This paper explores the macro data flow approach for solving numerical applications on distributed memory systems. We discuss the problems of this approach with a sophisticated ‘real life’ algorithm—the adaptive fu...
详细信息
This paper explores the macro data flow approach for solving numerical applications on distributed memory systems. We discuss the problems of this approach with a sophisticated ‘real life’ algorithm—the adaptive full multigrid method.
It is shown that the nonnumeric parts of the algorithm—the initialization, the termination and the mapping of processes to processors—are very important for the overall performance.
To avoid unnecessary global synchronization points we propose to use the distributed supervisors. We compare this solution with more centralized algorithms. The performance evaluation is done for nearest neighbour and bus connected multiprocessors using a simulation systems.
This paper addresses the problem of mapping the processes of a parallel program to the processors of the target multiprocessor. A new approach to the mapping problem is proposed. This approach is based on the use of s...
详细信息
This paper addresses the problem of mapping the processes of a parallel program to the processors of the target multiprocessor. A new approach to the mapping problem is proposed. This approach is based on the use of special system calls, called mapping directives, to signal (1) forthcoming changes in the communication pattern of the program, and (2) the occurrence of various mapping-related events. These directives provide the operating system with a run-time capability to tune the mapping in order to reduce the communication overhead.
暂无评论