Show simple item record

dc.contributor.authorLastra, Anselmo A.en_US
dc.contributor.editorW. Strasseren_US
dc.date.accessioned2014-02-06T14:30:48Z
dc.date.available2014-02-06T14:30:48Z
dc.date.issued1995en_US
dc.identifier.isbn-en_US
dc.identifier.issn-en_US
dc.identifier.urihttp://dx.doi.org/10.2312/EGGH/EGGH95/043-049en_US
dc.description.abstractPerformance, as measured by the number of primitives rendered per second, has been the most important rendering system design consideration while latency, the amount of time it takes to render an image, has largely been ignored. This is because a moderate amount of latency is not an issue for traditional interactive systems controlled by joysticks. However, latency has emerged as a major consideration when rendering for immersive systems, especially those using head-mounted displays. Maintaining low overall system latency is very important to create an illusion of presence in a virtual environment and very significant contribution to total system latency is the time it takes to generate an image. This paper examines some possible ways to reduce latency in the PixelFlow graphics computer.We first describe the standard rendering software for PixelFlow, and derive an expression for the time to render an image. We then propose two alternative software systems for the PixelFlow hardware. and derive expressions for the rendering latency. When we compare latencies for some common application scenarios, we find that the two prop~sed systems render with lower latency than the standard hlgh­ throughput system, but find that the benefits are not enough to outweigh the costs.en_US
dc.publisherThe Eurographics Associationen_US
dc.titleReducing Latency on PixelFlowen_US
dc.description.seriesinformationTenth Eurographics Workshop on Graphics Hardwareen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record