SAN JOSE, Calif. – HP Labs continues to make progress on its long term vision of smart memories based on its memristors as alternatives to server CPUs. The devices are one of several new categories of chips likely to seize the moment of disruptive changes in data center technologies and workloads ahead, said an HP Labs researcher.
Separately, Hewlett-Packard Co. is expected to announce within weeks the next steps in its Project Moonshot, its work on ARM- and Atom-based servers. HP is working with a broad group of companies including processor providers AMD, Applied Micro, Calxeda, Cavium and Intel on the project.
So far HP has announced an Atom-based server using Intel’s Centerton processor. It suggested it would use cartridges to flexibly upgrade a single server chassis for a wide range of ARM- and Atom-based chips in 2013 and beyond.
On a three-to-five year horizon, HP Labs is working on what it calls "nanostores." The chips combine memristors and logic that could challenge microprocessors in a new era of designs based on novel system architectures and memory hierarchies, said Parthasarathy Ranganathan, an HP Labs researcher in a keynote at the Server Design Summit here.
“We have the opportunity for new building block,” said Ranganathan. “It’s really a 3-D stack amenable to traditional workloads and even more so to new workloads, really changing the game with potentially a hundred-fold increase in performance per watt."
@bobdvb: It's unclear because they haven't said much about the lo0gic part of the device.
Many researchers including some at Stanford and Berkeley have talked about kinds of smart memories before. HP's unique angle is using its memristor as the memory.
Turns out there are many logic blocks each suited for different jobs that HP Labs is exploring adding to memristors.
The idea is to invert the old idea of a memory hierarchy serving processors. Instead memory is central and there is a hierarchy (or taxonomy) of processing done on it.
It will be great if something useful comes from HP's nanostore and 3D stacking crossbars. However, I would have more respect for the researchers involved if they stood on the merit of their own R&D rather than continuing to use Chua's "memristor" as a PR gimmick.
It is really astonishing that HP’s Labs still believe in their “memristor” stuff.
Non-volatile memristive systems are conceptually defined by a set of characteristic mathematical equations. Thus, solid state memory devices should only be labeled "memristors" if they operate physically in accordance with this mathematical framework. However, up to now no one has been able to propose a reasonable physical model that satisfies these equations, although there are some claims appearing in scientific literature. Even HP Labs have not invented or found a device which works like a genuine, non-volatile memristive system. Their fabled memristor model which was presented in the “NATURE” paper “The missing memristor found” (Nature 453, 80-83 (2008)) suffers from severe flaws in its construction. This can be easily shown by analyzing the model under aspects of textbook electrochemistry.
What is termed "memristors" by HP are memory devices based on "resistance switching" effects. Resistance switching behavior is often observed on specific metal/insulator/metal structures after a soft-breakdown of the insulating material has occurred (electroforming step). These phenomena are well known since decades and are in no way related to the concept of memristor/memristive systems. Soft-breakdown can induce highly defective, filament-like structures somewhere in the insulating matrix which are susceptible to external interferences. Probably, most resistance switching effects result from localized chemical/physical phase transformations in these regions due to, for example, local heating or high-field electrolytic processes triggered by means of electric stressing. Localized effects at the nanoscale involve a lot of reliability and stability issues. SK Hynix and other companies seem to be aware of these problems.
So, what is the real intention behind all these “memristor” stories? HP is doing no favors to itself announcing time and again such “breaking” news.
I believe A.Sceptic's issue is not with "Hynix and other companies" but rather with those who write memristor papers and are either not aware of the physics issues or have made no real attempt to incorporate the actual physics into dynamic systems models (regardless of whether it is called a "memristor" or not).
The lead HP memristor scientist (Stan Williams) has publically stated in an earlier EETimes article that HP's memristor research is "essentially complete" and any delay is for business reasons blamed on Hynix. However, to my knowledge, there is no realistic model from HP or anyone else incorporating the known physics into a dynamic systems model (regardless of whether you call it a memristor or not). The lack of accurate physics models will make product design difficult and Hynix's engineers will likely need to rely on trial and error for manufacture. This will likely make it more costly and time consuming to manufacture "memristors".
The memristor terminology is probably for PR. Defects, especially charge trapping type, lend themselves to memory effects pretty easily, and nothing is ever defect free, so a lot of these defect-driven memories can appear under the right stress conditions.
Charge trapping models for resistance switching would be open to objections which apply to all models which do not involve stable atomic/ionic rearrangements, i.e., phase changes, in localized regions of the considered materials: the memory states last for several years without decay, and it is hard to see that non-equilibrium charge distributions could exist for so long in thin-film devices.
David Patterson, known for his pioneering research that led to RAID, clusters and more, is part of a team at UC Berkeley that recently made its RISC-V processor architecture an open source hardware offering. We talk with Patterson and one of his colleagues behind the effort about the opportunities they see, what new kinds of designs they hope to enable and what it means for today’s commercial processor giants such as Intel, ARM and Imagination Technologies.