A multi-user Virtual World has been implemented combining a flexible-object simulator with a multisensory user interface, including hand motion and gestures, speech input and output, sound output, and 3-D stereoscopic graphics with head-motion parallax. The implementation is based on a distributed client/server architecture with a centralized Dialogue Manager. The simulator is inserted into the Virtual World as a server. A discipline for writing interaction dialogues provides a clear conceptual hierarchy and the encapsulation of state. This hierarchy facilitates the creation of alternative interaction scenarios and shared multiuser environment.

A parallelization of the Quicksort algorithm that is suitable for execution on a shared memory multiprocessor with an efficient implementation of the fetch-and-add operation is presented. The partitioning phase of Quicksort, which has been considered a serial bottleneck, is cooperatively executed in parallel by many processors through the use of fetch-and-add. The parallel algorithm maintains the in-place nature of Quicksort, thereby allowing internal sorting of large arrays. A class of fetch-and-add-based algorithms for dynamically scheduling processors to subproblems is presented. Adaptive scheduling algorithms in this class have low overhead and achieve effective processor load balancing. The basic algorithm is shown to execute in an average of O(log(N)) time on an N-processor PRAM (parallel random-access machine) assuming a constant-time fetch-and-add. Estimated speedups, based on simulations, are also presented for cases when the number of items to be sorted is much greater than the number of processors.>

We present here a study of parallelization of the Cooley-Tukey radix two FFT algorithm for MIMD (nonvector) architectures. Parallel algorithms are presented for one and multidimensional Fourier transforms. From instruction traces obtained by executing Fortran kernels derived from our algorithms, we determined the precise instructions to be executed by each processor in the parallel system. We used these instruction races to predict the performance of the IBM Research Parallel Processing Prototype, RP3, as a computer of FFT's. Our performance results are depicted in graphs included in this paper.

The combining of messages within a multistage switching network has been proposed to reduce memory contention in highly parallel shared-memory multiprocessors, especially for shared lock and synchronization data. A quantitative investigation of the performance impact of such contention and the effectiveness of combining in reducing this impact is reported. The effect of a nonuniform traffic pattern consisting of a single hot spot of higher access rate superimposed on a background of uniform traffic was investigated. The potential degradation due to even moderate hot spot traffic was found to be very significant, severely degrading all memory access, not just access to shared lock locations, due to an effect the authors call tree saturation. The technique of message combining was found to be an effective means of eliminating this problem if it arises due to lock or synchronization contention.

We present some straightforward algorithms for the generation and display in 3-D of fractal shapes. These techniques are very general and particularly adapted to shapes which are much more costly to generate than to display, such as those fractal surfaces defined by iteration of algebraic transformations. In order to deal with the large space and time requirements of calculating these shapes, we introduce a boundary-tracking algorithm particularly adapted for array-processor implementation. The resulting surfaces are then shaded and displayed using z-buffer type algorithms. A new class of displayable geometric objects, with great diversity of form and texture, is introduced by these techniques.

An object space method is given for interpolating between sampled and locally averaged signals, resulting in an antialiasing filter which provides a continuous transition from a sampled signal to its selectively dampened local averages. This method is applied to the three standard Euclidean dimensions and time, resulting in spatial and frame to frame coherence. The theory allows filtering of a variety of functions, including continuous and discrete representations of planar texture.