Yes , you're right . in bulk silicon , eDRAM needs a collar oxide (rather thick oxide on the walls of the top of the trench) to prevent a parasitic NMOS transistor to turn on. With SOI substrate , you don't need it anymore.
I did not mean to imply that SOI was required for eDRAM but that SOI was exploited by IBM's more recent eDRAM uses (i.e., linked). To confirm this vague recollection I found John E. Barth's 2008 presentation "eDRAM to the Rescue" in which it is stated "Use the Buried oxide to simplify the process & reduce parasitics – half the cost of bulk eDRAM".
In hindsight I should have been more clear (or even better searched for the above statement rather than rely on recollection).
MBA saleswomen Carly Fiorina and Meg Whitman ruined the once great hardware company HP. Now Rometty with experience mostly in sales is shutting down Hardware mfg at IBM. The US has had to pay a heavy price for women's equality ! Engineers and hardware guys have the handicap that they need capital to do most anything significant so these airhead MBAs in pantsuits sent by Wall St. can boss over them.
One cannot be in the electronics industry for long without being aware of the contributions of IBM, and admiring the transitions they have made over the years.
For this topic, IBM invested in custom development (fabs, design, eda) at a time when literally these markets did not exist externally. In the meantime, the world has significantly changed, and it is not clear whether these custom techniques in fact provide significant competitive differentiation for their server class products. Plenty of companies (HP, EMC, etc) seem to find a way to build compelling products without these investments.
Like any large organization, I expect it is difficult to change gears, but I suspect there is little choice. Inspired leadership would figure out how to utilize the talented individuals within these organizations in a more productive manner. At least, that is the hope.
There's a general problem with comanies:The stock market punishes them in long term projects. Attacking intel would be such project. Why behave in such manner ? Because stock investors basically look for short term gains. Invest in long term projects - and you decrease your appeal.  is a nice explanation of this.
That's why you get companies today hoarding cash , in a world so filled with technological opportunies.
While it's no substantial change for microelectronics, IBM is signaling fairly clearly that it's never going to invest in any new opportunity in hardware because of the commodity disaster that is the cloud.
I feel for this IBM employee that sees good technologies with opportunities to continue differentiation from competitors, but the sad truth is that when the buck stops at the C-level, IBM will never spend money they could use to buyback shares to invest in opportunities that might perhaps someday grow their hardware businesses. Not organically, and not through acquisition. Not unless something radically changes at the top levels of management.
You might look at GE reinvesting in being a maker of tangible things and think it could happen to IBM, too. But there's no bellweather moment for IBM like GE Capital pulling the whole conglomerate down like an anchor. IBM will continue to act like the share price is the company and all its worth, and continue to view any investment in its hardware business as detrimental. For the sake of the employees, it is hard not to hope they sell microelectronics entire.