On Mon, Sep 21, 2009 at 5:08 AM, Kenneth Ostby <[email protected]> wrote: > Hi, > > Timothy Normand Miller: >>As with Larrabee, I suggest that we provide dedicated texture >>hardware. We could cache the compressed data and use one decompressor >>or a small number to service all texel requests. I expect that random >>access to the graphics memory will have much higher latency than >>pushing all requests through a small number of decompressors. > > I agree on this as well, having dedicated texture hardware allows us to > offload a lot of the decompression we would otherwise have to do from > the cores. What we should try to build into the texture hardware is > support for decompressing the textures, plus maybe support for a simple > prefetching scheme. Since our basic working set is texture, we can > assume that we are going to, more or less, request addresses in a linear > manner. Thus, it should be simple to include a basic prefetching > algorithm.
Linear in 2D, not 1D. An expected "worst case" is where the texture will be read at a 270-degree rotation. To us, we might as well treat this as random. > > > I will try to address some of the other points later today. > -- Timothy Normand Miller http://www.cse.ohio-state.edu/~millerti Open Graphics Project _______________________________________________ Open-graphics mailing list [email protected] http://lists.duskglow.com/mailman/listinfo/open-graphics List service provided by Duskglow Consulting, LLC (www.duskglow.com)
