Macronix Solves Flash Wear Problem
In brief: Macronix’ researchers buried a heater in the array to heat the tunnel dielectric, annealing out the disruptions & traps that might cause a bit to fail.
A prototype has so far been tested more than 100 million cycles and it shows no sign of impending failure. Researchers believe that it is likely to reach one billion or more cycles, but such testing will take several months. This just may be able to eliminate any concerns about flash endurance.
The technique also accelerates erase cycles, but Macronix’ researchers aren’t sure why.
This is one of those technologies that makes you wonder: “Why didn’t they think of that before?” Such heaters have been around for decades, and are the basis for phase change memory and Crocus’ unique thermal MRAM.
The finding has phenomenal implications: If NAND flash can be as economically manufactured with this feature as it can without, then all the sophisticated algorithms currently required to manage wear will suddenly be rendered obsolete. This should be particularly upsetting to my evil twin The SSD Guy because he just finished publishing an eight-part series explaining How Controllers Maximize SSD Life.
On the surface this looks like a very significant breakthrough for flash. Time will tell if the approach can be brought into mass production economically enough to solve flash wear, which is one of the thorniest problems of using flash memory.