We present an HPF implementation of BT, SP, LU, FT, CG and MG of the NPB2.3-serial benchmark set. The implementation is based on HPF performance model of the benchmark specific primitive operations with distributed arrays. We present profiling and performance data on SGI Origin 2000 and compare the results with NPB2.3. We discuss advantages and limitations of HPF and pghpf com-

Abstract. The Oxford Supercomputing Centre OSC1 was established in April 1998 to provide high-performance computing services to a consortium of Oxford University research groups. The main computer resource, an 84-processor SGI Cray Origin 2000 known as Oscar, is being deployed in a wide variety of research studies covering biological, medical, chemical, mathematical, physical and engineering to...

Gamification is defined as the use of game design elements in non-gaming contexts. It is been getting a lot of attention in recent years. However, the amount of research undertaken on gamification is limited. One of the problems it faces is sustainability. Designers might overlook the elements that increase sustainability due to lack of a standard framework that contains the essential component...

The shared-memory multiprocessor system recently has attracted a lot of attention because of its low cost and wide availability to the graphics researchers. In this paper, we show practical parallel solutions to the following volume graphics[4] problems: volume texture modeling, volume texture rendering, and voxelization for unstructured grid rendering. All these solutions process 2D and 3D arr...

The Nonconforming Spectral Element Method (NSEM) solves PDEs in complex geometries with high accuracy, however, it is an expensive method. Since parallel computation is eeective in decreasing CPU time, a parallel algorithm for the NSEM is presented. Implementations on SGI Power Challenge using MPI are evaluated in terms of measured speedup and parallel eeciency for schemes of one element and mu...

Methods using OpenMP directives have been studied to parallelize an inherently sequential GaussSeidel algorithm on shared memory computers. Both hyperplane and pipeline parallelization schemes have been implemented to a non-equilibrium real-gas flow simulation code. The effects of different parallelization strategies and grid sizes on the parallel efficiency have been investigated on SGI Origin...

This paper discusses the design and implementation of an interface that allows a debugger to obtain the information necessary to display the contents of the MPI message queues. The design has been implemented in the TotalView debugger, and dynamic libraries that conform to the interface exist for MPICH, as well as the proprietary MPI implementations from Compaq, IBM, and SGI.

An instantaneously trained artificial neural network schema is used to improve the interactive speed in very large scale scientific visualization. An instant learning algorithm is adopted to reduce the training time for user behavior analysis in billion-particle walkthrough on an SGI Onyx2 graphics server connected to a PC cluster.

We have developed a detailed chemical scheme for the degradation of the short-lived source gases bromoform (CHBr3) and dibromomethane (CH2Br2) and implemented it in the TOMCAT/SLIMCAT three-dimensional (3D) chemical transport model (CTM). The CTM has been used to predict the distribution of the two source gases (SGs) and 11 of their organic product gases (PGs). These first global calculations o...

FLY is a parallel treecode which makes heavy use of the one-sided communication paradigm to handle the management of the tree structure. In its public version the code implements the equations for cosmological evolution, and can be run for different cosmological models. This reference guide describes the actual implementation of the algorithms of the public version of FLY, and suggests how to m...