Although the course was very well received, I never posted a link to it on The Memory Guy blog. This post is intended to correct that error.
The course runs 75 minutes and covers the basics of DRAM, non-volatile RAM, SRAM, NAND flash, NOR flash, mask ROM, and EEPROM. It explains each technology’s advances in size, cost and performance, leading up to the development of Continue reading
Crossbar says that the technology can put a terabyte onto a single chip. The company has already measured filaments as thin as 6nm, and is confident that it can be shrunk further and that it will support multilevel cells.
Crossbar’s device is a silver filament ReRAM with a difference. For one, the silver filaments are in standard silicon dioxide, probably the most Continue reading
Everyone knows that flash memory is about to hit its scaling limit – it’s right around the corner. We’re ready for it because it’s been right around the corner for more than a decade now. It’s so close we can taste it.
When will it happen?
One thing that is quite clear is that nobody knows when NAND flash will stop scaling. Everyone knows that it’s soon, but researchers continue to find ways to push the technology another couple of process nodes past where anyone thought it could possibly go, and they have been doing this since Continue reading
The IEEE Spectrum published an interesting article postulating that Russia’s recently-failed Mars probe may have suffered from bad memory chips. According to the Spectrum article the Russian government’s Official Accident Investigation Results faulted SRAMs:
The report blames the loss of the probe on memory chips that became fatally damaged by cosmic rays.
Both the main computer and the backup computer seem to have failed at the same time, Continue reading
Since ISSCC is a conference at which you meet the best and brightest minds in the industry it should come as no surprise that I was able to meet with several of the most forward-thinking industry luminaries. One of them explained to me a very fundamental difficulty with resistive RAMs (ReRAMs): These devices require a forward current to be programmed to a “1” and a reverse current to be set to a zero. This goes against the ideal crosspoint memory design in which a bit would consist of nothing more than a diode in series with a memory element. By inserting a diode, the current can only run in one direction, so a bit can be programmed or it can be erased, but not both.
Rambus announced that the company has acquired privately-held Unity Semiconductor, an alternative memory technology company for $35 million. Unity employees have joined Rambus and will continue to develop next-generation nonvolatile memory.
Unity has an interesting technology that has caught the eye of some leading memory firms, including Micron, who had an exclusive right to Unity’s technology. The company’s CMOx is based on oxygen ions moving within a semiconducting material. It’s one species of resistive RAM.
Although Unity has been trying for years to manufacture very high density nonvolatile memory chips, The Memory Guy is not aware that the company has yet produced the chips they have set out to make.
Elpida announced the development of a high-speed 64Mb non-volatile resistance memory (ReRAM) prototype using a 50nm process. The device was jointly developed with the New Energy and Industrial Technology Development Organization (NEDO), a Japanese-funded public institution.
Elpida will conduct further ReRAM development with Sharp Corporation, the National Institute of Advanced Industrial Science and Technology (AIST, another Japanese public institution) and the University of Tokyo.
It’s encouraging to see that Elpida still has its eye on projects into 2013 and beyond. The company is rumored to be working feverishly to find ways to stay in business through this year. Today’s DRAM market is a challenging one!