Effective clustering of complex objects in object-oriented databases
SIGMOD '91 Proceedings of the 1991 ACM SIGMOD international conference on Management of data
Software restructuring in performance-critical, distributed, real-time systems
Software restructuring in performance-critical, distributed, real-time systems
Object-oriented analysis (2nd ed.)
Object-oriented analysis (2nd ed.)
PicturePiper: using a re-configurable pipeline to find images on the Web
UIST '00 Proceedings of the 13th annual ACM symposium on User interface software and technology
Performance Engineering of Software Systems
Performance Engineering of Software Systems
Object-Oriented Software Construction
Object-Oriented Software Construction
Developing Software with Uml: Object-Oriented Analysis and Design in Practice
Developing Software with Uml: Object-Oriented Analysis and Design in Practice
Automatic Clustering of Software Systems Using a Genetic Algorithm
STEP '99 Proceedings of the Software Technology and Engineering Practice
Using Automatic Clustering to Produce High-Level System Organizations of Source Code
IWPC '98 Proceedings of the 6th International Workshop on Program Comprehension
A performance-engineered object-oriented design framework
A performance-engineered object-oriented design framework
Restructuring distributed object-oriented software using hierarchical clustering
ICCOMP'09 Proceedings of the WSEAES 13th international conference on Computers
Hi-index | 0.00 |
Pipelining is the suitable architecture to adopt applications that are naturally divided into stages. Recently, applications tend to be Object Oriented (OO). Within the context of OO, there are a lot of interactions among different objects that result in many communication activities. Besides the feed-forward communication activities, many bypassing activities are generated in the pipeline structure. In this paper, we present a performance model that analyzes and evaluates the execution and communication times of OO software that runs on pipeline architecture. The model realizes both the feed-forward and the bypassing communication. We utilize the model to restructure the target software to achieve better performance. The restructuring algorithm has two phases; the first phase is concerned with maximizing the throughput. The second phase aims to minimize the latency and fully exploit the system resources.