Follow Slashdot stories on Twitter

 


Forgot your password?
Close
typodupeerror
×
Data Storage Hardware

Samsung Announces Fastest 64-GB SSD 145

Posted by kdawson from the want-to-see-it-again dept.
XueCast writes "The new solid-state drive from Samsung can write data at 100 MB/s and read at 120 MB/s. This handily outperforms other SSDs now on the market, which typically feature only 50-80 MB/s read/write rates. Samsung's SSD will come in two form factors, 1.8" and 2.5", and will be running on the SATA II standard. It will only consume 50% of the power of current SSDs. There is no information yet about price."
This discussion has been archived. No new comments can be posted.

Samsung Announces Fastest 64-GB SSD More

Samsung Announces Fastest 64-GB SSD

Comments Filter:
  • A few machines in the past have had SSD's and the manufacturer did nothing to limit the Input and output of the operating system, therefore limiting the longevity of the drive. With Asus' eeePC just launched, I'm not sure what they've done as they do use a SSD. Does anyone expect we will see a rise in both development and popularity of Linux distributions that will limit input and output access to the drives by some means? Does anyone think Microsoft would do anything to this extent within the near futu

    • Re:I/O limited distros more popular? (Score:5, Informative)

      by HateBreeder ( 656491 ) on Wednesday November 07, 2007 @03:49AM (#21264303)
      Thanks to algorithms that spread written data across the chip, MTBF's of SSD are much higher than those of regular HDDs with similar usuage patterns.

      Furthermore, A simple buffering scheme sounds likely to solve most of the problems you're talking about (Assuming it's constantly many small writes done by the OS... for say, log file keeping or file access-time updating).

      • Re: (Score:3, Informative)

        by DoofusOfDeath ( 636671 )

        Thanks to algorithms that spread written data across the chip, MTBF's of SSD are much higher than those of regular HDDs with similar usuage patterns.

        MTBF doesn't mean [wikipedia.org] what most people think it means, and is less useful [wikipedia.org] than most people treat it.

      • Re: (Score:3, Interesting)

        by Taagehornet ( 984739 )

        Does anyone around here know of any numbers backing up the claimed high values for MTBF? I'm not unwilling to accept that the values are indeed high, but I'm looking for something closer to reality than the Wikipedia article arriving at an expected lifetime of 26,600 years.

        The flash memory modules I've encountered have guaranteed a minimum of 100.000 write cycles per data memory byte before failure (NDAs prohibit me from listing the specific devices, but I suspect that this number is nothing out of the

        • Your assumptions include an empty disk with one block of data having free reign of all 64 million pages. I doubt it would be that favorable in real life.

          Consider that no matter how "clever" the algorithm is, after you junk up the drive with videos, pictures, a copy of WoW and Doom III, it's going to be half full, so that clever algorithm only has half the space to work with, accelerating the time to failure.
          • Well, that's assuming the algorithm is not allowed to move unrelated, already written, data around.
            • If it *can* move unrelated already written data, that throughput is either hidden from the 100 MB/s bus speed or subtracts from it. Either way, the data rate is going to be higher than what you expect based on what you send to the disk. This affects the wear rate in new and exciting ways!
              • This highly depends on the chip architecture.

                You can quite easily design a logic that would allow you to shift one chunk of data and write a new one in the same "write-sequence" that the 100MB/s was derived from.

                • Re:I/O limited distros more popular? (Score:5, Insightful)

                  by torkus ( 1133985 ) on Wednesday November 07, 2007 @02:28PM (#21270153)
                  How often do you feed a disk (not in a server) at 100MB/sec for any sustained period of time? Heck, how often do you feed a disk 100MB/sec for one minute much less an hour much less 2 years straight.

                  I suggest two things:

                  1) those so paranoid about drive life return to their handy array of 9.1GB disks in raid 50 and leave the thread

                  2) run perfmon (or the linux equiv.) and look at your overall disk writes for an average day, triple it and then calculate the number of years the drive will last and cut it in half for the hell of it. I'd guess the computer and storge of the drive will be long obsolete before the expected lifetime.

                  If you need to handle writing 100MB/sec of data at a constant rate for weeks/months/years then you don't need a 1.8" SSD. You need a couple pentabyte san. These drives are *perfect* for normal users, power users, heavy users. I'd gladly put one in each of our developer's PCs for doing coding and builds. Our AV guys would love them too.

        • Re:I/O limited distros more popular? (Score:5, Insightful)

          by skelly33 ( 891182 ) on Wednesday November 07, 2007 @01:02PM (#21268809)
          "let's for a moment assume that you're able to max out the drive, writing at the rated speed of 100MB/s. With a page size of 1024 bytes, that's 100.000 page updates every second, so failure will set in after 64,000,000 seconds = 2 years."

          2 years seems pretty impressive to me for beating the virtual snot out of your test subject testing in a completely unrealistic scenario. I would be surprised if my car's engine survived 2 years of running non-stop at 7,000 RPM.
          • Airplane mechanics actually do keep track of flying hours as a maintenance target, but cars lifetimes usually get counted by miles. However, suppose you do look at times - my experience with Chevy engines has been that they last about 120,000 miles, so at an average speed of 30mph, that would be 4000 hours, or about half a year (other cars should of course run longer :-) While 7000 RPM is obviously not a good speed to run the engine at, running it continuously for long periods of time is likely to be much

        • Re: (Score:3, Interesting)

          by Surt ( 22457 )
          Samsung claims an mtbf of 2,000,000 hours, which is only ~200 years, not 26,000.
          I've seen some specs listing 300,000 program/erase cycles, minimum, which would boost your 2 years to 6, and note that that's their minimum guarantee, the average lifetimes are expected to be considerably (as much as 10x) higher. Presumably these devices just write off a page if it goes bad.

          • Re:I/O limited distros more popular? (Score:5, Insightful)

            by torkus ( 1133985 ) on Wednesday November 07, 2007 @02:38PM (#21270283)
            More than 10x higher. No one sustains 10MB/sec of writes 24/7 or even averages that on an individual's computer/laptop.

            The only situation you might find to push that is a dedicated high-use AV workstation in a 24/7 media company. Oh, and never mind that workstation would be using arrayed drives for additional speed and redundancy isntead of a single drive...which would of course increase the expeted overall lifetime.

            • Re: (Score:2)

              by Surt ( 22457 )
              My 10x was referring to the expected/average number of successful program/erase cycles. The expected lifetime gets multiplied by that, and then multiplied again if you don't write at maximum bandwidth 24/7.

        • Re: (Score:3, Informative)

          by Intron ( 870560 )
          Where are you getting your numbers? Block erase is 128K or 256K on NAND flash that I've looked at, and erase time is about 1500 usec. The large flash drives measure sequential I/O across multiple chips to get their meaningless performance numbers. Random writes are still painfully slow. The controller keeps an erase count for each block to do load leveling, and when a page gets used too many times it has to swap the whole page with one that isn't used much. The article claims 8GB per chip, which seems

    • Re: (Score:3, Interesting)

      by quitte ( 1098453 )
      distributors are definately in the process of getting io down. So is Linus himself. quote from http://lkml.org/lkml/2007/8/5/171 [lkml.org] : "change relatime updates to be performed once per day." It's not only the livetime of flash memory that benefits from this. also power consumption and noise goes down for hdds. and overall io performance benefits fromsuch improvements,too. About the swap: just keep it big enough so the Kernel can free the ram of some unused data, but not a lot bigger. Twice the size of the ram

    • Re: (Score:2)

      by torkus ( 1133985 )
      Why is this the first and most frequent post every time someone mentions SSDs?

      Wear leveling means your SSD will outlast a mechanical drive.

      Moving on to a useful comment. At this speed I'm going to start looking at SSD for our high end machines. If you have to weigh performance, weight, battery life, and cost...and this dramatically wins in 3 out or 4 i'm going to start equipping high-end laptops with these. Heck, i know ULV CPUs are slow but the crappy hard drives have always been hugely limiting. We're

  • Good to hear but there are other options (Score:5, Interesting)

    by webplay ( 903555 ) on Wednesday November 07, 2007 @03:40AM (#21264265)
    This drive doesn't outperform MTRON (http://www.mtron.net/english/ [mtron.net]). They announced 120 MB/s read, 90 MB/s write drives and they are shipping 100 MB/s read, 80 MB/s write drives already. The SSD-based Fusion IO card (http://www.fusionio.com/ [fusionio.com]) at the claimed 800 MB/s read and 600 MB/s write speed would beat both them handily. Still, it's good to see a major manufacturer up its speeds.

    • Keep in mind that the FusionIO card is a card, not an SSD. SSD is used to refer to "solid-state drives" (where "solid-state" is slowly becoming synonymous with "flash", but that wasn't always the case...).

      It's pretty clear that the FusionIO card isn't a drive, because there aren't any drive interfaces on the market today that can do 600 MB/s...

      Not that I have anything against FusionIO -- on the contrary, I'd love to have one to play with -- but it's not a drive.

      • Define "drive". Remember the hardcard? (Score:5, Insightful)

        by tepples ( 727027 ) <tepplesNO@SPAMgmail.com> on Wednesday November 07, 2007 @08:26AM (#21265375) Homepage Journal

        Keep in mind that the FusionIO card is a card, not an SSD.
        Do you remember the days before ATA, when hard disk drives each came with their own controller cards? Do you remember hardcards [wikipedia.org], or hard disk drives that plugged straight into the ISA slot?

        • Re: (Score:1)

          by vio ( 95817 )
          I think maybe the gpp was simply trying to point out that FusionIO is not a "hard drive" by today's definition, ie. I cannot simply (easily?) substitute my current laptop drive with a FusionIO card, so they don't really "compete"...

          But yes, I do remember those days... talk about dating myself :-(

        • Do you remember hardcards, or hard disk drives that plugged straight into the ISA slot?

          I have a 20MB hardcard salvaged from a 286 in my closet, why? Interested? I'll throw in an unopened Tandy CoCo-80 + monitor... I'd even consider letting go of my Qume 109 terminal, in all it's amber glory. And for the first time ever, I'm also offering my 33MHz Compaq 486 Laptop, with 7" 16 color screen and built-in trackball that puts modern track-pads to shame (NOTE: no floppy, CD, modem, USB, or ethernet).

      • So, is a RAM drive not a drive then, simply because it doesn't use SATA/IDE/etc?

        I don't see how it matters at all that the FusionIO uses PCIe instead of SATA, you're still going to use it like a regular hard drive (or solid state drive, for that matter).

        If the FusionIO was exactly the same except it connected via SATA instead of PCIe, would you consider it a drive then?

    • Fusion-io is targeting a retail price of approximately $30 per Gigabyte for the ioDrive(TM).

      My wallet just told me to go take a hike!

    • What speeds? (Score:1, Troll)

      by Chemisor ( 97276 )
      120 Mbps? Oh, please! My IDE drive can do 60 Mbps, with moving parts, including that huge "read arm" thingy that actually has to move a few inches to read something. Here you have a piece of pure electronics, with no mechanical parts, and it can only double the transfer rate? I say it's pathetic. An SSD ought to have speeds comparable to RAM, in the Gbps range, and until one does, the rest are just useless ripoffs. But, of course, that's just my opinion.

      • Re:What speeds? (Score:4, Insightful)

        by JoelKatz ( 46478 ) on Wednesday November 07, 2007 @09:01AM (#21265563)
        First, you mean MBps. We're talking bytes, not bits.

        Second, your hard drive can sustain 60MB/s on the fastest part of the drive. Its average is probably much less than that (due to different linear speeds on the inside and outside of the platters).

        That speed drops catastrophically in many real-world scenarios. Small random reads, for example, become dominated by seek time and rotational latency and the high transfer rate doesn't help very much. Small random writes are only slightly better.

        It is really not "only double". It has a real-world speed that is about twice a high-end hard drive's theoretical maximum speed.

      • An SSD ought to have speeds comparable to RAM, in the Gbps range, and until one does, the rest are just useless ripoffs. But, of course, that's just my opinion^H^H^H^H^H^H^H desire with no basis in what's actually technologically feasible.

        Fixed that for you.

        • An SSD ought to have speeds comparable to RAM, in the Gbps range, and until one does, the rest are just useless ripoffs. But, of course, that's just my opinion^H^H^H^H^H^H^H desire with no basis in what's actually technologically feasible.

          Fixed that for you. ^H without googling or even reading previous posts because I prefer to assume that I know everything.

          Fixed that for you. http://www.fusionio.com/ [fusionio.com]

      • Re:What speeds? (Score:5, Informative)

        by vadim_t ( 324782 ) on Wednesday November 07, 2007 @02:00PM (#21269771) Homepage
        That 60 MB/s is almost never attainable in practice.

        SATA drives have a seek latency of about 9ms. This means that the drive can perform 111 seeks per second. Assume a very pessimistic scenario of reading a 2KB cluster. Your drive's performance is now about 200KB/s.

        For an expensive and low capacity SCSI drive, you can get 3.3ms, with about 600KB/s worst case scenario.

        This is assuming you're actually reading data you're interested in. Some of that will involve reading filesystem metadata, which from the user's POV isn't what you're actually interested in. For a directory with lots of small files I imagine you could get maybe half of that performance.

        I've seen SSD latency being quoted to be around 0.01ms. The same calculation above gives 195MB/s, assuming reading takes no extra time (which is false)

        From this you can see that a hard disk is highly limited by seek latency, while a SSD is much more limited by read/write speed.
    • Even if there is competition, it still costs more than an entire laptop just for the drive. Pretty stupid if you ask me. Btw how come if I google product search it, only PQI and Super Talent have SSD's for sale and they're 64 GB? How could they have produced one already?! Anyway, they're listed for well over $1000 so I can only imagine what Samsung wants for theirs. If you're right, I hope they realize it and drop their price to like $300 lol.
    • I just had to go look at the Fusion IO page and their FAQ and... well, let's just say, does anyone have an URL for marketting-bullshit-bingo to English babelfish please?

      By the half of the page I had developped an extreme allergy to the word "leverage". Two sentences out of three were just saying that the lever some (supposedly awesome) proprietary technology. And more importantly, I was none the wiser. There wasn't a single sentence that even said what it _does_. What makes that technology so awesome? What'

  • Outperforms? (Score:2, Interesting)

    by Anonymous Coward
    This handily outperforms other SSDs now on the market,

    Texas Memory Systems http://www.superssd.com/benefits.htm [superssd.com] says can saturate Fibre Channel (GBs/sec) and this one caps out at 100s of MB/s. Perhaps not quite so unequivocally outperforms as this statement makes it out to be.

    How about outperforms other flash based SATA SSDs now on the market???? What is surprising is that more of the SSDs don't max out the SATA pipe.

    yeah they are in different price classes but it isn't like SSDs haven't been

    • Fibre Channel is (Gb/s) not (GB/s), there is an order of magnitude difference there. Theoretical max speed on a 4 Gb/s FC card would be ~400MB/s. I seriously doubt you ever see that kind of speed on any existing FC gear.

  • 1 essential fact missing (Score:5, Interesting)

    by polar red ( 215081 ) on Wednesday November 07, 2007 @03:47AM (#21264293)
    In what price range are we talking ?

    • Re:1 essential fact missing (Score:5, Informative)

      by leuk_he ( 194174 ) on Wednesday November 07, 2007 @04:52AM (#21264543) Homepage Journal
      A small google shows that current generation of 32 GB ssd cost about $599-$1500 [dvnation.com] (depending on speed)

      the new version has double the capacity, do the math yourself.
      • Wouldn't it cost more than double? But a lot depends on WHEN I guess.

      • Yes, but... (Score:4, Funny)

        by amake ( 673443 ) on Wednesday November 07, 2007 @06:48AM (#21264995) Homepage
        ...what does a large google show?

      • Re: (Score:2)

        by Kjella ( 173770 )

        the new version has double the capacity, do the math yourself.

        If you mean to multiply by two, that's not how it works in mooremathics (yes, I just made that up). I've been paying a little attention to the development on memory sticks over 4 doublings from 512MB to 8GB now at the same price point. Every time process tech has evolved to give double capacity, it has doubled and the price stayed the same. So if the last generation cost 600-1500$ for 32GB, I predict this generation will also cost 600-1500$ for 64GB, with 32GBs for half that.

    • http://www.cio-today.com/story.xhtml?story_id=130008HEVRPI

      They cost $920 when added to a Dell laptop. The 64-GB SSD is available initially on Dell's XPS M1330 ultraportable notebook Relevant Products/Services, and, later this year, on other models in the XPS line, as well as on Latitude corporate notebooks and Dell mobile workstations. For Alienware, users can choose dual 64-GB SSDs in RAID 1 or RAID 0 configuration, or a 64-GB SSD in combination with a magnetic drive for the Area-51 m9750 high-performance gaming notebook. Prices start over $1,000 for the SSD additions.

      As far as price is concerned. I would rather get this. http://www.engadget.com/2007/08/21/toshibas-320gb-2-5-inch-hard-drive-a-worlds-best-for-laptops/
      And if battery life really concerns you probably getting external battery from electrovaya or batterygeek may eliminate that worries.

    • Re: (Score:2)

      by hatchet ( 528688 )
      This is essentially the same technology as in usb memory sticks. Currently, 8GB chips inside one of those cost around $60 and samsung could easily put 8 of those inside 2.5" drive + multipipeline controller for increased performance. we are then talking about $600 end-user price for 64GB drive... with currently available technology.

    • Re: (Score:2)

      by fm6 ( 162816 )
      If you have to ask, you can't afford it!

  • Flash! Ah ahhhh... (Score:5, Funny)

    by Anonymous Coward on Wednesday November 07, 2007 @03:48AM (#21264295)
    Savior of the Universe!

  • Vaporware (Score:1, Troll)

    by Zebra_X ( 13249 )
    This is all crap. The supposed 64 GB drives are available from sony, there is reference on dells site as well but no link to buy and no machines that carry them - other than that you can't get them anywhere. The 32 GB drives are still ~ 600 bones. While I don't mind the price, the size is just to small. MTRON says "coming soon".

    Samsungs PR department needs to slow down...

  • Cheap, fast and good. (Score:5, Interesting)

    by colonslashslash ( 762464 ) on Wednesday November 07, 2007 @03:54AM (#21264315) Homepage
    Cheap, fast, good - pick two.

    "write data at 100 MB/s and read at 120 MB/s."

    Hey cool, that's pretty fast.

    "64GB .... will only consume 50% of the power of current SSDs"

    Good, good.

    "There is no information yet about price."

    .... Ah, shit!
    • I'll take cheap and good, kthx.
    • Cheap and fast are not good?

    • Re: (Score:3, Informative)

      by Laurentiu ( 830504 )
      Why would you buy a SSD?

      1) Power consumption
      2) Battery life
      3) Power. Consumption.

      I'm looking right now at the data sheet of the latest Seagate SATA hard drive models, that tout a 3 Gb/s data rate (325 MB/s, if you are too lazy to divide by 8), and I haven't even started talking about RAID 0 algorithms yet. Yes, the Samsung SSD is fast - the caveat here is that it is fast when compared with other SSD's. The good news is that this is a relatively new technology, with great potential for improvement IMHO. But

      • Re:Cheap, fast and good. (Score:5, Informative)

        by Kjella ( 173770 ) on Wednesday November 07, 2007 @08:02AM (#21265259) Homepage

        I'm looking right now at the data sheet of the latest Seagate SATA hard drive models, that tout a 3 Gb/s data rate (325 MB/s, if you are too lazy to divide by 8), and I haven't even started talking about RAID 0 algorithms yet. Yes, the Samsung SSD is fast - the caveat here is that it is fast when compared with other SSD's. The good news is that this is a relatively new technology, with great potential for improvement IMHO. But if you don't have a laptop and a need for 4-6 hrs/battery, don't. And even if you do, you'd be probably better off just buying a spare battery.
        LOL, you're looking at the wrong specs. 3GBit/s is the SATA2 interface speed, which by the way also has two bits error correction for every byte so divide by ten for 300MB/s maximum actual throughput. In reality even the fastest WD Raptor 10k SATA drives have a sustained read/write around 80MB/s with minimums around 60MB/s. The MTRON and these Seagate disks are already faster than non-RAID HDDs, in addition to near-instant access time, lower power, lower weight, no noise, shock resistant and in smaller form factors like 1.8" and 2.5" compared to the top-of-the-line 3.5" performance I'm comparing with. Or you can compare to a mobile HDD, but then it certainly gets severely beaten in performance. Oh and RAID0 - take the most unreliable component in the system, make it twice as big, powerhungry, noisy and errorprone...

        In other words, it's more like why are you not buying SSDs:
        1. Price
        2. Price
        3. Price

        • 3GBit/s is the SATA2 interface speed, which by the way also has two bits error correction for every byte so divide by ten

          Let's see:

          2^10 = 1024
          2^8 = 256

          1024/256 = 4

          10 is the new 4!

          • Re: (Score:2)

            by Kjella ( 173770 )

            2^10 = 1024
            2^8 = 256

            1024/256 = 4

            10 is the new 4!

            Congratulations, you've proven that 2 bits have 2^2 = 4 states. It's the answer to a completely different problem than the one presented though. In the SATA interface, 1 byte = 8 bits is stored as 10 bits (8 normal + 2 ecc). The interface can transfer 3Gbit, but you only get 8/10 * 3Gbps = 2.4Gbit/s = 300MB/s of data. So without the units you should end up at 8/10, but since we divide by 8 to convert to bytes the combined effect of error correction and unit conversion is to divide by 10. I can't even begin

            • The interface can transfer 3Gbit, but you only get 8/10 * 3Gbps = 2.4Gbit/s = 300MB/s of data.

              Gah! First time around I didn't notice that "10" was meant to include the conversion from bits to bytes.
        • Truth is, I couldn't be bothered to look further than the datasheet of that last generation drive. I don't have one in my possession, so I couldn't speak from experience. I see now one test here http://www.techreport.com/articles.x/13440 [techreport.com] showing a 105 MB/s sustained data rate on a Barracuda 7200.11 .

          So performance is still not the big winner with SSD, and as you kindly point out, neither is price per GB. I still believe that power consumption is the bigger win here - and I'm looking at it from the business

      • Re: (Score:1)

        by und0 ( 928711 )
        I would add noise too, a 2.5" HD is pretty quiet, but no noiseless.

      • Re: (Score:2)

        by nmg196 ( 184961 ) *
        > Seagate SATA hard drive models, that tout a 3 Gb/s data rate (325 MB/s

        Name just one of Seagates drives that can do anywhere NEAR 325MB/s for more than a few milliseconds. I think you must have mis-read the datasheet or something. That simply can't be true. Maybe as burst rate for tiny files which reside entirely in the cache and have previously already been read.

  • Old news (Score:5, Informative)

    by rrohbeck ( 944847 ) on Wednesday November 07, 2007 @04:04AM (#21264353)
    The announcement was in March [samsung.com], mass production in June [samsung.com] and availability in September [samsung.com].

    I haven't seen a price yet but it's going to be at least close to a grand.

  • Double Dupe? (Score:2, Informative)

    by Anonymous Coward
    Is this what you call something that has been duped twice?

    Today, plus...

    Oct 28: http://hardware.slashdot.org/article.pl?sid=07/10/28/1337207 [slashdot.org]
    Oct 25: http://hardware.slashdot.org/article.pl?sid=07/10/25/149202 [slashdot.org]

  • SSD (Score:5, Funny)

    by Remnant44 ( 866124 ) on Wednesday November 07, 2007 @04:38AM (#21264483)
    I shall make this SSD my flagship.. and I will call it the Executor.
  • I feel that this is major win for ssd, because this is first 'consumer-class' ssd that has actually better (non-random) transfer speeds than average desktop hdd, at least what I have heard

  • Can't one achieve such performance & more/w RA (Score:1, Interesting)

    by Anonymous Coward
    Fill up available USB slots with USB flash drives and use software RAID 0. With many boards having 6-8 USB slots, that should yield quite decent performance, and being flash drives, should skip RAID0's downside.
  • http://www.techeblog.com/index.php/tech-gadget/worlds-largest-capacity-ssd-drive-unveiled
    The largest SSD up to date.

    Adtron has just unveiled a 2.5-inch SSD drive, which is claimed to be the world's largest capacity at 160GB. Just one drawback, this drive will cost $80-$115 per GB. For those who haven't already seen, check out a SSD vs. HDD demonstration after the jump.

    If you are like me who doesn't need power packed laptop, rather light and long lasting battery is what matters the most, SSD is something for you.

  • Whine as much as you want. I think they're sexy. I want one... bad.

  • This is how it works (Score:3, Informative)

    by Anonymous Coward on Wednesday November 07, 2007 @05:30AM (#21264707)
    1. Get sixteen, 4 GB SDHC, Class 6 or 8 innards

    2. Strap the lot in parallel, giving 64 GB

    3. 6|8 MB/sec/innard x 16 innards begets 100 MB/sec

    4. Profit !!

    Each 4GB innard is $20 currently, so 16 by 20 is 320. Figure $10 for plumbing. 1% margin for OEM (335), 50% markup by distributor (500), and another 50% by retailer (750), and there you have it $750 for 64 GB.

    Thank you !! Come again !!

    • Re:This is how it works (Score:5, Interesting)

      by SharpFang ( 651121 ) on Wednesday November 07, 2007 @06:31AM (#21264931) Homepage Journal
      Don't get the innards of the cards. Place slots on your board.
      4 USB controllers, 16 readers, 1 PCI controller, support electronics. the device would cost some $30 to produce. Sell it empty, without the cards.
      And provide a good supply of bulk amount of the cards.

      The user can replace a faulty card without scrapping the whole device. They can add or remove cards depending on the needs. They can replace cards with bigger ones when they want more space. They can physically write-protect chosen partitions of the drive.

      If you don't worry about the speed much, you can use USB hubs instead of the controllers. Then the device plugs into USB.
      • If you're talking about putting SD card readers (or similar) on the motherboard and have the ability for users to replace the cards as they wear out or need increased capacity, I think its an awesome idea.

        I'd love to get a small form factor system. Using SD memory in place of hard drives is a great solution to reducing the space, noise and heat issues. Obviously, I'd like to see speed and size increases and cost decreases. But this is a natural move for the market which will happen over time anyways.

      • Re: (Score:2, Informative)

        by Anonymous Coward
        So would that be something like this? http://www.zentek.com/product_sd_md816.htm [zentek.com]

        I have to contact them to see how much they ask for the 16 slot model and if it supports SDHC. It's a bit large but still seems interesting.

    • Re: (Score:2)

      by Kjella ( 173770 )
      1. Get sixteen, 4 GB SDHC, Class 6 or 8 innards

      Are they like the cheapest CompactFlash cards with 10000 write cycles, and in general without much in the way of wear levelling? And you want to throw them all in parallel so every write is a write to every card? No, write cycles is not a problem for real SSD disks. It is a problem for cheap hacks, because 10000 cycles are plenty for say a digicam but very poor for a computer. Particularly since you'll use this for the "working files", static huge media files p
  • First they require a GPU accelaration for Vista(Aero), and now you can use much faster swap file(majority use big gigabyte-size pagefile).Windows is pushing the computer technology further ahead.

  • I think the folks at STEC [stec-inc.com] might be a bit surprised by these claims. Especially considering that their product has been shipping for months already.

    Of course, they might be quite a bit less expensive than the Zeus SSDs, which are quite pricey...

    For some folks, high performance is the requirement and cost is no object. Those folks get their solid-state drives from folks like STEC, Texas Memory Systems [texmemsys.com], or (soon) Violin Scalable Memory [violin-memory.com]. I'd love to be able to afford this stuff. Buy maybe Samsung w

  • $24 for 4GB SD card at newegg.
    *16
    ----
    $384

    Upper limit on the price...
    • Is your $24 card a high speed one?

      • Re: (Score:3, Informative)

        by JoelKatz ( 46478 )
        Speed doesn't matter. With 16 low-speed cards, you can make one really high-speed one. It just takes a smart controller.

        In any event, even if they are slow, the speed limit doesn't come from the flash chips themselves. The speed limit comes from the controller.

        This drive has a controller and some flash chips. The cost of the controller is, maybe, $50 tops. The question is -- how much do the flash chips cost? If you can get 4GB flash cards for $24, that means the flash chips inside there must cost at most $2
        • USB card readers are about $5. It should be easy to make one with eight SD card slots and a RAID-like controller for $25 (or even a cheaper one for four cards).

          You could than buy eight cards of whatever capacity you need and plug them in - instant high speed flash drive with decent capacity!

          SATA and Firewire versions would be even better.

          • Re: (Score:2)

            by JoelKatz ( 46478 )
            A 1U box with 128 such slots should be quite doable. A 3.5 inch hard drive sized box with 24 such slots should be quite doable. SATA2 would probably be the ideal interface.

            There are really only three pieces that you need. First you need the main controller that talks SATA2 out one end and talks to the flash controllers on the other end. Then you need the interface hardware to connect to so many SD slots. Then you need the software to do the wear leveling and drive emulation.

            Notebook size is a bit trickier.
  • I think you can only write to flash memory about 1000 times before it "wears out".

    ( Sorry, no thread on flash drives is complete without it... )

    This will be frighteningly expensive. I'd go for a cheaper 16Gb version - big enough for the system partition + swap file.

  • Maybe I've been an elitist geek for too long, but I clearly remember "real" SSDs being a heck of a lot faster than 100mb/sec. Of course, they used actual DRAM instead of flash, and they'd lose everything if your battery ran out. It was essentially a hardware Ramdisk, with the (then-tremendous) benefit that it doesn't depend on the PC's memory controller, so back when the average PC had 16mb ram, you could have a 640mb SSD that pwned everything without breaking a sweat.

    A few years ago there was this bizarr
  • That's quite a decrease! I betcha next time a Super Star Destroyer takes a little damage to the bridge module, it won't go immediately crashing into the surface of a Death Star!

    Hopefully the firepower hasn't been proportionately decreased as well...

Slashdot Top Deals

THEGODDESSOFTHENETHASTWISTINGFINGERSANDHERVOICEISLIKEAJAVELININTHENIGHTDUDE

Close