Abstract
Conference Title: 2014 9th International Conference on Informatics and Systems (INFOS) Conference Start Date: 2014, Dec. 15 Conference End Date: 2014, Dec. 17 Conference Location: Cairo, Egypt Massively parallel computers have found significant interest from researchers in recent years. These machines have been used for complex and sophisticated simulations, such as, the brain functions simulation. Due to the increase in the power demand by massively parallel computers and it's move into the exascale computing in future, temperature and power consumption has become a major constrains, many researches aimed to address the power efficiency and temperature problems. In this work, we studied the effect of the programming languages statements on system power consumption for three control loop statements. These statements are: For Loop, While Loop, and Do-While Loop. For each of the three statements six measurements were obtained: average temperature for the control loop, average maximum reached temperature for the control loop, average percentage of execution time when the control loop reach the maximum temperature, average number of times the control loop reach the maximum temperature, average power consumption for the control loop, and average execution time for the control loop. The findings indicated that the For loop statement was the most efficient control loop statement. Also, it showed that the While loop statement was the worst in efficiency.