For the NVDIMM in question, the whole point is for durability after a reboot or power loss. A fifteen minute cycle in which it would write its contents out to nonvolatile storage and then read it back, during which the firmware is too inept to notice that all the data is already loaded is a bug that should have been fixed. (In fairness, this was a pre-production model.)
Even ignoring the reboot time, SMBUS was needed to properly identify the device and to access its health-check data.
As for my database, it’s not intended for active-active HA setups — it’s intended for use on a small number of high quality machines. It has had zero meaningful data loss incidents in its entire time in production, and it’s extremely fast. But it has some other properties I don’t like and that would cause me to do it differently if I were to start over.
Somewhere I still have some actual battery-backed DIMMs (DRAM plus FPGA interposer plus awkward little supercapacitor bundle) in drawer. They were not made by Intel, but Intel was clearly using them as a stepping stone toward the broader NVDIMM ecosystem. They worked on exactly one SuperMicro board, kind of, and not at all if you booted using UEFI. Rebooting without doing the magic handshake over SMBUS [0] first took something like 15 minutes, which was not good for those nines of availability.
[0] You can find my SMBUS host driver for exactly this purpose on the LKML archives. It was never merged, in part, because no one could ever get all the teams involved in the Xeon memory controller to reach any sort of agreement as to who owned the bus or how the OS was supposed to communicate without, say, defeating platform thermal management or causing the refresh interval to get out of sync with the DIMM temperature, thus causing corruption.
I’m suspicious that everything involved in Optane development was like this.