Improving Performance of Virtual Reality Applications Through Parallel Processing

Abstract

Abstract. DLoVe (Distributed Links over Variables evaluation) is a new model for specifying and implementing virtual reality and other next-generation or "non-WIMP" user interfaces. Our approach matches the parallel and continuous structure of these interfaces by combining a data-flow or constraintlike component with an event-based component for discrete interactions. Moreover, because the underlying constraint graph naturally lends itself to parallel computation, DLoVe provides for the constraint graph to be partitioned and executed in parallel across several machines, for improved performance. With our system, one can write a program designed for a single machine but can execute it in a distributed environment with minor code modifications. The system also supports mechanics for implementing or transforming single user programs into multi-user programs. We present experiments demonstrating how DLoVe improves performance by dramatically increasing the validity of the rendered frames. We also present performance measures to measure statistical skew in the frames, which we believe is more suitable for interactive systems than traditional measures of parallel systems, such as throughput or frame rate, because they fail to capture the freshness of each rendered frame.

An actor-based distribution model for Realtime Interactive Systems

“…Intra-node distribution, aka clustering, has been a well-proven concept to provide the computational power for RIS applications [25,6,4,18,22]. Typically, clustering is used to serve multiple stereoscopic displays or to perform highly complex computational simulations in real time.…”

A pipeline virtual environment architecture for multicore processor systems

“…DLoVe provides a method for developing parallel applications that are distributed over several machines [10]. Relationships between objects are defined using a constraint graph.…”

“…Several works have focused on parallelizing specific aspects, such as collision detection [13,21,39,44,46], physical model updating [25,29,39], and rendering [11,20,22,28,30,38,45]. Other approaches provide a broader framework to define a VE and parallelize its workload [4,10,18,19,36,40,41].…”

A Methodology for Architectural Design of Concurrent and Distributed Software Systems

“…This feature, in turn, allows faster and more dependable systems. Examples of distributed and concurrent software systems include: data-intensive systems, which include centralized, distributed, parallel, or federated-database systems; computationally-intensive systems, which include grid computing and bioinformatics systems; and event-intensive software systems using middleware, which include mobile computing and network monitoring systems, and virtual environments that demands highly concurrent and distributed systems [36].…”