Real-time arithmetic unit

In this paper we discuss the paradigm of real-time processing on the lower level of computing systems. An arithmetical unit based on this principle containing addition, multiplication, division and square root operations is described. The development of the computation operators model is based on the imprecise computation paradigm and defines the concept of the adjustable calculation of a function that manages delay and the precision of the results as an inherent and parameterized characteristic. The arithmetic function design is based on well-known algorithms and offers progressive improvement in the results. Advantages in the predictability of calculations are obtained by means of processing groups of k-bits atomically and by using look-up tables. We report an evaluation of the operations in path time, delay and computation error. Finally, we present an example of our real-time architecture working in a realistic context. Higinio Mora-Mora received the BS degree in computer science engineering and the BS degree in business studies in University of Alicante, Spain, in 1996 and 1997, respectively. He received the PhD degree in computer science from the University of Alicante in 2003. Since 2002, he is a member of the faculty of the Computer Technology and Computation Department at the same university where he is currently an associate professor and researcher of Specialized Processors Architecture Laboratory. His areas of research interest include computer arithmetic and the design of floating points units and approximation algorithms related to VLSI design. Jerónimo Mora-Pascual received the BS degree in computer science engineering from University of Valencia (Spain), in 1994. Since 1994, he has been a member of the faculty of the Computer Technology and Computation department at the University of Alicante, where he is currently an associate professor. He completed his PhD in computer science at University of Alicante in 2001. He has worked on neural networks and its VLSI implementation. His current areas of research interest include the design of floating points units and its application for real-time systems and processors for geometric calculus. Juan Manuel García-Chamizo received his BS in physics at the University of Granada (Spain) in 1980, and the PhD degree in Computer Science at the University of Alicante (Spain) in 1994. He is currently a full professor and director of the Computer Technology and Computation department at the University of Alicante. His current research interests are computer vision, reconfigurable hardware, biomedical applications, computer networks and architectures and artificial neural networks. He has directed several research projects related to the above-mentioned interest areas. He is a member of a Spanish Consulting Commission on Electronics, Computer Science and Communications. He is also member and editor of some program committee conferences. Antonio Jimeno-Morenilla is associate professor in the Computer Technology and Computation department at the University of Alicante (Spain). He received his PhD from the University of Alicante in 2003. He concluded his bachelor studies at the EPFL (Ecole Polytechnique Fe’de’rale de Lausanne, Switzerland) and received his BS degree in computer science from the Polytechnical University of Valencia (Spain) in 1994. His research interests include sculptured surface manufacturing, CAD/CAM, computational geometry for design and manufacturing, rapid and virtual prototyping, 3D surface flattening, and high performance computer architectures. He has considerable experience in the development of 3D CAD systems for shoes. In particular, he has been involved in many government and industrial funded projects, most of them in collaboration with the Spanish Footwear Research Institute (INESCOP).     

The role of modeling in computational science education

Modeling and simulation skills are two core competences of computational science and thus should be a central part of any curriculum. While there is a well-founded methodology for the design of simulation algorithms today the teaching of modeling skills carries some intrinsic problems. The reason is that modeling is still partly an art and partly a science. As an important consequence for university education, the concepts for teaching modeling must be quite different from those for teaching simulation algorithms. Experiences made with the courses on ‘Modeling and Simulation’ at the University of Siegen are summarized and some general concepts for the teaching of modeling skills are presented. In particular, three practical approaches to modeling education are discussed with several examples.     

The computational science major at SUNY Brockport

The field of computational science is a recent addition to academic study. While the content of such an education is generally agreed upon, effective methods for imparting this knowledge are still being investigated. This paper describes the current state of the computational science degree programs at SUNY Brockport and the successes that have been obtained. Issues relating to the implementation of such programs in the context of a small, liberal arts college are also discussed.     

DLX处理器浮点数流水线性能的研究

DLX虚拟微处理机提供了一个基于PC机的研究平台，研究者可以在PC机上模拟新的处理机技术。该文先介绍DLX微处理机针对流水线处理的结构调整和流水线面临的问题，然后结合实例，介绍了对DLX浮点数流水线性能的分析研究。     

Implementation independent arithmetic: Speculation for discussion

The specification of a truly portable implementation independent programming language requires that digital arithmetic be specified in an implementation independent manner. Variable length storage is proposed for digital numbers. Linked storage and linked overflow storage are proposed so as to enable the use of variable length numbers. It is suggested that significant digit arithmetic be used for single numbers and interval arithmetic be used for interval pairs. The question is put to numerical mathematicians to specify the decision rules to be used in deciding on the number of digits to be retained when computing in either the significant digit mode or in the interval mode. The question is also raised as to what other arithmetic modes should be provided for. The speculation is offered not for the purposes of suggesting useful hardware design techniques but rather to indicate feasibility of some design. If the implementation independent arithmetic is considered feasible, then language designers can design a language freed from present hardware restrictions.     

一种改进的浮点乘加器结构的延时分析*

针对一种改进的浮点乘加器结构,对关键路径的延时进行定量的估算,并将其与传统乘加器结构的延时进行比较。     

Parallel programming in computational science: an introductory practical training course for computer science undergraduates at Aachen University

Parallel programming of high-performance computers has emerged as a key technology for the numerical solution of large-scale problems arising in computational science and engineering (CSE). The authors believe that principles and techniques of parallel programming are among the essential ingredients of any CSE as well as computer science curriculum. Today, opinions on the role and importance of parallel programming are diverse. Rather than seeing it as a marginal beneficial skill optionally taught at the graduate level, we understand parallel programming as crucial basic skill that should be taught as an integral part of the undergraduate computer science curriculum. A practical training course developed for computer science undergraduates at Aachen University is described. Its goal is to introduce young computer science students to different parallel programming paradigms for shared and distributed memory computers as well as to give a first exposition to the field of computational science by simple, yet carefully chosen sample problems.     

Mod m arithmetic in binary systems

Even if the most common approach to mod m arithmetic is based on look-up tables, the use of binary systems is valid in those situations, such as large-moduli residue arithmetic or conversion processes, where a memory approach is not viable. A general approach to the problem of performing mod m computations in binary systems is presented. The proposed solution proves useful in various applications, such as converting binary integers to residue notation and mod m addition or multiplication. Examples are given together with possible VLSI implementations.     

Evaluating signs of determinants using single-precision arithmetic

We propose a method of evaluating signs of 2×2 and 3×3 determinants withb-bit integer entries using onlyb and (b+1)-bit arithmetic, respectively. This algorithm has numerous applications in geometric computation and provides a general and practical approach to robustness. The algorithm has been implemented and compared with other exact computation methods. This work was partially supported by the ESPRIT Basic Research Action 7141 (AL-COMII) and by NSF Grant CCR 91-96176. Part of this work was done while J.-D. Boissonnat was visiting Brown University.