Welp, did some testing last night, and no, it doesn’t look like inpout32 is really going to be any faster.
Damn shame because it was relatively easy to setup and use.
Quick reply from the authors(thank you) who basically said I could modify the device driver to receive the data within the driver, and then xfer to back to the user app. I have no idea how I would approach this, but I’m taking a look at the code now to see how feasible it will be based on what I know.
I guess the overall idea (again from the reply) is to reduce the number of switches between ring0 and ring3 modes. This makes perfect sense, and I have a feeling there is some minimum amount of time to switch here —- and no matter whose driver I use, I’m still going to run into the same problem.
Damn win2k has to protect its crap. Windows 98 under a 100-200mhz machine was PLENTY to do this earlier. But I really want something updated to run under win2k. Looks like I have to figure out either MapPhysToLin with winIO or code for inpout32…….