Slashdot Mirror


Via Unveils 1-Watt x86 CPU

DeviceGuru writes "Taiwanese chip and board vendor Via Technologies has introduced a new ultra-low voltage (ULV) processor aimed at industrial, commercial, and ultra-mobile applications. Touted as the world's most power-efficient x86-compatible CPU, the 500MHz 'Eden ULV 500' processor debuted at an Embedded Systems Conference in Taipei this week. Via says its chip draws a minimum of 0.1 Watts, when idle, and a maximum of 1 Watt, making it a great candidate for consumer electronics devices such as UMPCs, PVRs, and such."

276 comments

  1. laptop anyone by IceFox · · Score: 4, Insightful

    A nice laptop cpu if I ever saw one.

    --
    Do you changes clothes while making the "chee-chee-cha-cha-choh" transformation sound?
    1. Re:laptop anyone by cnettel · · Score: 4, Interesting
      Yes and no. If we're going to have a backlit screen anyway (even with LEDs), we can only gain so much by reducing the CPU consumption. Amdahl's law and all that. I think the summary is quite right in pointing out UMPCs and similar devices instead.

      A really low-power Dothan or single-core Yonah will sure draw a few multiples of this beast, but they will do so while giving much better performance.

    2. Re:laptop anyone by RuBLed · · Score: 0

      Would you honestly want only 500Mhz in your laptop? But it would be great if handheld devices could have this much power though, preferably on something like a mini sized tablet (or an over-sized iPhone).

      Imagine able to code, run unit tests, access the cvs on the road.. hmmm.. but of course we all know a "better" use of such devices, like in a "quiet, secluded" place...

    3. Re:laptop anyone by FireFury03 · · Score: 1

      I think the summary is quite right in pointing out UMPCs and similar devices instead.

      Not entirely sure why we specifically need x86 for embedded stuff like PVRs though... It's not like you're having to run something Windows on it, which is tied to specific architectures.

    4. Re:laptop anyone by G+Fab · · Score: 1

      fine. Put ten of them in the laptop.

      And use that electronic paper stuff.

    5. Re:laptop anyone by montyzooooma · · Score: 2, Funny

      hmmm.. but of course we all know a "better" use of such devices, like in a "quiet, secluded" place...
      Sudoku?
    6. Re:laptop anyone by imbaczek · · Score: 2, Funny

      access the cvs on the road That's a novel, higher form of masochism. BDSM people will love you for the idea and VIA for making it possible.
    7. Re:laptop anyone by sonamchauhan · · Score: 1

      the glue chipset would take a fair bit of power :)

    8. Re:laptop anyone by Fred_A · · Score: 1

      Would you honestly want only 500Mhz in your laptop? But it would be great if handheld devices could have this much power though, preferably on something like a mini sized tablet (or an over-sized iPhone). I'm not sure MHz are a very good absolute measurement of the processing capabilities of this thing...
      But it could make a very decent laptop. I used to have a Vaio with a Pentium II 400 (PictureBook) that was quite nice. Not the kind of thing you'd run Vista on but with XFCE it ran like a charm despite having an abysmal battery life.

      --

      May contain traces of nut.
      Made from the freshest electrons.
    9. Re:laptop anyone by arivanov · · Score: 5, Informative

      Not really.

      I have used every single Via CPU from the original Eden 533 up to 1.5GHz C7 and IMO the C3-C5 spec Edens are just about useful for a dedicated appliances, small firewalls, small specialised servers and such. They do not have enough grunt for a laptop. The fact that most of them have are shipped bundled with relatively weak video does not really help either. Even the mpeg support on some motherboards cannot really help. Xterm is probably the most you can do with them as far as clients are concerned. Still better than similarly clocked Crusoe though (now that is a drag of all drags).

      C7 is a completely different beast. This is probably the best CPU for a corporate laptop out there at the moment. A laptop is worthless without a "link to the mothership". Intel Core and AMD have to use CPU resource to do all of the encryption and decryption. This may amount to 30-40% of your CPU on a 54G wireless lan. Compared to that Via C7 has hardware AES acceleration so you can actually protect your traffic properly while using less than 1% of your CPU. It also has enough grunt to run most common road warrior apps at acceptable speeds. It is a pity it is not available as a laptop choice anywhere outside the far east.

      --
      Baker's Law: Misery no longer loves company. Nowadays it insists on it
      http://www.sigsegv.cx/
    10. Re:laptop anyone by arivanov · · Score: 2, Informative

      Why not. If you are running an Intel Centrino or Core laptop you most likely having less most of the time.

      Centrino as well as any Core derived notebook under Winhoze uses voltage and frequency scaling. It will ramp up to its spec-ed frequency only when pushed really hard and in some laptops only when on AC power. If you want to actually have reasonable battery performance on Linux you end up doing the same using the cpufreq susbsystem. Example from a Core Duo on which I am typing this post:

      model name : Intel(R) Core(TM)2 CPU T5600 @ 1.83GHz
      stepping : 6
      cpu MHz : 229.167

      Note the actual CPU frequency above (this is using ondemand kernel governor). It is more than twice less than 500.

      --
      Baker's Law: Misery no longer loves company. Nowadays it insists on it
      http://www.sigsegv.cx/
    11. Re:laptop anyone by rikkus-x · · Score: 1

      My laptop's CPU (Pentium M 1.4Ghz) switches down to 600Mhz when it's on battery power. I use VS.NET with ReSharper on medium-sized projects and do Ruby on Rails development. I also use Firefox and play Internet radio. I occasionally notice that it takes longer to load an application than it does on my desktop machine, but apart from that, it's fine.

    12. Re:laptop anyone by Ed+Avis · · Score: 2, Informative

      Hardware AES? Can OpenSSH use it?

      --
      -- Ed Avis ed@membled.com
    13. Re:laptop anyone by jellomizer · · Score: 1

      Not really considering most new laptops now are duel core, with 2 ghz each.... And Vista still runs slow on those. For laptops people want Performance of a mid-to high mid range PC. They defiantly don't want 500 mhz where they can run all their cool apps from 1999.

      --
      If something is so important that you feel the need to post it on the internet... It probably isn't that important.
    14. Re:laptop anyone by Anonymous Coward · · Score: 0

      Yes. Theo likes the C7, OpenBSD / OpenSSH were early adopters.
      They've also been supported by Linux for quite some time, it appears as /dev/hwrandom.

    15. Re:laptop anyone by Calinous · · Score: 1

      By what I remember, yes. And encryption using the included hardware module is faster than most anything else x86 wise (or was when I've seen that benchmark). (But it was slower than mostly anything else in any other non-accelerated encryption tasks).
            I think it was tested under OpenBSD.

    16. Re:laptop anyone by IkeTo · · Score: 1

      Actually I'm more interested in using it as a home server. Home server usually operate 24-hours, with screen off most of the time until you want to use it as a desktop, and mostly used for serving your own home page. In such systems, a 1W PC really makes a huge difference. The next question is, of course, (1) is there any power-efficient hard disk, and (2) is there any way to make sure the disk will not be spinned up more than once a few hours.

    17. Re:laptop anyone by TheRaven64 · · Score: 1

      It's not like you're having to run something Windows on it, which is tied to specific architectures. And even if you were, you'd probably run Wince, which, last time I checked ran on MIPS, ARM and SuperH (not sure about PowerPC).
      --
      I am TheRaven on Soylent News
    18. Re:laptop anyone by TheRaven64 · · Score: 1

      Note the actual CPU frequency above (this is using ondemand kernel governor). It is more than twice less than 500. If this gets a similar IPC to other VIA CPUs then it's likely that the Core 2 at 229MHz is still faster.
      --
      I am TheRaven on Soylent News
    19. Re:laptop anyone by RAMMS+EIN · · Score: 2, Informative

      ``The next question is, of course, (1) is there any power-efficient hard disk, and (2) is there any way to make sure the disk will not be spinned up more then once a few hours.''

      (1) Yes. Take a look at 2.5" drives used in laptops, for example. You could also use flash instead of an actual disk. Having done that myself, I must give you a word of warning: don't do flash+usb on Linux. It will hang because of I/O errors every few days. I believe this is due to there being a hardcoded limit on the number of writes somewhere in the Linux drivers involved in this, but it could also be the flaky hardware (VIA SP8000E, never buy that one).

      (2) Yes. Run off a ramdisk, and just write changes to your real disk every few hours. Puppy Linux does something like this.

      Another thing you will want to look at are efficient power supplies (particularly, ones that are efficient at the low power draw of your machine).

      Finally, this being about VIA, you will have to be careful with enabling CPU frequency scaling. The board I have is known to crash when the frequency is changed too often.

      --
      Please correct me if I got my facts wrong.
    20. Re:laptop anyone by SL+Baur · · Score: 1

      Would you honestly want only 500Mhz in your laptop? Well, yes. Especially if it ran cool, which it sounds like is the point with low power.

      The ancient junk Matsushita notebook I had in Japan was plenty fast enough and was slower than 500MHz. Ran a now ancient version of Turbolinux, and I never had to reboot it the entire time I had it - about a year.

      I've gotten a Mac Powerbook Pro for my wife that runs much, much faster but it runs so hot I'm afraid both of it failing in the tropics and it is absolutely a Keep Out Of Reach Of Children thing. It gets HOT. Sadly when you do "cool" things on it like play WoW, it gets even hotter.

      If I can get a Mac OS X userland with a cool(er) running and child-safe Linux kernel that runs on this Via ... sign me up right now.
    21. Re:laptop anyone by pla · · Score: 2, Insightful

      Yes and no. If we're going to have a backlit screen anyway (even with LEDs), we can only gain so much by reducing the CPU consumption.

      For a user-oriented workstation, true. Even with the Via C7, a single HDD (at spin-up, anyway) could consume more than the CPU.

      I think, though, these things mostly don't go into actual desktop machines. They go into car audio solutions (with a 4x20 non-backlit LCD or even VFD), or routers (headless and with CF or USB storage) or various low-demand servers (also headless).



      But for use in a laptop, yes, a backlit LCD would dwarf this CPU for power consumption. But then, in a laptop, ever watt matters - If this CPU only cuts the total load by 10%, that means 10% more runtime on a given battery, or the same runtime with a smaller and lighter battery.

      Also, consider that low-power system designers typically pick the lowest fruit first... If we have a 1W CPU, solid-state primary storage, that leaves the LCD as the worst offender. How long will it take them to find ways to improve that? Whether making better use of ambient light (I've never understood why laptop screens don't have a clear/frosted back anyway, giving you the option of turning off the backlight), or using active OLED pixels that don't require an external light source, or something else entirely new and different.

      I, for one, look forward to a moderately powerful portable PC that can run for over a day on a pair of AA batteries.

    22. Re:laptop anyone by billcopc · · Score: 1

      Power efficient hard disks... get a 2.5" laptop drive, or do what I do and netboot the thing, with an NFS filesystem on some other box far far away. I started doing that years ago on file servers (to avoid having a boot drive). The beauty of Linux is that it will correctly use up all the RAM for disk caching, so as long as you load it up full of cheap ram, the NFS thing won't bother you much once it's up and running.

      430 days uptime and counting, on my little home network of firewall, print, web and file servers. They all run off of ~10w EPIA M10k's, save for the file server which is closer to 100w under load.

      For comparison, my SLI'ed Geforce 8800's suck down more power than all my Linux boxes combined :)

      --
      -Billco, Fnarg.com
    23. Re:laptop anyone by arivanov · · Score: 3, Informative

      By what I recall - no, but I have not looked at the OpenSSH latest and greatest (it has been 6+ months since I looked at this).

      The reason is that at least as of the versions present in major distros openssh does not for some reason support openssl engines. AES (and RSA in latest Via CPUs) is done using an openssl engine which has to be initialised and loaded. This can be done for OpenVPN, Apache, Pound and nearly any other piece of software using OpenSSL, but not OpenSSH. For some reason Theo's people in their infinite wisdom left that part out (it is trivial). There was a patch, dunno if it has made it into the main tree.

      As far as non-OpenSSL software is concerned, the kernel itself can use the hardware AES for filesystems and IPSEC. I have run it for quite a while for both OpenVPN and IPSEC. It can run around a Dual Xeon in circles. I would expect it to have the same killer performance for encryption of filesystems and encrypted backups as well. In fact this is possibly the only CPU on the market at the moment where having all of your data encrypted is a realistic proposition. The rest will choke on it and crawl like a 486.

      There is also further improvement from having true on-CPU hardware RNG which all programs in need of good random numbers can use as it is implemented at kernel level.

      Probably the highest praise to it is the fact that most of these features have now started showing up on Intel roadmap documents for the future x86 CPUs destined for the embedded market. It is the Athlon history repeating. When someone else is doing something right Intel copies it, claims innovation and launches a marketing salvo trying to lie that "they have been doing it all along".

      --
      Baker's Law: Misery no longer loves company. Nowadays it insists on it
      http://www.sigsegv.cx/
    24. Re:laptop anyone by arivanov · · Score: 1

      Quite likely. Though not per W. AFAIK even at 229MHz core is in the 10W+ area.

      --
      Baker's Law: Misery no longer loves company. Nowadays it insists on it
      http://www.sigsegv.cx/
    25. Re:laptop anyone by Orange+Crush · · Score: 1

      Not entirely sure why we specifically need x86 for embedded stuff like PVRs though

      My guess: compatible and widely available off-the-shelf components. There are a lot more TV tuners and TV-out vid cards in the wild w/ x86 drivers. Less an isssue for manufacturers, but definately one for the hobbyist.

    26. Re:laptop anyone by the-stringbean · · Score: 1

      OpenSSH can be hacked to use the hardware encryption engines using instructions on this site: http://www.logix.cz/michal/devel/padlock/index.xp? show_selected=1&msgid=407.

      I've done this in the past when I used to run Gentoo on an Epia MII. Combined with the XvMC support it was a cracking MythTV/mini server.

    27. Re:laptop anyone by Neoprofin · · Score: 1

      One reason may be the metal reflecting wall that encloses the florescent bulbs behind the screen as well as many having circuit boards that run behind large portions of the screen. You'd need some sort of reflective/transparent casing for that as well as finding a way to stash more boards and wiring out of the way. I also don't think natural lighting would be very effective. As someone who spends a lot of time with piles of laptop screens, they seem very opaque to ambient light, those fluorescents seem like they'd have a lot more power unless you put the screen directly between you and a sunny window.

    28. Re:laptop anyone by zippthorne · · Score: 1

      The reason is that you have to have the light source on the other side of the screen. So the sun can never be your light source without mirrors, and you probably won't see any better in the sun than you would've with regular lights.

      --
      Can you be Even More Awesome?!
    29. Re:laptop anyone by Arterion · · Score: 1

      I saw a C7 laptop for sale at Wal-Mart for cheap.

      --
      "That which does not kill us makes us stranger." -Trevor Goodchild
    30. Re:laptop anyone by Anonymous Coward · · Score: 0

      You mentioned the Via C7. I have a laptop with a Via C7M. Not much difference. I purchased my laptop a few months back. It is an Everex NC1501 Stepnote with a 1.5Ghz C7M. Great little machine. Does all I need a laptop to do, and it only cost $399 thanks to a Vista sale of $100 bucks off the price. I never booted Vista. I installed Debian Etch onto it after verifying hardware with DSL-N, KNOPPIX, and Backtrack. Everything worked so I went with it.

      My only two downfalls with Etch were video and sound. Sound was fixable with a new kernel. Note that most other distros already had the kernel that supported the sound chipset. Video will hopefully be fixed soon. I am currently using the VESA driver. The Via forums state there is a workable solution for video, but I have not attempted it yet. The main Via guys stated that the next release would be full 2D. Yep, no 3D acceleration. The video chipset is capable of DX9.0c. I will have to wait for either an Openchrome driver, or a Via one (not likely for 3D).

      My sound works fine with the kernel upgrade, even better than when using KNOPPIX. The video has no real drawbacks for basic things, like email, websurfing, and such. I will try my NES emulator again when I get a 2D driver and see if I don't have stuttering problems. If I get 3D acceleration there are a few DX7/8 type of games I would love to play on the little thing.

    31. Re:laptop anyone by Iron+Condor · · Score: 1

      I'm curious how a massively parallel box of these (say twenty or thirty) would stack up in terms of (1)power, (2)price and (3)performance to those Core2 or AMD64 behemoths.

      I keep thinking that I don't really need a quad- or eight-core cpu of the current generation; I need only one, maybe two high-powered core/s. Having another ten or twenty or so smaller processors to offload stuff onto would be much more useful.

      --
      We're all born with nothing.
      If you die in debt, you're ahead.
    32. Re:laptop anyone by Anonymous Coward · · Score: 0

      I wonder how it compares to Silverthorne. According to this website http://www.intel.com/community/texas/spotlight.htm , it will consume 0.5W-2W.

  2. How does it compare? by Ed+Avis · · Score: 4, Interesting

    How does this chip compare in performance per watt against ARM, PowerPC and the like?

    The article doesn't say what socket and interface the chip uses. Are they still on Socket 370?

    --
    -- Ed Avis ed@membled.com
    1. Re:How does it compare? by pslam · · Score: 5, Informative

      How does this chip compare in performance per watt against ARM, PowerPC and the like?

      Pathetically badly. Most modern low power ARM variants are in the range 0.3-0.5mW/MHz. At 500MHz you'd see them chewing up about 150-250mW. Last I checked the Via x86 chips were single issue, so it's not too unfair to compare an ARM11 (or similar) against them. Quite frankly an ARM11 will outperform the Via chip and run lower power.

      The idle power figure is a joke. I can't recall the last time I used an ARM chip that idled at 100mW. More like 1-10mW. Still, it's nice to see an x86 chip get into sub-watt territory.

      Of course, ARM doesn't run native x86... and that's pretty much the only reason there's such a large market for these Via x86 chips. It's also the reason you never see them in deeply embedded systems where people don't really care so much about what ISA you're running.

    2. Re:How does it compare? by arivanov · · Score: 1, Informative

      AFAIK all of the Via CPUs are designed to be soldered onto a motherboard.

      AFAIK Buswise they used to be compatible with 370. The original Eden 533 and 800 6 years back were actually available in 370 form to be used as a CPU upgrade. There was virtually 0 interest to this form factor and Via dropped it in favour of integrated MB + CPU and soldering the CPU onto the board.

      I suspect that you can probably have it done in a socket 370 form. I do not see the point though as most motherboards will not be able to provide the correct voltages and most BIOSes will not have any support for it.

      --
      Baker's Law: Misery no longer loves company. Nowadays it insists on it
      http://www.sigsegv.cx/
    3. Re:How does it compare? by dan+the+person · · Score: 4, Interesting

      I think the popularity is half x86 compatibility(windows users) and half retail cost / availability.

      When i was building a linux based PVR, x86 compatibilty was not a deciding factor *. What i wanted was a cheap fanless board that could playback mpeg2 and divx, with a PCI slot for a tuner card, TV-Out, and SATA.

      When i was looking there were hundreds of Via C3/C7 based boards from heaps of manufactures, with countless different options. There were one or two ARM and PPC boards, even one with a transmetta CPU, but they didn't have TV-Out, or they had TV-Out but no USB or PCI.

      I would have loved to go with another architecture but the market for retail consumers just isn't there.

      * Actually, now i've said that i imagine compatibilty of the tuner drivers with non-x86 could be an issue.

    4. Re:How does it compare? by nevvamind · · Score: 1

      Go back to school and learn the basics ..... you just can't compare x86 CPUs with ARM. They're entirely different designs for different purposes for a start x86 is CISC and ARM are RISC ... and ...CISC = more transistors enough said ?

    5. Re:How does it compare? by MemoryDragon · · Score: 1

      Problem with the arm stuff is, you cannot get it from retail for a decent price, the via boards at least are available. I agree arm is an excellent solution, and used probably more widely than x86 in sheer numbers, but the problem is it is almost non existent on the pc side of things, the few boards you can get cost a fortune compared to their via counterparts, and while via even is somewhat slower than arm you still have full x86 compatibility and board and processor availability. This is somewhat the same problem powerpc nowadays have, you still can get the boards but they cost way more than their x86 counterparts in retail!

    6. Re:How does it compare? by dreamchaser · · Score: 4, Informative

      Wow, flashback to the 90's. There is really no such thing as RISC or CISC anymore. Even massive general purpose CPU's like the x86 family use cores that are basically RISC by the classical definition, at least at the microop level. Conversely, today's RISC processors have instruction sets that have grown considerably in complexity since the days of true RISC chips.

      Your premise is correct that it is an apples to oranges comparison, but not really for the reasons you describe.

    7. Re:How does it compare? by evanspw · · Score: 1

      Six ARM cores in every iPhone (really!) I use a 1.2GHz C7 as a fanless server CPU. The machine is dead quiet (disk is muffled too) in an open aluminium frame I riveted together. Keeps cool, always on, proven very very reliable.

      --
      Interstitial spaces are filled with cream.
    8. Re:How does it compare? by Anonymous Coward · · Score: 1, Insightful

      Of course you can compare them. Let's see... ARM CPUs draw less power than x86. There. That wasn't so hard, was it?
      How on earth would you decide what CPUs to use for what purposes if you couldn't compare them, because they were different? Is this a 'embrace diversity' PC thing?
      x86 remains a good choice if you have to run x86 binaries, like Windows, or if you want good performance at mass-production prices. Apparently 'the world's most power-efficient x86-compatible CPU' still doesn't cut it for embedding. Stating that is not grounds for being sent to reeducation.

    9. Re:How does it compare? by flowsnake · · Score: 1

      It's true, and a real shame that ARM isn't more a more readily-available option for general purpose computing in the standard form factors. Low power consumption and low heat production would be fantastic if I wanted to put together a tiny, silent media centre-style PC. I guess there just isn't the demand for these things, which is a shame from an energy-efficiency view. Iyonix http://www.iyonix.com/ sell an ARM-based personal computer, the heritage of which goes back to the ARM-based workstations manufactured by the now-defunct Acorn Computers back in the late 80s to mid 90s. Personally I think they are far too expensive for what you get, and as they use mostly bog-standard PC components I can't imagine they are terribly energy-efficient, but it's nice to have the option at least.

    10. Re:How does it compare? by Christian+Smith · · Score: 4, Insightful

      There is really no such thing as RISC or CISC anymore. Even massive general purpose CPU's like the x86 family use cores that are basically RISC by the classical definition, at least at the microop level. Conversely, today's RISC processors have instruction sets that have grown considerably in complexity since the days of true RISC chips.


      RISC is an instruction set thing, with the caveat that RISC instruction sets lend themselves to pipelined instruction execution as a by product.

      Yes, modern x86 processors have RISC like microcode implemented using pipelined cores, but the x86 -> microcode converter is extra logic RISC processors just don't need.

      There is no way you can implement an x86 chip in the same number of transistors as a RISC chip like ARM or MIPS, hence this VIA chip having considerably more power draw.
    11. Re:How does it compare? by jcr · · Score: 1

      Wow, I didn't realize that the ARM manufacturers had made such impressive gains in power efficiency. I know that I'm seeing ARM cores on a lot of ASICs and FPGAs these days, I guess that's why.

      -jcr

      --
      The only title of honor that a tyrant can grant is "Enemy of the State."
    12. Re:How does it compare? by lazy_playboy · · Score: 2, Insightful

      Eh? Google seems to suggest plenty of Via CPUs are available in socket form.
      (Score:4, Wrong)

    13. Re:How does it compare? by Anonymous Coward · · Score: 0

      In a megahertz-for-megahertz comparison ARM draws much less power, Eden has much better performance.

      In other words (again, mhz for mhz) in a portable tablet you still choose ARM, while in a file server/router/firewall/media player, whatever, Eden would be the choice.
      This chip can't compete with ARM in portable apps, but 1W is still a good figure: that would mean for example several hours at full power with a cheap AA cells battery pack.

      Also, ARM performs very badly when moving large chunks of data, IIRC it depends on its cache. Comments from developers who know the platform are welcome.

    14. Re:How does it compare? by jimstapleton · · Score: 4, Insightful

      comparing two chips on their power:mhz ratios... Not exactly a good comparison, even within the same general architecture (say both are x86), but when you go cross arch, it gets worse.

      Ex. Take an Barton core Athlon and compare it with a 1st Gen P4, running both at the same clock speed. That Barton will significantly outperform the P4, even with the same Mhz. Conversely, thake a Core2 Duo and an Athlon64 X2 of the same clock speed - the Core2 Duo will wipe the floor with the Athlon64 X2.

      Mhz only means something when the processors are of the same line. Different lines in an arch can drastically modify the CPUs relative performance by Mhz, varying app to app, and changing the arch completely will destroy most comparisons.

      Another example, would be to compare a 500Mhz EV6 Alpha to a 1Ghz Athlon - There are many tasks at which that Alpha will pretty much destroy the Athlon in terms of performance, even at half the clock speed.

      So, what you want is power:performance-at-desired-tasks ratios, it's more complex, but it's not useless (and in some cases, counterproductive/counter intuitive)

      --
      34486853790
      Connection too slow for X forwarding? Try "ssh -CX user@host"
    15. Re:How does it compare? by Ed+Avis · · Score: 1

      I think the right comparison is watt-for-watt or MIPS-for-MIPS not MHz-for-MHz. Nobody has a functional requirement for a certain clock speed, although they may require performance of at least a certain level or power usage below a certain level.

      --
      -- Ed Avis ed@membled.com
    16. Re:How does it compare? by pslam · · Score: 3, Informative
      I am very much aware that comparing power:mhz is often an incredibly bad thing to do, but I am also very much aware of the internal architecture of these two cores.
      • Via is single issue like ARM11. (At least, last I checked, but maybe they've changed that)
      • ARM1176 (a common variant) has hit-under-miss caches, some SIMD extensions (slow compared to Via, though), and a decent FPU (optional). No write order dependency issues on ARM. Very comparable to Via.
      • ARM11 has much lower memory latency than Via. It only takes 3 clocks to drag something out of memory while execution continues, you get write-to-read forwarding and a lot more registers which means less memory hits overall anyway.
      • The bus speeds of both are comparable. External memory is implementation dependent, but can also be matched.

      So they're actually pretty similar in a lot of ways. I guess I should restrict my usage of "better" to the usual target market: ARM11 is a better core at being a web browser or general multimedia device. It'll do the same job at lower power. In addition, you could run an ARM11 comfortably past 600MHz without a fan or even a heatsink. If you felt like splashing out, you could get a 4 core variant that would cream pretty much anything Via offers. Obviously 4 times the peak power, but still the amazing idle power consumption most ARMs give you.

      Again, x86 is still the obvious choice in the market due to a SOFTWARE problem. I say "problem", but what I really mean is the unwillingness of vendors to write portable code and realise that recompiling for multiple platforms stopped being a major headache about 10 years ago.

      It's pretty sad that an ISA is still a barrier to this kind of thing. There is a major example in the volume market where this did work out, though: Apple switching to x86. Hell, they even had to switch endian and everything worked. If anyone ever tells you that switching ISA is prohibitive, go point them at Apple, because it worked out damn well for them, and you can always use Apple as some kind of Godwin's Law because nobody will ever argue they're wrong.

    17. Re:How does it compare? by Anonymous Coward · · Score: 0

      You know who else said you could use Apple's CPU migration as a kind of Godwin's law?

      That's right...

      Goebbels.

    18. Re:How does it compare? by Anonymous Coward · · Score: 0

      Amusingly Intel and AMD both have "instruction packets" in their processors now. Intel calls it "micro-op fusion," but the name is unimportant. What is important is that small micro-ops are promoted into larger, complicated macro-ops to consume fewer slots in the OoO hardware. The naive "omfg x86 is RISC inside" description is so Pentium Pro to Pentium 4.

    19. Re:How does it compare? by LWATCDR · · Score: 1

      It does depend. The GummStix is pretty cheap but it isn't a PC.
      For putting a DIY media center I don't think this VIA or an ARM would be a good choice. Both would tend to lack the power to transcode video at anything like a reasonable speed. The one thing this VIA chip has over the other CPUs in the embedded space is that it uses the X86 isa. It is annoying but there are some Linux drivers that ONLY exist for the X86! they are nasty binary blob or wrapped windows drivers but if you want that hardware to work you need an X86 :(

      --
      See my blog http://ilovecookes.blogspot.com/ for light hearted technical information.
    20. Re:How does it compare? by arivanov · · Score: 1

      Mind posting some links? As all I can see a presoldered shipped together with the motherboard as an EPIA solution. The official Via specs say BGA by the way which means it is soldred.

      --
      Baker's Law: Misery no longer loves company. Nowadays it insists on it
      http://www.sigsegv.cx/
    21. Re:How does it compare? by rbanffy · · Score: 1

      "There is no way you can implement a current x86 chip in the same number of transistors as a RISC chip like ARM or MIPS"

      There... I corrected that for you.

      the original x86 had less transistors than, probably, my wristwatch.

      And you can implement a MIPS or ARM core with the same space you would a x86. It will just have 10x more cache ;-)

    22. Re:How does it compare? by rbanffy · · Score: 1

      "If anyone ever tells you that switching ISA is prohibitive, go point them at Apple, because it worked out damn well for them"

      Actually, they did it twice.

      I still have my Color Classic around. It runs SSH just fine.

    23. Re:How does it compare? by Bill_the_Engineer · · Score: 1

      Of course, ARM doesn't run native x86... and that's pretty much the only reason there's such a large market for these Via x86 chips. It's also the reason you never see them in deeply embedded systems where people don't really care so much about what ISA you're running.

      You pretty much hit the nail on the head, but some embedded people care about ISA. I've been working with the PC104 form factor for a number of years now, and this platform is biased toward x86 due to the ISA bus. Right now, I am using a PPC405gpr because of its power savings compared to a similarly powered x86 but the CPU card that I have to use interfaces the PPC to the ISA with a PIIX4 south bridge.

      I'd have to still do something like this on the x86 platform but there are more turnkey solutions that support that arrangement. (Note: Not all required DAQs have transitioned to PC104+ which is PCI based).

      Now on my "simple" embed projects, I don't use the ISA and things are much simpler and PPC and ARM are always the first candidates for the design.

      --
      These comments are my own and do not necessarily reflect the views or opinions of my employer or colleagues...
    24. Re:How does it compare? by letxa2000 · · Score: 1

      Nobody has a functional requirement for a certain clock speed, although they may require performance of at least a certain level or power usage below a certain level.

      Of course people have requirements for certain clock speeds. Maybe not in the psuedo-embedded field, but true embedded development (which excludes Linux and Windows-based operating systems which just happen to be running on small form-factor hardware but are otherwise no different than "non-embedded" applications) often requires a certain clock speed.

      You're still right that MIPS vs MIPS or watts vs. watts is the best way to compare two processors since two processors can do vastly different quantities of work given the same clock speed. But you're wrong that there can't be functional requirements for clock speeds.

    25. Re:How does it compare? by MarsDefenseMinister · · Score: 1

      You forgot one.

      6502 -> 68K Macs
      68K -> Power PC
      Power PC -> x86

      --
      No weapon in the arsenals of the world is so formidable as the will and moral courage of free men.-Ronald Reagan
    26. Re:How does it compare? by Ed+Avis · · Score: 1

      Why would you require a certain clock speed? Is it some hard-realtime or DSP environment where you want the processor clock exactly synchronized to an input signal? Apart from that, there is no reason to prefer a 100MHz part to a 50MHz one that can do twice as much work per clock cycle.

      --
      -- Ed Avis ed@membled.com
    27. Re:How does it compare? by beckerist · · Score: 1

      eeeexactly. I see this is a win for Microsoft more than anything else.

    28. Re:How does it compare? by rbanffy · · Score: 1

      The II (6502) to Lisa/Mac (68K) was not a real transition. They had different lines of computers with different software. The Lisa or the Mac was never compatible with the II (without an expansion card). Even the Apple III, which used the same 6502, was barely compatible with the II.

      The 68K to PPC transition was very smooth and much of the software base ran without a hitch. It worked so well only 8.6 was fully PPC and I bet a lot of it still ran under 68K emulation.

      The PPC to x86 transition was interesting. Seemingly nothing changed, but the computers got a whole lot faster.

    29. Re:How does it compare? by OrangeTide · · Score: 1

      It's not unusual for a POWER chip to have the same complexity as a modern x86 and take a similar amount of transistor logic.

      --
      “Common sense is not so common.” — Voltaire
    30. Re:How does it compare? by chthon · · Score: 1

      It meant Instruction Set Architecture, not Interface System Architecture (or whatever the abbreviation for ISA the bus is).

    31. Re:How does it compare? by aliquis · · Score: 1

      If I remember it correctly the 433MHz or something CPU (PPC) of the Genesi Efika uses around 1 watt aswell.

      A whole moderboard with that cpu and 128MB ram is very cheap.

    32. Re:How does it compare? by letxa2000 · · Score: 2, Informative

      Why would you require a certain clock speed?

      In true embedded applications (which are built with microcontrollers, not processors), it's usually critical for establishing baud rates. A certain clock speed also may be necessary if you use a single clock source to drive multiple parts on the board which can reduce electrical noise caused by multiple clocks flailing aroumd.

      Apart from that, there is no reason to prefer a 100MHz part to a 50MHz one that can do twice as much work per clock cycle.

      I agree. That's why I agreed that MIPS vs MIPS and watts vs. watts is a better comparison. I simply pointed out that in real embedded work, clock speeds are often a design criteria. You still look for the best MIPS and power consumption you can get, but constraints on the clock speeds often reduce the field of viable options even if another part might have better MIPS or better power consumption but doesn't meet your clock speed requirements.

    33. Re:How does it compare? by repvik · · Score: 1

      PVRUSB2 works on ARM (both LE and BE) and PPC :)

    34. Re:How does it compare? by Iam9376 · · Score: 1

      Depends on the setup, a decent DIY PVR will use a hardware based mpeg encoder/decoder freeing the process from the CPU, as such, you wouldn't need a very powerful CPU. (This is how TiVo does it)

    35. Re:How does it compare? by Bill_the_Engineer · · Score: 1

      Ok. Conflicting acronyms (coupled with me obsessing over this DMA prob), but my point is still valid.

      --
      These comments are my own and do not necessarily reflect the views or opinions of my employer or colleagues...
    36. Re:How does it compare? by dreamchaser · · Score: 1

      That's another good example of a 'Chip formerly known as RISC' taking on more and more 'CISC' like features.

      My main point was that you can compare #'s of transistors, but to use broad strokes and talk of 'RISC' vs 'CISC' is basically meaningless now.

    37. Re:How does it compare? by idontgno · · Score: 1
      I guess that depends on your wristwatch, but here are the numbers for the first x86 (where x=null), the Intel 8086:

      5-12MHz 5-12MHz 16-bit (8086) June 1978 29 thousand

      (from http://redhill.net.au/c/c-1.html

      So, 29k transistors. Hmm. How many transistors does a wristwatch have? I'm guessing, for instance, that my P.O.S. Timex LCD critter can't have too much semiconductor complexity. OTOH, this prolly has scads and scads more transistor-y goodness.

      --
      Welcome to the Panopticon. Used to be a prison, now it's your home.
    38. Re:How does it compare? by dgatwood · · Score: 1

      http://www.mdofpc.com/onlinestore/via-c3-600mhz-64 k-133mhz-pga-cpu-socket-370-oem-p-10068.html

      That said, most VIA CPUs do seem to be of the soldered-onto-the-board variety, and I'm not sure they still make any socketed chips---I get the impression these chips are NOS.

      --

      Check out my sci-fi/humor trilogy at PatriotsBooks.

    39. Re:How does it compare? by willy_me · · Score: 1

      Yes, modern x86 processors have RISC like microcode implemented using pipelined cores, but the x86 -> microcode converter is extra logic RISC processors just don't need.

      You are correct, but this is becoming less and less of an issue as transistor counts increase. The ratio of wasted transistors to total transistors is decreasing as CPUs become more complex and include huge caches.

      There was a window of opportunity in ~97 for RISC to take over. I remember the 350MHz PPC G3 selling at the same time as a 300MHz PII while consuming ~1/5 of the power. The overall performance was comparable - so long as you ignored floating point calculations....

      I hate the x86 architecture but it is here to stay. Competing ISAs will die off unless they have a niche market. ARM has the low power / high efficiency niche. SPARC has the massively parallel / dedicated hardware niche (like built in encryption and such.) PPC is in trouble - ARM is invading from one side and x86 the other. POWER is impressive but it is basically an AIX niche.

      There is no way you can implement an x86 chip in the same number of transistors as a RISC chip like ARM or MIPS, hence this VIA chip having considerably more power draw.

      You can, but only if it is a really big, powerful chip. For the embedded market you are 100% correct.

      Willy

    40. Re:How does it compare? by lordSaurontheGreat · · Score: 1
      Not just that it's x86, but VIA chips and board are very compact and easy to build with. They have a lot of standard IDE/PCI stuff that's very easy to throw together with other bits of hardware you can just go buy off of newegg. It makes for a very cheap, very stable product because it's using the tested-and-broken stuff we use in everyday pcs. If you wanted a simple terminal to hook to a touchscreen in a warehouse for inventory purposes, it'd be ideal. It's small and can in most cases be mounted to the back of the LCD screen so it's a inobtrusive little box on the wall. Great for keeping track of inventory. The number of uses like that are legion. And to test the software you can have the devs on their x86 machines simply throttle back to 250MHz without needing to get them expensive IDEs that support remote debugging on weirdo architectures. I've also seen them in little tiny remote terminal connections, where they're essentially a bootable flash drive, network card, keyboard, mouse, and video card connected to a larger server via remote desktop. Rather than use a gigantic tower PC for that, a simple embedded VIA chip is used which means less cost and power consumption. So instead of having 10 computers in the school library we now have 40 (with LCD monitors) because these little devices are so cheap. Of course, the master server is still Windoze, so most of the wow factor dies with the first porno some kid changes the desktop to, but you get the idea of the possibilities a small, low power x86 chip gets you.

      It's cheaper and more reliable in many ways. It's a smart choice unless you actually have a bone-crushing, product-killing need for less than 1W in a CPU. Don't underestimate the power of x86.

      --
      Consider yourself spoken to.
    41. Re:How does it compare? by emil · · Score: 1

      I remember that the progenitor architecture was the "IDT Centaur/Winchip" - and that this processor was described as a simplified, single issue, classic CISC (or maybe that was Cyrix, which was bought and abandoned, but the name was applied to the Centaur).

      Are there micro-ops on VIA's chips?

    42. Re:How does it compare? by Anonymous Coward · · Score: 0

      I write this from my fanless eden 600 mhz running debian and icewm. I bought it 1,5 years ago because;
      * Fanless
      * 2 eth-ports
      * x86 compatible.

      My plan was to use it as a silent firewall in front of my regular home desktop. But soon I didn't care to start the "fat desktop" and found myself logging in to X to surf the web.
      Sure, it's no where near as fast as modern desktops. But at home i mostly just read my gmail and surf check things up on the net. It's a nice feeling to have a browser available 24/7 in my small apartment - and it's dead silent when the HD spins down.
      As a matter of fact, today I got my 8gb SSD drive to make it completely silent!
      Bu be warned - VIA has a BAD track record in open linux support and buggy bioses and so on, read on http://forums.viaarena.com/categories.aspx?catid=2 8&entercat=y

    43. Re:How does it compare? by Bluesman · · Score: 1

      I'm just left shaking my head that after all this time, x86 compatibility is still such a big selling feature that you'd compromise on just about every performance improvement just to have it.

      If you were to translate this to the auto industry, "you can reuse your old Ford Pinto carbeurator" would be the feature that would ensure your new car design would capture a large portion of the market.

      Yeah, I know the reason for it, major investment in existing software and all that, but I doubt even Intel in the 80's would have thought x86 would have lasted half this long.

      --
      If moderation could change anything, it would be illegal.
    44. Re:How does it compare? by OrangeTide · · Score: 1

      I agree entirely. I think maybe the R in RISC should stand for Regular instead of Reduced. If you look at modern "RISC" they have hundreds of specialized instructions. And Intel's Pentium and later really blurred the line between RISC and CISC camps.

      What matters more than the size of your instructions set is how well the cache works, how well the pipe line works, and the latency induced by certain operations (exceptions, branching, etc).

      --
      “Common sense is not so common.” — Voltaire
    45. Re:How does it compare? by LWATCDR · · Score: 1

      "Depends on the setup, a decent DIY PVR will use a hardware based mpeg encoder/decoder freeing the process from the CPU, as such, you wouldn't need a very powerful CPU. (This is how TiVo does it)"

      That is why I said "Transcode". I would think that in a DIY PVR you would want the option to do H.264, DivX, Theora, or what every might come along in the near future.
      You could use a FPGA to create your own accelerator for the different codecs but that would be a lot for the average DIY.

      --
      See my blog http://ilovecookes.blogspot.com/ for light hearted technical information.
    46. Re:How does it compare? by Anonymous Coward · · Score: 0

      > You could use a FPGA to create your own accelerator for the different codecs but that would be a lot for the average DIY.

      Naw, not really, but you would definitely blow your power budget. FPGAs take a lot of juice to run.

    47. Re:How does it compare? by Anonymous Coward · · Score: 0

      Please post links to support your claims. I'm not trying to flame you. I am just curious to know how you've discovered this.

      Thanks.

    48. Re:How does it compare? by kabz · · Score: 1

      You forgot one: x86 -> ARM-based iP(h)o[dn](e) Woo. The OS X iPods are coming soon.

      --
      -- "It's not stalking if you're married!" My Wife.
    49. Re:How does it compare? by Anonymous Coward · · Score: 0

      A better auto analogy is "you can use gasoline to run this car" where gasoline = software.

      x86 has lasted for so long because of the availability, amount and quality of software for it. No other architecture comes close in any one of those areas.

    50. Re:How does it compare? by pohl · · Score: 1

      Don't forget that they ported osx to the ARM architecture for the iPhone.

      --

      The "cue the foo posts in 3, 2, 1..." posts will commence with no subsequent foo posts in 3, 2, 1...

  3. Obligatory by maroberts · · Score: 1, Redundant

    Imagine a Beowulf cluster of these....

    --

    Donte Alistair Anderson Roberts - hi son!
    Karma: Chameleon

    1. Re:Obligatory by ookabooka · · Score: 2, Insightful

      Imagine a Beowulf cluster of these....

      So like. . an intel 2 duo that takes a room and miles of cable?
      --
      If you are about to mod me down, keep in mind that this post was most likely sarcastic.
    2. Re:Obligatory by threaded · · Score: 2, Funny

      Couldn't even keep a dorm room warm. Boo hoo.

    3. Re:Obligatory by Gordonjcp · · Score: 1

      ... running off a couple of AAs.

  4. Yes but ... by Anonymous Coward · · Score: 0

    ... does it run Linux ?

  5. holy cow! and their 1.5GHz is only 7.5W by spagetti_code · · Score: 5, Interesting

    My mythtv PVR uses the MII12000 (1.2GHz), which is rated at
    20-30W. With HDD, DVD, encoder card etc, it draws 80W on start,
    and somewhere between 30-60W when running.

    Take 10-20W off my figures by using their 1.5GHz ULV
    and you get potentially more processing power at less
    than 50W!

    I know that VIA chips are pretty feeble (i.e. their 1.5GHz
    chip is probably closer to a 1GHz intel chip), but with an
    encoder card (dual actually) I can be recording two
    channels with the CPU at 10%. Given their mobos have
    mpeg decoders on board, I can add watching a DVD or TV
    for another 30-40% CPU time.

    The only thing is ad-skipping and re-encoding are pretty
    slow.

    1. Re:holy cow! and their 1.5GHz is only 7.5W by Anonymous Coward · · Score: 0, Informative

      Actually 'pretty feeble' is an understatement, these CPUs are in my expierience _very_ slow. Also forget the mpeg-decoder onboard. Chances are their drivers don't even support their very own chip. Also the documentation for VIA-products is horrible. Sometimes even the most basic tech-sheets are wrong and they often advertise stuff that actually isn't implemented yet.

    2. Re:holy cow! and their 1.5GHz is only 7.5W by Anonymous Coward · · Score: 0

      And I feel positively paleolithic. Work provided me with an 8 core Mac Pro, with dual xeon 5365s. The power usage measured at the socket for the entire machine reveals it idles at about 220W. The highest I've had it is 697W while working.

      Anyone have any carbon credits handy? Damn.

    3. Re:holy cow! and their 1.5GHz is only 7.5W by Professor_UNIX · · Score: 2, Informative

      Also forget the mpeg-decoder onboard. Chances are their drivers don't even support their very own chip.
      Stop spreading bullshit FUD. The MPEG2 decoder hardware has been supported for years now in open source. My MythTV frontend, a Via EPIA M10000 running at 1 GHz uses the MPEG2 decoding hardware when playing back video saved from my backend's Hauppauge PVR 250 hardware mpeg2 encoders just fine with very little CPU usage. The only problems arise when you try playing DivX or MPEG4 streams.
    4. Re:holy cow! and their 1.5GHz is only 7.5W by Calinous · · Score: 1

      I'm not sure if using a horde of those new processors would give you better performance for lower power use.
      Again, these things might be included into a new variant of the 128-processors-supercomputer in an ATX form factor. Power-wise, it should fit the bill, and it might even be more powerful than the 96-processors supercomputer under the desk Orion DS-96 (http://www.pcstats.com/articleview.cfm?articleID= 231)

    5. Re:holy cow! and their 1.5GHz is only 7.5W by tksh · · Score: 1

      My Intel Mac mini on the other hand idles around 25 watts and boot at ~35 watts. My monitor draws more wattage than my computer.

    6. Re:holy cow! and their 1.5GHz is only 7.5W by Anonymous Coward · · Score: 0

      I just build a be-2350 for my brother, dual core athlon. The box has a tv tuner 1 hard drive, 1 dvd-rw and the entire box pulls no more than 70w even when spinning up the disk. I typically see 58-65W during normal usage.

    7. Re:holy cow! and their 1.5GHz is only 7.5W by rbanffy · · Score: 1

      They would need a decent FPU/vector accelerator for this kind of application. I say it's very feasible, but, perhaps, not the best way to go.

      OTOH, it would be much more clever to use MIPS or ARMs as general-purpose CPUs. On the same space, it should be feasible to cram a couple ARM11s, lots of cache and a couple DSP/SPU/GPU-like cores sitting around the main cores. It would no longer be as low-power as these x86s, but it would be a lot more interesting for desktop workstations. I find the Tilera 64-core chip very interesting in this regard. If they could build 32 CPU/FPU pairs instead of 64 FPU-less cores, it would be even more impressive. I would love to see a desktop made with them.

      Best of all, they would be remarkably Windows-proof.

    8. Re:holy cow! and their 1.5GHz is only 7.5W by Perspectives · · Score: 1

      Which driver package did you use for your Media Center? Did you use the UniChrome from sf.net, or OpenChrome, or did you go with the package from viaarena.com?

      I know others have shared my pain in trying to get a C7 based xorg setup with mpeg2 decoding, decent 3d performance, and stability. You spend an afternoon compiling/installing many different versions of openchrome only to watch it crash after a few seconds of video playback. Then you go to UniChrome and see that it doesn't have modeline support for the latest TV Encoder chips. Finally you go back to the drivers from viaarena.com and get stability but no hardware mpeg2 decoder playback because the patches to mplayer or xine no longer work?

      I guess what I'm asking is, what combination of software did you end up using for your Media Center PC?

    9. Re:holy cow! and their 1.5GHz is only 7.5W by asm2750 · · Score: 1

      I run a Via SP13000 as my mythtv box and it hasn't let me down yet, it also made an affordable computer to learn how to use linux as well.

    10. Re:holy cow! and their 1.5GHz is only 7.5W by tknd · · Score: 2, Interesting

      The VIA epia platforms like the one you have weren't that great. I had their 600mhz chip and ITX board and on the meter it was still drawing about 40 watts idle at the plug. The power supply probably wasn't the greatest but still I had higher hopes. That was only the ITX board plus a normal 3.5" 7200rpm hard drive. The cpu was barely enough for most tasks and some tasks you didn't even want to do. It is probably much better with your cpu but you're still drawing more power than necessary.

      As a comparison, I built an Athlon64 power efficient system with normal PC parts (no laptop parts, including the CPU). I clocked down the cpu to 1ghz and with a radeon 7500 video card plus a standard 3.5" 7200 rpm hard disk and a atheros 802.11g pci card, I was able to get it to draw about 46 watts at the plug idle. During boot and while it loaded the OS, the power draw was around 60watts to 80watts. Even with only 1ghz, the athlon box could do a whole lot more than the epia. Replacing the video card with something more useful like a geforce 6200 bumped the idle watts to the 50s.

      I also have a dell 600m with a pentium M chip that has the "centrino" sticker on it. The power draw from the laptop while idle with the screen off is 26 watts. If you run something it can jump up to the 60 watt range.

      I've found that when buying PC parts, the hardest part to evaluate for power consumption is the motherboard because there are no specifications that really help you and the amount of parts used on the board vary. Just by replacing the motherboard in the athlon64 system, I could increase the idle wattage by 10 to 20 watts. I've also found that all motherboards are coming with more and more junk these days. There are few bare and basic full size motherboards for PCs. There are some companies that manufacture and sell small form factor itx size motherboards with laptop grade chipsets and parts, but the prices are usually insane.

    11. Re:holy cow! and their 1.5GHz is only 7.5W by Belial6 · · Score: 1

      I bought one of those for my wife, as she wanted a completely silent computer for her desk in the bedroom. I was considering getting another for a MythTV box, but had nothing but trouble when I tried to install MythTV on her's. What distro, and Video capture did you use? Was it a total pain to set up? and do you know a good tutorial for installing to that board? I also have a PVR350 that I was going to use for video capture.

    12. Re:holy cow! and their 1.5GHz is only 7.5W by asm2750 · · Score: 1

      I used kubuntu with a hauppage pvr-150 mce, you can use a mce pvr-500 if you need two tuners, pvr-350 should work as well. Only real problem I have is the sound cuts out and goes to static if I leave it on for a few days (probably a driver issue), other than that it pretty much golden. To setup mythtv I used the community docs on the ubuntu website and some of the mythtv wiki.

      Heres my specs:
      Board: Via SP13000
      Ram: 1GB Corsair XMS DDR 400
      Drives: DVD-RW IDE and a 320GB SATA HD
      Capture Card: Hauppage pvr-150 mce
      OS: Kubuntu Fiesty
      PSU: PicoPSU 120W
      Fan: 1 120mm case fan

      You might want to replace the thermal grease with arctic silver if you build it.
      I might try hdtv when the new via board with pci-express 16x slot comes out so I can use a beefier videocard.

      http://www.pchdtv.com/
      http://epiacenter.com/modules.php?name=News&file=a rticle&sid=1147
      Cheers

    13. Re:holy cow! and their 1.5GHz is only 7.5W by caldodge · · Score: 1

      That's curious. I use a SolarPC with a Mini-ITX board, a 500 MHz Via C3 and no hard drive as a diskless workstation, and it draws about 17 watts. I'm pretty sure the average 3.5 inch drive doesn't draw 23.

    14. Re:holy cow! and their 1.5GHz is only 7.5W by LuSiDe · · Score: 1

      The cpu was barely enough for most tasks and some tasks you didn't even want to do.
      Most tasks? WTF does that include? Watching your DVD porn collection? Seriously, I wonder what people expect when they buy a low-end, low-power x86 computer. Its meant for (some) embedded purposes while still having the benefits of x86 architecture (backwards compatibility, portability, familiar platform). For example, together with MythTV you can make a TV recorder from the thing. Or you could jack in another NIC and build a nice, lightweight, low-power firewall smooth in a dedicated case. Tomorow on Slashdot: 'Soekris not powerful enough for Doom3'

      As a comparison, I built an Athlon64 power efficient system with normal PC parts (no laptop parts, including the CPU). I clocked down the cpu to 1ghz and with a radeon 7500 video card plus a standard 3.5" 7200 rpm hard disk and a atheros 802.11g pci card, I was able to get it to draw about 46 watts at the plug idle.
      Kudos, but that doesn't clear the above one dime, and not all Athlon 64 are equal esp not regarding TDP (but also idle usage). EE, if possible, should be considered.

      I've found that when buying PC parts, the hardest part to evaluate for power consumption is the motherboard because there are no specifications that really help you and the amount of parts used on the board vary.
      Agreed. This is not well documented, but I found out interesting data on my motherboard on forums dedicated to discussion of low power usage.
      --
      WE DON'T NEED NO BLOG CONTROL.
    15. Re:holy cow! and their 1.5GHz is only 7.5W by evilviper · · Score: 1

      holy cow! and their 1.5GHz is only 7.5W

      You're buying into the MHz myth again, and even more sadly, getting modded up for it. I admit I got sucked into the same thing, TWICE. Once with Cyrix, and again with VIA a while back.

      VIA chips are far more comparable to AMD/Intel CPUs at about half the MHz rating. VIA's statements about the relative performance of their chips, borders on fraud. Even Apple in the old PPC days would be envious.

      If you want a low powered processor with good performance, I'd strongly suggest a single-core Turion CPU... NewEgg had a 2GHz model for $90 a while back. With a max of 25W, and aggressive power savings for much lower power when idle or just not maxed out, you'd really do even better than any of VIA's solutions, with plenty of performance to spare. And you don't need VIA's expensive proprietary mini motherboards either, just a $50 Socket 754 mobo that can support the lower voltage.

      For slightly less performance, look at Geode CPUs. AMD's NX line of Geode CPUs are also very high performance (up to 1750+ and completely wipe the floor with the fastest VIA has to offer) and work in any old Socket A system that can support low voltages. MiniITX Mobo+CPU combo can be found on eBay for $200.

      Intel had some good solutions in the past, like their 933MHz LV Pentium 3, but they're getting hard to find, and the price is going way up. Getting a motherboard that will accept their lower power mobile CPUs is just too expensive.
      --
      Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
    16. Re:holy cow! and their 1.5GHz is only 7.5W by Professor_UNIX · · Score: 1

      I guess what I'm asking is, what combination of software did you end up using for your Media Center PC?
      I just use MiniMyth on my Epia. It looks like it uses the OpenChrome Xorg driver. All the backend recording is handled on an old 1.4 GHz Athlon system with 600 GB of storage and two Hauppauge PVR 250 MPEG2 encoders and the diskless Epia sits in my entertainment center and boots MiniMyth via PXE over the network from a TFTP server.
  6. Why not make 64 of these on a single chip? by G3ckoG33k · · Score: 1, Interesting

    Why not make 64 of these on a single chip? 64W + some additional overhead shouldn't be bad.

    1. Re:Why not make 64 of these on a single chip? by imbaczek · · Score: 1

      That additional overhead will amount to quite a lot, and performance in most applications scales sublinearly with amount of processors.

      IOW, I'd take a Core2 quad core over 64 Vias anyday.

    2. Re:Why not make 64 of these on a single chip? by dcapel · · Score: 1

      Ignoring the nickle and dime losses you'd have just by design, you run in to the same old problem: What are bad at writing for multiple cores/cpus.

      Concurrency is perhaps the biggest problem to modern day CS.

      If we could figure out how to use all those cores effectively, it would be awesome. Until then, its of dubius as a archaeticture

      --
      DYWYPI?
    3. Re:Why not make 64 of these on a single chip? by Fred_A · · Score: 1

      Why not make 64 of these on a single chip? 64W + some additional overhead shouldn't be bad. Presumably because they need to have some space left on the motherboard to put all the rest of the stuff, like memory, controllers, expansion slots, etc. If the CPU takes all the motherboard it's not practical.
      --

      May contain traces of nut.
      Made from the freshest electrons.
    4. Re:Why not make 64 of these on a single chip? by Anonymous Coward · · Score: 0

      So make the mother board bigger.

    5. Re:Why not make 64 of these on a single chip? by tomstdenis · · Score: 1

      There is a reasonable extreme to this though, why not a 2P or 4P setup though? Make it so you can fully shut off (re: relay) other cores. That'd rock. Of course I don't know what their cache is like but it'd have to be a decent size to make it worthwhile.

      Tom

      --
      Someday, I'll have a real sig.
    6. Re:Why not make 64 of these on a single chip? by Anonymous Coward · · Score: 0

      If we could figure out how to use all those cores effectively, it would be awesome.

      Simple:
      Core 1 runs the firewall.
      Core 2 runs the virus checker.
      Core 3 runs the rootkit checker.
      Core 4 runs the continuous search indexer.
      Core 5 runs the continuous disk defragmenter.
      Cores 6 to 62 run the DRM licensensing processes.
      Core 63 runs the GUI.
      Core 64 runs the user's applications.
    7. Re:Why not make 64 of these on a single chip? by cyfer2000 · · Score: 1

      How much bandwidth you need to access the memory if you use all those cores? How much memory you are going to feed to the cores? And how much power those DRAM will consume?

      --
      There is a spark in every single flame bait point.
    8. Re:Why not make 64 of these on a single chip? by Anonymous Coward · · Score: 0

      Dude, was someone murdering you as you typed that?

    9. Re:Why not make 64 of these on a single chip? by Anonymous Coward · · Score: 0

      I usually have enough process running to use two-four processors at a time. I wouldn't mind having four of these on a single chip.

    10. Re:Why not make 64 of these on a single chip? by Wesley+Felter · · Score: 1

      The Eden/C7 is 30 sq. mm., so 64 of them would be over 1,000 sq. mm., which would cost a fortune to manufacture. In comparison, high-end server processor chips are generally in the 300-400 sq. mm. range.

    11. Re:Why not make 64 of these on a single chip? by dcapel · · Score: 1

      I was a little loopy at the time... Heh.

      --
      DYWYPI?
  7. Cool! by Zubinix · · Score: 3, Interesting

    Put this in SBC (Single Board Computer) form together with wireless support and a nice sized flash hard drive would make it ideal for applications such as home monitoring and other uses around the typical house for us home automation geeks.

    1. Re:Cool! by Alioth · · Score: 2, Informative

      ARM11 is already better for that kind of application - much lower power still, and for embedded stuff, the need for x86 compatibility really doesn't exist.

    2. Re:Cool! by chuckymonkey · · Score: 1

      Not to mention this thing would be great in crash cart like equipment. For instance with one of these I could have my crash cart, my Fireberd 8000, and a whole suite of test equipment all in one easy to manage package. It would have to be a specialty built system, but the reason I like these with their low power requirement means that a cart with a good battery can run all this for a while and I don't have to rely on rack power or pulling a tile to get at one of the power mains underneath.

      --
      "Some books contain the machinery required to create and sustain universes."-Tycho
    3. Re:Cool! by Anonymous Coward · · Score: 0

      ... or just build it on a BUG (http://www.buglabs.net/).

    4. Re:Cool! by asm2750 · · Score: 1

      Look at the pico-itx and nano-itx by via if you are interested. You might like what you see.

  8. Sounds like an overclocker's dream by vadim_t · · Score: 1

    I wonder, how far can these things be overclocked? Certainly there shouldn't be a problem with cooling, so it should be possible to push these things to the maximum they're capable of.

    1. Re:Sounds like an overclocker's dream by Anonymous Coward · · Score: 0

      Sure cooling might not be a problem, but when you open your eyes you end up with a via cpu (i.e not even half the IPC of a decent intel/amd cpu), running on a very small motherboard with the most crippled BIOS ever, with a VIA chipset

      overclockers mostly care about high performance, and sadly, via and performance are mutually exclusive

      i had a via epia M10000n (C3 nehemiah chip at 1 GHz) a few years back, the thing would get beaten by a 500 MHz Pentium 3, and only barely managed to beat a fast clocked P2. Then take into acount the huge IPC improvements intel has made to the P6 architecture since the P3 days (the comparison was even to a P3 katmai with off-die cache, just imagine this thing versus a 1 GHz coppermine) and you seen realise that a cpu like this is only suited for embedded stuff like PDAs, in which case a RISC cpu is much more interesting then an x86 design

      Its nice to see Via still doing their thing, but these things are at least an order of magnitude slower then a $100 consumer level cpu

      if you want to see what this would be in a laptop, find an old P2 233/266 laptop and imagine not having to recharge as often

    2. Re:Sounds like an overclocker's dream by vadim_t · · Score: 1

      overclockers mostly care about high performance, and sadly, via and performance are mutually exclusive


      Oh, I don't doubt performance will be crap. It's just curiosity about how far you could push something that would be just fine with a heatsink, if it needs it at all.

      It seems that it takes liquid nitrogen to really squeeze out everything possible out of a normal Intel/AMD, but that can't be kept up for very long, and is very expensive to try.
    3. Re:Sounds like an overclocker's dream by Anonymous Coward · · Score: 0

      The FPU on the C3 sucks. IIRC it runs at half core clock. The C7 is still significantly slower for most things than an Intel/AMD CPU at the same clock (except encryption, where it's ridiculously fast) but it's a definite improvement. It's just a shame they're not a bit cheaper, but I suppose it's hard competing with Intel/AMD when they're in a price war.

    4. Re:Sounds like an overclocker's dream by Calinous · · Score: 1

      I suppose you could push the 1W, 500MHz processor to the 1.5GHz of its brethren, assuming you would have the technical possibility to do so (BIOS, increased voltage, chipset support). More than that? Hardly, with a processor built for low power consumption

  9. PVRs? by ffejie · · Score: 2, Insightful

    Without actually taking the time to do any calculations, shouldn't this chip be a little weak to be powering PVRs and other media devices? With the proliferation of HD, I see more and more people (thankfully) going to h.264 to reduce their file sizes. However, to play a 720p file that is encoded with h.264, you need some serious punch in the processing realm. Recording/encoding to h.264 is a level far beyond that. I don't have the specs in front of me, but even the most minimal player is going to require more than 500 MHz. Now, if you're talking about a few of these in one system you may be on the right track. Anyone have more experience than me in this kind of thing and can comment further?

    --
    Disagreeing with me does not mean you get to mod me troll.
    1. Re:PVRs? by Anonymous Coward · · Score: 0

      However, to play a 720p file that is encoded with h.264, you need some serious punch in the processing realm.

      Can't you leave that to the video card?

    2. Re:PVRs? by Stevecrox · · Score: 1

      Your right, I recently tried to build a Media Centre out of old computer parts, I built a:

      700Mhz Intel Pentium 3
      512mb SDram
      Nvidia 5200
      Avermedia TV card

      Windows Media Centre was barely able to run on the machine taking recordings was pointless using windows media centre or the avermedia PVR software. This 500Mhz chip would definitly not be enough, the 1Ghz and 1.5Ghz chips would do it though and even at 7.5watts the 1.5Ghz is redicoulously low power.

    3. Re:PVRs? by TheRaven64 · · Score: 1

      If you want a very low power PVR, you would probably use dedicated MPEG-1/2/4(including H.264) hardware, which would use less power than a general purpose CPU doing the same thing. Mind you, you'd probably use something like a PowerPC 405 instead of an x86 chip.

      --
      I am TheRaven on Soylent News
    4. Re:PVRs? by DrXym · · Score: 1

      I have trouble believing that a 500Mhz PC device is going to manage it though the PSP can play 480p H264, so perhaps the CPU requirements aren't that great for playback. My experience of encoding H264 is that they're pretty horrific. I doubt this chip would be any use at all for PVR devices unless the H264 already arrived at the CPU encoded, e.g. it was extracted from a DVB-T signal or similar.

    5. Re:PVRs? by dotnetatemybaby · · Score: 1

      In my experience the Xbox cannot acceptably play even basic NTSC resolution h.264 and its CPU is clocked higher than 500MHz.

      Of course the Xbox has very limited RAM so that could be a factor also.

    6. Re:PVRs? by smallfries · · Score: 1

      I'm guessing that these new chips use the same MPEG acceleration as their older models. When I had a Nehemiah running at 1Ghz on a Gentoo setup it was an absolute bitch to get Unichrome support. I believe that has all been sorted out now and the software is more stable. My box used to play both DivX at 720p and H.264 at 720p without any problems. For H.264 you are locking up the box and can't do anything else, for DivX it was more like 20% cpu.

      For encoding - just don't bother. I thought that encoding H.264 might work out well because the box was on 24/7, but it encoded at less than 1fps. While my main desktop box would encode a DVD in about 8 hours, the via would take about 6 days of running flatout at 100% utilisation. Unless there is hardware support for encoding, and open source drivers then don't even think about it.

      --
      Slashdot: where don knuth is an idiot because he cant grasp the awesome power of php
    7. Re:PVRs? by jshriverWVU · · Score: 1
      You're right, this really wouldn't be suitable for a DVR. Just look at the MythTV requirements. Usually if you're going to do best quality video recording you need at LEAST 1-1.5ghz if hardware encoding and 2ghz+ if you are doing it all in software. Granted the last time I tried this kind of thing I was using a Hauppauge WinTV (good linux support) but couldn't get the mpeg2 hardware encoding to work, and it chocked on my 1ghz machine. That was regular video not HD, and was recording in mpeg and not some highly compressed format like divx or h.264.

      So you can pick, low CPU bigger files less compression, or higher compression and higher CPU. Regardless I dont think 500mhz would cut it. Curious what Tivo uses, know it's PPC but nothing beyond that.

    8. Re:PVRs? by AmiMoJo · · Score: 1

      You are right, it is too slow for a PVR.

      The C7 can cope with SD video in XVID at 1GHz and most H.264 at 1.5GHz, but not HD video. Via claimed that it can, but that was a lie. In theory the hardware assist for decoding is there, but not a single codec can make use of it so it's pointless.

      Via really screwed up on this one. They could have owned the PVR market if they had just bothered to get a working codec made.

      --
      const int one = 65536; (Silvermoon, Texture.cs)
      SJW, n: "Someone I don't like, and by the way I'm a fuckwit" - AC
    9. Re:PVRs? by martrootamm · · Score: 1

      You probably should have shut off any resource-hungry functionality, much of which is visual stuff.

      MCE 2005's system requirements are higher than those of Windows XP. While you probably had every other requirement right, the required CPU must be at least at 1.6GHz or somesuch.

  10. Redundand? by spectrokid · · Score: 3, Insightful

    Isn't everybody always complaining how x86 is an awefull archtecture dragging 20 years of backward compatibility like a block of concrete? A one watt processor surely aims at the mobile/embedded market. Backward compatibility is not an issue there. I can't see anybody running his old Windows 3.11 accounting software on his mobile, and this thing won't come with a "Vista-ready" sticker...
    Linux and Windows CE (or whatever they call it today) run just fine on ARM and similar. Will a low-power x86 compete performance-wise with a low-power RISK architecture?

    --

    10 ?"Hello World" life was simple then

    1. Re:Redundand? by voxel · · Score: 1

      This is targeted to Windows 2000 and Windows XP running on a ULV CPU. At the same time it can handle Linux with every major popular distribution, where as an ARM cpu while it can run linux, is less flexible.

      The x86 architecture does drag a lot of baggage, but Intel, AMD and possibly VIA seem to have figured out how to deal with it by now. Look at the Core 2 Duo compared to the performance of any Itanium processor or what not.

      I think the baggage isn't really a big deal anymore as it used to be.

      --
      Modesty is one of life's greatest attributes
    2. Re:Redundand? by acalthu · · Score: 0

      ..RISC

    3. Re:Redundand? by aclarke · · Score: 2, Interesting

      There are lots of uses for a CPU like this. I, for example, run a VIA CPU/mobo in my truck. It draws very little current which means my auxilliary battery will run the computer for a lot longer. It also produces less heat than my AMD/Intel options, which means the computer needs no fans, which also saves power and keeps the system quieter. I run Windows XP on there as pretty much all the good GPS software runs on Windows. An ARM chip wouldn't do me much good there, unfortunately.

      I agree though, this chip is never going to be the financial success that the Core2 is.

    4. Re:Redundand? by Woy · · Score: 1

      I'll pay twice as much for a Linux mobile computing device where i don't have to recompile. Not that i hate recompilation, I just don't want to be bothered with the times it goes wrong.

      --
      "If God created us in his own image we have more than reciprocated." - Voltaire
    5. Re:Redundand? by InvalidError · · Score: 1

      The legacy stuff (modes and quirks) still costs transistors and these transistors translate into extra power and extra execution latency... but because the CPU cores (excluding L2 caches) are getting bigger and pipelines have stretched, the legacy overhead has become proportionally less significant.

      Still, an hypothetical legacy-free x86-like CPU with a redesigned ISA to simplify instruction decoding could shed at least one pipeline stage along with ~10% of the core transistor count and ~10% of the power for a given performance level.

      Since 70-80% of the transistors in today's upper mid-range CPUs go into L2 cache, this hypothetical complete core (including L2) would not be noticeably smaller but it would be slightly more efficient and could take performance/watt up a notch. Then again, minor performance/watt CPU gains (something like 10-15% in my hypothetical case) are quickly eclipsed by the ~40W idling power from HD2600 and GF8600 GPUs. (Yuck! And even entry-level GPUs from older generations are 20-30W idle.)

      It would be nice to see a fresh ISA optimized for current and foreseeable desktop needs instead of sticking with stuff designed back when memory was over $10/KB with all sorts of extensions grafted on in variably elegant/seamless ways... but with Itanium headed Itanic (many predicted this based on the ISA's structure and production delays before the name was announced), Apple gone x86 and the few remaining independent ISA vendors slowly abandoning their low-volume in-house designs to jump on Opteron or Itanium, a desktop ISA refresh appears more unlikely than ever.

      If we're lucky, mainstream desktop Linux will materialize and lure embedded ISAs into beefing up a bit and go after desktop market share.

    6. Re:Redundand? by marcosdumay · · Score: 1

      No, it does not compete with ARM, MIPS and others at the embebbed market, simply because it consumes a lot of power and is seriously unpowered.

      If sucessfull, that chip will open a market on its own for legacy software to run on small power appliances.

    7. Re:Redundand? by Anonymous Coward · · Score: 0

      Will a low-power x86 compete performance-wise with a low-power RISK architecture?

      Well, I'm sure many people would avoid having any risk in their computing. On the other hand: No risk, no fun, thus I guess as gaming platform a risk processor would be an absolute must.
    8. Re:Redundand? by Waffle+Iron · · Score: 1

      You missed one major advantage of the x86 instruction coding: it is extremely compact compared to "easy to decode" ISAs. This allows you to get by with a smaller instruction cache, and as you point out, caches dominate chip real estate these days.

    9. Re:Redundand? by leoc · · Score: 1
      A one watt processor surely aims at the mobile/embedded market. Backward compatibility is not an issue there.


      Not quite. DOS is used quite heavily in embedded systems still, and it only runs on x86. I've done projects where we had to port DOS software over to Linux specifically to take advantage of the lower power ARM boards. With this chip (assuming it is available in quantity and in the right form factors) many companies can continue to use DOS and still save energy.

      --
      STFU about slashdot bias.
    10. Re:Redundand? by InvalidError · · Score: 1

      IMO, today's larger caches and cheap RAM actually do make super-compact instructions less relevant. Also, if you consider all the tack-on prefixes, an hypothetical x86-like ISA based on 16bits base opcodes (instead of the current 8) could actually yield more compact code by eliminating the vast majority of prefix codes and work-arounds - at least while dealing with 64bits code. For example: on x86-64, a REX prefix is required to specify 64bits operands or to access extended general registers, which basically grows all 64bits r/r and extended register file (like "mov rax, r10") operations to at least 16bits.

      Making instructions more uniform in both length and structure are keys to increasing instruction decoder throughput. x86's screwy ISA makes it difficult to improve, that's why current x86 CPUs can only decode 2-3 instructions per cycle (not to be confused with the 3-4 uOps/cycle dispatch to execution units) and we are unlikely to see them go much beyond that. (Wider dispatch units would still be useful in SMT CPUs - I remember reading that HT will be back in some flavors of either Nehalem or its 32nm follow-up... I hope they won't resurrect the Netburst replay engine this time around.)

  11. I wish mainstream CPUs / GPUs would focus on power by DrXym · · Score: 4, Insightful

    I wish the EU would start rating PCs by their energy consumption, perhaps accompanied by an energy tax for the worst categories. The amount of power in a modern PC from CPUs & GPUs wasted as heat, fans etc. is just ridiculous.

  12. How does it compare to AMD Geode, then? by tzot · · Score: 1

    http://www.amd.com/us-en/ConnectivitySolutions/Pro ductInformation/0,,50_2330_9863_9864,00.html

    I'm sure that the AMD CPU has better performance per MHz than the VIA one, although I didn't bother to find facts about that.

    --
    I speak England very best
    1. Re:How does it compare to AMD Geode, then? by bunratty · · Score: 1

      Yes, the Geode has generally better performance per MHz than even the VIA C7, according to this comparison of Celeron, VIA C7, and AMD Geode. Geode beat the VIA C7 on the SPECint and SPECfp at performance per MHz, but VIA C7 beat the Geode slightly at performance per MHz in the CPU score in that article. The article also notes the Geode does not support SSE instructions. On the other hand, Geode also seems to use more power per MHz than VIA's chips, according to the Wikipedia article on Geode.

      --
      What a fool believes, he sees, no wise man has the power to reason away.
  13. On a somewhat related note by value_added · · Score: 2, Informative

    Soekris is now shipping a New and Improved product, the net5501. Early reports suggest that this is their first product that's able to route at line speed. I have two on order that I should receive next week.

    The release of Vista suggests that we need more and more powerful systems to do our work, but the irony, at least for me, is that I keep buying more of the little guys. Being able to use fanless cases and/or flash drives is a definite selling point, but there's a surprising amount of processing power available in such products and their uses are as limitless as your own imagination. Besides, hacking those ubiquitous blue boxes can never be as satisfying as building your own.

    The VIA units I own could be described as underpowered, but having onboard MPEG decoders, for example, can make up for the shortcomings.

    1. Re:On a somewhat related note by phrasebook · · Score: 1

      What does 'route at line speed' mean?
      Can you mount the board in a regular ATX case?
      Can it be hooked up to a regular ATX PSU?
      Who is Soekris? Do you work for them? What's the warranty like?
      Does it run Linux? I mean really. lspci output?
      Is there video out? How do you 'interact'? COM port?

      Seems interesting, but not enough to trawl the website!

    2. Re:On a somewhat related note by Calinous · · Score: 1

      "Route at line speed"? I don't know
      Mount the board in a regular ATX case? I think it comes with a case.
      Same with ATX PSU.
      Power consumption is (I suppose) in the tens of watts maximum, so ATX PSU is overkill.
        I know Soekris as they make boxes which can run OpenBSD and their PF firewalling solution.
        If it runs OpenBSD, then you can find some Linux for it.
      Once installed, you can access it by network (it has two or three LAN interfaces).

    3. Re:On a somewhat related note by value_added · · Score: 1

      What does 'route at line speed' mean?

      The new model can fill 100Mbit ethernet. Fairly useful, given that with 4 NICs, you might have more than one network (aside from your slow cable/ADSL link) through which to pass traffic.

      Seems interesting, but not enough to trawl the website!

      Judging from your laundry list of questions, you're unaware of both Soekris products and their widespread popularity. I'd suggest first visiting the link I provided for people in your position, and then do a Google search for 'Soekris' using 'inurl:slashdot'.

    4. Re:On a somewhat related note by phrasebook · · Score: 1

      Judging from your laundry list of questions, you're unaware of both Soekris products and their widespread popularity. I'd suggest first visiting the link I provided for people in your position, and then do a Google search for 'Soekris' using 'inurl:slashdot'.

      lol. Probably the least helpful response I've had on slashdot. Cheers.

    5. Re:On a somewhat related note by tomstdenis · · Score: 1

      lolocopter rofl omg wtf bbq ... just do the damn search ya boob.

      --
      Someday, I'll have a real sig.
    6. Re:On a somewhat related note by e2d2 · · Score: 1

      Interesting board. I just picked up an AVR32 based SBC that may interest you also:
      http://www.atmel.com/dyn/products/tools_card.asp?t ool_id=4102

      Here is a dev kit for the same chip:
      http://www.atmel.com/dyn/products/tools_card.asp?t ool_id=3918

      It's not an x86 platform, but there is gcc support and it runs linux just fine out of the box.

      Check out avrfreaks.net for a great community based on atmel's AVR offerings (from 8bit to 32 bit). What really draws developers in is how great the community is for these devices/chipsets. AVR is definitely a fan favorite.

    7. Re:On a somewhat related note by IvyKing · · Score: 1

      Technologic Systems will be shipping their TS-7800 at the end of September, which is powered by a 500MHz ARM9 processor. Maximum power consumption for the board is 4 watts.

  14. Besides its pad power/watt by Anonymous Coward · · Score: 0

    It should make things much easier for people to install linux and write apps. Imagine being able to buy a dvr, install linux on it, and start running some software you downloaded... or better yet, something you wrote yourslef.

  15. Re:I wish mainstream CPUs / GPUs would focus on po by DrXym · · Score: 1

    To clarify, if the EU slapped a tax on the worst offending PCs, it might focus consumers and the industry on producing more efficient designs. Most domestic appliances such as fridges and dishwashers already get rated in the EU and it clearly does shape people's decisions.

  16. Strange. by Anonymous Coward · · Score: 1, Interesting

    I construct, install and maintain automatic weather stations at remote sites. They are solar-powered systems usually. I've mostly been using the 533 MHz Edens since they were first released and been very happy with them. Although I don't make much use of the video decoding, I've yet to run into any problems with these CPUs, or mini-ITX systems in general.

    No driver issues and the documentation has been more than adequate for my needs. The total cost of these off-the-shelf consumer-level setups is a fraction of that for an equivalent embedded system and can do more than just log and transmit data from a weather station, something techs and operators appreciate when they're working on them at remote locations.

    Let's not forget that not everybody is fixated on kick-ass in-car theater systems, or uber-1337 gaming rigs.

  17. Re:I wish mainstream CPUs / GPUs would focus on po by sniepre · · Score: 1

    That is like saying that there should be a tax on buying a non-econobox car.

    Yes, some people want to buy a video card that requires some amps to play the current games. Some people want to buy a car that performs well. (I'm not talking about SUVs or huge waste hogs)

    Everyone pays for the power they consume, be it gasoline or electricity. Who cares?

    --
    Is not life a hundred times too short for us to bore ourselves? -Friedrich Wilhelm Nietzsche
  18. I protest by maroberts · · Score: 1

    As the first Beowulf comment, it cannot be Redundant.

    --

    Donte Alistair Anderson Roberts - hi son!
    Karma: Chameleon

    1. Re:I protest by Evanisincontrol · · Score: 1

      As the first Beowulf comment, it cannot be Redundant.

      Every Beowulf cluster comment is automatically redundant because that joke is old and tired. It's not clever; it's overused, and it's irritating that we can't see a single story posted about a processor without some jackass saying to themselves, "lol it wud b sooooo funny if i made a beowulf joke lololol!!!!!!1!!1!!!one"
    2. Re:I protest by Anonymous Coward · · Score: 0

      Lighten up Francis.

    3. Re:I protest by MBGMorden · · Score: 1

      I'd like to add to the list of tired, unfunny jokes: putting the word "one" in your exclamation points to make fun of leet-speak. ;)

      The other that I find the most irritating and completely asinine is the ^H "accidental backspace joke". Example:You know when some idiot^H^H^H^H^Hposter pretends to replace their original word with a less offensive one but "accidentally" leaves the original in.

      For the love of all that is Holy people: stop this! :)

      --
      "People who think they know everything are very annoying to those of us who do."-Mark Twain
    4. Re:I protest by Anonymous Coward · · Score: 0

      Well, I think watching people with 800K+ UIDs piss and moan about what bothers them on Slashdot is just about the funniest thing ever.

    5. Re:I protest by hawk · · Score: 1

      >to make fun of leet-speak. ;)

      You misspelled "dork-type."

      > idiot^H^H^H^H^Hposter

      The artificial ^H: A more civilized weapon of a more civilized time . . .

      (a time in which ending up with ^H on your screen instead of deletion was far from unknown)

      hawk, supposing the next response complains about "you misspelled . . ."

  19. Will this scale? by SD-Arcadia · · Score: 1

    The TFA has a chart which shows a 1.5Ghz part with a 7.5W TDP. That's 3x the mhz for 7.5x the power. Will VIA's technology scale relatively easily, say a 2.5Ghz chip with 20W TDP?

    --
    https://dalgamotor.wordpress.com/ - Elektronik beyinlere ozgurluk asisi (Turkish)
    1. Re:Will this scale? by Anonymous Coward · · Score: 0

      I hope not. My WHOLE FUCKING LAPTOP doesn't even use 20 watts, and it's a 1.8GHZ Pentium M.

  20. Re:jews did wtc by IhuntCIA · · Score: 0, Offtopic

    ... yawn

    OT: I did wtc. Keep the jews out of it!

  21. Re:I wish mainstream CPUs / GPUs would focus on po by DrXym · · Score: 5, Insightful
    Everyone pays for the power they consume, be it gasoline or electricity. Who cares?

    Exactly. Who cares? People are generally selfish and sometimes you must do things that benefit people as a whole instead of individuals. If slapping a tax on the most energy consuming devices in some category causes people to buy the more efficient ones, that is a benefit to every one. If you still want to buy that device despite the tax then nobody is stopping you. But I guarantee that for everyone who does than many more will choose one which doesn't.

    It does not mean either that you're getting a crappier machine as a result. While there is a relationship between CPU / GPU performance and power, I doubt it is a 1:1 mapping. Some processors and GPUs are going to deliver more operations per watt than others. Companies and consumers should be encouraged to favour the more efficient designs over the less efficient designs and a tax for the worst offenders in any class is one way of going about that.

  22. Re:I wish mainstream CPUs / GPUs would focus on po by XedLightParticle · · Score: 2, Insightful

    Not sure if parent was a joke, but i found it funny.

    In some EU countries economic cars have less yearly tax already, I think it's calculated from the CO2 emission pr. km.
    And cars that can't perform 15km/l or more, have had their price tax raised, while longer running ones have had it reduced.

    --
    If I was as pragmatic and objective as I claim to be, would I be commenting?
  23. Re:I wish mainstream CPUs / GPUs would focus on po by imbaczek · · Score: 1

    That is like saying that there should be a tax on buying a non-econobox car. Yes. Exactly.

    Everyone pays for the power they consume, be it gasoline or electricity. Who cares? Those who understand that money is not everything.
  24. Re:I wish mainstream CPUs / GPUs would focus on po by DrXym · · Score: 2, Informative

    Ireland sets the rate of annual motor tax based on the size of the vehicle engine. Someone with a 1.6 litre engine pays over a hundred more euros than someone with a 1.3 litre engine. It's probably explains why SUVs are quite scarce in Ireland. Which isn't a bad thing at all.

  25. FIRST 1Watt device? by MikShapi · · Score: 1

    I seem to have had the impression that my Soekris firewalls, running a National (today AMD) Geode SC1100 at 266MHz, a P1-class CPU that, coupled with 3 100MBit NICs, 128MB of RAM, IDE, USB etc eat a whopping 3-5 Watts for the entire machine, was x86.

    The FreeBSD kernel I run on them seems to think so too.

    Kudos to Via for taking ULV to a whole new level and giving us P2-class performance in that watt range, but this is by no means revolutionary, just evolution that allows us to do more with a ULV box.

    --
    -
    1. Re:FIRST 1Watt device? by TheRaven64 · · Score: 1

      I seem to have had the impression that my Soekris firewalls, running a National (today AMD) Geode SC1100 at 266MHz, a P1-class CPU that, coupled with 3 100MBit NICs, 128MB of RAM, IDE, USB etc eat a whopping 3-5 Watts for the entire machine, was x86. I have a WRAP machine based on a 266MHz Geode. It is not a P1-class machine, it's a fast 486, with some minor tweaks, but still a fairly nice CPU given that it's x86. I believe some of the new Geodes (500MHz sort of speed) are based on a newer design, which is 586-class.

      The FreeBSD kernel I run on them seems to think so too. OpenBSD runs very nicely on them too, which makes them ideal for firewalls. Recently, OpenBSD dropped support for i386, in the basis that it cluttered up the tree (potentially hiding bugs) and only half a dozen people were using it. A lot of people commented that they should not do the same thing for 486-class CPUs, since OpenBSD ran on a huge number of Geode systems.
      --
      I am TheRaven on Soylent News
    2. Re:FIRST 1Watt device? by MancunianMaskMan · · Score: 1

      the first sub-1Watt x86 device surely was the Intel's original 8086 from 1981. I've just looked up the data sheet, it draws 350maA at 2V. That's only 700mW!

    3. Re:FIRST 1Watt device? by wiredlogic · · Score: 1

      That's nothing. The Intersil 80C86 datasheet shows that it consumes 0.4W max.

      --
      I am becoming gerund, destroyer of verbs.
  26. Re:I wish mainstream CPUs / GPUs would focus on po by tomstdenis · · Score: 1

    1.6L is considered big? I have a 2L 4cyl Focus in Canada, and that's considered "small" by our standards. Not that I really push my car, but I am curious as to how a 1.3L accelerates [to say hwy speeds]. Because even in my car I have to really floor it [re: 5000 RPM] to hit highway speeds before I exit the ramp, well that's exaggerating a bit. usually I hit speed before the dotted lines (that let you get out of the merging lane). So I probably could accelerate at like 3-4K RPM just fine.

    A 1.3L must be near redline though to go from say 40km/h to 100km/h on an onramp.

    Tom

    --
    Someday, I'll have a real sig.
  27. Real Low-Power CPUs by RAMMS+EIN · · Score: 1

    ``Via says its chip draws a minimum of 0.1 Watts, when idle, and a maximum of 1 Watt, making it a great candidate for consumer electronics devices such as UMPCs, PVRs, and such."''

    Of course, in consumer electronics devices, you could just use any kind of MIPS or ARM or whatever other CPU you want, and have even lower power usage and/or better performance. It's not like you're gonna be running Windows on these devices, anyway, which is pretty much the only reason you would need an x86 in my book.

    --
    Please correct me if I got my facts wrong.
  28. Re:I wish mainstream CPUs / GPUs would focus on po by Stonent1 · · Score: 1

    I wish people would stop encouraging the government to administer my life.

  29. Happy by RAMMS+EIN · · Score: 1

    It makes me happy that someone is still catering to those who realize they don't need more CPU power and would rather, say, save money, or save the environment.

    --
    Please correct me if I got my facts wrong.
  30. x86 compatible, yes by Almahtar · · Score: 1

    but just what is "x" in this case? I mean, it'd be ridiculous if it was 286 of course because we'd need protected mode and 32 bit support to be even remotely relevant to today's software market. Oh, and TFA mentions it running XP, so yeah definitely at least 386 (my uni currently had a project to get XP running on a 386 and it succeeded - naturally slow as crap). But there's still a pretty decent gap between 386 and 486, 486 and 5x86 (Pentiumish level), and each subsequent iteration.

    I mean, 500 MHTZ with MMX and SSE 1, 2 and 3 is vastly different from 500 MHTZ with just 386 level support. Just look at how Athlons destroyed P4's with an even similar clock speed for another example of how MHTZ aren't a definitive measure. I'd like to know more about these CPUs when it comes to performance.

    1. Re:x86 compatible, yes by bWareiWare.co.uk · · Score: 1

      i686 + MMX + SSE1-3 + NX + some hardware cryptography.

      With 400Mhz FSB and 128 KiB L1 and L2 they have compromised, but they are more Pentium-M then 286.

      The companion North/South bridge chips are even better, with integrated video, network, memory, sata, and hardware MPEG2/4 acceleration for a couple of watts more. You could have a responsive desktop system including memory, video, network etc. etc running ~10W full load (So long as you don't spin up the hard disk). Couple that with very aggressive power saving and your idle is going to be low.

    2. Re:x86 compatible, yes by Almahtar · · Score: 1

      It's no end-all solution to all problems, but it's definitely a pretty incredible accomplishment and the perfect solution for a few. Thanks.

  31. Re:I wish mainstream CPUs / GPUs would focus on po by david.given · · Score: 1

    1.6L is considered big? I have a 2L 4cyl Focus in Canada, and that's considered "small" by our standards. Not that I really push my car, but I am curious as to how a 1.3L accelerates [to say hwy speeds].

    Very nicely, actually. Bear in mind that these engines are in what you'd consider to be small cars; typically two- or four-door hatchbacks. I used to have a Ford Fiesta with a 1.4l engine (IIRC), and while admittedly I'm a conservative driver, I had no complaints about acceleration. (There is one hill near where I live which it didn't like going up in third, but that was about it.)

    A 1.3L must be near redline though to go from say 40km/h to 100km/h on an onramp.

    Unfortunately my old Fiesta didn't have a rev counter, but peak torque was at about roughly 4 thou IIRC; the gearboxes are calibrated so that 70mph in fifth makes the engine run near peak efficiency, which is usually a bit below peak torque. I'd accelerate from 30mph to about 60 in third gear at a little above that, and then change down to fifth once I was up to speed in the slow lane. It was definitely pushing the engine above normal town driving, but not overly so.

  32. Re:I wish mainstream CPUs / GPUs would focus on po by hauntingthunder · · Score: 0, Flamebait

    Did you forget to put your fraking brain in this morning certain componats require a certain level of power or they wont work or wil lfail potentialy in a dangerous way.

    --
    You will never get to heaven with an Ak 47... But A Zu 30 is good for Low Flying Cherubim
  33. Re:I wish mainstream CPUs / GPUs would focus on po by DrXym · · Score: 2, Interesting

    I mentioned 1.6L more as a way of showing that the scale goes up proportional with engine size. I have a 1.3L car (a Citroen C4 coupe) which has no trouble at all on Irish roads even with passengers. Naturally there are still luxury vehicles, SUVs on the roads, but the overall emphasis is generally on what Americans probably call compacts - hatchbacks, saloons and so on. Most of those are probably 1.6L or less with a lot of 1.3, 1.2 and 1.1 size engines. If you drive around in a 3L SUV in Ireland you're going to be raped by the tax man.

  34. Re:I wish mainstream CPUs / GPUs would focus on po by 0100010001010011 · · Score: 1

    Or it's a diesel and produces all it's torque down low.

    I have a 'tiny' 1.9L diesel and shifting at 3000 RPM I can be at 80 or 90 by time I merge and that's carrying around a fat (by european standards) Jetta. But hell, in the states my car counts as compact and I can park in those compact spots.

  35. Re:I wish mainstream CPUs / GPUs would focus on po by DrXym · · Score: 1

    Oops correction, my engine is 1.4L. I should have thought more carefully before saying 1.3L. My last car was 1.3.

  36. Re:I wish mainstream CPUs / GPUs would focus on po by hauntingthunder · · Score: 1

    yeh but in the UK you just buy a classic over a certain number of years old and no tax you can get a nice starter Ferari for around 8-9k in the Uk now ;-)

    --
    You will never get to heaven with an Ak 47... But A Zu 30 is good for Low Flying Cherubim
  37. Re:I wish mainstream CPUs / GPUs would focus on po by DrXym · · Score: 1
    Did you forget to put your fraking brain in this morning certain componats require a certain level of power or they wont work or wil lfail potentialy in a dangerous way.

    I'm so glad you pointed that out. I shall return my A rated washing machine immediately since clearly the only way it could have gotten that rating is if the engineers dangerously interfered with the power levels required by some of its components. Idiot.

  38. Re:I wish mainstream CPUs / GPUs would focus on po by hauntingthunder · · Score: 1

    re 3l suv it would probably be a Diesel and probably running on bootleg farm fuel to boot - do irish farmers get the same deals (tax payer subsidy) the Uk ones do?

    --
    You will never get to heaven with an Ak 47... But A Zu 30 is good for Low Flying Cherubim
  39. Re:I wish mainstream CPUs / GPUs would focus on po by KlaymenDK · · Score: 2, Interesting

    (I've found discussing car performance where USians can eavesdrop always leads to flaming. Still...)

    In Denmark, a sizeable chunk of the total car park are small or family cars with engines in the 1.3-2.0L range. Sporty cars (Alfa Romeo et al, not Ferrari) are probably in the 2-3L range, no more. Of course the SUV-style cars will have way bigger engines (but I suspect that's more to help push the ego rather than the car).

    A relevant tidbit: we pay ~7$ per gallon of petrol.

    I drive a VW station wagon. It's 4 cylinders, 2L, 115bhp, ~1500kg. I don't have the stats for 0-60 (or 0-100) because I just don't drive that way, but its accelleration is quite adequate even without going over 3000rpm (usually I stay within 900-2500). I think I hit 4000rpm maybe three times a year. I average 7.3L/100km, or 32.2mpg.

    My old car (Peugeot 206) had 1.4L and 75bhp to push its 975kg, and its performance was quite comparable (better low end, worse top end).

    I lurk on an american classic car forum, and the rule of thumb there seems to be "(at least) 1bhp of power per 10lb og car", which translates to >300bhp for a station wagon, which again translates into race car (ok sports car) performance. I can't help wondering if that is really necessary for a family car, or a classic built for cruising.

  40. Re:I wish mainstream CPUs / GPUs would focus on po by shicklin · · Score: 1

    Did you see the Top Gear episode where Hammond bought and old Ferrari for under £10k? http://en.wikipedia.org/wiki/Top_Gear_Cheap_Car_Ch allenges#Series_7.2C_Episode_4_-_The_Top_Gear_Ital ian_Mid-Engined_Supercars_For_Less_Than_A_Second-H and_Mondeo_Challenge I wouldn't have called that nice although in fairness the other two cars were even worse.

  41. Re:I wish mainstream CPUs / GPUs would focus on po by hauntingthunder · · Score: 1

    If you overload a power suply it can overheat and cause fires for example. You have seen the damaged cause by the exploding laptop havn't you.

    your trying to relate totaly diferent technologys to pc technology (well embeded systems in the case of this cpu)

    its not like a car where a basic bmw 5 series functions as a car just as well as the sports modifed M5.

    yeh take your A rated washing machine back hire and  an eastern european woman to take you clothes down the the river it will be cheaper and much more energy efficiant.

    --
    You will never get to heaven with an Ak 47... But A Zu 30 is good for Low Flying Cherubim
  42. Re:I wish mainstream CPUs / GPUs would focus on po by gnasher719 · · Score: 2, Interesting

    '' 1.6L is considered big? I have a 2L 4cyl Focus in Canada, and that's considered "small" by our standards. Not that I really push my car, but I am curious as to how a 1.3L accelerates [to say hwy speeds]. Because even in my car I have to really floor it [re: 5000 RPM] to hit highway speeds before I exit the ramp, well that's exaggerating a bit. usually I hit speed before the dotted lines (that let you get out of the merging lane). So I probably could accelerate at like 3-4K RPM just fine. ''

    Get a Diesel engine. Massive torque = massive acceleration. Not that much horse power, but that only matters at high speeds (100mph+) where you lose your driving license anyway.

    In the UK, tax goes by carbon dioxide emission per km, engine size doesn't matter. There is a small number of cars that pay £35 per year, others pay between £115 and >£200 tax per year. But there are other differences: At the moment, you pay a £8 charge every time you drive into London. In the future, that will be free for cars with very low emissions, and up to £25 for very high emissions.

    But the thing that really hits is company car tax. If you have a company car, you have to pay income tax on X percent of the value of the new car every year. X ranges from 15% to 35%, depending on carbon dioxide emissions. For a £20,000 car, you pay tax on £3000 to £7000, depending on emissions. At 40% tax rate, that is £1200 to £2800 tax, in other words up to £1600 punishment every year for high carbon dioxide emissions for a £20,000 car.

  43. Re:I wish mainstream CPUs / GPUs would focus on po by tomstdenis · · Score: 1

    I cruise at 100km/h doing about 2.1K RPM or so. Heck, even at 40km/h my car is still in the 950-1K RPM range.

    I can't see going from 40km/h to 100km/h without hitting at least 3K RPM, unless you're the type that merges on the highway at 20km/h under the limit (of which there are plenty around here). And I get about the same mileage as you do btw (well for highway driving).

    Tom

    --
    Someday, I'll have a real sig.
  44. Re:I wish mainstream CPUs / GPUs would focus on po by DrXym · · Score: 1

    I don't know what deals farmers get but I do know that commercial and agricultural diesel is dyed green (in ROI) or red (in NI), to prevent the less taxed stuff from being sold and used in cars. You occasionally hear about the police conducting raids etc. I assume that since farming is a business that taxes on private motor vehicles are not necessarily applicable to SUVs used to conduct their business. I have no idea of the details though.

  45. Re:I wish mainstream CPUs / GPUs would focus on po by tomstdenis · · Score: 1

    Fair enough. Though HP also matters when you got peeps in your car. My car can hit 100km/h from 40km/h without accelerating much harder with 4 people in the car compared to just me. Granted it takes longer, but I can still manage without going over 4K. And once I'm at speed it cruises maybe 100 RPM faster [if that].

    Tom

    --
    Someday, I'll have a real sig.
  46. co-processor by Anonymous Coward · · Score: 0

    I'd go for one of these as a co-processor on any system, let the system do its simple things on this cpu, and if it needs the speed, turn on a faster cpu, and switch it over, and then keep taking care of the simple things.

    or maybe a few fast cores and this one, dedicated to the running the host OS and dedicating out the other cpu's to VM's

  47. One laptop per child by EagleEye101 · · Score: 1

    Does anyone know how this compares with the current one that the one laptop per child thing is using?

  48. Re:I wish mainstream CPUs / GPUs would focus on po by pimpimpim · · Score: 2, Interesting
    Any start is a good start, and one is already been made for supercomputers: Next to the top500, a few people have started a new list, ranking supercomputers on performance per watt, the green500. This is actually not an easy task, as to be honest one also has to include the power consumption of the cooling. Taking into account that one server room can contain various supercomputers, some estimated guesses are needed.

    With the relatively low cost and high availability of computing speed nowadays, the green500 list might become very important, as it is not only the environment-friendliness but also a lot of the running cost that is involved here.

    --
    molmod.com - computing tips from a molecular modeling
  49. Re:I wish mainstream CPUs / GPUs would focus on po by afidel · · Score: 1

    My problem is the whole idea of using the government and tax policy to punish "bad" behavior. I would prefer to include the cost of ALL externalities into the price of the consumable and have everyone pay the same amount per unit used, that way people would be free to use however little or much as they chose and everyone would be paying there fair share. If you want to make the scheme progressive you offer a yearly refund up to a certain amount to allow for lifting up of the disadvantaged.

    --
    There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
  50. Re:I wish mainstream CPUs / GPUs would focus on po by KlaymenDK · · Score: 1

    I can't see going from 40km/h to 100km/h without hitting at least 3K RPM,unless you're the type that merges on the highway at 20km/h under the limit. Ugh no, I rather dislike that, too. But I do shift as early as possible, and for casual accelleration (that is, NOT highway ramps) I often shift directly from 3rd to 5th (the ratio difference between 4th and 5th is not that great; when accellerating away from a red light I will usually spend only about 1/2 to 1 second in 4th).

    The only time I do high rpms is when I'm in 5th, driving fast. Or so I think! You know, now you got me curious ... I'll make a note of my rpm at various intervals when I drive home from work today (it's afternoon here now). I suspect I may have a slightly inaccurate idea of my engine rpm at speed. :-p

    And I get about the same mileage as you do btw (well for highway driving). Um, what I stated is my "total monthly average", including when my wife is driving. My home-to-work route is about 90% highway and 3% residential, so my highway average is better.

    Our data seem surprisingly different; I wonder if there is a difference in the petrol, gearing, tires, suspenson, or something else.
    Are Canadians (generally speaking) using the soft "american-style" suspension, or the harder "continental-style" suspension?
  51. It'd be good for tiny servers like the $99 decTOP by Sun+Tzu · · Score: 1

    The decTOP is a tiny AMD Geode-based box that consumes a total of about 8 watts, doesn't have a fan, runs Linux, and the only noise is the hard drive. With a flash-based drive, the power would drop to around 5 watts, perhaps, and it'd be totally silent.

    The 1 watt AMD Geode in the decTOP runs at 366 MHz and makes a fine light-duty server.

  52. Power rating by Dolda2000 · · Score: 2, Interesting

    I, too, do not agree with the GP's idea of actually taxing high-power computers, but I do think he might well have a point in just rating the computers after their power usage. If people buying computers see some real statistics of how much it is going to cost them in electricity to run their new computer, it is very likely that they are going to choose after that criterion, which will drive manufacturers to make more power-efficient computers. Which is good, because if they make computers that draw less power, then I, too, could get one of them and pay less for electricity (and having them run longer on the UPS :).

  53. Re:I wish mainstream CPUs / GPUs would focus on po by hauntingthunder · · Score: 1

    well a lot a smugeling goes on on the border of NI (used to be easy because of the troubles) and uk farmers have been known to use farm diesel in there private cars.

    --
    You will never get to heaven with an Ak 47... But A Zu 30 is good for Low Flying Cherubim
  54. Can you provide more details? by gr8dude · · Score: 1

    I am planning to build such a system precisely for the reasons you've mentioned - low power consumption, low noise. The problem is that I did not find any benchmarks that compare VIA's CPUs with alternatives.

    Can you tell me which CPU and motherboard you are using? Is Window XP usable on that machine? (I intend to run a flavour of Linux on mine, but your feedback will be valuable anyway)

    1. Re:Can you provide more details? by aclarke · · Score: 1

      Hey. Feel free to email me if you have further questions, but as you probably know a great place to start is mp3car.com. They have awesome forums there, and that's where I got my integrated startup/shudown controller and 12V DC power supply. I have a VIA EPIA M10000 rev.2 board, which is a 1GHz system. I'd say it's barely fast enough but I got it for something like C$156 shipped so I can't complain.

      As far as speed goes, I'd say overall it's maybe slower than my old PIII-800 laptop I used to have. Faster than my old PII-400 by a good margin. It's slow, but it's fast enough for what I use it for. I only have 256MB of RAM in there right now which is most of the problem I think. I also think that maybe I have a bad board, or bad something, because occasionally it slows WAY down and takes 5 minutes to do something that should take 5 seconds. Then eventually it will catch up again. I also get BSODs occasionally, so I wonder if I got a bad board.

      It's fast enough to run Google Earth though, or Delorme Street Atlas. It just takes maybe 2-3 minutes to load Google Earth, but once it's going it's not bad.

      You can see a couple photos of my setup here and let me know if you have any other questions.

      - Andrew.

  55. Re:I wish mainstream CPUs / GPUs would focus on po by tomstdenis · · Score: 1

    I think Canadian cars differ very little from the american style. When I was shopping for my car I wanted a small sedan that was light on the gas. I didn't plan on entering any races, or towing an RV. The 2L Focus was the smallest I could find that was reasonably priced. It's not bad on the gas when I treat it right. Though lately, I've been accelerating a bit faster than normal to stave off th assholes [re: french quebecers] who can't be bothered to do 60km/h in a 60km/h zone.

    Though justice was handed out two days ago. An unmarked car nabbed a few quebecers who were probably doing 80 or more.

    I always get nasty looks for doing 60-65km/h in a 60km/h zone. Yet so far, no tickets. Tickets cost money, receiving the evil eye from impatient drivers costs nothing :-)

    Tom

    --
    Someday, I'll have a real sig.
  56. Re:I wish mainstream CPUs / GPUs would focus on po by YttriumOxide · · Score: 1

    Moving back to Europe was quite a shock for me after 6 years in Australia. I had become quite used to my (perfectly normal) 3.6 litre V6 engine in my Holden Commodore. Here, that's considered quite a monster of an engine. You don't achieve "monster status" in Australia until at LEAST the 4 and half or higher litre V8 beasts.

    When I moved here, I bought myself a 2.0 litre Renault Megane and I've had a couple of people ask me why I didn't buy something with a smaller engine - to me, 2.0 litres IS small! I'm sure I'll get used to it though - and the biggest thing I've found is that my little 2.0l Megane can do pretty much anything my 3.6l Commodore could do, with the exception of pushing you back in your seat when you put your foot down when you're already going over the legal speed limit in Australia. I'm pretty happy with it, and even more so when looking at the petrol prices here compared to Australia! (Australia's prices would be considered high by people in the US, but DIRT cheap by people here in Europe... I think they're comparable to Canada, but don't quote me on that)

    --
    My book about LSD and Self-Discovery
    Also on facebook as: DroppingAcidDaleBewan
  57. What about a "heterogeneous dual processor"? by Anonymous Coward · · Score: 1, Interesting

    What if one combined such a processor with a standard Intel or AMD one, which would normally be deactivated, but be activated whenever you need high performance? That should give you the best of both worlds: Low power while doing normal, performance-insensitive stuff, and high performance when you need it. E.g. if you are a gamer, the Intel/AMD would be off while reading mail (doen't need much performance), but would be started when you start your games.

  58. There are aspects of your life which affect me... by Joce640k · · Score: 1

    Your private affairs should be your own business but there are aspects of your life which affect the planet and people around you. Power consumption is one of them.

    Slapping a tax on heavy consumers seems fair enough.

    --
    No sig today...
  59. How about the OS? by Joce640k · · Score: 1

    All these 3D fancy spinning desktops have suddenly upped the power consumption of PCs. GPUs consume as much as CPUS, and now they're running flat out for more time.

    --
    No sig today...
  60. Don't tell AMD by gillbates · · Score: 1

    I find it kind of odd that this is news considering that the AMD Geode runs a 1 GHz and draws only 1 watt of power. And it, too, is x86.

    And the Geode is at least a year old.

    --
    The society for a thought-free internet welcomes you.
  61. Re:I wish mainstream CPUs / GPUs would focus on po by archen · · Score: 1

    Japan does the same thing actually. Which is why they have sports cars like the Honda S2000 which manages to somehow get 240hp out of a 2.2 liter engine.

  62. Screw you, I like feeding trolls by Anonymous Coward · · Score: 2, Insightful

    0. Your use of punctuation, spelling, capitalization, and grammar makes me think you actually put effort into making it this crappy.
    1. I point at my wrist because you aren't paying attention. You might not realize the words, but the motion is undeniable.
    2. I search for the remote because while the channel may eventually be changed, the remote is still fucking missing.
    3. Fuck you and your 4 pounds. Either you're part of the EU or you're not.
    4. Maybe you're not waiting for a bus.
    5. "Are you alright" is a simple of way of asking if you can talk, move, respond. If you don't, you're not. You probably deserved the punch anyway..

  63. Re:I wish mainstream CPUs / GPUs would focus on po by Anonymous Coward · · Score: 0

    The less retarded tax would be on the electricity. Just like they tax the fuel more than the cars.

  64. Re:I wish mainstream CPUs / GPUs would focus on po by DrXym · · Score: 1

    While you could hike the unit price of electric to discourage its use, you're unable to distinguish between some old age pensioner heating their house versus some guy who's playing UT3 20 hours a day on their Alienware rig. It therefore seems more transparent to put the tax on the item when its purchased rather than hike the underlying unit price.

  65. menial task system... by Anonymous Coward · · Score: 0

    I've been wanting to build a secondary computer that does menial backup tasks for me, such as a small box for storing my source code as a version control system. But I haven't done it yet because I didn't think having a PC-grade computer using typical PC-amounts of electricity would justify just that one use (electricity isn't free, after all, and I don't make money off my home programming projects). I'm guessing this kind of thing might make this a cost-effective reality for me?

    1. Re:menial task system... by Bryan+Ischo · · Score: 1

      I built a home server in 2002 out of a PCChips VIA CPU integrated board (a Samuel 2 at 667 Mhz), 128 MB of RAM, and a hard drive, and RedHat Linux 7.3. The board had everything else integrated into it. It used to do more in my old apartment (print server, file server, firewall, backup server) but now all it does is act as a backup server for my hosted-at-a-datacenter main server. Runs rsync nightly to incrementally back up the master. It's been running since 2002 without crashing or hanging one single time (although it has been shut down on numerous occasions because of power outages, system maintainance, moving house, etc). It is the single most reliable computer I have ever built. A bit over a year ago the CPU fan died and I just took it off. It's just running with the tiny CPU heatsink, and never gets very hot. And I added a power supply that spins the fan up only when needed. So far I have never heard the power supply fan spin up. The system is silent (except for the teeny bit of hard drive noise) and I can't imagine it draws much power, to not even require the power supply fan to come on.

      Oh and the whole thing cost about $200 in 2002. Just a data point for you; these types of systems can be built and they work very, very well.

  66. Re:How does it compare [To ARM, etc]? by TW+Burger · · Score: 1

    All true, but business is run by accountants and banks, not engineers. A reasonably low power x86 opens up development of a plethora of cheap devices. You and I and anyone doing consumer homework will want an ARM based device for the better power performance, but the average consumer is only concerned with the price in Best Buy's and Walmart's weekend flyer. The ratio of x86 programmers to competent ARM developers must be enormous; so must the development tools. This would reduce development costs significantly and allow smaller players into portable device markets. I think they may not have a top mobile technology product, but Via has a winning marketing product.

    When I start building embedded I used the Zilog Z80. It was not the best performance choice but it was very cheap and that's what the customer cared about.

  67. Re:I wish mainstream CPUs / GPUs would focus on po by Anonymous Coward · · Score: 0

    > Some people want to buy a car that performs well. (I'm not talking about SUVs or huge waste hogs)

    Hmmm, there are some things that a Hummer H2 does much better than anything produced by Ferrari. So when you say 'performs well' it all depends on what you mean by 'perform'. Taking along five passengers while pulling a trailer with six horses in it would be ugly in your Ferrari, regardless of the symbol on the emblem.

    I will admit that most big trucks are used for image rather than actual work, but the same is true for most high performance sport cars. My four cylinder sedan (no turbo) will pull in excess of 110 MPH easily, yet I seldom get to drive that fast. Most of the time I am stuck in a steam of traffic going 75, and the Corvettes and BMW M5s around me are going no faster. They do, however, look much more hip and important. I guess that is worth the extra fuel consumption.

  68. Re:I wish mainstream CPUs / GPUs would focus on po by DrXym · · Score: 1
    The less retarded tax would be on the electricity. Just like they tax the fuel more than the cars.

    Right... so you can't tell the difference between some 80 year old heating their house to survive the winter as opposed to some disposable income guy playing with his new dual SLI rig.

    That sounds more retarded, not less.

  69. you forgot one as well by OrangeTide · · Score: 1

    6502 -> 65816

    originally Jef Raskin's Mac was going to be more like an Apple IIgs (which was developed and came out after the Mac did)

    --
    “Common sense is not so common.” — Voltaire
    1. Re:you forgot one as well by huckamania · · Score: 1

      Apple IIgs rocked. My friend bought one when it first came out. I bought a PC for half the price. 6 months later they cancelled IIgs support. Still, Bard's Tale was a great game and much better than anything my pc could do at the time.

    2. Re:you forgot one as well by Tumbleweed · · Score: 1

      The IIgs may have rocked compared to the Apple //e (which I had at the time), but it was a joke compared to the already-released Amiga 1000. I waited for the IIgs to come out to see how it would compare to the Amiga 1000, and was sorely disappointed. My next computer was an Amiga 500 (it took me awhile to save up the money :)

      What Commodore did to the Amiga line was a crime.

    3. Re:you forgot one as well by rbanffy · · Score: 1

      Agreed.

      The IIgs was too little, too late to save the Apple II line. It came out after the Mac, the Amiga 1000 and the Atari 520ST. At the time, it ran mostly 8-bit Apple II software (so, it was an overexpensive IIe that could run few software the older brother couldn't) and the full GS/OS only appeared much later. As things happened, it stood little to no chance of survival. In the end, the Apple IIe outlived it.

      If you ask me, what doomed the II line was the failure of the IIx project. Had they finished it as a next-gen Apple II and launched it before the competition, they would have ensured the survival of the II line for a couple more years.

      Not to say I don't want one. Really, I want all three in my interesting computer collection.

    4. Re:you forgot one as well by Tumbleweed · · Score: 1

      I never heard of the IIx project, and haven't been able to find anything via Google - do you know of anything online where I could read about that?

  70. No laptops for you by OrangeTide · · Score: 1

    Everyone keeps saying how great this chip will be for laptops. You won't be seeing it in laptops. People want multi-GHz multi-core laptops that can run Vista.

    You will see them in PDA-like devices, industrial portable computers(like inventory systems, medical systems), home routers/appliances, and possibly smartphones.

    Why have a 1Watt cpu in a laptop that can give it a 14 hour battery life, when it's not powerful enough to do full screen playback of mpeg4/dvix/xvid?

    --
    “Common sense is not so common.” — Voltaire
    1. Re:No laptops for you by DragonWriter · · Score: 1

      Why have a 1Watt cpu in a laptop that can give it a 14 hour battery life, when it's not powerful enough to do full screen playback of mpeg4/dvix/xvid?


      Because a laptop that doesn't do fullscreen video playback is still useful.
    2. Re:No laptops for you by OrangeTide · · Score: 1

      As if people buy laptops based on utility.

      We've learned that our cool alternative OSes or super efficient hardware is not marketable as a laptop. To most people a laptop represents a significant investment that entirely replaces the need for a desktop computer. Many people are laptop only. If you're a college student who must survive on a single laptop, or are a business professional who must use the latest productivity software, then a wimpy Via Eden laptop is not for you.

      So who other than you and me would actually buy such a laptop? It's far easier to leverage the chip in a smartphone where the market is far more willing to accept that you can't run Vista or play HD video content on it.

      --
      “Common sense is not so common.” — Voltaire
    3. Re:No laptops for you by Anonymous Coward · · Score: 0

      Considering this cpu will probably be paired with a cx700m or similar via chipset, wich does mpeg2, mpeg4 and wmv9 hardware accelerated decoding, I don't think this will be a problem.

  71. Re:I wish mainstream CPUs / GPUs would focus on po by Red+Flayer · · Score: 1

    The problem with that is that the external costs cannot be calculated at a fixed rate per unit. What do you do if there is a geometric relationship between environmental damage (an external cost) and total power consumed? Or how about factoring in the cost of reducing the world's fossil fuel supply? As each unit is consumed, should the increase in price to the rest of the supply be counted as an external cost?

    What I would propose is a stepped price scale based on each purchaser's usage for the billing period, with credits for certain necessary high-power appliances (such as certain medical equipment needed for long-term home care).

    Of course, this tax would need to be put into the coffers of government for remediation and offset of those external costs, which has its own problems.

    --
    "Trolls they were, but filled with the evil will of their master: a fell race..." -- J.R.R. Tolkien on Olog-hai
  72. Re:I wish mainstream CPUs / GPUs would focus on po by hansamurai · · Score: 1

    Someone with a 1.6 litre engine pays over a hundred more euros than someone with a 1.3 litre engine. It's probably explains why SUVs are quite scarce in Ireland. That and the fact that unless you're on a motorway (M) or national primary road (N), an SUV is generally going to be a really tight ride. When not on the main roads, you have to be constantly aware of how far your passenger side window is from the rock wall and how far your driver side window is from the oncoming traffic. Anyways, I barely see an SUVs on the western side of Ireland when I visit, and I'm happy for that just because it makes for a much easier drive!
  73. now add several hypertransport busses by Sloppy · · Score: 1

    And sell me a motherboard with 64 CPU sockets. ;-)

    --
    As copyright owner of this comment, I authorize everyone to defeat any technological measure which limits access to it.
  74. Theoretical Computation Limit? by Doc+Ruby · · Score: 1

    What is the theoretically minimum power consumption for physical computers?

    What's even the unit to measure it? "Joules per bit"? Bits of what? What's the theoretically least power consuming computation? Is it a bitwise comparison like "not equals", or NAND? Maybe something more primitive, like a half adder?

    And what's the lowest power consuming physical device, made of molecules (not, say, electrons or quarks) that can compute that minimum unit?

    And with that standard established, how "infodynamically" efficient is a 1-W 500MHz Pentium/MMX/SSE2?

    --

    --
    make install -not war

    1. Re:Theoretical Computation Limit? by JavaJunkie · · Score: 1

      The theoretical minimum power consumption is a nice round number; it is exactly 0 watts. Google 'reversible computing' for details. Unfortunately, if you want to extract the results of a calculation there is some loss.

      So by that measure, the processor you mentioned is infinitely 'infodynamically' inefficient :)

  75. AMD is better by Anonymous Coward · · Score: 0

    We are actually trying to build portable, solar-powered/gel battery systems. We've been experimenting with the AMD LX800 (rated @ 0.9W) and are very impressed so far. Our results show that it idles at about 800mA and briefly jumps to 1800mA during processor peaks. Our field application also uses touchscreen LCD's which adds another 800-900mA to the equation. Add a thermal printer 400mA idle and a cellular modem @ 200mA idle.

    0.1W is nice, but adding a 3.5W northbridge/southbridge makes the complete package worse than the Geode. Considering the LX800 "Companion Chipset" brings the total package to 2.4W, and the Geode includes MMX and SSE instructions the Geode more bang for the power buck.

  76. Bill Gates Quote: by crhylove · · Score: 1

    One watt should be enough for ANYBODY!

    --
    I hold very few opinions. I hold information based on observation and fact. If you wish to disagree, please use facts.
  77. low spin drives & asymmetric RAID by hawk · · Score: 1

    What I want for a home server is

    1) "low spin drives". Rather than stopping entirely, they would keep up a modest rotation (60rpm?) so that when spun up, they don't have to start with he resultant wear.

    2) Asymmetric RAID. While I haven't done the math (maybe I should do it and publish it, but then someone would expect the algorithm from me, too :), with four drives it should be possible to form an asymmetric raid. Periodically, the smallest disk would be replaced with a larger disk, rather than a need for matched drives.

    hawk

  78. FUCK! It needs a 3.5 W Companion Chip so FUCK THAT by Anonymous Coward · · Score: 0

    FUCK! It needs a 3.5 W Companion Chip so FUCK THAT. 1+3.5= 5 WATTS then DRAM sucks a WHOLE LOT. Nothing to see here. Move right along geeks!

  79. TS-7400 by IvyKing · · Score: 1

    Sounds like you're describing a TS-7400 from Technologic Systems - although the 7400 is ARM9 based. They ship a version with built-in wireless in a case about the size of a deck of playing cards. You can get Debian on a 512MB SD card for the system.

  80. Please stop talking out of your rear sphincter. by Inoshiro · · Score: 1

    "If we're going to have a backlit screen anyway (even with LEDs), we can only gain so much by reducing the CPU consumption. Amdahl's law and all that."

    Amdahl's law relates parallelism to MP -- it has nothing to do with power consumption. Amdahl's law is why only embarrassingly parallel software will gain much from a quad core (or octo-core) setup, unless you're running a system multiple people access concurrently.

    --
    --
    Internet Explorer (n): Another bug -- that is, a feature that can't be turned off -- in Windows.
    1. Re:Please stop talking out of your rear sphincter. by Chandon+Seldon · · Score: 1

      Amdahl's law relates parallelism to MP -- it has nothing to do with power consumption.

      Wrong. Amdahl's Law is a formula that covers optimizing a linear combination of resource usage. Amdahl's Law is frequently talked about in the context of parallel programming, but it applies anywhere where 1.) you want to optimize resource usage and 2.) total resource usage is the sum of the resource usage of a number of discrete components.

      You can use Amdahl's Law to prove statements like "if the CPU consumes 20% of the power than cutting it's power consumption in half will make you use 10% less power over all" just as easily as you can use it to prove "if only 20% of the runtime your program can be parallelized, then doubling the number of processors will only give you at most a 10% performance increase".

      --
      -- The act of censorship is always worse than whatever is being censored. Always.
  81. Re:I wish mainstream CPUs / GPUs would focus on po by Yeroc · · Score: 1

    I wonder if part of the reason for larger engines in vehicles in the US and Canada is the proliferation of automatic transmissions as opposed to Europe where the majority of vehicles have manual transmissions. I've found a manual transmission to be vastly superior when driving a vehicle that's a little on the under-powered side because you can downshift when you need the extra power instead of tromping on the accelerator and waiting a few seconds for an automatic to downshift for you. As a result I think my perception of the vehicle is vastly improved over the same vehicle with an automatic.

  82. Re:I wish mainstream CPUs / GPUs would focus on po by Chandon+Seldon · · Score: 1

    While you could hike the unit price of electric to discourage its use, you're unable to distinguish between some old age pensioner heating their house versus some guy who's playing UT3 20 hours a day on their Alienware rig.

    Electric heating is, if anything, more wasteful of energy than a crazy gaming rig. Are we trying to discourage wasting electricity here, or to punish people for recreational usage?

    If we can convince that pensioner to switch over to gas heating we save quite a bit more energy than we do if the gamer buys an Alienware with only one GeForce 8800 GTX instead of two.

    --
    -- The act of censorship is always worse than whatever is being censored. Always.
  83. Re:I wish mainstream CPUs / GPUs would focus on po by jubei · · Score: 1

    Do you have a CVT or something? Otherwise your comment doesn't make sense. In a conventional transmission, you will generally have the same RPM-to-MPH ratio for any speed in a specific gear, no matter how many people are weighing down your car.

  84. Re:I wish mainstream CPUs / GPUs would focus on po by Chandon+Seldon · · Score: 1

    Here's a much better plan: First, remove non-renewable energy subsidies. That, by itself, would have more of a beneficial effect on the environmental effects of power consumption than any five "overconsumption" taxes.

    --
    -- The act of censorship is always worse than whatever is being censored. Always.
  85. Re:I wish mainstream CPUs / GPUs would focus on po by daft_one · · Score: 0

    Exactly! We need to discourage pensioners from spending all that extra energy on heat, when they have perfectly good gas furnaces just sitting in the attic, waiting to replace the electric heat they installed just to be wasteful! ;-)

  86. Re:I wish mainstream CPUs / GPUs would focus on po by Chandon+Seldon · · Score: 1

    No, seriously. We either want to discourage wasting electricity or we don't. If we do, then people with electric heating systems should be one of our first targets. Maybe we would want to use some of the money raised from this electricity tax to assist people in upgrading their heating systems (and insulation), but saying "we should introduce a tax to reduce electricity usage, but let's start by exempting the largest users" is absurd.

    --
    -- The act of censorship is always worse than whatever is being censored. Always.
  87. Re:I wish mainstream CPUs / GPUs would focus on po by LuSiDe · · Score: 1

    My problem is the whole idea of using the government and tax policy to punish "bad" behavior.
    What you call "bad" behaviour I define as bad behaviour. Vice versa is also likely to be true. The environment is affected hence owned by all the inhabitants of Earth, and should be protected by all of them. We humans have great power and hence also great responsibility, even in this regard. Such power is, in nowadays societies, protected by so-called democratically elected governments. Hence, this is indeed the task of our government although as of now we're free to discuss useful alternatives on Slashdot.

    It really pisses me off to read about childish nerd with his toy car (SUV) which is dangerous for both pedestrians and environment. Then I feel some kind of jealousy about the low tax the childish American pays for his fuel. Then I'm reminded how well that works here in Europe and btw here in the Netherlands cars which are bad for the environment are going to pay substantially more regarding road-tax while the opposite is true for environment-friendly cars. The fuel itself ofcourse, costs still approx the same.
    --
    WE DON'T NEED NO BLOG CONTROL.
  88. Perhaps it is not a Linux bug... by adolf · · Score: 1

    Meaningless off-topic anecdote regarding USB:

    I've had bad luck with every single VIA-based add-on USB controller card that I have attempted to use. Strange things, like only negotiating at USB 2.0 speeds -if- the machine is booted with the USB 2.0 device attached. Random hard lockups (not even a BSOD) under moderate (2.5" HDD speeds) data transfer in multiple, otherwise rock-solid Proliant machines under Win2k3.

    In all cases, it seems that it's something that a driver update would fix. But also in all cases so far, no update has existed.

    I've had much better results with randomly-selected NEC-based controllers, which so far have always just worked in every machine I've tried.

  89. Hmm... by woolio · · Score: 1

    echo "$PARENT" | sed 's/RISC/Republican/g' | sed 's/CISC/Democrat/g'

    and you just described politics in the US for the last decade or two....

  90. Re:I wish mainstream CPUs / GPUs would focus on po by Red+Flayer · · Score: 1

    Yes and no. The problem is that the US needs the capability to mobilize for war, which requires both a large reserve of fossil fuels and a huge metaphorical pipeline for fuel on demand. This is what drives the subsidization, to ensure that the US's wehrmacht capability is there.

    Until the military runs on fuels other than fossil, the subsidies aren't going away. Equivalent subsidies for renewable/less-polluting energy resources would be more to my liking.

    --
    "Trolls they were, but filled with the evil will of their master: a fell race..." -- J.R.R. Tolkien on Olog-hai
  91. Re:I wish mainstream CPUs / GPUs would focus on po by kabz · · Score: 1

    You'd need a beowulf cluster of such tiny engines to power the typical US SUV.

    I'm imagineing at least 4 of these under the hood of a Yukon Denali ...

    --
    -- "It's not stalking if you're married!" My Wife.
  92. Re:I wish mainstream CPUs / GPUs would focus on po by DrXym · · Score: 1

    I doubt an SUV would be a tight ride. Irish roads are not especially narrow in general and have to accommodate coaches, trucks etc. But it's just really quite pointless to be driving an SUV unless you absolutely have to since the taxes and fuel costs make it prohibitive and rather pointless. It's not even obvious to me why SUVs are popular in the US. They're not more spacious or safer than other vehicles so it's a puzzle why people would choose them over conventional vehicles. Perhaps they're perceived as safer even though they're very easy to tip over.

  93. no SSE by r00t · · Score: 1

    The Geode NX has SSE. It's really an Athlon. It eats power too.

    The Geode GX and Geode LX do not have SSE. They are derived from the Cyrix MediaGX. (which passed through National Semiconductor before AMD bought it) They have MMX, 3dNow!, and a vector sqrt() function.

  94. Re:I wish mainstream CPUs / GPUs would focus on po by Chandon+Seldon · · Score: 1

    I guess that brings up the question of how much it's worth warping the economy to speed up our preparation for all-out war mobilization against China (since there is no other potential enemy that would require a full-scale mobilization like that). Personally, I think we'd have enough warning that would have time to ramp up supply lines and such in a war like that - and the military could easily increase their petrol stockpile to take up the slack during a ramp up period.

    But that's even accepting the premise that it's potentially worth seriously warping the entire world energy market and causing untold economic damage everywhere just to marginally decrease the USA's preparation effort for a major war. That definitely doesn't seem like the sort of trade off a democratic society (or any society that made rational decisions to maximize its own wellbeing) would intentionally make.

    --
    -- The act of censorship is always worse than whatever is being censored. Always.
  95. Re:I wish mainstream CPUs / GPUs would focus on po by Neuticle · · Score: 1
    Try doing 3k RPM in any specific gear in a truck over the same stretch of road with and without a full load in the bed, or towing a boat. You will have to hit a higher RPM or go slower under load.

    Speed is not just RPM x (gear ratio) x (wheel size)

    The difference with just passenger weight is usually pretty small (barring super-fatties), but if you really pay attention you'll notice it too. Especially if you're paying for gasoline.

    /If you have an SUV or van and don't normally have many passengers, take out a seat or two. You will save money!

    --
    "Cheeze it!" - Bender
  96. Apple //x by Tumbleweed · · Score: 1

    Interesting. It kinda reminds me a bit of the original idea being the 'Commodore One' project (which has since moved to an FPGA design which loads hardware/OS personalities, as I understand it). Too bad the //x didn't happen. I doubt it would have given the Amiga much competition technically (though I'm sure Apple could've competed very well via marketing), due to the lack of all the special co-processors the Amiga used, plus the very advanced (for its time) OS, but it sure sounds like it would've blown away the //gs.

  97. Re:I wish mainstream CPUs / GPUs would focus on po by KlaymenDK · · Score: 1

    Yup, now I've looked at my rpms under accelleration. Relatively lively accelleration on a highway on-ramp takes me to about 3k rpm in 3rd and 4th, but nowhere near 4k. In 4th gear, 4k rpm equals 110km/h which is the speed limit. In 5th, it's more than 140 (don't know how much because that would not just be a ticket more, but a license less...).

    Must be different gear ratios. Otherwise I don't get our different observations.