memory mapping based versions taking less CPU time compared to fread() based ones.
International Journal of Information Technology and Knowledge Management. 08/2002; 2:365-370.
