Performance visualization of parallel programs

The user of a parallel computer system would like to know the performance of a program in terms of how optimally it uses the system resources. This task is increasingly performed by program performance visualization. The limitations of conventional performance data analysis techniques necessitate better visual analysis methods that are scalable with the problem and system sizes and extensible. They should represent some physical and logical structure of the parallel system and program. The analysis techniques presented here have been motivated by the use of signal and (two- and three-dimensional) image processing techniques being applied in some areas of scientific visualization. Results of applying selected techniques are shown. These techniques and tools have advantages and disadvantages when applied in this area.<
>