Taiwan engineers defeat limits of flash memory

[Drone]

We heard of HAMR and salty HDDs and now it's getting even better, this time for NAND. Flash memory can get its life prolonged Significantly ...

Taiwan-based Macronix has found a solution for a weakness in flash memory fadeout. A limitation of flash memory is simply that eventually it cannot be used; the more cells in the memory chips are erased, the less useful to store data. The write-erase cycles degrade insulation; eventually the cell fails. "Flash wears out after being programmed and erased about 10000 times," said the IEEE Spectrum. Engineers at Macronix have a solution that moves flash memory over to a new life. They propose a "self-healing" NAND flash memory solution that can survive over 100 million cycles.

Self-healing lol just like the The Ol' Canucklehead.

And guess what ... life-giving workaround is ... heat

They redesigned a flash memory chip to include onboard heaters to anneal small groups of memory cells. Applying a brief jolt of heat to a very restricted area within the chip (800 degrees C) returns the cell to a "good" state. They said that the process does not have to be run all that often. According to project member Hang‑Ting Lue, the annealing can be done infrequently and on one sector at a time while the device is inactive but still connected to the power source. It would not drain a cellphone battery, he added. Macronix estimates that the flash memory cells could beat the 10,000 cycle limit by lasting for as much as for 100 million cycles but a commercial product is not imminent.


Source

 

[de.das.dude]

so.. a normal SSD chip dies after 10000 cycles?

 

[McSteel]

@de.das.dude: A chip is a collection of flash cells. Cells are organized into pages, typically ~1000 cells per page. Pages are then organized into blocks, 32, 64, 128 pages per block exist. Chips can have from one to eight blocks.

But to answer your question, a mediocre SSD will endure about 10GB of random writes each day for 3 years before starting to wear out. Even then, as writes become impossible, reads will still be possible for some time, meaning you can copy your data before the drive fails completely.

@Drone: I don't see how flash-heating the flash (heh) will help with anything, long-term... All heat does is randomize the electron distribution between the substrate and the floating gate. Flash cells degrade because electrons that are tunneled into the floating gate from the substrate can leave the floating gate at random (on average, that's literally a one-in-a-billion chance when accessing a cell). Also the substrate "evaporates" slowly, as the electrons rushing through the depletion region can sometimes push out substrate atoms, thus damaging/degrading it. All other degradation occurs as a direct consequence of the way NAND flash is organized and engineered. Until I see where exactly the heat is applied, how, and why it should help with anything, all this is simply baseless sensationalism.

 

[Drone]

all this is simply baseless sensationalism.

Baseless what? I don't get yr point They'll propose and demonstrate their "high-temperature" flash at presentation.

 

[McSteel]

Macronix estimates that the flash memory cells could beat the 10,000 cycle limit by lasting for as much as for 100 million cycles but a commercial product is not imminent.

Meaning they're still working on it. And until they provide a very detailed explanation as to why heat even works as a solution (or even a workaround), and until there is a working prototype, I call shenanigans.