Acoustic Assisted Magnetic Recording is invented

Read an article today about Acoustic Assisted Magnetic Recording (See Oregon State University article Researchers invent “acoustic-assisted magnetic recording”).

Just like heat assisted magnetic recording (HAMR, see our Disk density hits new record… post) which uses laser beams, acoustic assisted magnetic recording (AAMR) uses ultrasound to heat up a spot on media to help it be magnetized.

Why heat up media?

The problems with the extremely dense storage coming out of the labs these days is that the bits are becoming so small that’s it’s increasingly hard to insure that bits close by aren’t being disturbed when a bit is modified. This has led to an interest in shingled writes which we discussed in Sequential only disks and Shingled magnetic recorded disks posts.

But another possibility is to add heat to the process to isolate a bit on magnetic media. In this way a heated bit will be changed while its cooler neighbors are left alone.

I was at the dental hygenist the other day and she was using a new probe which used ultrasound to break up the plaque. In this case, it was also spewing water to cool the tip.  In any event, it appears as if ultrasound can be used to heat up, break stuff and image soft tissue, pretty versatile technology.

Is AAMR better than HAMR?

The nice thing about AAMR is that it can potentially be made with all solid state electronics and as such, wouldn’t require any optical componentry like HAMR.   So in the race against HAMR this could be a crucial edge and thus, could potentially be much easier to fabricate for use in tomorrows disk drives.

I foresee some possible problems with the technology, such as what is size of the heated spot and will the ultrasound emitter need any cooling (like the dental probe).

But it all seems like a reasonable and  logical extension of HAMR technologies being developed in labs today. Also, AAMR could quite probably could make use of the same thermally activated media developed for HAMR applications. Not having to come up with a new media formulation should help it get out of the lab even quicker. That is, if its other problems can be worked out.

In the post on HAMR, it had achieved a Tb/sqin in the lab, as the new media density high watermark.  As far as I could tell from the information published on AAMR, there were no new density records being discussed. However, if AAMR is able to achieve anything close to HAMR densities, we are in for larger capacity disk drives for another decade or so.


Photo Credit: AAMR head assembly by Oregon State University


7 grand challenges for the next storage century

Clock tower (4) by TJ Morris (cc) (from flickr)
Clock tower (4) by TJ Morris (cc) (from flickr)

I saw a recent IEEE Spectrum article on engineering’s grand challenges for the next century and thought something similar should be done for data storage. So this is a start:

  • Replace magnetic storage – most predictions show that magnetic disk storage has another 25 years and magnetic tape another decade after that before they run out of steam. Such end-dates have been wrong before but it is unlikely that we will be using disk or tape 50 years from now. Some sort of solid state device seems most probable as the next evolution of storage. I doubt this will be NAND considering its write endurance and other long-term reliability issues but if such issues could be re-solved maybe it could replace magnetic storage.
  • 1000 year storage – paper can be printed today with non-acidic based ink and retain its image for over a 1000 years. Nothing in data storage today can claim much more than a 100 year longevity. The world needs data storage that lasts much longer than 100 years.
  • Zero energy storage – today SSD/NAND and rotating magnetic media consume energy constantly in order to be accessible. Ultimately, the world needs some sort of storage that only consumes energy when read or written or such storage would provide “online access with offline power consumption”.
  • Convergent fabrics running divergent protocols – whether it’s ethernet, infiniband, FC, or something new, all fabrics should be able to handle any and all storage (and datacenter) protocols. The internet has become so ubiquitous becauset it handles just about any protocol we throw at it. We need the same or something similar for datacenter fabrics.
  • Securing data – securing books or paper is relatively straightforward today, just throw them in a vault/safety deposit box. Securing data seems simple but yet is not widely used today. It doesn’t have to be that way. We need better, more long lasting tools and methodology to secure our data.
  • Public data repositories – libraries exist to provide access to the output of society in the form of books, magazines, papers and other printed artifacts. No such repository exists today for data. Society would be better served if we could store and retrieve data if there were library like institutions could store data. Most of these issues are legal due to data ownership but technological issues exist here as well.
  • Associative accessed storage – Sequential and random access have been around for over half a century now. Associative storage could complement these and be another approach allowing storage to be retrieved by its content. We can kind of do this today by keywording and indexing data. Biological memory is accessed associations or linkages to other concepts, once accessed memory seem almost sequentially accessed from there. Something comparable to biological memory may be required to build more intelligent machines.

Some of these are already being pursued and yet others receive no interest today. Nonetheless, I believe they all deserve investigation, if storage is to continue to serve its primary role to society, as a long term storehouse for society’s culture, thoughts and deeds.