Slashdot Mirror
Scientists Unveil Most Dense Memory Circuit Ever Made
adamlazz writes "The most dense computer memory circuit ever fabricated, capable of storing around 2,000 words in a unit the size of a white blood cell, was unveiled by scientists in California. The team of experts at the California Institute of Technology (Caltech) and the University of California, Los Angeles (UCLA) who developed the 160-kilobit memory cell say it has a bit density of 100 gigabits per square centimeter, a new record. The cell is capable of storing a file the size of the United States' Declaration of Independence with room left over."
I know DNA has been proposed as a storage mechanism before. Since the immense human genome fits inside a cell, wouldn't DNA offer much denser storage?
And have a stray biological virus get in and alter my computer's DNA-based memory?
I wouldn't want to think what the computer would use to alter its DNA-based memory fast enough to be useful, let alone what would happen if it escaped and latched onto an organism.
Oh, say does that Star-Spangled Banner entwine / The myrtle of Venus with Bacchus's vine?
You know what I hate? Articles that show the scale of whatever they're talking about in obscure ways, like "size of a red blood cell" or "as long as eighteen schoolbuses lined end to end". Next time, just tell us the actual size and we can make that approximation ourselves!
d12
With 100 Gigabits per square cm, that means that a standard 3.5" platter would hold about 25 Tb of data, or about 3.1 terabytes of data.
Not as impressive with the new 1 TB drives coming out now.
I assumed a word in the data storage sense. n bits to a word. Then I thought "wait a minute, which architecture?".
Reality is fluffy!
As a Read only option, I suspect. The problem isn't really data density, it's data access speed. Three terrabytes of storage isn't going to do you much practical good if it takes two hours to find and recover the bit of information you want.
A positive attitude may not solve all your problems, but it will annoy enough people to make it worth the effort.
Why not just say "densest"?
In all seriousness, I know how long a London Bus is, I know that an elephant is pretty heavy, I know roughly how much shelf space the Encyclopedia Britannica takes up and I know tall buildings can be quite tall.
But I have no real concept of how big a white blood cell is, or how much some thousand words (how many thousand? It's out my mind now that it's off the screen...) really is.
For all I know, the hard drive in my computer could be storing 600 birthday cards per germ already and I wouldn't have a clue.
Anyone care to quote how fast the Concorde went in Ford Escorts per millisecond? (the link will give you a good start)
Is crushing a suspect's child's testicles illegal?
John Yoo: "No, [if] the President thinks he needs to do that."
- Is this volatile or non-volatile memory?
- What size word are they using?
- If non-volatile, what kind of endurance can be expected? What about data retention? It doesn't matter how small the memory is if the data only lasts 5 minutes. (Yes, I'm sure there would be applications even for that, but you get the point.)
- What are the write and read times?
- If volatile, does the data need to be refreshed continuously, or will it hold its value as long as power is applied?
- How much power is required for different operation?
Okay, so maybe I was expecting too much. But they could've at least given some of the most basic details, like word size (damned marketing dept!).There is a large class of data storage requirements that could be met with a two hour seek time. As long as the throughput is there, it could replace tape drive type storage applications, for example.
Or extremely large databases, which may be 99.995% write. Archival storage would be another example, if the medium proved hardy enough.
While it won't replace RAM or hard drives, I would LOVE to see extremely high density storage of this type.
Um... gigabits per square centimeter is a horrible storage density metric. We need to deal with volume - unless we suddenly moved to a 2-dimensional universe - and even volume isn't perfect. For a drive platter do you only count the magnetic medium, or the underlying material as well? What about the space between platters or the read/write mechanism? I could have great storage density, but it wouldn't do me much good if I needed an entire scanning tunneling microscoope to read it.
Reading code is like reading the dictionary - you have to read half of it before you can go back and understand it.
Not a reliable media. Biological media, especially if it's based on Human DNA would potentially suffer from disease or short lifespan (begging the question of a special environment to keep it functional and stable). Non-living cells of DNA could be used to circumvent disease and lifespan issues, however they would deteriorate far more rapidly under any known method of reading (be it electrical, photo-reactive, irradiated, or chemical)
A further set of issues, irradiation. Especially at such a small size, there's a higher danger of DNA material becoming corrupt due to mutation. Inside of a box filled with magnetic fields, electrical fields, high temperature, and continually higher frequency RF...well, I wouldn't be confident that my G wouldn't randomly mutate into a C.
It's not a bad idea at all, it's just that science isn't anywhere close to being capable of using this as a reliable medium inside of a computer.
As others have said, it seems that it would have to be read-only unless somebody figures out how to control irradiated mutation...then who needs a computer, we can change our own DNA to become more capable than any computer we could ever build. Wow, I've seen too many episodes of Dark Angel
- Nobody would know what RTFA meant if it didn't need to be said all the time
I think the issue is more one of market demand. Who cares if you can put 8 GB on a stick if 99% of the potential customers are running an OS that can barely handle 4 GB ?
Sure, there's the high end Unix crowd that would go crazy over that stuff, but trying asking SGI or the Itanium department how profitable it is to cater to that market nowadays.
Also, don't forget that Windows hasn't had a major upgrade since 2001. Windows upgrades are a large factor in how much RAM people need.
I am TheRaven on Soylent News