In this paper, we claim that memory migration mechanism is a useful approach to improve the execution of parallel applications in dynamic execution environments, but that their performance depends on related system co...
详细信息
In this paper, we claim that memory migration mechanism is a useful approach to improve the execution of parallel applications in dynamic execution environments, but that their performance depends on related system components such as the processor scheduling. To show that, we evaluate the automatic memory migration mechanism provided by IRIX in Origin systems, under different dynamic processor allocation policies when executing OpenMP parallel multiprogrammed workloads. We have focused the evaluation on the effects of the page migration mechanism on the CPU time consumed by each application, the processor allocation received, and the speedup. Results demonstrate that, if the processor scheduler is memory conscious, that is, it maintains as much as possible the system stable, the automatic memory page migration mechanism provided by IRIX improves the CPU time consumed by OpenMP applications.
In this paper, we claim that memory migration mechanism is a useful approach to improve the execution of parallel applications in dynamic execution environments, but that their performance depends on related system co...
详细信息
In this paper, we claim that memory migration mechanism is a useful approach to improve the execution of parallel applications in dynamic execution environments, but that their performance depends on related system components such as the processor scheduling. To show that, we evaluate the automatic memory migration mechanism provided by IRIX in Origin systems, under different dynamic processor allocation policies when executing OpenMP parallel multiprogrammed workloads. We have focused the evaluation on the effects of the page migration mechanism on the CPU time consumed by each application, the processor allocation received, and the speedup. Results demonstrate that, if the processor scheduler is memory conscious, that is, it maintains as much as possible the system stable, the automatic memory page migration mechanism provided by IRIX improves the CPU time consumed by OpenMP applications.
DRAM is widely used as main-memory storage in contemporary computer systems. As VLSI process technology advances, more transistors can be integrated in a single die leading to higher storage capacity and communication...
详细信息
ISBN:
(纸本)9781612848570
DRAM is widely used as main-memory storage in contemporary computer systems. As VLSI process technology advances, more transistors can be integrated in a single die leading to higher storage capacity and communication throughput per DRAM chip. New DRAM standards are created in order to keep up with these trends, and many factors such as performance, energy efficiency, reliability, and fabrication/testing cost are considered when a new DRAM architecture is designed. However, there are few studies on DRAM array organizations that consider both performance and energy efficiency of entire computer systems using the organizations. In this paper, we explore the design space of contemporary DRAM array organizations by varying the number of pages that can be concurrently accessed and the size of the pages. We compare various main-memory DRAM array organizations using multithreaded and multiprogrammed workloads on a chip-multiprocessor system with die-stacked DRAM memory in search of energy-efficient array configurations.
暂无评论