backtop

Print E-mail del.icio.us 42 comment(s) - last by mindless1.. on Jan 31 at 11:47 PM
Intel and Nanochip team up to develop 100 gigabytes per chip

This article was syndicated from Tiago Marques' blog at SiliconMadness.com

Nanochip, Inc., a Silicon Valley startup, has managed to raise $14 million in funding from Intel Capital, Intel's global investment organization, for further development of the MEMS technology.

You read it right: gigabytes, not gigabits.

According to Nanochip (PDF), the technology isn't lithography constrained, allowing production of chips of more than 1GB in capacity, in plants that have already been deemed outdated by current standards.

The lack of lithography constraints means cheaper products, resulting in an opportunity to also replace flash memory, as the technology is also non-volatile.

Today's factories should be able to produce the first products, estimated at 100GB per chip, when the technology is expected to be unleashed for public consumption by 2010. The first samples will be available during 2009.

PRAM, or phase change memory, was expected to be the technology to replace flash in the coming years, since it is also non-volatile, while it is much faster than flash. As Intel found out over the last few years, PRAM doesn't seemed to scale so well, in regards to density, and still has some boundaries to overcome -- namely it's thermal principles of operation.

Nanochip's details of the technology are ambiguous at best, though what is known is that the company is working on hybrid micro-electric-mechanical -- the partnership with Intel suggests a PRAM connection too.  The company has described this as a very small platter coated in chalcogenide is dragged beneath hundreds of thousands of electrical probes which can read and write the chalcogenide.  Casual estimates put this sort of density at one terabit per square inch, or 125GB per square inch. 

The company has not disclosed access speeds. That's a place where PRAM is appointed to be the undisputed king of the hill, so it could limit applications of this type of technology.

For now it seems that the flash SSD drives are going to be replaced before they even reach mass consumption -- which is a good thing. The technology is expensive, doesn't provide a lot of storage space and is prone to failure, due to the low amount of write cycles available per cell. Flash is perfect for pendrives and resisting shock, not so good for regular, intensive, HDD usage.

Comments     Threshold


This article is over a month old, voting and posting comments is disabled
Which is it?
By slashbinslashbash on 1/28/2008 12:39:49 PM , Rating: 2
quote:
Casual estimates put this sort of density at one terabit per square inch; or 116GB per square inch.


I'm guessing the 2nd part is supposed to be square cm?

Also, this tech seems to require mechanical movement -- a step backward?




RE: Which is it?
By Polynikes on 1/28/2008 12:50:35 PM , Rating: 2
It does indeed sound like a strange way of storing information.


RE: Which is it?
By Oregonian2 on 1/28/2008 2:34:47 PM , Rating: 2
I think it's a clever way of mixing technologies, and it'll be interesting to see if it's cost effective.

If you haven't yet, go to their website and read about the basis of their technology. It's phase-change memory that's written by zillions of probes that are in turn moved mechanically. Like a disk you say? Well, kind-of, except that the movement isn't done by a rotating motor, the movement is MEMS driven. Solid state "motor" of sorts. A MEMS driven solid state hard disk. It's at least intellectually interesting. TBD about cost effectiveness (like what kind of yields can they produce, assuming its reliable, etc).


RE: Which is it?
By Methusela on 1/28/2008 12:51:41 PM , Rating: 5
1 Terabit per square inch is roughly equal to 116 GigaBytes per square inch (math tells me it'd be exactly 125 GigaBytes, but who's going to quibble over a few gigs? Certainly not HD manufacturers! ;)


RE: Which is it?
By Assimilator87 on 1/28/2008 1:51:08 PM , Rating: 3
I'm pretty sure Seagate recently had a class action lawsuite filed against them for misrepresenting the actual size of the HDDs. Only a few GB? The consumers care.


RE: Which is it?
By onwisconsin on 1/28/2008 2:15:07 PM , Rating: 2
Or lawyers...


RE: Which is it?
By omnicronx on 1/28/2008 2:54:03 PM , Rating: 2
quote:
I'm pretty sure Seagate recently had a class action lawsuit filed against them for misrepresenting the actual size of the HDDs. Only a few GB? The consumers care.

What would we ever do without our extra 48 576 bytes per MB ;)
HD manufacturers purposely did this when HD sizes where small to not confuse consumers (made it easy 1MB = 1000 kilobytes).

Although it seems like manufacturers are trying to make every extra penny, the truth is probably that the people who first thought up of this plan, did not take into account how far HD space would actually scale. The bigger the hard drive gets, the more times you lose those extra 48 576 bytes ;)

I never really understood how somewhere around 50G lost every 1TB warranted a class action suit..


RE: Which is it?
By HaZaRd2K6 on 1/28/2008 3:37:19 PM , Rating: 5
The reason that whole situation existed at all was because of the different ways drive manufacturers and software programmers measure a gigabyte. A gigabyte, technically speaking, is exactly one billion (10^9) bytes. This is what drive manufacturers put on their drives. What software programmers call one gigabyte is actually one gibibyte (giga binary byte or GiB, 2^30).

An example, take a hard drive that can store exactly 250×10^9 or 250 billion bytes after formatting. Generally, operating systems calculate disk and file sizes using binary numbers, so this 250 GB drive would be reported as "232.83 GB". The result is that there is a significant discrepancy between what the consumer believes they have purchased and what their operating system says they have. So when Seagate says you have a 500GB drive, they're right. You have five hundred billion bytes of storage on that drive. Just because Microsoft measures five hundred billion bytes as binary bytes does not mean that there are differences in the actual, physical storage capacity of the drive.


RE: Which is it?
By mindless1 on 1/28/2008 6:43:44 PM , Rating: 1
Wrong. It's not just software programmers, it's everyone else, the hardware manufactureres ratings of bus speeds, chip capacities (including memory). It was also hard drive manufacturers! Did you get that last sentence? Hard drive manufacturers did correctly state capacity early on, then changed to the present capacity mislabeling.

A gigabyte technically speaking is not 10^9 bytes. Understand what a prefix is, it is to describe the suffix which is a binary not decimal value.

The fact is, the entire computer industry and scientists do accept the binary number system. Only ignorant people who can't understand that there is more than one number system think that a prefix can only exist in the decimal system or has to have a decimal value, that it couldn't be a binary value.

The entire computer industry defined what gigabit, gigabyte, megabit, etc, meant and it was a standardized fixed term BEFORE certain companies misused the term trying to make it a decimal value. That's the whole point of a standardized term, that it doesn't change even if the hard drive industry or a confused poster like yourself really really want it to change.


RE: Which is it?
By chekk on 1/28/2008 8:07:36 PM , Rating: 2
Wow, did get up on the wrong side of your cage this morning? There's no need to be nasty.
quote:
Understand what a prefix is, it is to describe the suffix which is a binary not decimal value.

Exactly. Which means that whether one is referring to decimal values, binary values, apples or whelks, the giga prefix means 10^9.


RE: Which is it?
By chekk on 1/28/2008 8:10:44 PM , Rating: 2
Crap. Apparently, I can't proofread.
"... did you get up ..."


RE: Which is it?
By the goat on 1/29/2008 8:57:20 AM , Rating: 2
quote:
Exactly. Which means that whether one is referring to decimal values, binary values, apples or whelks, the giga prefix means 10^9.


You sir are 100% wrong. The these prefixes are based on accent Greek and Latin languages. Nobody owns these Greek and Latin prefixes. The "International System" (SI for short) system of measurement (meters, liters, etc.) uses these prefixes to represent powers of ten (i.e. giga = 10^9). This is true for every SI unit of measure.

But it is very important to realize that bits, nibbles and bytes are not SI units. Therefore SI has no authority to dictate how accent Greek and Latin words used as prefixes modify these computer memory units of measure.

Everybody in the computer memory industry knows how to use prefixes on binary units correctly. There is no dispute as to what a kilobyte, etc. is defined as (hint: kilobyte = 2^10 = 1024 bytes, not more, not less).


RE: Which is it?
By grv on 1/29/2008 9:19:09 AM , Rating: 2
just because a couple of uneducated programmers misused decimal prefixes doesn't mean its somehow right or "standard".
learn, binary prefixes are standardized since 1998: http://physics.nist.gov/cuu/Units/binary.html
and don't forget to ask your money back for IT education. stupid teachers deserve no money


RE: Which is it?
By the goat on 1/29/2008 2:51:25 PM , Rating: 2
quote:
just because a couple of uneducated programmers misused decimal prefixes doesn't mean its somehow right or "standard". learn, binary prefixes are standardized since 1998: http://physics.nist.gov/cuu/Units/binary.html
and don't forget to ask your money back for IT education. stupid teachers deserve no money

The units for measuring computer memory were defined way before 1998. The alternative binary only prefixes you are talking about are a joke. Nobody uses them.

Like I said before the prefixes in question are based on ancient Greek and Latin. They are not misused by the computer memory industry. They are not tied to decimal units only.

SI gets to make up prefixes for all the units of measure they invent. But SI didn't invent bytes and bits. So why does anybody think SI should dictate how prefixes work with bits and bytes?


RE: Which is it?
By mindless1 on 1/31/2008 11:42:17 PM , Rating: 2
I think you mean the entire computer industry, not just a couple of programmers. Obviously you have no arguement if you choose to ignore such a basic fact that the computer industry did standardize the terms gigabyte, etc, to mean a value in the binary system. They DEFINED what giga, mega, etc, meant in the binary system. 10^9, etc, is in the decimal system not the binary system.

I'd have to agree with the goat, in that it's laughable you reference 1998, what about 30 years earlier?

The problem is simple, you don't know what standardization is or why it's important.


RE: Which is it?
By HaZaRd2K6 on 1/29/2008 2:50:59 PM , Rating: 2
Now that's where you're wrong.

The Système International prefixes are based on ancient Greek. Specifically, the prefix "giga" refers to billion (or ten to the power of nine or 1,000,000,000). The Système International works in base ten, yes, hence giga is base ten.

Computer programmers and component manufacturers turned this definition upside down, made it two to the power of thirty and called it a gigabyte. Two to the power of thirty, as I mentioned before in this thread is 1,073,741,824. Not one billion. In base two (binary), gibibyte is the correct definition of one billion binary bytes. Gigabyte refers to exactly one billion bytes--no more, no less. Gibibyte refers to exactly 1,073,741,824 bytes.

So stop it. You're wrong. Gigabyte means one billion bytes. Gibibyte means 1,073,741,824 bytes. Now you can either tell programmers to start coding in base ten, tell drive manufacturers to start listing drive sizes in base two or just put up with it and realise no matter what happens, neither side is going to give up.


RE: Which is it?
By the goat on 1/29/2008 3:02:30 PM , Rating: 2
quote:
The Système International prefixes are based on ancient Greek. Specifically, the prefix "giga" refers to billion (or ten to the power of nine or 1,000,000,000).

Incorrect in so many ways. First of all the word Giga is Latin not Greek and it means giant not 1,000,000,000.

Mega = Great (Greek)
Tera = Monster (Greek)

What do the words giant, great and monster have to do with base ten?

quote:
The Système International works in base ten, yes, hence giga is base ten.

SI is base ten no doubt. But Bytes and bits are not SI units. So why should I case about SI prefixes?


RE: Which is it?
By HaZaRd2K6 on 1/29/2008 11:09:38 PM , Rating: 2
From Merriam-Webster dictionary:

Giga
Etymology: International Scientific Vocabulary, from Greek gigas giant: billion (10^9) <gigahertz> <gigawatt>

Notice words number two through four there? International Scientific Vocabulary . In other words, your opinion counts for nothing. And if you still want to argue, take it up with the National Institute of Standards and Technology. Here, I'll even give you the link to the .pdf: http://physics.nist.gov/cuu/pdf/sp811.pdf

You done now? I am Greek. I know the word. The word itself (???a?, actually pronounced "gigas" (soft 'g')) does mean giant, yes, but gigabytes and gigahertz and gigawatts are not giantbytes and gianthertz and giantwatts. They're billions. Same as a terabyte and a terahertz and a terawatt are not monsterbytes and monsterhertz and monsterwatts. Those are trillions. Stop confusing standard convention in the scientific community with the etymology of ancient Greek words.

quote:
SI is base ten no doubt. But Bytes and bits are not SI units. So why should I case about SI prefixes?

Nobody was ever saying bytes and bits were SI units. We were saying the prefixes used to describe them in quantity (including kilo, mega, giga and tera) are SI prefixes and are attached to specific quantities.