Timothy Miller wrote: > As our own PCI controller matures, we're going to want to test it in > situ. The trouble will be when it fails to work properly, and the > solution will be to use some device to watch the PCI bus activity and > let us observe them. Such "PCI bus analyzer" devices to exist, but > they cost a fortune. Then it occurred to me that perhaps another OGD1 > board would be ideal for this. It's got plenty of memory to store a > large window of bus activity, and with the user I/O pins, we could rig > up an RS232 port on it that we could use to communicate with the > device. Moreover, it had occurred to me that we could make some money > selling such a product. Of course, we couldn't sell it for the same > amount as competing products (because it's open source... you can just > buy and OGD1 board and download the FPGA code), but we could sell it > pre-installed with support at a premium. The only thing about this > that's a major drawback is that the market is waning rapidly as PCI > Express takes over. > > Thoughts? > How much speed can we get from the XP10? Enough to do any meaningful timing captures? According to the raw specs, we could theoretically sample at 10x the PCI bus clock for a 33Mhz bus but the front end would have to be very carefully crafted to ensure the timing was fast enough.
BTW, I always find it amusing when I'm doing google searches and the OGP wiki or something related is the top result as it is with "Lattice XP10". Patrick M _______________________________________________ Open-graphics mailing list [email protected] http://lists.duskglow.com/mailman/listinfo/open-graphics List service provided by Duskglow Consulting, LLC (www.duskglow.com)
