I think what can be done alternative before hardware failure. There could be several factors that could trigger this error, one of which is the FW versions (and the most common) but if they are up to date, maybe you can check "memory operating mode" in the memory settings in the BIOS. Sometimes 11G could have problems if "optimizer mode" was selected, and users who chose "advanced ECC mode" stated that the problem was gone. Of course, if the memory configuration supports this feature.
please check this guide pg131 and check sample memory configurations in the following pages https://downloads.dell.com/manuals/all-products/esuprt_ser_stor_net/esuprt_poweredge/poweredge-r710_owner%27s%20manual_en-us.pdf
Apart from that, power drain can be done, after server shutdown disconnect server from all power cables, network cables, all PSUs remove, hold down the power button continuously for at least 30 seconds, wait about 2 minutes before powering on server.

If these do not work, hardware failure is suspected. You can try to understand whether the problem is in the memory or in the slot by X-testing the memories(You are warned by replacing the memory, for example DIMM_A3 with solid memory on another channel, DIMM_B3). One step further may be a problem with the channels going to the processor.

Thanks Erman, but this was working perfectly back in July and I haven't changed anything since.  When I last checked it was all up to date anyway.

Thanks Erman, I'll give that a try and report back.  It may take a while!

Andy

I looked in the BIOS, but it wouldn't allow me to change the memory settings, so off with the lid. I did the power drain trick and re-seated all the A Bank DIMMs.  Powered back up - and success, all 128GB back again.

Thank you Erman!