Runtime Speed Research Articles

Environment for multiprocessor simulator development

AbstractTo develop multiprocessor systems for continuing the precipitous increase in performance seen in recent years, it is important to include performance prediction at a preimplementation stage. Since software simulation, which is one such performance prediction technique, has a high degree of flexibility, it is used in diverse situations. To simulate a multiprocessor system, a simulator is implemented for a specific architecture. However, this method has accompanying implementation costs for building a simulator for each different target architecture. In this paper, the authors propose the multiprocessor simulator library ISIS as a multiprocessor simulator construction support system. ISIS is a collection of multiprocessor system internal function block simulators. Multiprocessor simulators having any kind of architecture can be constructed by combining function block simulators. Compared with conventional techniques, implementation costs can be reduced without directly impairing simulator runtime costs. Several multiprocessor simulators were implemented by using ISIS, and their execution speeds and implementation costs were evaluated. Sufficient runtime speeds were obtained for practical uses at extremely low implementation costs. ISIS has actually been used in research for on‐chip multiprocessor cache systems, and various kinds of knowledge have been obtained from the evaluation results of that research. © 2003 Wiley Periodicals, Inc. Electron Comm Jpn Pt 3, 86(10): 74–84, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecjc.10122

Object-oriented symbol management in syntax-directed compiler systems

Each symbol in a source program has a series of attributes that govern the operations performed on it. In this paper, we explore object-oriented techniques for representing the attributes of symbols and translating the operations performed on them. This approach is shown superior in memory and run-time speed to the procedural style traditionally used for writing compilers. We demonstrate object-oriented symbol management in a compiler for an arithmetic subset of C. We have used C++ --- a single-dispatching language --- to implement the same, but we emphasize the need for multiple dispatching to develop programs in a heavily-object-oriented style.

ORBIT: An Object Oriented Development System for Real-Time Traffic Algorithms

Abstract The operation of traffic management algorithms in a real-time environment places high demands on the software architecture. Aspects of security and stability together with a flexible internal structure and run-time speed have to be considered. A new approach to this problem is the ORBIT system (Object Oriented Base for the Integration of Traffic Management Algorithms). It supports implementation and dialog between different algorithms in two levels, using aspects of object oriented programming. The main objective of ORBIT is to provide implementation- and network interfaces for the creation of an open architecture for scientific demands.

Efficiency Mechanisms for a Class of Blackboard Systems

This paper presents efficient mechanisms for activation, execution and rating that are suitable for use in BB1-style blackboard architectures. We describe a knowledge source compiler that produces match networks and demons for efficient activation and rating while compiling the entire system for increased execution speed. Experiments using the enhancements in a general-purpose blackboard shell illustrate approximately a doubling of run time speed, including an increase in activation speed by a factor of 7.6 on the average. We have also resolved a subclass of blackboard systems that can be compiled down to the machine level by using a condensed representation where low-level blackboard accesses are replaced by vector references. Our analysis shows that the time complexity of the execution cycle of a condensed system is faster than the conventional approach by the ratio of the time required for blackboard retrievals to the time required for vector element retrievals. In practice, this ratio is approximately four orders of magnitude.

Gait abnormalities in chronic fatigue syndrome

To evaluate our clinical impression that patients with the chronic fatigue syndrome (CFS) did not walk normally, we assessed gait kinematics at slow walking speeds (i.e., 0.45, 0.89 and 1.34 m/sec) and 30 m run time speeds on CFS patients and on a comparison group of sedentary controls. Run time was significantly slower for CFS than control subjects ( p < 0.001). There was a significant interaction ( p < 0.01) between group and speed for maximum hip angle during stance and swing phase with hip angle being significantly larger at 1.34 m/sec for CFS than controls subjects for both cases ( p < 0.05). Knee flexion during stance and swing phases was significantly larger for controls than CFS subjects at 0.45 m/sec ( p < 0.01). Ratio of stride length divided by leg length was significantly larger for the control subjects than for the CFS subjects with differences occurring at 0.45 and 0.89 m/sec ( p < 0.01) but not 1.34 m/sec. The data indicate that CFS patients have gait abnormalities when compared to sedentary controls. These could be due to balance problems, muscle weakness, or central nervous system dysfunction; deciding which will require further research. Evaluation of gait may be a useful tool to measure outcome following therapeutic interventions.

Oberon-2 in Windows: what price compatibility?

A compiler has been developed so that programs can be written in the modular object oriented language Oberon-2 for the Windows 3 environment. To assess the price of making the Oberon-2 compiler compatible with Windows 3 the relative value of several factors compared with the original ETH Oberon compiler have been measured. In summary, compiler size increased by 70%, its compile speed dropped by 40%, runtime speed dropped by 50% and project time was twice that expected.