On 8/20/06, Timothy Miller <[EMAIL PROTECTED]> wrote:
The only problem I haven't totally resolved yet (in any case) is that
while DMA is going on, you really don't want to try to do a PIO to the
same device.  This isn't a logical problem so much as a physical one.
During the transfer of a DMA burst, the bus is tied up doing
something, and it's going to be doing it for a while.  Any attempt by
the CPU to access the bus is going to suffer a massive latency.
Imagine how many CPU cycles are wasted while waiting for 32 PCI bus
cycles at 33MHz.

In command stream mode the Radeon chips don't need to do any PIO. You
put commands in the command stream that write to the same registers.
It is a somewhat general mechanism, commands can write 1,2,3,4,5, etc
registers. Command blocks contain pairs of register numbers and
values.

DMA to/from the cards is overrated. Most apps load their textures into
the card and then never use DMA again.  DX10 specs virtual VRAM which
eliminates even more need for programmed DMA. Only a few apps read
textures back from the card.

--
Jon Smirl
[EMAIL PROTECTED]
_______________________________________________
Open-graphics mailing list
[email protected]
http://lists.duskglow.com/mailman/listinfo/open-graphics
List service provided by Duskglow Consulting, LLC (www.duskglow.com)

Reply via email to