Philip Brown wrote: > > On Mon, Dec 10, 2001 at 05:53:32PM -0800, Gareth Hughes wrote: > > On Mon, Dec 10, 2001 at 05:33:09PM -0800, Philip Brown wrote: > > > ... > > > But... isnt there a straightforward mmap type way to access the RAM on > > > board the card, then? > > > Or is it usually "load the data to the aperture, then copy it > > > into card-local RAM from there" ? > > > [or via the "drmDMA" stuff, I suppose?] > > > > Why do you want to touch the framebuffer (video memory, that is)? > > That's one way to make your 3D graphics go really slowly... > > I dont know... I'm new at all this :-) > > I just figured that since it only takes about 8 megs of RAM to hold all the > pixels for high-res 24-bit displays, then if a card has 32 megs of RAM or > higher, then programs have to be doing something interesting with the rest > of the ram. > I thought under 2d, it gets used for sprites, and other various cached > pixmaps. So in 3d, it got used to store textures or something. > So I'd better know how to enable access to it, if I want to implement DRI > on my platform.
Just look at /proc/pci or similar on a linux box. All the pci cards have memory ranges assigned to them - that's where your on-card memory lives in the physical address space. The pci bus hardware diverts memory accesses in this range to the appropriate card. But don't use it if you can avoid it, as Gareth mentioned, because it is as slow as a dog. Keith _________________________________________________________ Do You Yahoo!? Get your free @yahoo.com address at http://mail.yahoo.com _______________________________________________ Dri-devel mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/dri-devel
