Tim,
Sorry, I can't test the patch easily. I'm working on my own
device driver using double-buffered dma to capture a
continuous stream of video data. We just got the whole
system (hardward + software) working yesterday.
As a result I'm not using the normal parport code. I thought
the patch looked reasonable.
On my own project, we need to run at something close to
the rated 2 megabyte/sec capacity of ECP mode. But the
dma hardware seems to run at 2 microseconds/byte on the
system I'm using (4 times slower than our goal). Since this is
the first PC I've looked at in this detail I don't know if this is
going to be typical. Do you have any experience in this
area? Are there faster dma controller chips? Or is this set
by some old standards (like ISA)?
Richard
-- Richard Stover email: richard@ucolick.org Detector Development Laboratory http://gardiner.ucolick.org/~ccdev UCO/Lick Observatory Voice: 831-459-2139 Natural Sciences Bldg. 2, Room 160 University of California FAX: 831-459-2298 Santa Cruz, CA 95064 USA FAX: 831-426-5244 (Alternate) ------------------------------------------------------------------------ To unsubscribe, send mail to: linux-parport-request@torque.net -- -- with the single word "unsubscribe" in the body of the message. --
This archive was generated by hypermail 2b29 : Thu Mar 23 2000 - 13:15:03 EST