I am interested in executing the CVI RTE in a real-time environment. Does anyone have experience doing this in ETS or RTX? Or do you have specific suggestions of a different way to get real-time performance from a CVI application.
The application I have in mind was developed this last year to run in an XPE environment using CVI 8.1. It works very well, but responding to interrupts, such as a FIFO interrupt from an A/D card, exhibits 10-30 milliseconds jitter, because there is a lot going on at the same time. I would like to get this down to something like 1 or 2 milliseconds jitter. The system is headless, so the OS overhead should be minimal -- com port, TCP services, and IDE I/O.
And no, this is not something I would ever consider doing in LabView. Besides the fact that I hate LabView, this application is more than 10,000 LOC.