I have struggled with the PRU scratchpad, persisting because it seems that it could be a very powerful feature. In particular, the XCHG instruction (pseudo-op) has caused me hours of frustration to identify and diagnose a problem. It seems that XCHG (swapping current PRU register values for those in a specified scratchpad bank) does not work - it is effectively an XIN op. I researched and found only one bit of content about this, here <https://e2e.ti.com/support/arm/sitara_arm/f/791/p/340589/1189854>: The accepted answer was provided by a (supposed) TI employee. I find it hard to believe...
Is it possible that he PASM compiler accepts the XCHG instruction, and all the PRU documentation from TI documents this instruction, but it is not even implemented? I understand the "PRU is not officially supported" claim. -- For more options, visit http://beagleboard.org/discuss --- You received this message because you are subscribed to the Google Groups "BeagleBoard" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/beagleboard/42441994-13c9-4309-80f3-16b61c2f6e77%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
