Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

NAND Flash Better Than DRAM For PC Performance

Soulskill posted more than 3 years ago | from the drams-do-better-for-memory-loss dept.

Hardware 205

Lucas123 writes "Adding NAND flash memory to a PC does more for performance than DRAM and costs less, according to a new study. As the price difference between the two memory types widens, NAND flash will become the memory of choice in the PC. The effects of NAND flash adoption are already being felt in the DRAM market, as revenue in 2011 is expected to decline 11.8%."

cancel ×

205 comments

Sorry! There are no comments related to the filter you selected.

Rebecca Black - My Moment - Official Music Video (-1, Flamebait)

Anonymous Coward | more than 3 years ago | (#36819810)

http://www.youtube.com/watch?v=2OxWD85Ngz4 [youtube.com]

'Dislike' for good luck (like kissing the Blarney Stone)

Huh? (1)

LongearedBat (1665481) | more than 3 years ago | (#36820064)

This seems to have nothing to do with topic. Am I completely whooshed, or is this a trick to get YouTube hits?

Re:Huh? (0)

Anonymous Coward | more than 3 years ago | (#36820104)

It's still nice - spam but at least a good one (a change from disguised/disgusting goatse).

(another AC, still offtopic, but resenting a Flamebite mod)

Re:Huh? (1)

BitZtream (692029) | more than 3 years ago | (#36820134)

Its just spam used to get fake account to appear less fake, as are almost all first posts.

Re:Huh? (0)

Anonymous Coward | more than 3 years ago | (#36820176)

What fake account?

Re:Huh? (0)

Anonymous Coward | more than 3 years ago | (#36820478)

LongearedBat

One Problem (4, Informative)

rhook (943951) | more than 3 years ago | (#36819892)

NAND flash degrades over time and has a limited amount of program/erase cycles.

Re:One Problem (2, Funny)

MichaelKristopeit423 (2018892) | more than 3 years ago | (#36819902)

so do humans.

Re:One Problem (2)

king neckbeard (1801738) | more than 3 years ago | (#36819966)

and humans make horrible PC components.

NSFW (1)

MrEricSir (398214) | more than 3 years ago | (#36819984)

No, but they're great in iPads [southparkstudios.com] .

Re:One Problem (1)

MichaelKristopeit425 (2018896) | more than 3 years ago | (#36820180)

who is going to plug them in?

Re:One Problem (-1)

Anonymous Coward | more than 3 years ago | (#36820042)

you're such a worthless nigger

yeah yeah why do i cower etc etc blah blah shut the fuck up asshole. i cower from worthless niggers like you just in case you're contagious. i can feel my IQ lowering just by talking to you.

Re:One Problem (0)

MichaelKristopeit425 (2018896) | more than 3 years ago | (#36820090)

you're an ignorant hypocrite.

cower in my shadow some more, feeb.

you're completely pathetic.

Re:One Problem (1)

c0lo (1497653) | more than 3 years ago | (#36820110)

so do humans.

Wake me up when NAND has a life-time 10% of an average human and we'll talk.

Re:One Problem (-1, Flamebait)

MichaelKristopeit502 (2018076) | more than 3 years ago | (#36820248)

posting in your sleep? does the average human post in their sleep?

cower in my shadow some more behind your chosen misspelled hosting solution based pseudonym, feeb.

you're completely pathetic.

Re:One Problem (0)

Anonymous Coward | more than 3 years ago | (#36820768)

Fail troll is fail.

Re:One Problem (1)

Terrasque (796014) | more than 3 years ago | (#36820710)

Heh. My main computer's SSD, with the current write pattern, is expected to last at least 10 years before it starts to fail (before it hits the limit where manufacturer says the first chips might start to fail).

(well, according to this program [ssd-life.com] at least)

Re:One Problem (1)

John Allsup (987) | more than 3 years ago | (#36820894)

"expected": So it could fail today or tomorrow. This is unlikely, but you should plan to cover this contingency with a proper backup plan so that if it fails, you lose neither time nor data.

Re:One Problem (1)

Matt_R (23461) | more than 3 years ago | (#36820992)

"expected": So it could fail today or tomorrow.

So will some humans.

Re:One Problem (1)

Terrasque (796014) | more than 3 years ago | (#36821110)

Why thank you for pointing this out! This is so completely unlike HDD's which I've used for over 20 years now! You should write an article and post it to Slashdot [/sarcasm]

Sorry, was too big a temptation :)
Anyway, what you point out is true, and is exactly the same for harddisks. Which is why I have a server with 6tb in raid5 for storing anything important (and, I'll admit, a truckload of unimportant stuff).

Plus dropbox also works as a secondary backup system for some of my data (mostly code snippets and projects, savegames, text documents.. Generally data that's small and is survivable if US govt looks at it :) ) - dropbox also have the bonus of mirroring the data over several seperate computers, making it a good backup even if my house burned down and dropbox went tits-up at the same moment.

Re:One Problem (1)

c0lo (1497653) | more than 3 years ago | (#36821016)

And you compare a 200 GB HDD with an 8 GB one? More over, in the context of TFA, with an 8 GB meant to replace the RAM?

Re:One Problem (1)

Imbrondir (2367812) | more than 3 years ago | (#36821194)

so do humans.

Wake me up when NAND has a life-time 10% of an average human and we'll talk.

I don't think too many can 'store' a memory for 7 years without the memory being constantly 'copied'. I mean it has to constantly be refreshed. First preferably the next day, then a week later, a month, then every year after that to truly keep it. NAND should be able to compete with that.

Re:One Problem (0)

Anonymous Coward | more than 3 years ago | (#36820084)

Exactly what they want. Planned obsolescence.

Re:One Problem (2)

c0lo (1497653) | more than 3 years ago | (#36820126)

Exactly what they want. Planned obsolescence.

From my perspective, NAND as RAM are already obsolete. Voting with my wallet, never going to buy as such (I ruined one of the first eeepc-es by installing a Linux and setting up a swap space. What I was thinking? 10 minutes later, I almost have a brick in my hands... salvaged only with an external SD card for storage).

Re:One Problem (1)

Skuto (171945) | more than 3 years ago | (#36820166)

Sounds like you're saying first-generation NAND controllers are obsolete. Woohoo. Doesn't say much for the technology in general.

Re:One Problem (1)

Vectormatic (1759674) | more than 3 years ago | (#36820444)

No offense meant, but why the hell did you do that? If you bought a first gen eee, you knew what you where getting into, that it had a small SSD instead of a spinning platter drive, and since SSDs werent firstly introduced in the eee, the fact that NAND degrades and isnt a good choice for swap space was known as well.

I got a first gen eee as well, and did install linux as well, but instead of using swap, i just doubled the ram and disabled swap.

Re:One Problem (1)

c0lo (1497653) | more than 3 years ago | (#36820484)

No offense meant, but why the hell did you do that?

No offence taken. As an excuse for a stupid thing... I was doing it at wee hours in the morning.

Anyway, I wrote off the money for the extra SD card as "tuition fees" (as in "lesson learnt").

Re:One Problem (2)

jawtheshark (198669) | more than 3 years ago | (#36821030)

Weird... I have done that too. Asus EEE 704 4G, with a swap space. I installed other operating systems a few times (Reset the original a few times, Debian Sid, Ubuntu 10.10/Netbook edition, Debian Squeeze which is what it's currently running) It's still going strong. My wife was in hospital for a full 8 months and it was her (only) computer during that time and she used it every day to email/surf/watch movies/listen to music. During that time it did have a small swap partition (By now, I switched to swap files as they are easier to change when running out of disk space).

The only difference I might see is that I installed a 2GB module the day I got it. From what I've seen it rarely to never passes the 512MB usage mark with the above mentioned systems So, with only 512MB RAM, it might hit the swap space occasionally. To kill it? Probably not enough.

Re:One Problem (0)

Anonymous Coward | more than 3 years ago | (#36820312)

Sorry, but you obviously have no concept of the physics behind how these things work. Your willful ignorance does not prove their malice.

Re:One Problem (1)

symbolset (646467) | more than 3 years ago | (#36820384)

NAND flash degrades over time and has a limited amount of program/erase cycles.

Spinning rust degrades over time and has a limited amount of write/erase cycles.

The difference between NAND flash and spinning rust is that it's faster. Early evolutions of NAND flash reached the limits of their write cycles therefore. Modern evolutions of NAND flash make it more durable and reliable than spinning rust in every instance - and the speed and storage density is just a bonus.

Re:One Problem (0)

Anonymous Coward | more than 3 years ago | (#36820458)

Storage density - at least in terms of cost/GB - is still the big advantage HDD holds. If that were gone, it'd be curtains for HDD and Seagate and WD would be selling only SSDs.

But the original argument is about the endurance of flash, which is typically 1000 cycles per sector/block/whatever one calls it. The number of times RAM is written to by a CPU far far exceeds that! That metric alone would ensure that RAM won't be replaced, unless a non-volatile RAM came about.

Re:One Problem (2)

symbolset (646467) | more than 3 years ago | (#36820636)

Forgive me, but you've shifted the context.

I was using RAMdisk for storage over 30 years ago. It's great performance storage, but the whole forgetting everything on power loss is an issue. We've done ten workarounds that I know about.

You kids these days, you think you invented everything.

Re:One Problem (5, Informative)

Anonymous Coward | more than 3 years ago | (#36821398)

NAND flash degrades over time and has a limited amount of program/erase cycles.

Spinning rust degrades over time and has a limited amount of write/erase cycles.

Total bullshit. Please try to have a clue when you try to be clever. There is no wearout mechanism which eventually makes it impossible to alter magnetic domain orientations in spinning rust. You can keep doing that forever. In practice, the lifespan of a HDD is limited by mechanical failure or the death of the controller electronics.

The difference between NAND flash and spinning rust is that it's faster. Early evolutions of NAND flash reached the limits of their write cycles therefore. Modern evolutions of NAND flash make it more durable and reliable than spinning rust in every instance - and the speed and storage density is just a bonus.

Good god, you're clueless. Every evolution of NAND flash makes its durability and reliability worse, not better, due to some fundamental physics problems with NAND technology. The only thing keeping NAND viable is throwing ever-stronger ECC codes at the problem (decreasing the effective density gain from each process shrink by consuming more bits in error correction overhead). Write/erase cycles also keep going down, not up.

And then there's the fun phenomenon called "read disturbance". If you haven't guessed just by reading the phrase, this means you can alter the state of a bit cell in the latest and greatest generation of NAND flash by reading it (or its neighbors) too many times. Whee!

Don't confuse the application of stronger and higher overhead techniques for managing the problems with NAND with it being a super-memory with no flaws. It has a lot of issues.

Re:One Problem (4, Informative)

hairyfeet (841228) | more than 3 years ago | (#36820480)

Not to mention what TFA neglects is the simple fact that one doesn't need as much memory as they do storage space so comparing the two? More than a little pointless.

When DDR 2 was so cheap I bought 8Gb for my PC, which thanks to Superfetch means ALL of the programs that I use frequently? Instant load, poof, faster than even an SSD could possibly load them because they are already in RAM waiting for me and as we know RAM is several orders of magnitude faster than the fastest SSD. I won't build a PC anymore with less than 3Gb and I usually try to talk the customer into 4Gb, why? Again thanks to intelligent prefetching by the OS the programs they use most often will be preloaded into RAM waiting on them, thus not only making the PC crazy fast but also cutting down on drive spinning which lets the drive park the heads and thus lowers heat and power usage.

Meanwhile the tech they are pushing is so damned unreliable Jeff Atwood at Coding Horror says they should be judged on a hot/crazy scale [codinghorror.com] as they go tits up quite often in return for the crazy speed. Atwood still loves them but I would point out he is the same guy that recommends spending over $400 on a pair of headphones like he does. If you have the money to blow a couple of grand a year on big fast SSDs? I'm happy for you, you are doing better in a dead economy than most. But RAM almost never wears out and can easily last a decade, is still relatively cheap for maxing out a PC, and the performance one gets nowadays for giving the OS plenty of RAM for fetching is really quite stunning. By having plenty of RAM and hybrid sleep my customers have an instant on PC that loads every program they use as fast as they can click the button. What more can you ask for?

Re:One Problem (1)

IICV (652597) | more than 3 years ago | (#36820608)

You're very much a question talker, aren't you?

And anyway, the reason why you would use NAND as RAM instead of the current DRAM if they could work out the kinks is because NAND doesn't need power to maintain state. This means that you could be doing something on your computer, kill the power without any sort of warning at all, and then plug it in later and resume exactly where you were before. It would lead to, for instance, near-zero battery usage sleep in mobile devices; they would be able to almost shut off when you're not using them, using only very little power to do wireless upkeep type stuff.

It will be awesome when they get it to work, and believe me it's only a matter of time; once SSD technology becomes more stable, the fabrication capacity and experience will exist to make even more expensive and delicate NAND ram.

Re:One Problem (0)

Terrasque (796014) | more than 3 years ago | (#36820694)

It's when I see posts like this I'd wish we had "-1, Just Plain damn wrong" mod.

I agree with your first two sentences, but the two paragraphs under are just .. well.. how shall I say it? It's like listening to a crack-smoking environmentalist talking about cars.

Return rates: HDD & SSD [behardware.com]

And prefetch is nowhere near the same feeling as an SSD. I know. I have 6gb ram, and ran Win7 on a raptor before switching to SSD. The difference really was huge. I have bought a total of 3 SSD's (2 el cheapo's and one proper), and all three still works perfectly.

I've also convinced 2 work colleagues and a friend to try out SSD. All three had Win7 and plenty of RAM. All three was astonished over how much better responsiveness the PC had after the upgrade. One even said it fundamentally changed how he used the PC, from keeping it on all the time, to just turn it on when needed.

With current data write rate and wear leveling the SSD in my gaming rig is expected to have a lifetime of minimum 10 years before the flash bricks will start to wear out.

Re:One Problem (0)

Anonymous Coward | more than 3 years ago | (#36820860)

meh. I've 8gb of ram and the only time I hear disk spinning is when I bring up the start menu to shut down the pc.

Re:One Problem (5, Insightful)

daid303 (843777) | more than 3 years ago | (#36820728)

I work with flash daily, we make products that last 15 years with flash. Without large failure rates. The problem is not with flash. It's with the SSD implementation. It's the "let's replace harddisks with flash! and don't change anything else!" that causes problems. Because of this normal filesystems are used, that assume to be on spinning harddrives, which have no issue in writing the same sector twice, or just writing 1 sector at once. On flash on the other hand you need to do wear-leveling, and have large erase blocks. Both are handled on the SSD right now, and that's where it fucks up. It needs to maintain an internal mapping of all the flash, accounting for wear-level and shifting blocks around. One error in this internal management and your disk is junk. Even with your fancy journaling filesystem (ntfs/ext3,4/...) you are just 1 power failure away from losing your data.

Compact flash cards, SD cards, SSD, USB sticks all see this problem. So far we've only found a few suppliers of Compact flash cards which guarantee the internal management is safe, and we tested it and found it to be true. SD cards, I've a few broken "industrial grade" SD cards on my desk as proof that this is not the case. SSD is to large for our product, so I have no tests for these, but I expect the problem to be the same.

We use raw flash, with linux and JFFS2 or UBIFS. Which is a filesystem designed to run on flash, raw flash. Wake me when "SSD" offers that solution.
(TRIM is not a sollution, it's a workaround)

A CPU w/ a NAND interface? (0)

Anonymous Coward | more than 3 years ago | (#36821202)

I'm assuming that you mean raw, NAND flash. So in other words, your CPU bus has the same sort of bus that NAND does - 8 or 16 I/O lines where a control signal (namely ALE) determines whether the lines are @ any given moment carrying address or data? I've known of CPUs that have multiplexed address/data buses, but which CPU has the same sort of NAND interface that I just described?

That is the main reason controllers are needed - and b'cos they are there, more tasks are almost always assigned to them, be it file management, ECC... That results in people thinking that that is the main use for the controller. Nope, the reason the controller has to be there in the first place is that the NAND interface is completely different from almost all CPU interfaces. When you have 2 devices w/ different interfaces and need them to exchange data, you need 'glue logic' of some sort that translates the input of one into the output of the other, and that is the primary function of the controller. ATA controllers, which are used in CF, SD and other such cards provide one familiar interface for the system - it makes the flash look like an ATA hard disk. One could use a controller w/ a different interface that the CPU is used to talking to. But an interface has to be there - this is not like directly connecting a CPU to an SRAM bus. After that, put on it the file system that supports the housekeeping activities you listed, assuming that the OS natively supports it. Since most systems are using Windows & NTFS (is FAT32 still used for these high >4GB densities?), the flash - whether it's CF or SD or SSD - will have to support NTFS, unless and until such time Microsoft decides to go your route and produce a native filesystem specific for SSDs, CF cards, SD cards and other flash memory based media.

Re:One Problem (5, Interesting)

Anonymous Coward | more than 3 years ago | (#36821236)

Compact flash cards, SD cards, SSD, USB sticks all see this problem. So far we've only found a few suppliers of Compact flash cards which guarantee the internal management is safe, and we tested it and found it to be true. SD cards, I've a few broken "industrial grade" SD cards on my desk as proof that this is not the case. SSD is to large for our product, so I have no tests for these, but I expect the problem to be the same.

If you expect SSDs to have exactly the same problems as SD cards, you're a total moron with at best shallow expertise in the field. Go look up the specs of controller ICs used in SSDs and try to tell me with a straight face that they're exactly the same thing you'd get in a SD card, or even a very good CF card.

To pick just one example, do you know of any CF cards which compress all data on the fly in order to increase effective flash lifespan by reducing the total amount of data written? (Since the SSD controllers in question use hardware compression engines which can handle hundreds of megabytes per second throughput, this also has the nice side effect of increasing effective performance, unless you're storing incompressible data.)

We use raw flash, with linux and JFFS2 or UBIFS. Which is a filesystem designed to run on flash, raw flash. Wake me when "SSD" offers that solution.

Whatever makes you think the FTL (flash translation layer) firmware inside SSDs isn't designed to run on flash, raw flash? Whatever makes you think that a generic one-size-fits-all software solution like JFFS2 applied to whatever random flash memory you put in your embedded system is better than a SSD whose firmware has been tuned for the specific flash chips it was built with? (One of the fun things about NAND flash is that it's far from generic, especially MLC, and even more especially sub-30nm MLC NAND.)

More broadly, JFFS2 is one way to skin the cat, having a "drive" abstract flash into a generic block device is another. If you want low cost, low-to-medium performance, and probably not the best possible reliability, especially for heavy write loads, JFFS2 and friends will do just fine. If you want a real HDD replacement for non-embedded-systems, it's not even close to being the right solution. Which is why you don't see anybody trying to deploy flash-managing filesystems as HDD replacements.

The controllers used in real SSDs are expensive enough that it would be a huge win if you could toss them and just use a flash FS. There are lots of very good reasons why this has not happened and will not happen. Take your head out of your butt and get some perspective, right now you're a classic example of how a little knowledge is a dangerous thing.

(TRIM is not a sollution, it's a workaround)

No, TRIM is an attempt to improve performance which has been oversold a bit in the popular computer press.

Re:One Problem (1)

Ant P. (974313) | more than 3 years ago | (#36821622)

Because of this normal filesystems are used, that assume to be on spinning harddrives

Worse still are cheap-ass SSDs that assume "normal" filesystems are being used, and corrupt your data if you aren't using windows [seagate.com] .

No kidding (3, Interesting)

Sycraft-fu (314770) | more than 3 years ago | (#36820828)

It is far, FAR more important for your computer to have enough RAM than to replace a HDD with an SSD. At this point (and probably for a long time) flash is not replacing DRAM. You need to have RAM in your system for it to work. Flash replaces hard disks.

Well cool, HDDs are by far the slowest component these days. SSDs are have somewhere in the range of 2-5x the transfer rate they do and more importantly are an order of magnitude or more faster on access.

Well that still is no comparison to DRAM. DDR3 is 40x the transfer rate of even fast SSDs and about 4-5 orders of magnitude less access time. So you can't just have flash, at least not if you want a nice n' fast CPU.

Now in terms of practical usage I find RAM is way, WAY more important. If you don't have enough, some programs will just flat out not run. If your system is starved, paging kills the performance, even with an SSD handling the paging. Knocking in a good amount of RAM is the #1 thing you can do to keep your system running well and it is damn cheap.

SSDs improve responsiveness, don't get me wrong. I love mine and I'm happy to have them (though to be fair I wasn't willing to get them until I saw some on sale for $200 for 256GB). However it is a more minor improvement than having a system with plenty of RAM or a good CPU. I do notice some slowness to my non-SSD work system, but not much.

The other problem is even though flash is cheaper per GB ($2ish per GB as opposed to more like $9ish for DRAM) you need more disk space than memory. My laptop has what I consider a reasonable amount of both, that is 4GB of RAM and 256GB of SSD. My desktop has a ton of RAM, 16GB, and a moderate amount of SSD, 512GB. So the SSDs cost me a hell of a lot more, despite their lower per unit cost. I could easily recommend a 4GB or more RAM upgrade to anyone, I couldn't recommend an SSD big enough to hold a good amount of stuff.

Pretty much I only recommend SSDs if you've already maxed out your RAM. Spend your money on that first, then if you are still willing to bear the cost of an SSD, go ahead.

In that vein, I noticed more improvement on my laptop than on my desktop. No small part of that is likely the RAM. The desktop has RAM to spare, it can cache a ton of stuff. The laptop is not starved for RAM, but not does it have a massive surplus. The base usage on the system is about 1.5GB for OS and background services. Gives it maybe 2.5GB for caching when nothing else is running. Hence the SSD helps more.

Re:One Problem (1)

Pharmboy (216950) | more than 3 years ago | (#36821498)

3 or 4 GB of RAM on new systems? Seriously, why would you create a new system without being fully 64 bit and a minimum of 8mb of RAM, preferably in two slots with two more open? Not knocking your logic, just your implementation. History has shown this old man that RAM requirements go up faster than Moore's Law. 4GB of RAM is too low with Win7 aggressive caching, which is one of the very few advantages of it. Even the file servers (Linux) are using 24GB of ram so they can cache everything, and they were installed two years ago. 4GB just isn't enough for anything other than an email/web only laptop.

Re:One Problem (2)

w0mprat (1317953) | more than 3 years ago | (#36821042)

In practice it won't matter. I calculated my 60gb SSD would have a lifespan of eight years based on it's current use over 6 months. Well before then 60gb won't be a useful size, and it would be bested in both price and performance by a $20 bargain bin 2 terabyte USB stick in 2019. It's more likely the RoHS compliant crap the controller board is soldered up with these days will fail long before the NAND chips actually begin to eat itself. Considering many gadgets these days have a 2-3 year design life (OTTOMH some laptop manurfacturers report 25% failure on three year warranty programs) before they are horrifically obsolete flash cycle limitations is just not a problem.

I'm confused (1)

jandrese (485) | more than 3 years ago | (#36819896)

Last time I checked, DRAM was still an order of magnitude faster than NAND flash, so swapping out your memory for flash storage would seem to be insane to me. At first I thought it was going to be how replacing a spinning disk with a flash drive is a much more noticeable upgrade than going from 4GB to 8GB of memory, but the article seems to suggest that because the market dipped a bit, DRAM is going to die out entirely and we'll be using only NAND flash for all memory on the system.

There would have to be some tremendous breakthroughs in speed, power, and especially reliability before I ever considered such a thing. It would be complete lunacy with today's technology.

Re:I'm confused (2)

MrEricSir (398214) | more than 3 years ago | (#36819934)

You're missing the point:

After reviewing a "wide range of DRAM and NAND configurations," as well as nearly 300 industry-standard PC benchmarks, the researchers concluded that even at today's prices, a dollar's worth of NAND flash improves PC performance more than adding a dollar's worth of DRAM.

Nobody is talking about what's faster or cheaper. They're comparing apples and oranges -- and telling you which to buy.

Re:I'm confused (2)

afidel (530433) | more than 3 years ago | (#36820106)

Well, I guess that's true to a point. For instance for my Oracle BI database server we put as many 8GB DIMM's as would fit into the system (at full speed) and the next biggest bang for the buck was using a 640GB MLC flash card from FusionIO, the card cost about as much as swapping the DIMM's for 16GB units but provided significantly more performance improvement than adding another 96GB of ram would have. Now if you told me to put 4 or 8GB of ram in the box and add flash I would laugh at you.

Re:I'm confused (2)

timeOday (582209) | more than 3 years ago | (#36820156)

No, they're rebutting the conventional wisdom that the most cost effective way to speed up a PC is by adding more RAM. According to their (unspecified) benchmarks, you get better bang for the buck using NAND to relieve pressure on the hard disk (since they're inherently horribly slow).

Here's the crux:

"A well-designed NAND/DRAM combination brings SSD-like performance to a system at little or no price increase over a standard system based on the conventional DRAM-plus-HDD platform."

Obviously this is moot for a $2500 laptop with 8GB of ram, a big flash drive, and no hard drive. It sounds like they're arguing companies like Dell with, say, a $500 price point should start using some flash to augment the HDD even if they have to back off RAM to hit their price point.

Re:I'm confused (1)

hairyfeet (841228) | more than 3 years ago | (#36820704)

The problem is like Chewbacca it makes no sense and I sure as hell ain't paying to read their report! Here is what we DO know: 1.-RAM is several orders of magnitude FASTER than NAND, 2.- most intelligent modern OSes do serious caching of the most used programs into RAM to seriously speed performance, 3.- 4-8Gb of RAM will allow the OS to prefetch pretty much everything you use on a daily basis and then some, while 4-8Gb of NAND? Kinda useless.

In certain use cases and in certain use cases ONLY does having a MIXTURE of RAM and NAND make sense. In a mobile user's laptop, one that is constantly on the move? Makes sense. On a server where IOPS are the most important metric? makes sense. On a PC where there is only 2Gb of RAM? Does NOT make sense and would be better served by 4-8Gb of RAM which would be a hell of a lot cheaper than a SSD of any real size.

Hell with all the crap they install on them and the size of cameras nowadays i find plenty of 200-300Gb HDD PCs being brought in to add bigger drives simply because they are overloaded, yet we are talking a cool $500+ to add a SSD of that size or larger easily. ATM unless you are a geek that know about installing to separate partitions so you can use a mixed drive setup, or as I said one of the above use cases SSD just doesn't make sense for the vast majority and trying to claim just because the price of RAM went up a bit suddenly SSDs, which are still frankly insanely priced and are still not really stable [codinghorror.com] is suddenly the better deal? I gotta call bullshit.

Re:I'm confused (2)

TheRaven64 (641858) | more than 3 years ago | (#36820868)

4-8Gb of RAM will allow the OS to prefetch pretty much everything you use on a daily basis and then some, while 4-8Gb of NAND

The first of these is only true in theory. You may only access 4-8GB of data per day, but predicting which 4-8GB that will be is hard. Operating systems get the low hanging fruit, but the difference in performance from disk caching hits diminishing returns after about 1GB. With 8GB, you're likely to have memory free, because the OS can't make good decisions about what to cache.

The second half is completely missing the point made in the summary. 8GB of RAM may give more of a performance increase than 8GB of flash, but they're not the same price. You can get about 64GB of flash for the price of 8GB of laptop RAM, and 64GB of flash makes a much bigger difference to performance than 8GB of RAM.

Re:I'm confused (1)

Culture20 (968837) | more than 3 years ago | (#36821272)

and 64GB of flash makes a much bigger difference to performance than 8GB of RAM.

except it doesn't. That's like saying 2TB of 5.25 Floppies make a bigger difference to performance than an 8MB HDD. Bigger storage space does not equal faster speed.

Caching disk data in Flash instead of DRAM (1)

billstewart (78916) | more than 3 years ago | (#36820228)

I suspect that what they're talking about is the effect of caching data from your disk drives in Flash instead of DRAM, and also letting you swap data out of DRAM into Flash instead of disk. Flash is cheap enough that for typical applications, you can cache most of your active data there, not having to wait for rotating machinery.

Windows 7 is supposed to have some feature that manages this in an intelligent way - so you can speed up your machine for a year or so by adding a $10-20 memory stick. (I'm not running Win7, so I haven't tried it - but my laptop has an SD card slot, which would let me leave a card in there full time, without it sticking out like a USB stick.)

Re:Caching disk data in Flash instead of DRAM (1)

bemymonkey (1244086) | more than 3 years ago | (#36820426)

"Windows 7 is supposed to have some feature that manages this in an intelligent way - so you can speed up your machine for a year or so by adding a $10-20 memory stick. (I'm not running Win7, so I haven't tried it - but my laptop has an SD card slot, which would let me leave a card in there full time, without it sticking out like a USB stick.)"

I've tried it on multiple systems, with fast USB sticks - Superfetch is much faster and more efficient. Only problem there: Many of the current generation (Sandy Bridge) laptop chips only seem to support 8GB of RAM, with the top end models (mostly quad cores) maxing out at 16GB.

BS Article (1)

fluffy99 (870997) | more than 3 years ago | (#36819912)

The article gives zero useful information and a link where you can buy the actual study. What was the pricing used for the comparison of $1 dram versus $1 nand? Surely this is OS dependent as well.

Re:BS Article (1)

Anonymous Coward | more than 3 years ago | (#36819986)

It is. Sounds like they haven't taken SSD wear into account. Windows' "swap long before I've run out of physical RAM" behaviour would kill an SSD long before any other OS would.

Re:BS Article (1)

Skuto (171945) | more than 3 years ago | (#36820158)

People are using Windows on SSD's just fine. Windows 7 actually disables the behavior you speak of on an SSD, anyway.

Most SSD's seem to die from controller failure way before the actual flash cells are dead.

die from controller failure? (1)

reiisi (1211052) | more than 3 years ago | (#36820440)

Why should the controller fail, especially, why should the controller fail before the flash?

Re:die from controller failure? (2)

Skuto (171945) | more than 3 years ago | (#36820506)

You have to ask the makers of the devices, but if I have to guess: the flash cells are designed by the top engineers of each fab+their partners and go through very extensive testing and validation cycles. The controllers are a complicated electronic designed for maximum speed by the lowest bidder and rushed to the market, and which additionally has to interact with similarly designed devices.

Human failure will kill the devices way before low-level physics will.

Re:die from controller failure? (0)

Anonymous Coward | more than 3 years ago | (#36820526)

Bcos they are the ones who translate slow data transfers to & from the flash to faster data transfers from & to the host. Flash read & write times are typically slow, and that's not the part that will cause a controller to fail. A controller, over time, is more likely to fail due to the high speed data transfers to and from the CPU of the host system.

Re:die from controller failure? (1)

daid303 (843777) | more than 3 years ago | (#36820762)

Because it's badly designed. Or more, it's designed for speed, not data safety. Read that again, SSD is designed to give you data fast, not to give you the right data all the time. The controllers need to account for wear-leveling and shifting around data so it uses less erase blocks. (A sector on a spinning harddisk is 512bytes, an erase block on a flash chip can be as large as 128kb)

The controller needs to maintain internal management of the flash layout. A virtual mapping so to say. 1 error in this mapping and your drive is junk. SD, compact flash, USB flash drives all show this problem. And there are only a few manufacturers have products that guarantee the safety of your data, and you pay the top price. (600 euro for an industrial grade CF card of 32GB) just having an "industrial grade" device doesn't guarantee anything, I have a few broken SD cards on my desk to prove it. So far CF is the only thing we found to be really safe, for a price, from the right manufacturer.

I won't trust my data to flash until we can access the raw flash and use something like JFFS2 or UBIFS.

Re:BS Article (2)

Required Snark (1702878) | more than 3 years ago | (#36820026)

Does this take into account the user software profile? Somehow I doubt that trading NAND for DRAM will give you muct help when you are running a lot of CGI rendering or PhotoShop code. Maybe there would be a benefit if you are just running a browser, but even that sounds a bit off base to me.

Who do they expect to buy this study? It has a rotten order about it...

Re:BS Article (1)

yacc143 (975862) | more than 3 years ago | (#36820546)

Well, it's obvious, that Flash is superior swap:

-) it's random access. The huge impact of seeking (measured in ms) is gone.
-) it's relatively fast at reading/writing too, compared to normal hdd.

So yes, it's obvious that adding flash for swap makes sense.

Now if flash-swap can substitute RAM depends naturally a little bit on the workload.

But 2x4GB DIMMs cost your around 44€ here around. A small SSD in 230-270MB/s range costs 62€ for 32GB.

So you get about 2.8x as much "capacity" for SSD compared to RAM, per monetary unit.

Ah, one important point, most motherboards are limited to at most 16GB RAM in practice (4 DIMM slots), and many users might have a setup where they cannot add RAM without at least throwing away some (4x2GB DIMMs is a popular setup for 8GB some time ago, implies that to upgrade to 16GB you need to replace the complete memory). SATA connectors are usually not as scarce, plus you can stuff 300GB SSD swap into a common PC, while anything more than 16GB will take you into the realm of expensive server/workstation motherboards.

So the benefits for SSD swap are:
-) it's much better swap than hdd.
-) it allows to run workloads that need more than 16GB RAM neatly. (it's more than a magnitude faster than hdd, and it's random access, which makes it many magnitudes better in that discipline. Actually, with highend SSDs you can get into a range of being only about a magnitude slower than RAM)

The benefits of RAM OTOH.
-) it's directly addressable, it's faster, it's RAM.
-) it's clearly faster than SSD swap, if you can get enough RAM into the box to run your job.

yacc

Re:BS Article (1)

elashish14 (1302231) | more than 3 years ago | (#36820144)

FTA :

After reviewing a "wide range of DRAM and NAND configurations," as well as nearly 300 industry-standard PC benchmarks, the researchers concluded that even at today's prices, a dollar's worth of NAND flash improves PC performance more than adding a dollar's worth of DRAM.

How in hell's name do they conclude this? Do they extrapolate from zero or something? I mean, if your machine starts out with say, 2-4GB of RAM, which is usually enough for running most of your applications (minus cache), what do you think is gonna make more of a difference? Adding RAM will just cause the OS to cache more, so you're just limited by HDD-DRAM speed. On the other hand, if you stick a NAND in there, you'll still be caching but at the speed of NAND-DRAM, which is considerably faster, plus stored permanently over power cycles. Of course, I'm sure the authors failed to take into consideration the long-term durability and performance issues of NAND which makes these dollar figures totally worthless.

All we're seeing is a finer segmentation of memory/storage hierarchy, but DRAM and NAND still have entirely different niches, though NAND tends to encroach on both of its sides. The take-home message is that if you have a lot of RAM, adding more ain't gonna help cause you're just throttled by your HD transfer speeds and the efficiency of your caching algorithms - so just buy a nice, reasonably speedy 8-16GB SSD and put all your system files on that.

Any fool could tell you this without needing to read this stupid report. DRAM isn't going anywhere. Of course it will devalue slightly, but there will always be an incentive for computers to have more, even if the gains are slim - NAND can't change that in any way.

Re:BS Article (1)

yacc143 (975862) | more than 3 years ago | (#36820588)

Okay, have anyone here experienced flash wear out? Hmmm, no hands raised. Performance issues with modern OS and modern (as in last year introduced stuff) SSD? No hands again.

It's absolutely correct, that flash can wear out. Flash as in flash memory cells. Modern SSDs have quite a bit of controller logic to handle this. Plus replacement blocks. So yes, if you use it extremely intensively, e.g. as swap, SSD may (or not) give up after 2 years or so. Hint: I'm used to swapping hdds once per year, to avoid data loss. Wonder where the durability problem of flash is?

Re:BS Article (1)

gmack (197796) | more than 3 years ago | (#36821032)

Caching more is pointless since it only caches when you load things the first time. Adding a 32 GB SSD as an OS drive did more to accelerate my system than going from 4 GB to 8 GB RAM did. For desktop use where each app load will pull in a ton of libraries from all over the drive it is ideal and at my usage pattern it will be a good 10 years before I even start to see the drive wear out.

Details: 8 GB RAM, 32 GB SSD for OS and applications, 1 TB for data.

Missing quote (2)

DigiShaman (671371) | more than 3 years ago | (#36819920)

"An appropriate balance of NAND, DRAM, and an HDD yields superior performance per dollar to a simple DRAM/HDD system,"

Basically, TFA is saying that it will be awhile before we go back to a unified cache that's both RAM and storage (like core memory). Need more RAM, shrink the drive partition. Need more file storage, sacrifice RAM. It all sounds good in theory, but bus speeds and CPU technology change rapidly. I seriously doubt they can create a standardized I/O bus for removable NAND based storage devices and still keep up with future performance demands.

Re:Missing quote (0)

Anonymous Coward | more than 3 years ago | (#36820056)

I seriously doubt they can create a standardized I/O bus for removable NAND based storage devices and still keep up with future performance demands.

Basically they did a study, and buying an SSD improves performance per dollar in a system with DRAM and HDD already in it. Hardly groundbreaking imo.

Re:Missing quote (1)

kaizokuace (1082079) | more than 3 years ago | (#36820350)

wasn't that the potential for memristor technology if that ever pans out? Except its storage, RAM and logic?

Re:Missing quote (1)

blind biker (1066130) | more than 3 years ago | (#36820516)

Basically, TFA is saying that it will be awhile before we go back to a unified cache that's both RAM and storage (like core memory).

Actually, core memory was used exactly as RAM and not as storage, even though it did have data retention capability (obviously, as it was based on ferromagnetic effects). The actual storage was done on mechanical devices. Heck, back in those days, you had some fast rotating drums with lots of reading heads - a hard drive of sorts, except that it had fast data access and throughput, but limited capacity. Even this, seemingly hard-drive-like device, was used as RAM only.

Correlation is not causation (2)

scdeimos (632778) | more than 3 years ago | (#36820062)

The effects of NAND flash adoption are already being felt in the DRAM market, as revenue in 2011 is expected to decline 11.8%.

The former is not the cause of the latter. The rise of mobile devices with less DRAM in them is more likely to blame: less people are buying new PCs and Laptops when their phones and/or tablets can do everything they need.

Re:Correlation is not causation (0)

Anonymous Coward | more than 3 years ago | (#36821376)

It is also because of a bubble of people buying computers in 2009/2010. The revenue is more than 5 mil than in 2009.

There is a reason why flash is not used as system memory except in mobile devices - it is S L O W ! !
It will most likely replace spinning HDD's eventually, but not it won't touch system ram for a long, long, time.

This whole article is a whole load of crap designed to spread FUD and to get people to buy a report online that says you should use rapidboost on a pc or SSD's, and that flash is is the future for all.

Seriously, this is for a computer magazine(supposedly by a tech), been slashdotted, and no-one has picked up on the tech issues and flamed to oblivion??

article and post - sucks (1)

postmortem (906676) | more than 3 years ago | (#36820080)

Holy confusion. From reading the slashdot post you would think that NAND is faster than DDR3...Neither post or article are explaining this in simple terms: if you replace/augment your HDD with SDD you get more performance boost that any other upgrade would for $

Re:article and post - sucks (1)

BitZtream (692029) | more than 3 years ago | (#36820154)

And that is a false statement.

At least some times.

Its also true sometimes.

Either way, both the summary and the article are ignorant, poorly written amateur pieces written by someone who probably just learned what flash is and that SSDs exist by the looks of it.

If I boot my system and run entirely from ram, because thats the way my workload works ... NAND is going to do me no good. My little app spends its time doing nbody physics simulations via opencl ...

However, if I do a lot of random file IO and spend most of my time reading/writing data to the disk rather than performing raw calculations, then disk IO speed matters more. Say ... like my DB server.

There is no magic bullet, pretending there is ... is retarded.

Hasn't learned what flash is, maybe? (1)

reiisi (1211052) | more than 3 years ago | (#36820460)

I'm more inclined to think the author has just learned what RAM is and doesn't yet understand the difference between flash RAM and dRAM.

Nether have you? (0)

Anonymous Coward | more than 3 years ago | (#36820944)

Unless it's a typo, even you don't seem to know that flash is a more versative type of ROM, not RAM (DRAM or SRAM)

The nether reaches of my memory (1)

reiisi (1211052) | more than 3 years ago | (#36821386)

A quick web search doesn't bring up any examples, but I remember when flash first came out, some of the manufacturers insisted on calling it "flash RAM" in their ads.

I also remember the arguments on the BBSes, and the conclusion that EEPROM was already different enough from UVEPROM and other ROM as to call into question the ROM part of the acronym, and that "flash ROM" seemed a bit like an oymoron. Enough people have complained about calling it flash RAM that the maufacturers have gone to "flash memory". But you still see lots of examples of the term "flash RAM" in use on the web, and it's really not technically incorrect. (Any re-writable store used to be called RAM in some camps, although you're probably too young to remember that. Sure, some other camps insisted on SRWM or the like for serially re-writable devices.)

Sure, the term causes confusion, see the article we seem to be commenting on.

Re:Nether have you? (1)

jawtheshark (198669) | more than 3 years ago | (#36821630)

ROM means Read Only Memory. Flash definitely isn't ROM in that sense: it is EEPROM, Electrically Erasable Programmable Read-Only Memory. The most common use of this before the SSD craze was the storage of BIOS settings. RAM means Random Access Memory, which typically is writeable (but doesn't have to be) as ROM usually is also RAM.

RAM and ROM are as such not mutually exclusive and mean different things. They don't even have to be silicon. Take a CD-ROM, which is read-only memory, but also random access (it's a block device when used as data. Music CDs are not random access) and they are not chips made from silicon.

A bit confusing (3, Insightful)

m.dillon (147925) | more than 3 years ago | (#36820118)

I think all they mean is that dram isn't really all that cost effective as a data cache. For data that one intends to export out the network. Storing that data on a SSD, assuming it's a relatively static data set (which most is), uses far less power and costs less than purchasing an equivalent amount of DRAM (and the much larger mobo required to hold that DRAM). The access times are plenty fast enough to still saturate the network. That's all. Not rocket science.

This has been known for several years. Replicate a small server with 8-16G of ram + a 160G SSD + a 2TB HDD sits right on the sweet spot. In fact, even 4G of ram would probably be fine. The idea is not to replace your hard drive but instead to insert another layer of cheap caching to avoid having to maintain a complex, expensive, power hungry HDD storage system just to get better throughput.

-Matt

Re:A bit confusing (1)

BitZtream (692029) | more than 3 years ago | (#36820220)

This has been known for several years. Replicate a small server with 8-16G of ram + a 160G SSD + a 2TB HDD sits right on the sweet spot. In fact, even 4G of ram would probably be fine. The idea is not to replace your hard drive but instead to insert another layer of cheap caching to avoid having to maintain a complex, expensive, power hungry HDD storage system just to get better throughput.

Wow, did you really just make such a silly statement?

I expected far better out of someone like you.

Hits the sweet spot for what? Something that easily fits its working set into 8-16G of ram? Sure. But the SSD is entirely unneeded in that situation too probably, but oh hey, you might boot an extra second or two faster. No, I'm not wrong, you and I just have entirely different ideas about what we're trying to do with that machine. I have a customer firewall that needs not an SSD and 2TB drive, it net boots. It needs massive amounts of ram for the huge state tables it maintains, but there is 0 disk IO on the machine after boot. Adding an SSD and standard HD to it would be a waste of money and additional points of failure.

This whole discussion is silly, it assumes that there is 'a better way to do it every time', which both you, and the article seem to not understand is utterly wrong.

Next you'll try to tell us what the answer is to 'whats the best possible computer configuration?' or 'the best programming language is always XXX'.

You of all people should know better than to make such silly blanket statements. Its mind boggling that someone who plays with VMM code for fun would be so silly. Did someone hack your account? I had to check at least 3 times to verify that you are the same Matt Dillion that I'm thinking of.

Re:A bit confusing (1)

Skuto (171945) | more than 3 years ago | (#36820600)

Woosh!

Hits the sweet spot for what?

The very first lines of the post you're criticizing describe the use case:

I think all they mean is that dram isn't really all that cost effective as a data cache. For data that one intends to export out the network.

Matt's point explained succinctly: SSD speeds are faster than network speeds. SSD cost per Gb is less than RAM cost per Gb. Ergo, SSD are a more cost-effective cache, because the extra speed from RAM is useless.

A firewall clearly doesn't fit the "data that one intends to export out the network" use case.

wow, people are finally catching on (0)

Anonymous Coward | more than 3 years ago | (#36820142)

I've been telling people this ever since SSD drives came out. A system with 2GB of DRAM and an SSD drive will easily outperform a system with 8GB of DRAM with a traditional Hard Drive in every benchmark that matters to the average user. It'll boot far, far faster, programs will load instantly, defrag's are a thing of the past, virus scans take mere seconds instead of hours, and by the time your SSD drive is used up, you probably need a new computer anyways.

Now mix two Corsair SSD drives in RAID 0 like i've done for the past year along with 4GB of DRAM and the PC absolutely screams, there is no comparison, none whatsoever between traditional hard drives and SSD drives. Even (6) 15k RPM SCSI drives in stripe RAID can't keep up with the I/O of 1 SSD.

LESS DRAM != Performance hike (0)

Anonymous Coward | more than 3 years ago | (#36820328)

No, reducing RAM never results in increased performance, since the processor is going to depend only on RAM for memory access. You have a memory hierarchy whereby data from HDD/SSD will be moved to DRAM, data from DRAM to the CPU cache, and data from CPU cache to its internal registers. The CPU will never access data directly from SSD, which has the identical interface to HDD*. So altering the density of the RAM will have a negative performance impact, unless the system itself is doing maximum utilization @ 2GB and doesn't need the extra 6GB.

The only thing that will be faster will be the data transfer b/w SSD and DRAM, as opposed to HDD and DRAM. That performance improvement does allow less DRAM to be used, but if less DRAM is used, it has a negative effect on the CPU, which is more likely to encounter a miss while fetching data from DRAM.

*Note I'm talking here about SSDs w/ SATA/PATA interfaces, not the ones that are on the PCI-X bus.

Re:wow, people are finally catching on (1)

WaffleMonster (969671) | more than 3 years ago | (#36820398)

I've been telling people this ever since SSD drives came out. A system with 2GB of DRAM and an SSD drive will easily outperform a system with 8GB of DRAM with a traditional Hard Drive in every benchmark that matters to the average user. It'll boot far, far faster, programs will load instantly, defrag's are a thing of the past, virus scans take mere seconds instead of hours, and by the time your SSD drive is used up, you probably need a new computer anyways

Unless you need to use 8GB of RAM to complete your work. At which point your totally screwed. I'm pretty sure using an MLC SSD as virtual memory at this scale voids your warranty.

Now mix two Corsair SSD drives in RAID 0 like i've done for the past year along with 4GB of DRAM and the PC absolutely screams, there is no comparison, none whatsoever between traditional hard drives and SSD drives. Even (6) 15k RPM SCSI drives in stripe RAID can't keep up with the I/O of 1 SSD.

A pair of mirrored 7200 RPM disk drives with 32 GB of RAM and a warm cache runs circles around your setup. It would also be more reliable, cheaper and provide 10x the storage capacity.

Re:wow, people are finally catching on (1)

Skuto (171945) | more than 3 years ago | (#36820556)

A pair of mirrored 7200 RPM disk drives with 32 GB of RAM and a warm cache runs circles around your setup. It would also be more reliable, cheaper and provide 10x the storage capacity.

Depends entirely on the workload. The HD drives will lose if:

a) The working set exceeds 32GB. If the accesses are random, they will lose by 2-3 orders of magnitude.
b) Whenever there is a need to commit or sync the writes to disk. On a normal system, that will happen every few seconds. If you disable that, your reliability argument is gone.

Re:wow, people are finally catching on (1)

gilesjuk (604902) | more than 3 years ago | (#36821648)

I think that's an admission that modern software is too bloated and virtual memory on a computer kills performance.

Apples & pineapples (0)

Anonymous Coward | more than 3 years ago | (#36820194)

Since a Cesarean is a lot less expensive than a heart bypass operation, expect a lot of heart patients to visit OBGYNs instead of heart specialists

Have the geniuses who put this report together considered the fact that the architecture of NAND flash has remained largely unchanged since its original definition, whereas DRAM has undergone several generational changes in architecture, starting from asynchronous DRAM to EDO-DRAM to SDRAM to DDR1 to DDR2 to now DDR3? A lot more techniques have been incorporated to make these faster and lower power, while struggling on the cost front. Had NAND undergone all this, they too wouldn't be any cheaper than DRAM. Besides, these prices are more often a function of supply/demand, and sometimes, you have fabs switching b/w these products depending on their margins.

There have been some moves towards incorporating some of these interfaces, such as DDR, in flash, but that's been happening in NOR flash, which is completely different from NAND not only architecture wise, but also cost wise. Usually, when that's happened, it has been for the sake of eliminating shadow RAM (usually SRAM) that is needed to feed the processor data at a rate that standard mode flash cannot deliver. The calculation here is that the extra cost of these performance enhancement features is less than the cost of the RAM that's being replaced, or else, what good is it?

In theory, the ideal memory is that which would be really fast in both reading & writing (like RAM), non-volatile (like flash), low power consumption, capable of packing really high density on a die, and extremely low $/GB ratio. Since no type of memory satisfies all these, you have things like SRAM, DRAM, NAND flash, NOR flash and some variations. Each has its own importance, and the main importance of NAND flash has always been mass data storage. DRAM, otoh, is an external cache memory to a processor. That's a role that simply can not be fulfilled by NAND flash. Battery backed DRAM can, in some applications, substitute flash if those read/write times are more important than the cost of the whole thing.

If the DRAM market has been feeling a pinch, it ain't, and cannot be b'cos of NAND flash, but rather, b'cos memory prices across the board have always been under pressure (except during shortages). Sometimes, it's due to fabs switching b/w DRAM and NAND depending on which is more profitable @ any given time. But projecting the business decisions of manufacturers on to their customers, whose needs for these different products vary, and are by no means interchangeable, is a ludicrous assertion to make.

NAND Flash worse the DRAM (1)

WaffleMonster (969671) | more than 3 years ago | (#36820292)

Is the assertion really hybrid hard disks and turbo memory are having a noticable negative effect on the DRAM market?

Trying to imply a relationship between two markets by realitive growth is especially rediculous considering explosion of the smart phone market which relies entirely on flash.

The only thing more rediculous about TFA is the idea NAND is in any way a suitable replacement for DRAM.

Re:NAND Flash worse the DRAM (0)

Anonymous Coward | more than 3 years ago | (#36820822)

In the long term, it could be. I could see portable devices and eventually even desktops/servers moving to a model where there's a limited pool of very fast DRAM for truly ephemeral stuff (like trashable caches and indexes, etc that the OS maintains), and a large amount of NAND being used as persistent storage (both for the filesystem *and* as a persistent area of virtual memory for user processes and the kernel to use, allowing super low power sleep states that can wake instantly).

Server market (1)

Torodung (31985) | more than 3 years ago | (#36820324)

I see this article as being myopically focused upon "main memory in portable end-user devices."

DRAM is going to stay vital for at least the server market, and I would guess the desktop market too (for as long as desktops last). Your iPad 3, maybe they have a point, but server apps would work current NAND into an early grave. The cost savings would be greatly offset by the service outages.

And since "the Cloud" is the new big thing, that means that DRAM is going to be around for a while. I don't see how the marginalization of the desktop is going to also kill the server market. The death of the PC? I'll buy that. But it's not going to kill DRAM because too many other platforms use it.

Now, if we ignore all those servers and just look at the magical end-user devices, well, that would be totally daft. Those devices aren't worth spit without something storing and delivering content to them. That something is an actual computer, rather than just a device, and it can't be using NAND for its main memory.

IMO, anyone who is doing actual computing is going to be using DRAM for the foreseeable future.

Pirates and Global warming (1)

drolli (522659) | more than 3 years ago | (#36820464)

If SSDs appear and DRAM goes down it could aso be that there are now more subnotebooks or ultraportibles in which DRAM is a power consumer and HDs are too big? It could be that MS, under the pressure of the first netbook wave which contained linux has shown reason and put out Windows 7 in opions which allow to run it on normal machines. I mean. Just thinking.

I personally dont see Flash replacing DRAM soon. I see that DRAM memories stop to grow for other reasons.

Let me say it that way round: i see that my PCs DRAM in 2000 was 128 times more than in 1990 and i see that until 2010 it has only grown by 16 times, nevertheless if the machine contains SSD or HDD.

They should make a mini-PCIe device for laptops (1)

Animal Farm Pig (1600047) | more than 3 years ago | (#36820504)

It would be a couple GB of flash that is accessible to the OS as a block device. Then, let the OS use it for paging and for caching of frequently access files or blocks.

There should be a branding campaign so that consumers know that it is extra memory that will speed up their machine. Call it something like "turbo memory."

SSD ReadyBoost ? (1)

obarthelemy (160321) | more than 3 years ago | (#36820726)

I'm assuming MS is keeping an SSD version of ReadyBoost as a Windows 8 "new feature". This should offer a very good price/performance ratio.

Re:SSD ReadyBoost ? (1)

gbjbaanb (229885) | more than 3 years ago | (#36820986)

I think there's a limit to how big your readyboost cache canbe before it starts to degrade performance - if you're reading all the time, then it's fine, but when you start to write you have to write to both your SSD and the backing store or invalidate the cached data you've just modified.

Besides, a USB flash drive comes in sizes up to 128Gb, and they're a lot cheaper than SSDs. If you have a SSD, install it as a drive!

Re:SSD ReadyBoost ? (1)

obarthelemy (160321) | more than 3 years ago | (#36821178)

I was thinking, indeed, of a very small SSD delivering most of the performance of a full-size one, at a fraction of the cost. Something along the lines of 80% of the performance for 20% of the size, and cost.

I'm trying out USB3 readyboost, 7 seems to grab 4GB max.

NAND/DRAM/HDD (1)

hsa (598343) | more than 3 years ago | (#36820912)

The right balance of NAND, DRAM and an HDD yields better results than DRAM and HDDs, study finds

So.. they have NAND, DRAM and HDDs, and they choose to kill.. DRAM? What? If something is going to fade away it is the HDDs..

I actually read the "article" (1)

strikethree (811449) | more than 3 years ago | (#36821004)

They give no information about how they measured and came up with this: a dollar's worth of NAND flash improves PC performance more than adding a dollar's worth of DRAM. The closest they come to explaining it is this: After reviewing a "wide range of DRAM and NAND configurations," as well as nearly 300 industry-standard PC benchmarks

Total garbage. After working with systems that have huge amounts of RAM in them, I can only conclude they are basing this off of Microsoft's paging algorithms. Put the swap/pagefile on a NAND device and things will really speed up due to the abusively aggressive nature of Microsoft's paging algorithms. If you could make a virtual ram drive to put the page file in, it would be even faster than a NAND solution... but these guys probably do not know how to do that.

Again, if such grandiose claims are going to be made, provide some hard data.

strike

Re:I actually read the "article" (0)

Anonymous Coward | more than 3 years ago | (#36821268)

The actual article costs 5000 $.
Are you referring to that?

It'll never happen (0)

Anonymous Coward | more than 3 years ago | (#36821096)

The block-erase nature of NAND will preclude its use as main system memory. One application changing one bit of memory would necessitate the erasure and reprogramming of an entire block of memory, some of which would probably belong to another application, which would be a security violation, or at the very least require that application to halt while the read/modify/erase/write cycle is performed.

Second, NAND does not last forever. The newer 25nm NAND flash is only good for a couple thousand PE cycles, so you'd be replacing your system memory every, oh, couple of hours or so.

XIF works great for embedded systems where only a small amount of data needs to be stored or changed frequently. For server or desktop applications where things are constantly changing on a more massive scale, XIF is impractical.

NAND _might_ be faster in XIF applications not requiring many writes. DRAM blows NAND away on write speed, especially if the NAND block has to be erased.

Re:It'll never happen (0)

Anonymous Coward | more than 3 years ago | (#36821530)

XIF is precisely the sort of application for which NOR flash would be preferred.

But your explanation is right - block sizes, which typically keep growing w/ flash density, are enough of a reason flash (be it NAND or NOR) can never replace DRAM. Only scenario I see it happening is if DRAM finds a way of being non-volatile, in addition to everything else it already is.

Turbocharging (0)

Anonymous Coward | more than 3 years ago | (#36821608)

It's just like cars....

For my daily driver (server), I want something reliable and stable. I'll accept lower horsepower for reliability and wear/tear.

For my weekend toy, I want fulltime AWD, a turbocharged motor, and a manual transmission. Handles like no other, 400+ horsepower from a little 4 cylinder, and decently reliable, but not compared to my daily driver.

In short, you people are idiots placing such fragile tech into servers, just to gain a bit more performance. I'll see you in 6 months when your SSD fails and your NAND Flash memory is corrupting your caches and causing all kinds of problems. +1 if you had RAID and had that corrupted too when the SSD never reported a failure to the controller. SSDs + RAID = headache.

I'll keep my reliability on the servers and use the new stuff to have fun on my desktop every once in awhile.

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?