Sci/Tech IBM scientists achieve storage memory breakthrough

[tom_mai78101]

For the first time, scientists at IBM Research have demonstrated reliably storing 3 bits of data per cell using a relatively new memory technology known as phase-change memory (PCM).

The current memory landscape spans from venerable DRAM to hard disk drives to ubiquitous flash. But in the last several years PCM has attracted the industry's attention as a potential universal memory technology based on its combination of read/write speed, endurance, non-volatility and density. For example, PCM doesn't lose data when powered off, unlike DRAM, and the technology can endure at least 10 million write cycles, compared to an average flash USB stick, which tops out at 3,000 write cycles.

This research breakthrough provides fast and easy storage to capture the exponential growth of data from mobile devices and the Internet of Things.

IBM scientists envision standalone PCM as well as hybrid applications, which combine PCM and flash storage together, with PCM as an extremely fast cache. For example, a mobile phone's operating system could be stored in PCM, enabling the phone to launch in a few seconds. In the enterprise space, entire databases could be stored in PCM for blazing fast query processing for time-critical online applications, such as financial transactions.

Read more here. (PhysOrg)

 

[Accname]

Dont believe it until you see it yourself.

 

[Varine]

Ten million write cycles? Bullshit.

 

[The Helper]

I still have not had a reason to use the SSD drives yet. One of them came on the bosses computer and it is empty. Everything runs smooth as glass on his bad ass box and even though it might run better on the ssd drive i am not signing up for that shit lol.

 

[Varine]

I have SSD's in my laptops. They are nice, but on the older one I can tell it's slowing down. Cheap shit though.

 

[Accname]

Have an SSD in both my desktop and my laptop. Its nice, but it isnt that big a difference. The most obvious benefit is how silent they are compared to those old HDD's with all the moving parts. Cant really say how much faster they are because on Windows it always starts out fast and goes slower and slower the more you use it.

 

[jonas]

I talked to an IIT professor a year ago who was involved with PCM and he explained to me what they do. He said they are close to building real hardware with that technology. I have been looking forward to a breakthrough since then, but mostly in energy saving RAM chips for smartphones. I don't understand what "3 bits per cell" is supposed to mean (Maybe my problem is - what is a cell?), and I remember him saying that the crystalline structure deteriorates over time (but not nearly as fast as RAM). I think he called them memsistors.

 

[Accname]

"3 bits per cell" doesnt mean anything. Its media buzzwords without any actual value. How many bits you encode in one cell doesnt really matter. Its just arbitrary units anyways.

I know a little bit about phase-change memory and all the other new esoteric memory technologies. They each come with their pros and cons. But they have teased this kind of technology for years. They always say they are "this close" to releasing it. Of course they are, they want funding. If they were honest nobody would want to invest into the research. That is why I dont take articles like these serious until I actually see a product on the market.

 

[jonas]

"3 bits per cell" doesnt mean anything. Its media buzzwords without any actual value. How many bits you encode in one cell doesnt really matter. Its just arbitrary units anyways.

Thanks. That was my feeling as well, but I'm not an expert in transistor technology - I've been working on gate level, but not below.

They always say they are "this close" to releasing it. Of course they are, they want funding. If they were honest nobody would want to invest into the research. That is why I dont take articles like these serious until I actually see a product on the market.

Haha, same old same old

 

[tom_mai78101]

They are using a technology breakthrough, which is 3D transistors, so that "3 bits per cell" meant "3 sides for 1 bit per cell". :/ Something to ponder about.

And note, I no longer have access to scientific papers.

 

[Varine]

... how does that work? That doesn't make sense.

 

[jonas]

Even if you build the transistor as a cube, which sounds well possible with pcm, you can only read out 1 bit at a time.

 

[tom_mai78101]

Even if you build the transistor as a cube, which sounds well possible with pcm, you can only read out 1 bit at a time.

But since it is going on 3 sides, you're reading 3 bits at a time.

If I have access to my school account for me to login to the library database, I can find the scientific paper that explains the process.

 

[jonas]

But since it is going on 3 sides, you're reading 3 bits at a time.

If I have access to my school account for me to login to the library database, I can find the scientific paper that explains the process.

But if you put VCC on one input, but not another, it sounds like you have a short circuit (like on a tristate bus)!

On an afterthought, I can see now that the remaining outputs would actually output the right bits; so by putting VCC everywhere you can probably read out all of the bits at once.