Micron Technology and Intel announced today (6 December, 2011) that the two companies are sampling a 128 gigabit (that’s 16 gigabytes) NAND flash chip manufactured by the company’s IMFT joint venture.
This is a doubling of the capacity of the 64Gb chip the companies announced in April, but they assure us that the size of the die hasn’t doubled, and the accompanying photo supports this. Intel tells us that the die will fit into standard BGA and TSOP packages.
Furthermore, the companies announced that the 64Gb chip announced in April is now in volume production.
The companies’ willingness to produce 20nm chips at double the density of the original 64Gb chip is a validation of their 20nm process and their confidence that this technology will yield well even with a significantly larger chip.
The IMFT 20nm “planar” process differs from other companies’ technologies in that the memory cell is symmetrical – it has the same dimensions in the horizontal as in the vertical directions. Other companies have resorted to asymmetrical cells for their smaller process generations, yielding larger die sizes for process that appear, in print, to be more aggressive than IMFT’s. IMFT is able to manufacture a symmetrical cell through the use of a High-K metal gate stack (the subject of a later post) and an ONO gate dielectric (another upcoming post.)
Intel and Micron proudly point out that this chip supports the manufacture of a 1-terabyte memory card through a commonly-available 8-die stack.
New features supporting high-speed interfaces were less loudly trumpeted, but testify to both companies’ focus on providing flash to meet the needs of computing devices. The chip supports the ONFi 3.0 interface to blast out 333 million transfers per second of data, and the chip has been internally designed to facilitate this high data rate. The page size has been increased from 8 kilobytes to 16 kilobytes.
Objective Analysis follows the NAND flash market very closely, and sells reports on its website detailing the workings of the market with enough detail to allow the reader to predict upcoming trends and price moves.
