Michel =?ISO-8859- writes: > On Mon, 2002-05-13 at 22:04, Rog�rio Brito wrote: >> On May 12 2002, Michel D�nzer wrote: >>> On Sun, 2002-05-12 at 14:34, Rog�rio Brito wrote:
>>>> What is the problem with publishing the interfaces for that? I >>>> thought that ATI were an open-source friendly company. :-( >>> >>> They are IMHO. Every company seems to be afraid of releasing that >>> kind of information, I have an idea why but people tell me there's >>> no reason... >> >> Could you say what could be the possible reasons for ATI to >> not release the specifications? I'd be really interested to >> know. I promise that I won't start a flamewar if I don't like >> what I read. :-) > > My idea is it has to do with certain US laws, but what do I know. Companies license stuff from others. ATI might not be able to release the info. Perhaps "Who should I ask?" would be a better question for ATI. Plus imagine you worked there. You don't have authority to release the info. Who does? Does anyone? In theory the stockholders could sue if you give away anything that might offer competitors some help. Maybe you think you do have authority, but do you want to risk your job? > Right, but with a catch: the DMA transfer must complete > before the image can displayed. Exactly why? It isn't real nice to just DMA one frame on top of the next, but in this case it would be a dramatic improvement. At worst: You have an 85 Hz monitor, needing 11.76 ms per frame. If you can DMA in less time, then the DMA engine will keep ahead of the display. >>> Using an interrupt might help there. >> >> I don't understand this, sorry. :-) > > The chip could issue an interrupt when the DMA transfer is complete so > the CPU could do something useful while it's in progress. Then you suffer interrupt overhead. You should be able to do something useful while you wait, polling when you expect the DMA to be about done. -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
