Brian Bailey writes:
Moore’s Law may not be running out of steam, but it may be running out of money, as scaling to smaller geometries becomes more cost prohibitive. We also have an insatiable appetite for memory these days, but our tastes are changing from DRAM to nonvolatile memory—a market largely served by flash devices. Whereas DRAM can possibly scale down to 1 nm, we are already encountering floating-gate scaling problems for NAND flash. The answer to the scaling problem appears to be growing devices “up”; the question is how best to do it.
Three-dimensional die stacking uses a silicon interposer and TSVs (through-silicon vias) to connect the stacked dice electrically, allowing the integration of multiple, smaller dice—each processed using an optimal technology—within a package. Many memory manufacturers are already creating 3-D die-stacked chips in production quantities (Figure 1), and the technology’s use for memories paves the way for its use elsewhere.
More-than-Moore memory grows up - [Link]
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 10,000 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” NAND flash memory - [Link]
Brian Bailey writes :
Flash memory has very quickly risen from being an obscure memory type to perhaps becoming the dominant memory type for many devices, including music players, cell phones, tablets and now increasingly servers and mainstream PCs. But flash memory does not scale quite as well as the more traditional DRAM that it is replacing. It is thought that DRAM can scale down to 1nm whereas we are already hitting some problems with the scaling of the floating gate in NAND flash. It is not thought that planar NAND can go below 10nm which is only a couple of processes steps away from where we are today.
3D NAND flash is coming - [Link]
Hot off the heels of last month’s Raspberry Pi manufacturing deal with Sony, element14 today announced its continued partnership with the Raspberry Pi Foundation, launching an upgraded 512 MB version of the credit card-sized development board. Featuring double the RAM, the higher performance mini-computer is suited to multimedia, high-memory and mobile applications. The additional memory is also an enabler to allow the Raspberry Pi to run a future version of an Android 4.0 operating system.
The $35 Raspberry PI 512MB board is available now at element14 on a first come first served basis through its brands Newark element14 in North America, Farnell element14 in Europe, and element14 in Asia Pacific, as well as through subsidiaries CPC in the UK and MCM Electronics in the US.
Members of the element14 Community are invited to join the discussion online and share ideas and plans for the Raspberry Pi on the dedicated Raspberry Pi Group, bolstering more than 7,000 new members from across the globe. Plus, make sure to check out the revolutionary board and accompanying accessories on display at electronica in Munich, Germany on November 13-16, 2012.
The full press release is included below with additional details. Please let me know if you have any questions or would like to speak with an element14 representative about the new Raspberry Pi development board and its impact on the programming revolution.
Element14 launches new Raspberry Pi Board; drives programming revolution forward - [Link]
If you have a micro-controller based application and you face the problem with insufficient memory space, the micro-drive uSD-G1 may be an ideal solution for you.
The micro-DRIVE uSD-G1 is an extremely compact high performance “Embedded Disk Drive” module that can be easily added to anymicro-controller design that requires a DOS-compatible file and data storage system.
Most micro-controllers have small and limited on-chip memory. For those applications that require large volumes of data, the uSD-G1 with the GOLDELOX-DOS chip is a simple solution in a form of a tiny ‘drop-in- module’. A simple serial interface is all that is required to take away the burden of low level design that would otherwise be required for the host controller. The micro-DRIVE module utilises common microSD memory cards of up to 2GB of capacity as its medium. A handful of straightforward commands provide direct access to the onboard memory card or storing and retrieving any size or type of data. Access to the card can be at (FAT based)
Don´t be limited by a memory space! - [Link]
Researchers at Purdue University (USA) are developing a new type of computer memory that could be faster than the existing memory devices and consume far less power than flash memory. The devices combines silicon nanowires with a ferroelectric polymer, which is a material that switches polarity when an electric field is applied, to make storage cells whose polarity can be read as digital ones and zeros.
The new technology, which according to the researchers is still in a very nascent stage, is called FeTRAM for “ferroelectric transistor random access memory”. FeTRAM devices are nonvolatile, which means that data is retained in the absence of power. They could potentially use only 1% of the power of current flash memory devices, although the current version consume more power because it is not properly scaled. [via]
Radically new memory technology - [Link]
This is interesting. Researchers are trying to improve Flash memory density and retention time by using graphene structures. From IEEE Spectrum: [via]
Nanotechnology has a somewhat infamous relationship with flash memory. It has usually taken on the role as its adversary, such as in the case of Nantero or IBM’s Millipede project, and walked away with less than encouraging results.
So I was interested to see that researchers were using graphene as a platform for flash memory that appears to outperform other flash memory structures. If you can’t beat ‘em, join ‘em.
Researchers from UCLA, IBM’s T.J. Watson Research Center, Samsung Electronics, Aerospace Corporation, and the University of Queensland, team led by Kang Wang have recently published in ACS Nano an article entitled “Graphene Flash Memory” that demonstrates that graphene may have what it takes to outperform current flash memory technology.
As I have suggested in my post from last week, researchers are not breaking their backs trying to overcome graphene’s lack of band gap as much now as they are instead looking for ways to exploit its intrinsic strengths.
In this case, the researchers were trying to take advantage of graphene’s high density of states, high work function, and atomic thinness.
Graphene-based Flash Memory - [Link]
JeeLabs has a very informative post about memory usage on the ATMega, along with some Arduino sample code and an explanation of how bad memory management can cause sketches to fail. More from Jean-Claude: [via]
Sometimes, it’s useful to find out how much memory a sketch uses.
Sometimes, it’s essential do so, i.e. when you’re reaching the limit. Because strange and totally unpredictable things happen once you run out of memory.
Running out of RAM space is the nasty one. Because it can happen at any time, not necessarily at startup, and not even predictably because interrupt routines can trigger the problem.
There are three areas in RAM:
static data, i.e. global variables and arrays … and strings !
the “heap”, which gets used if you call malloc() and free()
the “stack”, which is what gets consumed as one function calls another
The heap grows up, and is used in a fairly unpredictable manner. If you release areas, then they will be lead to unused gaps in the heap, which get re-used by new calls to malloc() if the requested block fits in those gaps.
At any point in time, there is a highest point in RAM occupied by the heap. This value can be found in a system variable called __brkval.
The stack is located at the end of RAM, and expands and contracts down towards the heap area. Stack space gets allocated and released as needed by functions calling other functions. That’s where local variables get stored.
ATMega Memory Usage – [Link]
In memory of the patent Ben North and Oliver Nash have come up with a 32-bit core memory Shield for the Arduino! Check out the great report at the project page on how the memory works. They Include all the Eagle files, Gerber files, parts list, and Arduino code for the boards as well.
Core Memory Then and Now – [Link]
Engineering researchers at the University of Michigan have found a way to improve the performance of ferroelectric materials, which have the potential to make memory devices with more storage capacity than magnetic hard drives and faster write speed and longer lifetimes than flash memory. [via]
Fundamental discovery could lead to better memory chips – [Link]