Lag in Multiprocessor Virtual Reality

Lag in virtual reality (VR), i.e., the delay between performing an action and seeing the result of that action, is critical when trying to achieve immersion. While multiple, networked processors have been used to increase throughput, we concentrate on using multiple processors to reduce lag. To that end, we present a complete list of all possible lag sources in VR applications, review available lag reduction techniques, and investigate how these reduction techniques interrelate. We also introduce a new process-synchronization scheme that reduces lag. We evaluate the effectiveness of this synchronization scheme by software simulation as well as by actual lag measurements in our sample application.