ABSTRACT
Using the compiler and interpreter published by Ben-Ari, an algorithm performance monitoring system is built. By removing the randomness from the procedure which selects and controls the execution of multiple processes an unbiased execution of two algorithms can be achieved. Creating a window mechanism for viewing simultaneous execution is accomplished by the creating extensions to the language and rewriting portions of the interpreter.
The extensions indicate where performance monitoring is to begin and where it is to end as well as how the screen is to be controlled during execution. A new standard procedure is used to split the screen vertically into two windows and to set flags that control input and output to each window. Another standard procedure indicates where performance monitoring is to end and causes the screen to return to normal.
All instructions encountered by the interpreter which handle the input and output have been altered. The flags cause each process's input and output requests to appear in the correct window.
In an educational environment, this system can be used to illustrate the fundamental operations of an algorithm. By viewing two algorithms executing simultaneously, the student can directly compare the performance of both algorithms.
The complete system was constructed using VAX Pascal and utilizes the VMS Screen Management routines to manage input and output.
- 1.Ben-Ari, M., Principles of Concurrent Programming, Prentice-Hall,Englewood Cliffs, N. J. (1982). Google ScholarDigital Library
- 2.Brown, M., Algorithm Animation, the MIT Press, Cambridge, Mass. (1987).Google Scholar
Index Terms
- A dual-algorithm performance monitoring system (abstract)
Recommendations
High-Performance and Low-Cost Dual-Thread VLIW Processor Using Weld Architecture Paradigm
This paper presents a cost-effective and high-performance dual-thread VLIW processor model. The dual-thread VLIW processor model is a low-cost subset of the Weld architecture paradigm. It supports one main thread and one speculative thread running ...
Dual-Core Execution: Building a Highly Scalable Single-Thread Instruction Window
PACT '05: Proceedings of the 14th International Conference on Parallel Architectures and Compilation TechniquesCurrent integration trends embrace the prosperity of single-chip multi-core processors. Although multi-core processors deliver significantly improved system throughput, single-thread performance is not addressed. In this paper, we propose a new ...
Comments