Crossbar Resistive RAM stores a terabyte on a chip • Hacker News Board

Re: Crossbar Resistive RAM stores a terabyte on a chip

#41

Post by yread » Tue, Aug 06, 2013, 5:41 AM UTC

agildehaus wrote: post #29

ars wrote: post #27

Earlier quoted context omitted.

The price of a chip is more or less the die size. And they clearly show a smaller die than existing technology.

Since when is the price of a chip in any way related to the size of its die?

Please, be civil. There are better ways to ask a question.

Re: Crossbar Resistive RAM stores a terabyte on a chip

#42

Post by MarcScott » Tue, Aug 06, 2013, 5:56 AM UTC

Interesting to see that Samsung started mass production of their 3D NAND memory yesterday.

http://www.engadget.com/2013/08/05/samsung-ships-first-3d-ve...

Re: Crossbar Resistive RAM stores a terabyte on a chip

#43

Post by touristtam » Tue, Aug 06, 2013, 6:04 AM UTC

maybe a more tech oriented article would have been preferable: http://www.theregister.co.uk/2013/08/05/crossbar_uncloaks_fa...

(venturebeat sounds like a investor magazine to me)

Re: Crossbar Resistive RAM stores a terabyte on a chip

#44

Post by anigbrowl » Tue, Aug 06, 2013, 6:23 AM UTC

drcode wrote: post #14

This article makes a lot of extraordinary claims. Extraordinary claims require extraordinary evidence. In this case, that means a reputable tech reporter from a reputable publication has to say "this is the real deal" before these guys can be taken seriously. (I'm not doubting that they have any tech, it's just that they seem to be promising something with no downsides, which in most cases means a marketing team has…

Well you could verify the patents for yourself, you could cross-check the opinion of the Convergent Semi analyst for yourself, and you could reflect on the fact that Kleiner Perkins is a well-established VC firm, and a bunch of other things.

Re: Crossbar Resistive RAM stores a terabyte on a chip

#45

Post by anigbrowl » Tue, Aug 06, 2013, 6:25 AM UTC

standel wrote: post #22

Alex3917 wrote: post #20

Earlier quoted context omitted.

"This article makes a lot of extraordinary claims. Extraordinary claims require extraordinary evidence." Does it? It just sounds like a normal memristor to me.

Memristor does not seem to be normal neither. Is there any on the market?

Just because you don't know about it doesn't mean anything. I don't mean that to be snide, but just to point out that you may have encountered a limit in your own knowledge. I've known about memristors for years and have been waiting to see a product come to market. They're interesting devices, you should read up on them. Also, search back through HN as there have been several worthwhile discussions of the technology.

Re: Crossbar Resistive RAM stores a terabyte on a chip

#46

Post by nshepperd » Tue, Aug 06, 2013, 7:53 AM UTC

It's nice to see memristors bearing fruit (or about to soon) finally.

Re: Crossbar Resistive RAM stores a terabyte on a chip

#47

Post by vlasta2 » Tue, Aug 06, 2013, 7:58 AM UTC

shenberg wrote: post #39

wging wrote: post #35

Earlier quoted context omitted.

They do say "It can access that data 20 times faster than the best breed of flash memory" but a rate of 17 MB/s means this is incorrect.

They're probably referring to latency, which is very low (30ns). It still is disingenuous, but that's marketing.

I guess it is more accurate to talk about latency, because throughput can always be improved by accessing multiple cells in parallel.

Re: Crossbar Resistive RAM stores a terabyte on a chip

#48

Post by rorrr2 » Tue, Aug 06, 2013, 9:31 AM UTC

sillysaurus wrote: post #2

Does anyone know if there has been progress in volatile memory tech? I'm hoping for 1TB RAM chips with 10x faster access times than current RAM. It will enable PC gaming to deliver unmatched immersive experiences, among other applications.

Gaming is limited by the CPU/GPU, and a bit by the bandwidth in between. Not by the RAM speed/latency.

Re: Crossbar Resistive RAM stores a terabyte on a chip

#49

Post by Filligree » Tue, Aug 06, 2013, 9:48 AM UTC

GravityWell wrote: post #11

Crossbar believes it can write data to its chip at 140 megabytes per second, compared to 7 megabytes a second for flash. Read performance is 17 megabytes per second, with a random read latency of 30 nanoseconds. The write performance sounds good, but the read performance seems very low. Also I don't know where they get 7 megs per second for flash. Sounds like the picked the worst performer to compare to. I'd be more…

They're talking about per-chip performance. Flash write performance really is that low - they get around it by spreading writes to multiple chips.

Crossbar can do the same thing, in which case the same number of chips provide higher throughput. Read latency is not parallelisable, of course, so there'll be no way for flash to catch up there without making fundamental advances.

That is, if all these numbers are correct.

Re: Crossbar Resistive RAM stores a terabyte on a chip

#50

Post by RyanZAG » Tue, Aug 06, 2013, 9:49 AM UTC

rorrr2 wrote: post #48

sillysaurus wrote: post #2

Does anyone know if there has been progress in volatile memory tech? I'm hoping for 1TB RAM chips with 10x faster access times than current RAM. It will enable PC gaming to deliver unmatched immersive experiences, among other applications.

Gaming is limited by the CPU/GPU, and a bit by the bandwidth in between. Not by the RAM speed/latency.

Not strictly true. Most algorithm choices in gaming can make trade offs between CPU and RAM. If you increase available RAM, you can usually use algorithms that are more RAM hungry and less CPU hungry for large speed benefits.