- Sponsor:
- sigapp
No abstract available.
Experiences with the Intel Hypercube
This paper presents a comparative analysis of the performance of two different parallel algorithms for solving the prefix problem on the Intel Hypercube. Estimates of the key parameters that determine the cost of communication between nodes are also ...
A Mathematical Software Environment
Several hundred scientists and engineers work at Amoco Production Company's Tulsa Research Center. Naturally, scientific computing is an important part of their research in petroleum exploration and production. General purpose mathematical and ...
Incorporating software engineering techniques into a computer architecture course
This paper describes a computer architecture course which provided students with a thorough grounding in a non-vonNeumann computer architecture and also increased the understanding by the students of the size and complexity of the work which they will ...
Microcomputer technology for drilling
Drilling costs are a significant portion of exploration and production budgets. For this reason, the use of complex mathematical models to optimize drilling operations began in the early 1950s, at roughly the same time as the introduction of the first ...
The Oklahoma advanced parallel processing research facility
An advanced research facility has been installed in the Norman campus of the University of Oklahoma. This facility will support innovative research in parallel processing, vectorization and supercomputing. In this talk the advanced nature of the ...
The versatility of color mapping
Extracting information from large amounts of data by using tables of numbers is difficult. Often, such data can be presented more effectively with graphics. The reduction in the cost of memory has allowed more powerful display systems to provide for the ...
The study of a new parametrized spline algorithm
The method applied most frequently in drawing a curve to interpolate a set of given points without spoiling the aim for “shape preserving” is parametrized cubic spline method; however, possibility of producing a bad result on “shape preserving” exists. ...
Calculating the block preconditioner on parallel multivector processors
A parallel algorithm for the preconditioning of nonsymmetric sparse linear systems generated by various discretizations of highly coupled partial differential equations in two spatial dimensions, is discussed. Gathering of the highly coupled unknowns, ...
Design issues in distributed multidatabase systems
Many reports have been published on the design strategies employed in the development of multidatabase systems. This paper examines some of these strategies and compares the design of the ADDS system to other efforts in the development of multidatabase ...
A parallel Data Base Machine for query translation in a distributed database system
A special purpose Data Base Machine (DBM) designed to translate queries between data models is examined. The DBM will provide a means of direct communication between different DBMSs in a distributed database system. The design utilizes the concept of ...
Dividing patterns into deterministic regions
The LR(k) parsing provides a deterministic table driven algorithm for pattern recognition. An LR parser scans the text from left to right while reducing handles. The process is sequential in nature. This paper describes a parsing method based on SLR(1) ...
Applying program restructuring to dataflow environments
This paper describes the effects of program restructuring in a dataflow environment. Previous studies showed that dataflow programs can exhibit locality and that a memory hierarchy is feasible in a dataflow environment. This study shows that the order ...
Index Terms
Proceedings of the 1986 workshop on Applied computing



