Slashdot Mirror


Single-Chip x86 Chipsets Around the Corner?

An anonymous reader writes "Kontron, a giant among industrial single-board computer vendors, yesterday revealed a credit-card sized board apparently based on a single-chip x86 chipset that clocks to 1.5GHz and supports a gig of RAM. It targets portable devices — not x86's usual forte. Kontron isn't saying whether the board uses a Via or an Intel chip(set) — both vendors reportedly have single-chip chipsets in the works, part of their respective missions to drive 'x86 everywhere.'"

170 comments

  1. Great idea by nurb432 · · Score: 2, Insightful

    If they can find a market for it. Its going to be hard to unseat the arm.

    "generic" embedded devices come to mind. ( but you have the pc104 standard there already..

    --
    ---- Booth was a patriot ----
    1. Re:Great idea by truesaer · · Score: 3, Informative
    2. Re:Great idea by Jeff+DeMaagd · · Score: 1

      If they can find a market for it. Its going to be hard to unseat the arm.

      It doesn't have to "unseat" anyone. I think it would be great if it makes enough of a market for itself sufficient to support continued development. It's possible to make a profitable product even if it's not #1 in the market segment.

      I thought AMD had a product like this though.

    3. Re:Great idea by Calmiche · · Score: 3, Interesting

      Yah, but current ARM processors max out at about 700-900 mhz.

      If they can really pull off a good, stable, low powered chipset in the 1.5 ghz range.. I would be very interested.

      I am still waiting for a revival of the handheld computers. UMPC isn't going anywhere, Palm is getting out of most hardware.

      HP is FINALLY getting back into the handheld market, but it's WAY late for it's projections and dosen't seem to be doing any advertising at all for it's new line.

    4. Re:Great idea by Colin+Smith · · Score: 3, Insightful

      Yah, but current ARM processors max out at about 700-900 mhz.

      If they can really pull off a good, stable, low powered chipset in the 1.5 ghz range.. I would be very interested. Right. Because more gigahertz means faster.
      --
      Deleted
    5. Re:Great idea by spirit+of+reason · · Score: 5, Interesting

      I am still waiting for a revival of the handheld computers

      You mean something like the Pandora?

      Also, more information here.

      While it's technically meant more for a gamer market like the GP2X, the arm + linux + wifi + usb host + decent resolution screen might make it a more general purpose machine.

    6. Re:Great idea by bombshelter13 · · Score: 4, Insightful

      Yes. That's ~exactly and exclusively~ what more (giga)hertz means: it's faster.

      Now, what it doesn't say anything about is whether it's higher performance.

    7. Re:Great idea by crhylove · · Score: 1

      Ha. When I can run all my windoze virtual machines and such on a hand held, I won't see the point of ARM vs. x86. There is way too gigantic of a code base for x86, anywhere it goes, it will dominate, quickly and easily.

      --
      I hold very few opinions. I hold information based on observation and fact. If you wish to disagree, please use facts.
    8. Re:Great idea by nurb432 · · Score: 2, Insightful

      Arm is still lower power. That is pretty important.

      But i do agree there is a large x86 codebase out there. ( but then again, there also is a decent sized codebase for ARM and other embedded processors )

      --
      ---- Booth was a patriot ----
    9. Re:Great idea by Tony+Hoyle · · Score: 0

      It also means more power drain, more heat, etc..

      ARM runs cool and on little power, which is why it's so popular. x86 is such a cludgefest with backward compatibility etc. it needs significantly more power to do the same work.

    10. Re:Great idea by canuck57 · · Score: 2, Funny

      Right. Because more gigahertz means faster.

      That is a fallacy big time.

      One game is to just clock up the frequency and make you think you have more. Put a divider in the middle and I could give you a 20GHz CPU. It is about throughput. How much can I get don in n cycles. For this, benchmarks are where it is at. Pick a benchmark(s) that is similar to the anticipated loads and work from there.

    11. Re:Great idea by Sardaukar86 · · Score: 1

      > Yah, but current ARM processors max out at about 700-900 mhz.
      >
      > If they can really pull off a good, stable, low powered chipset in the 1.5 ghz range.. I would be
      > very interested.

      Yeah man, those ARM people must be on crack, vending a CPU in '07 that can barely match the 900Mhz Celeron in my mum's ~2002 PC!

      oh wait..

      --
      ..Mullah or Pope, Preacher or Poet, who was it wrote: "Give any one species too much rope and they'll fuck it up"?
    12. Re:Great idea by Anonymous Coward · · Score: 1

      Wow didn't you catch the sarcasm?

    13. Re:Great idea by Anonymous Coward · · Score: 0

      From http://en.wikipedia.org/wiki/Gigahertz

      In computing, most central processing units (CPU) are labeled in terms of their clock speed expressed in megahertz or gigahertz

      more gigahertz, more speed = faster

    14. Re:Great idea by ystar · · Score: 1

      That's why the word 'faster' is meaningless without a discussion on the pipeline depth of the chip(s) in question.

    15. Re:Great idea by afidel · · Score: 3, Interesting

      When you're comparing a superscaler, out of order, multipiplined x86 chip vs an ARM? Yeah I think the 2x faster chip will win, in fact even at the same mhz the x86 part would most likely be faster. Now the question is, is it capable of more MIPS/WATT, which is what matters almost as much as absolute performance in the embedded space. There the answer is possibly but unlikely.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    16. Re:Great idea by SageMusings · · Score: 1

      Right over your head, Sport.

      --
      -- Posted from my parent's basement
    17. Re:Great idea by Eli+Gottlieb · · Score: 1

      Right, except not as vaporous.

    18. Re:Great idea by spirit+of+reason · · Score: 1
      Well, I think the projected release date is optimistic at best (atomicthumbs, who maintains the wiki, took it from a post months ago, but the design has gone through quite a few revisions). However, the folks behind the Pandora were already prominent in the GP2X realm, and they've been quite open with their design process.

      I think there's a good chance it will materialize. You can continue to ignore the hype and put it out of mind, though; I'm sure it'll make a slashdot story once it does.

    19. Re:Great idea by Eli+Gottlieb · · Score: 1

      I love the idea, but I think it will end up like the OpenMoko: a few developer's prototypes with a notice on the website saying that consumer models will be ready Real Soon Now.

    20. Re:Great idea by LarsG · · Score: 1

      And how do we know this single chip thing is superscalar ooo etc? Previous x86 SOCs have been rather weak in that area. You are absolutely right in that performance/watt is very important. And that's an area where "native" embedded procs like ARM have eaten x86's lunch.

      This SOC might be a breakthrough for x86 embedded, hard to tell since there's virtually no information on the specs. But based on previous history, pretty much the only reason for choosing x86 for embedded has been compatibility with existing x86 software.

      Hmm, a quick google shows that this thing is running a Via Eden and using the Via VX800 chipset.

      --
      If J.K.R wrote Windows: Puteulanus fenestra mortalis!
    21. Re:Great idea by jacquesm · · Score: 1

      funny how this is considered 'news', there are lots of little boards around the Geode chip, which is essentially a pc on a single chip.

    22. Re:Great idea by hitmark · · Score: 2, Interesting

      read up on cortex A8 and A9...

      --
      comment first, facts later. http://chem.tufts.edu/AnswersInScience/RelativityofWrong.htm
    23. Re:Great idea by MrNaz · · Score: 1

      3 Testicles per instruction?

      --
      I hate printers.
    24. Re:Great idea by JamesP · · Score: 1

      2001 called. They want their Pentium 4 clock speed bullcrap back.

      --
      how long until /. fixes commenting on Chrome?
    25. Re:Great idea by MobyDisk · · Score: 1

      When you're comparing a superscaler, out of order, multipiplined x86 chip vs an ARM? Except that a small low-power single-chip version of the x86 probably won't have those features.
    26. Re:Great idea by stonecypher · · Score: 1

      Right. Because more gigahertz means faster.
      That is a fallacy big time.
      Actually, it's a falsehood, not a fallacy. A fallacy is a flaw in reasoning, and doesn't actually mean that the conclusion is incorrect. My personal favorite example of a logical fallacy is to suggest that, in order to reduce 16/64, you simply cancel the sixes. Of course, that's total nonsense, but the result (1/4) happens to be correct.

      Incidentally, you do realize that the person you were replying to was being sarcastic, and pointing out the very thing you tried to point out to him, yes?
      --
      StoneCypher is Full of BS
    27. Re:Great idea by Directrix1 · · Score: 1

      You can get a FIC Neo right now. It just doesn't have all the final hardware revisions specs.

      --
      Occam's razor is the blind faith in the natural selection of least resistance and in universal oversimplification. -- EF
    28. Re:Great idea by Eli+Gottlieb · · Score: 1

      That being my point. You can get a developers' preview without the final hardware specs or the software and hardware polish necessary for an end user (rather than a fairly skilled Linux and embedded-hardware hacker) to make phone calls with their new Neo. That's 100% of why both projects will probably fail: I can convince my mother to buy a laptop with Ubuntu Linux on it and virtualize the Windoze software she needs, but I can't get an OpenMoko phone or a Pandora handheld that even the most unscrupulous marketing department will call "consumer-ready" because the people on those latter two projects want to hack rather than release a product, whereas when users have problems, Ubuntu has problems. These are two entirely different attitudes that create two entirely different outcomes.

  2. x86 cores? by heroine · · Score: 2, Insightful

    It would be huge if x86 or x86_64 was available as a core like MIPS & ARM. Life would be much easier for the set top boxes.

    1. Re:x86 cores? by The_Mystic_For_Real · · Score: 1

      Not sure if this is a good thing, an architecture monoculture (as far as consumer devices go) will decrease innovation. We need different architectures to be a breeding ground for new ideas, and to make sure that everyone in the technology field is aware of differences so that they will be more adaptable if a totally new architecture came around. Also I have seen Theo de Raadt talk about poor security on x86, something about proper separation of processes.

      --

      _____

      Thank you.

    2. Re:x86 cores? by 0100010001010011 · · Score: 3, Insightful

      Just like a monoculture of GSM has hurt the innovation of mobile phones in Europe.

      God bless the USA where competition between GSM, CDMA, & what ever sprint uses has increased innovation such that the USA always has the best cellphones out of any civilized country.

      Not that I don't think in

      And Theo's quote can be found here: http://kerneltrap.org/OpenBSD/Virtualization_Security

      "x86 virtualization is about basically placing another nearly full kernel, full of new bugs, on top of a nasty x86 architecture which barely has correct page protection. Then running your operating system on the other side of this brand new pile of shit. You are absolutely deluded, if not stupid, if you think that a worldwide collection of software engineers who can't write operating systems or applications without security holes, can then turn around and suddenly write virtualization layers without security holes."

    3. Re:x86 cores? by Anonymous Coward · · Score: 0

      ...Like Intel's Menlow and Silverthorne which are heading into the "MID" (and presumably, high-end cellphone) market?

    4. Re:x86 cores? by Vegeta99 · · Score: 1

      Why the hell wouldn't Europe have the same GSM phones I do?

    5. Re:x86 cores? by JoshHeitzman · · Score: 1

      Because they get access to new phones about a year earlier then the US because the phones are just sold as devices at retail unbundled from the carrier. In the US you have to get your phone from the carrier, so you only get it if and when they choose to offer it.

      --
      Software Inventor
    6. Re:x86 cores? by Anonymous Coward · · Score: 0

      >God bless the USA where competition between GSM, CDMA, & what ever sprint uses has increased innovation such that the USA always has the best cellphones out of any civilized country.

      I hope to god that you're kidding...

    7. Re:x86 cores? by mcrbids · · Score: 1

      "x86 virtualization is about basically placing another nearly full kernel, full of new bugs, on top of a nasty x86 architecture which barely has correct page protection. Then running your operating system on the other side of this brand new pile of shit. You are absolutely deluded, if not stupid, if you think that a worldwide collection of software engineers who can't write operating systems or applications without security holes, can then turn around and suddenly write virtualization layers without security holes." Long response:

      I present to you, the rule of profanity: The use of profanity in any kind of prepared statement is proof positive of the weakness of the underlying argument.

      It may or may not be true. But it's perceived as true by many, if not most, so it might as well be true. And in this case, poor Theo shot himself in the foot.

      Profanity is used to add weight to a statement, but it's a very crude, rough kind of weight. As in "Oh shit, I've just been shot!" can be said by anybody, because being shot is, well, rough. But "shit" when talking about X86 code is just... quaint. And low brow. And self defeating.

      Is the X86 instruction set weak? Yeah. Sure is. I won't argue that point. But the X86 instruction set has a strength that cannot be denied - it's compatible with a vast percentage of the software out there in the binary landscape. Everything from the flash player to freeDOS, all works with X86 first. It's an "upward spiral" where the mere inertia of the platform causes more people to jump on the bandwagon, which further increases the inertia, etc.

      It's how ideological wars are won, and truth be told, X86 is an ideology as much as an engineering practice. X86 will continue to rule the day until the basic rules of computing change. This "sea change" will make X86 computing irrelevant, and there are already several things that might do this: Virtualization might be this. The Internet itself is a powerful driving force, since, with commodity exchange formats, the X86 platform offers reduced value. And finally, there's quantum computing out there, on the horizon.

      But X86 has been actively developed for just shy of 30 years and the incredible investment in making it work, despite its warts, is high enough and profitable enough to nearly eliminate alternate platforms. AMD proved this with their Opteron processor, to replace X86 you first have to emulate it. Perfectly.

      And I, myself, am an example of the strength of the X86 - I won't even consider anything but X86 for my servers - what I have works, and the perceived risk in going with anything else is greater than the relatively low, commodity cost of a new server. I can spend $2,500 on a nice, whitebox 1U Rackmount server and get all the bells and whistles, hundreds of GB of RAID 1 10K SCSI drives, 8 GB of ECC RAM, and 4 cores, each running at close to 3 Ghz.

      That's an awful lot of power for the buck. Combined with reasonably well-designed software, and you have a mighty effective information processing tool that can single-handledly make hundreds, maybe thousands of users happy.

      Short response:

      Suck it, Theo!
      --
      I have no problem with your religion until you decide it's reason to deprive others of the truth.
    8. Re:x86 cores? by CBravo · · Score: 0, Redundant

      Just like a monoculture of GSM has hurt the innovation of mobile phones in Europe. ROTFLOL. I always perceived the US as a fragmented market for cell phone manufacturers and a closed market which is expensive for the end user.
      --
      nosig today
    9. Re:x86 cores? by johnwbyrd · · Score: 0, Redundant

      Is this irony? Japanese cell phones run at least two to three years ahead of the functionality in US cell phones.

    10. Re:x86 cores? by RAKtheUndead · · Score: 1

      >>> Just like a monoculture of GSM has hurt the innovation of mobile phones in Europe.

      God bless the USA where competition between GSM, CDMA, & what ever sprint uses has increased innovation such that the USA always has the best cellphones out of any civilized country.

      Hasn't hurt sales in Europe to have a single standard - notably, the UK and Ireland each have mobile phone presence in excess of 100% (more mobile phones than people). This seems to be more important to the companies than the actual power of the phones, and being able to connect anywhere in Europe has been a boon to the consumer, despite the lack of innovation - one of the few areas where a lack of technical innovation isn't that much of a drawback.

  3. The future is here by Anonymous Coward · · Score: 1

    I'm just aghast at the advances in PC tech in my lifetime. I've always been aware of Moore's Law and all that, but sometimes taking a step back is necessary for perspective.

    Merry Christmas, and thank God for all you engineers that bless us with this stuff.

  4. Who's in charge of code names? by KevinKnSC · · Score: 5, Funny
    From the article:

    Codenamed "John," the processor will integrate CPU, northbridge, and southbridge...

    That was the best code name they could come up with? Seriously?

    1. Re:Who's in charge of code names? by User+956 · · Score: 2, Insightful

      "Codenamed "John," the processor will integrate CPU, northbridge, and southbridge..."

      That was the best code name they could come up with? Seriously?


      Given what they probably had to do in the area of patent licensing, calling it a "John" is pretty polite, if you ask me.

      --
      The theory of relativity doesn't work right in Arkansas.
    2. Re:Who's in charge of code names? by Anonymous Coward · · Score: 0

      Thomas Crapper and John Harington.

    3. Re:Who's in charge of code names? by Anonymous Coward · · Score: 0

      You may sneer, but it's only one step removed from blackjack and hookers, which is quite popular around here if what I read is to be believed.

    4. Re:Who's in charge of code names? by gendusoa · · Score: 2, Interesting

      Via's code names are almost always biblical:

      * Luke
      * Esther
      * Nehemiah

      and I'm sure the others I can't remember off the top of my head are biblical names too.

    5. Re:Who's in charge of code names? by Anonymous Coward · · Score: 0

      Eden

    6. Re:Who's in charge of code names? by Mex · · Score: 1

      I see you couldn't do much better than "KevinKnSC" either ;)

    7. Re:Who's in charge of code names? by Anonymous Coward · · Score: 0

      Should I watch for x86 chipsets on johnornot.com soon now?

    8. Re:Who's in charge of code names? by brit74 · · Score: 4, Funny

      Via's code names are almost always biblical:

      * Luke
      * Esther
      * Nehemiah


      I'm still looking forward to the Satan and Whore of Babylon chipsets.

    9. Re:Who's in charge of code names? by williamyf · · Score: 1

      Via uses codenames from the bible, so probably refer to some famous John

      --
      *** Suerte a todos y Feliz dia!
    10. Re:Who's in charge of code names? by Eli+Gottlieb · · Score: 1

      I'm just waiting for the one that lets my people go.

      No, really. Intel's got a bunch of us trapped in here designing their new processors! Help, there's a turre___________

      NOTHING TO SEE HERE. PLEASE MOVE ALONG, AND THERE WILL BE CAKE.

    11. Re:Who's in charge of code names? by BosstonesOwn · · Score: 1

      Does the Rule out Hughe Grant ?

      --
      This package Does Not Contain a Winner
  5. Power consumption please? by 4D6963 · · Score: 2, Insightful

    It targets portable devices -- not x86's usual forte

    Yeah, that's not x86's usual forte because x86s are more power thirsty than say MIPS or ARM, which is why it would be interesting if the article could mention how much this new thing is supposed to drain.

    --
    You just got troll'd!
    1. Re:Power consumption please? by RightSaidFred99 · · Score: 4, Informative

      This isn't true because of some "law" that says x86 must be power hungry, it's true because nobody's really sat down and done an x86 processor for the embedded market, or at least not donw well. Check out Silverthorne, it has power use comparable to MIPS/ARM.

  6. A whole lot of shaking going on. by Anonymous Coward · · Score: 0

    "both vendors reportedly have single-chip chipsets in the works, part of their respective missions to drive 'x86 everywhere.'"

    It's not in vibrators yet.

  7. But is it worth switching from ARM? by NickCatal · · Score: 1

    But with so many people already developing for ARM, why would you want to spend the time and money switching to x86... it isn't like people want XP/Vista on their mobile phone (if at all) and there are already ARM releases of a bunch of stuff...

    Although I am not a developer, so I am anxious to hear what people in this thread say regarding any technical advantage having x86 may have over say ARM.

    --
    -nick
    1. Re:But is it worth switching from ARM? by ch0knuti · · Score: 1

      Although I am not a developer, so I am anxious to hear what people in this thread say regarding any technical advantage having x86 may have over say ARM. Neithe ram I but wouldn't it be much easier to provide the same applications which people use on their desktop if the pocket pc is running the same OS? It would require at most a tweaking of the UI.
    2. Re:But is it worth switching from ARM? by nerdyH · · Score: 1

      Software, software, software! X86 enjoys by far the most readily available open source software, well-tested and debugged due to zillions of x86 users. Software is increasingly key in device development, as consumer expectations about device features and functionality rise. ARM will always have its place for truly mobile devices like phones. But for a web tablet you carry around the house, and plunk into a charging cradle now and then, wouldn't you rather have the same web browser exactly that's on your desktop?

    3. Re:But is it worth switching from ARM? by skelly33 · · Score: 1

      Working with the likes of XP/XPE on a device like this provides a path of migration into mobile computing for companies with well established product lines who want to enter the mobile computing market or want to leverage small footprint computing, but can't re-engineer the application to do it. If you're not a programmer, you have to imagine a scenario where a company has millions to tens of millions of development effort invested into a software application and couldn't possibly hope for a "do-over" to switch platforms. Yes, XP/XPE does very much make sense commercially for mobile computing.

    4. Re:But is it worth switching from ARM? by Tony+Hoyle · · Score: 1

      X86 enjoys by far the most readily available open source software

      If it's opensource, recompile it FFS.

      Things like OpenWrt have been doing this for years.. architecture doesn't matter to well written code. Even my own humble efforts run on all sorts of arcane platforms.

    5. Re:But is it worth switching from ARM? by larry+bagina · · Score: 1

      wouldn't you rather have the same web browser exactly that's on your desktop?

      I do. Safari. And Opera.

      Meanwhile, open source (tm) firefox eats ram like CowboyNeal at a chinese buffet. Not my cup of tea.

      --
      Do you even lift?

      These aren't the 'roids you're looking for.

    6. Re:But is it worth switching from ARM? by K.+S.+Kyosuke · · Score: 1

      Even my own humble efforts run on all sorts of arcane platforms.
      ...provided that you are using languages for there is already a compiler port...
      --
      Ezekiel 23:20
    7. Re:But is it worth switching from ARM? by MrCopilot · · Score: 1
      Well, as an embedded Linux developer, I can tell you it takes me quite a bit longer to tweak an ARM kernel then a x86 desktops. Mostly due to drivers which vary greatly from ARM to ARM.

      I'm pretty comfortable in the ARM space now though and would not likely consider a new x86 project over an ARM unless Performance demanded it. Thus far it hasn't.

      --
      OSGGFG - Open Source Gamers Guide to Free Games
    8. Re:But is it worth switching from ARM? by Ash-Fox · · Score: 1

      ut with so many people already developing for ARM, why would you want to spend the time and money switching to x86
      ARM licensing costs a bundle.
      --
      Change is certain; progress is not obligatory.
  8. 'x86 everywhere.' by geekoid · · Score: 3, Funny

    What did we do to you to deserve this?

    --
    The Kruger Dunning explains most post on /. http://en.wikipedia.org/wiki/Dunning%E2%80%93Kruger_effect
    1. Re:'x86 everywhere.' by K.+S.+Kyosuke · · Score: 1

      You infidel dog! That's the punishment for so many people byuing Windows! See? Collective guilt, just get over it. *grin* ;-)

      (...on the other hand, if it's x86, SBCL might run on it, even OpenMCL in the future - compact, yet nice and quite fast. No need for C? Sure would be great!)

      --
      Ezekiel 23:20
  9. It's VIA by RzUpAnmsCwrds · · Score: 5, Informative

    If the chip is codenamed John, as the article claims, it's a VIA chipset. VIA uses biblical names for their CPU codenames.

    Previous VIA CPU codenames:

    Samuel
    Esther
    Nehemiah
    Ezra

    Note also that VIA combined a C3 CPU and a northbridge into a single package - it was codenamed "Luke".

    1. Re:It's VIA by Zwack · · Score: 0, Redundant

      I guess you didn't read the fine article... They state that it looks like a single chipset system and then state that VIA have been working on such a chipset codenmaed John and Intel have been working on a different one codenamed something else.

      Z.

      --
      -- Under/Overrated is meta-moderation, and therefore is Redundant.
    2. Re:It's VIA by TubeSteak · · Score: 2, Informative

      If the chip is codenamed John, as the article claims, it's a VIA chipset. Not to bruise your karma, but I suspect people are going to get the wrong idea from your post.

      Here are the two quotes FTFA:
      1. "It is based on an unnamed "highly integrated chipset" from an unnamed silicon vendor."

      2. "Via has long planned to bring out a single-chip part in its CoreFusion line. Codenamed "John," the processor will integrate CPU, northbridge, and southbridge into a single x86-compatible SoC (system-on-chip)."

      AFAIK, Via & Kontron have nothing to do with each other.
      TFA is not stating that Kontron is using Via's chipset.
      TFA later goes on to say that Via may eventually be a competitor to Kontron.
      --
      [Fuck Beta]
      o0t!
    3. Re:It's VIA by Anonymous Coward · · Score: 0

      New! Announcing VIA's newest and most powerful chipset, the Sodom. A design optimized specifically for the most demanding porn aficionado. Simply nestle it any tight form-factor box and it literally blows away other units. Try one today!

      Available wherever fine porn accelerated motherboards are sold. VIA, where the customer used to come first.

    4. Re:It's VIA by xs650 · · Score: 1

      John interfaces with Hooker

    5. Re:It's VIA by Anonymous Coward · · Score: 0

      read the fine article... What's this?

      Redefining the commonly used acronym, RTFA?

      It means Read The Fucking Article (7460), not Read The Fine Article (866). If you're that averse to swearing, use the abbreviation like a normal person.
  10. Re:FIRST TROUT! by Anonymous Coward · · Score: 0

    Do you need a bicycle?

  11. Sounds like a bad idea to me by Vthornheart · · Score: 3, Insightful

    "'x86 everywhere.'"
    Can I pass on that? The x86 architecture may be POPULAR, but it's inefficient, forced into backwards compliance with horribly outdated standards, and has been horseshoed for the past 20 years into a full architecture chip when the initial design was never meant to become like this.
    If a realm of computing has x86 as the non-dominant chipset, I think that's a blessing and it should remain that way. You can't do anything about the PC market at this point, for example... but I think the motto should be "x86 only where it already exists" rather than "x86 everywhere."

    --
    -Vendal Thornheart
    1. Re:Sounds like a bad idea to me by pla · · Score: 3, Insightful

      The x86 architecture may be POPULAR, but it's inefficient, forced into backwards compliance with horribly outdated standards, and has been horseshoed for the past 20 years into a full architecture chip

      The "x86 architecture" doesn't exist. x86 merely describes an ISA exported by the microcode of whatever underlying architecture a given chip really uses. An ARM chip could look like an x86 chip. A PPC chip could look like an x86 chip. The Core2 or Athlon64 could just as well export a traditional Motorola ISA as the chosen x86 - and with modern chips, they could do so with a microcode patch at boot time, you wouldn't even need to buy a new chip!

      Thus, any holy wars regarding its efficiencies or inefficiencies must remain firmly rooted in the ease of actually using it for coding. I do so, and find it for the most part adequate. It traditionally lacked enough GP registers, but even that doesn't hold true these days (at least for AMD's version - Not 100% sure about the Core line). And for that matter, very few coders even bother with ASM anymore... Even firmware development (which I also do) uses C almost exclusively nowadays.


      Not to say I want to see it everywhere, but we can't really hold the flaws of ancient hardware with no current connection to the ISA against it.

    2. Re:Sounds like a bad idea to me by Windom+Earle · · Score: 2, Informative

      Well, this discussion appears to be about an 'x86 Chipset,' not an x86 processor. Which means more than just the processor. So there is an 'x86 architecture.' If there wasn't, this topic would be meaningless.

    3. Re:Sounds like a bad idea to me by pla · · Score: 2, Informative

      Well, this discussion appears to be about an 'x86 Chipset,' not an x86 processor. Which means more than just the processor. So there is an 'x86 architecture.' If there wasn't, this topic would be meaningless.

      My earlier post may have sounded more caustic than I intended it, but I meant what I wrote literally.

      A "x86 chipset" just describes the supporting chips (usually memory, bus, and I/O) that let the CPU-which-happens-to-speak-x86 do its thing in a way familiar to programmers and users of non-embedded PC hardware. Although the PC world has a somewhat standardized set of these, by no means do all x86-speaking CPUs require similar enough supporting hardware as to justify the overly broad generalization.

      Simple example - The earliest x86 chips manually controlled DRAM refresh. Then that moved out into the chip-set (a large collection of single-purpose chips each doing their own thing - including a memory controller as one of them). Then a handful of those merged into a single-chip solution that handled all the critical non-CPU functionality (but had basically nothing we would think of as actual features by itself). Then as more and more I/O tasks also merged into that one chip, it eventually split into the Northbridge (bus and memory) and Southbridge (I/O). And now, we have CPUs with integrated memory controllers once again (though they have dedicated hardware for it rather than needing to tie up actual processing cycles for the job). Which of those would you call "the" x86 chipset?


      Perhaps you could more accurately say that this provides for a single-chip PC architecture, since most of what the chipset does has little to no relevance to what language the CPU speaks.

    4. Re:Sounds like a bad idea to me by LoudMusic · · Score: 1

      and has been horseshoed for the past 20 years into a full architecture chip when the initial design was never meant to become like this Welcome to business driving technology, rather than technology driving business.
      --
      No sig for you. YOU GET NO SIG!
    5. Re:Sounds like a bad idea to me by Sardaukar86 · · Score: 1

      > Not to say I want to see it everywhere, but we can't really hold the flaws of ancient hardware
      > with no current connection to the ISA against it.

      Surely though if we are actually *using* the architecture in some capacity we must then be subject to its limitations, the shiny hardware we run this stuff on today notwithstanding?

      --
      ..Mullah or Pope, Preacher or Poet, who was it wrote: "Give any one species too much rope and they'll fuck it up"?
    6. Re:Sounds like a bad idea to me by truesaer · · Score: 2, Interesting
      x86 is actually quite efficient and flexible. Variable length instruction sets have a lot of benefits, especially in embedded applications where memory is at a premium. You'll get a lot more data into your cache and memory with x86 code as opposed to a fixed length instruction set. Most of the disadvantages (complex decoders, etc) are borne by the chip designer. And for embedded there's no reason they need to support legacy stuff.


      This common belief that x86 is the devil is simply absurd. It sounds good but it doesn't really match with reality. As long as the chip designers are willing to make them, they're a great choice for software and system developers.

    7. Re:Sounds like a bad idea to me by Anonymous Coward · · Score: 0

      The "x86 architecture" doesn't exist. x86 merely describes an ISA exported by the microcode of whatever underlying architecture a given chip really uses. The ISA is not an independent entity to the underlying microprocessor. The microprocessor's architecture is designed to efficiently implement an ISA. The ISA is also designed to be fast on a given microprocessor design. The engineering suggest a higher degree of specialization between ISA and implementation in the microprocessor. The theory suggests they can emulate each other (Turing equivalent). But to emulate another ISA as a practical sense, you have to devote chip space to a dedicated translation unit.

      The pedagogical example is the MIPS instruction set on a classic scalar five stage pipeline (but now superscalar and superpipelined on modern implementations). The instructions are designed to allow a higher degree of pipelining. The ARM ISA specifies an inline barrel shifter because the transistor cost for this piece of hardware is cheap. That ISA is extensively designed around this single piece.

      If my memory serves me, Transmeta produced processors that emulated x86 through translation. And modern processors which implement the x86 ISA break each instruction into micro operations that are easier to pipeline, e.g. Netburst with 20 stages!

      There are certainly other microprocessors that do hardware emulation but they use more than just microcode reprogramming. It would be wasteful to design for this level of generality.
    8. Re:Sounds like a bad idea to me by Eravnrekaree · · Score: 1

      It is not true that the x86 architecture is somehow severely limiting of CPU design. All x86 is is a instruction set. The actual chip can be designed and laid out in any way you like, the instruction set does not greatly inhibit this. The instruction set increasingly has very little to do with the actual design and layout of the chip, and its performance. x86 can be and has been extended to eliminate defincies in the instruction set as well. Increasingly, and I have heard CPU engineers say this, instruction sets are pretty inconsequental as CPU design goes, it really would be of very little or no benefit to dump x86, so you might as well keep it to retain backwards compatability.

    9. Re:Sounds like a bad idea to me by Anonymous Coward · · Score: 0

      All "exported ISAs" (butt-ugly x86 in particular) are less efficient, more costly, and use more power than a base (raw) machine.

      There was a time when binary compatibility was all-important but that time is over. Now we consider performance, power, and price, and the relationship between them. I can't think of a solid requirement for binary compatibility except the case of direct replacement. I await enlightenment.

    10. Re:Sounds like a bad idea to me by Jeff+DeMaagd · · Score: 1

      How many people actually bother with x86 instructions?

      I guess techies seem to like to complain about it, but it's generally not really a problem.

      ARM has been doing pretty well where extremely low power consumption is neceesary, but that seems to be its only advantage. For getting a lot computation done affordably, it doesn't look like x86 even has any competition anymore. There's stuff like the Cell, it's expensive and where it sounds like it's even worse to program than x86, then there's Niagara, sounds like more of the same, the onus on the programmer to break things into as many threads as possible. The CPUs in the Blue Gene are low performing as well, but try to make up for it in the number of CPUs, still requiring breaking problems down as much as possible. I suppose IBM has the POWER architecture, but it's simply not designed for anything other than mainframes, PowerPC is a significantly cut-down version of that. IBM couldn't make a very efficient PowerPC chip without stripping out a lot of features. Their G5 couldn't convert an int to a float or the reverse, there was no way to move data between the two data types without going to memory, and their XBox 360 chip took a lot of modern features out too.

      So really, complaining about x86 doesn't really make sense other than in some abstract sense, because it doesn't look like anything can beat it in its own game, even with backward compatibility taken out of the picture.

    11. Re:Sounds like a bad idea to me by Windom+Earle · · Score: 1

      Perhaps you could more accurately say that this provides for a single-chip PC architecture.

      Indeed. When you translate the jargon 'chipset' that is exactly what it means.

      I am not sure what you mean 'manually controlled DRAM refresh' though. There was additional hardware, made up of TTL gates, for that function, on machines before the 'chipset' market took off. For example, the IBM PC-XT, the PC-AT and the earliest 'full AT footprint' clone motherboards generally did this, with big bunches of 74xx TTL gates. I don't consider that the processor doing something 'manually', it is actually just completely separate hardware doing the task. I have examples of those motherboards in my collection, and in additon all the schematics for all of it in my collection of Tech Ref Manuals.

      The 'chipsets' brought this all into proprietary large scale chips and ushered in the era of the 'Baby-AT' motherboard (dramatically reduced size from the Full-AT layout.)

      Probably the earliest example of 'integrated' x86 chip design was the 80186 and 80188, which brought a bunch of the functions of the 8088 processor on-chip, for embedded applications.

    12. Re:Sounds like a bad idea to me by Anonymous Coward · · Score: 0

      "Variable length instruction sets have a lot of benefits, especially in embedded applications where memory is at a premium"

      Full stop, end list of benefits. Smaller code size is about the only benefit of CISC over RISC these days, and even that is mostly only going to come into play if all of your code is written by assembly language experts. Everything else about CISC is a *penalty* on price/speed/performance/efficiency, and these effects are *strongest* on the embedded platforms.

      That horribly complex instruction decoder runs slower and costs gates. A LOT of gates if you want to implement pipelining, at it's a given that you want pipelining, especially when we're talking about modern x86 chips, which have those 10-20 stages of execution that you really, really want to keep full as often as possible. Those extra gates cost hardware space, consume power, and generate waste heat. All of which could have gotten you more performance or more battery life or more memory space. And because of the decoding needs of the x86, you also need a more complicated cache system, and cache misses and pipeline stalls are that much worse, further magnifying all the above issues.

      "You'll get a lot more data into your cache and memory with x86 code as opposed to a fixed length instruction set."
      Only by an extremely naive view of how x86 is actually implemented these days. You see, because the instruction set is so complicated, it can't actually be sanely implemented in hardware. Instead, the decoder is a computer in its own right, and what it does is translate x86 instructions into the real underlying instruction set, which is what gets stored in the instruction cache. It follows that the actual cached instructions end up being the same size as in an equivalent RISC machine.

      "Most of the disadvantages (complex decoders, etc) are borne by the chip designer."
      If you're only talking about the design phase, sure. In real life though, that leads to more difficulty in designing the chip, more expense in producing it, and more difficulty for the programmers who now have to work with a somewhat more tempermental chip (due to that extra complexity). It also makes it harder to write a compiler that fully takes advantage of the instruction set. (and that especially hurts when using higher level languages; it was always a problem with CISC that the special extra instructions weren't fully utilized). So you see, all of this does trickle down to the nuts and bolts of implementing a real product using an embedded chip. It's been mitigated somewhat in the PC realm by the fact that Intel and AMD are huge enough to eat the extra development costs. The other survivors in the chip wars survived by going RISCward and getting the same bang for fewer bucks.

      "And for embedded there's no reason they need to support legacy stuff."
      That's an argument *against* switching to x86, not for. This new x86-in-one setup seems more designed for people to stuff Windows onto a smaller package.

  12. next generation laptops by FudRucker · · Score: 1

    extra lightweight, extra thin, extra long battery life, i can see the benefits of this extra bigtime, looking forward to a laptop with this in it...

    --
    Politics is Treachery, Religion is Brainwashing
  13. PCMCIA sized, interesting by ThreeGigs · · Score: 1

    Every time I read about a shrinkage of form factors, I wonder how many you could fit in the volume of a standard 42u rack, ala blade servers.

    Now I'm wondering if this form factor isn't aimed at being able to add more processor power via a Cardbus slot, as the dimensions are within a millimeter of a PCMCIA card. Or perhaps aimed at mating directly to a SSD device. Fully equipped PC the size of a deck of cards, just add input and output.

  14. VIA user since 2005 by Anonymous Coward · · Score: 0

    VIA products rule. Been running silent low power PCs since the Nehemia came out. They were expensive to begin with, compared to the big power hungry CPUs, cost per GHz was about 5 times the amount. After supporting them for years the cost gap has reduced so they are only about twice as expensive as big chips. But the power ratio, 7Watts vs 300Watts means I can save that in electricity over the lifetime of the board! You kinda get used to the lower CPU speed and choose efficient applications, so I run a fluxbox desktop and carefully choose my applications. That means many mobile devices will soon be more powerful than my desktop! Just one word of advice, don't buy from mini-itx.com, they are thieves who take your money and don't ship the goods. There are plenty of other reliable suppliers.

  15. x86 programming by neapolitan · · Score: 4, Interesting

    It's a shame that the x86 is such a complex instruction set; this means that the age of the handheld computer as an easy programming platform for hacking is over.

    When I was programming for Apple //e, I had a good majority of the opcodes for the 6502 chip memorized, laying out assembly by hand. I later learned 68k assembly, and again, it is very "understandable" to a person just sitting down in front of the computer looking at an assembly printout. In the early 90's, pretty much x86 dominated and I stopped doing pretty much all assembly programming.

    In 1996 I was delighted when the palm pilot came out, using a 68328 (68k instruction set). It was like a renaissance, again programming in assembly and hacking other things for fun. Now, once again, it appears this will be dead!

    As a question to the slashdot community, is it possible to program "naked" x86 assembler? I have never really put in the time to learn it, but it just seems exceedingly complex and tedious to program for this chip without use of a higher level crutch (C compiler...) I am sad that once again everything I know is becoming outdated... :)

    --
    Slashdotter, ID #101. UIDs are in binary, right?
    1. Re:x86 programming by Zwack · · Score: 1

      Sure it is... I for one have written some 8086 assembler code by hand... But what's the point. Given the improvements in computer performance you don't usually have to write code that is so tight you can't squeeze any extra cycles out or remove any instructions for it to run at a reasonable speed. And if people went back to using code written as well as some of the older stuff these days they'd realise that they don't need to upgrade their computers every few weeks and the hardware market would collapse.

      Z.

      --
      -- Under/Overrated is meta-moderation, and therefore is Redundant.
    2. Re:x86 programming by Shikaku · · Score: 1

      NASM

    3. Re:x86 programming by dosius · · Score: 1

      nasm ftw?

      I don't do 8086 asm much though, most of my code is C, though I write to 65C02 asm once in awhile.

      -uso.

      --
      What you hear in the ear, preach from the rooftop Matthew 10.27b
    4. Re:x86 programming by Waffle+Iron · · Score: 4, Funny

      but it just seems exceedingly complex and tedious to program for this chip without use of a higher level crutch (C compiler...) I am sad that once again everything I know is becoming outdated... :)

      You sure are outdated. Today's "higher level crutch" is Python.

    5. Re:x86 programming by Anonymous Coward · · Score: 0

      what's the point? its l333T to have a 8088 webserver stand up to a slashdotting, that's the point. or similar accomplishments.

      Oh, did you mean, "what's the practical use of asm?" ... umm... i don't understand that question. yeah that's it. gotta run now.

      Art is its own reason.

    6. Re:x86 programming by Windom+Earle · · Score: 1

      If you have the bare processor to work with, and can implement it however you want, i.e. you don't need to map it into some arcane IBM-PC clone thing, the x86 processor has some neat features for small-model coding. You can, for example, use the segmenting features as an advantage. I am talking about the 'classic' x86 model, i.e. the 8086 and the 80286. And Assembly Language, of course. Segmentation is pretty cool when you use it that way. However, most programmers are terrified of environments where they don't have system calls and libraries to rely on.

      But if you use the processor the way IBM kludged it for the IBM-PC many of these features are lost, let alone if you write mere applications for an 'OS' that (usually badly) uses the 'x86 processor. Features in the '286 and '386 were ignored for decades by people running DOS and the 'doze. Early on there were some (a few) cool Unix boxes that used the '286 and protected mode 'correctly' as the Intel engineers apparently intended, not as the 'fast 8088' that most people ever used it as.

    7. Re:x86 programming by Windom+Earle · · Score: 1

      Most people never write ASM code for 'big' processors. The little 8-bitters (6502, Z-80, 6809/11) are little ponds by comparison to the 'lakes' that bigger processors (68000, 8086, etc.) represent. In the 'classic' period the home computers used the little 8-bit parts, so most people who started hacking ASM as kids played with these machines. Processors with pipelines, etc. are more complicated. You just don't hear kids hearkening back to the time when they hacked ASM on their PCs the way they did on Commies and Apples. By the time the PC was affordable enough for kid-hackers to get them to play around on, there were Turbo Pascal and similar beasts to code with.

    8. Re:x86 programming by Tony+Hoyle · · Score: 1

      If you'd said Java or c# then you might have a case (although even that's got limitations that mean it doesn't work for a lot of cases). Python? It's a freaking scripting language.

      You choose the language to suit the task. Design the app, pick the best language (and you'd be amazed how many projects C/C++ are the only choices.. eg. Java simply doesn't exist on some of the platforms I work on). Unfortunately it's not fashionable to do that any more and people start with the language then design the app around it.. which is why there's so much crap out there.

    9. Re:x86 programming by Anonymous Coward · · Score: 0

      Forth Assisted Hand Assembly. It's not quite naked but it is pretty revealing. :-P

    10. Re:x86 programming by Waffle+Iron · · Score: 1

      It's a freaking scripting language.

      i.e., crutch.

    11. Re:x86 programming by Nazlfrag · · Score: 1

      Ive coded 30,000+ lines of x86 assembler and hate it with a passion. 68k is a dream in comparison, the arguments are in a sane order (opcode soruce, destination) and you feel like you're swimming in registers. Just compare the elegance of DBRA with the abomination of LOOP or REP MOVSx (a simple DEC reg/Jcc is far more efficient). Still, the quirks of the x86 architecture make for some fun hacks. This was in the P1 days though, I stopped large scale asm coding around the PII MMX era and now like the others would just use C with perhaps a little splash of inline asm. There's just too little benefit, and x86 asm is just painfully ugly. My warning if you try to attempt x86 asm - don't. Hundreds of horrific hidden headaches await you. Just pull out an old ][e or palm and delight in a sane architecture.

    12. Re:x86 programming by mstahl · · Score: 1

      Ruby FTW!

    13. Re:x86 programming by Anonymous Coward · · Score: 0

      >is it possible to program "naked" x86 assembler?

      I am not sure, but it is possible to program x86 assembler while naked.

      Not that you asked though, and don't ask me how I know.

    14. Re:x86 programming by Almahtar · · Score: 1

      Can't speak for other platforms, but I taught myself X86 assembly in Jr. high, so it can't be that bad.

    15. Re:x86 programming by Anonymous Coward · · Score: 0

      It's possible to become very fluent, versatile and productive in programming pure x86 assembler. Witness the PC demoscene, expecially the 4K and 64K total size limit competitions say in Assembly or The Gathering every year... truly amazing stuff!

      But the flip side is poor maintainability. Which pretty much eliminates pure assembler coding from the enterprise domain, that is, 99% of software out there. The days of Mel Kaye and other Real Programmers are long gone -- they wouldn't be let in the front door lest they have bad influence on junior programmers.

    16. Re:x86 programming by lysse · · Score: 1

      Admittedly I learned the 8086 instruction set first, and I'm not entirely up to speed on the more abstruse bits or the vector instructions - but I actually quite like the x86 instruction set. It actually falls out quite logically - most instructions are composed of one or two bytes, with each octal digit of the byte conveying a distinct meaning; likewise, most addressing modes are conveyed with an additional one or two octal bytes. It actually hangs together quite nicely. The 16-bit instruction set is somewhat scattered with special cases, unfortunately, which betrays its 8080 heritage somewhat (the V30, NEC's sped-up 8086 clone, gave a lot of instructions Z80-style mnemonics, and indeed I'd say that anyone who grew up on a Z80 machine would probably find the 8086 similar in ethos); but the 32-bit instruction set is mercifully free of most of that. It's not as nice or orthogonal as the ARM instruction set, of course, but IA32 is probably not too far behind the 68k for pleasantness.

      Of course, there's one advantage to still using real mode - being limited to four segments of 64k each and only a megabyte of addressable RAM in total, 16-bit applications fit entirely into cache and consequently run like shit off a shovel on modern CPUs. :) (Indeed, 16-bit instructions are also a lot more compact than 32-bit ones, so your 64k and L1 icache go a good 30-50% further.)

    17. Re:x86 programming by John+Courtland · · Score: 1

      You don't HAVE to use all the opcodes, you know. Unless you're writing an operating system, you can probably get away with just MOV, LEA, PUSH, POP, CALL, RET, CMP, the branching opcodes (JZ JNZ JNE, etc.) and the math opcodes. In fact, from what I understand, it's usually better to not even bother with the other opcodes.

      --
      Slashdot is proof that Sturgeon's Law applies to mankind.
  16. What would it take? by Zaphod-AVA · · Score: 4, Funny

    What would a chip have to include for VIA to codename it Jesus?

    1. Re:What would it take? by Kagenin · · Score: 5, Funny

      A built-in WINE environment.

      --
      "All warfare is based on deception."
      Sun Tzu, "The Art of War"
    2. Re:What would it take? by Evil+Attraction · · Score: 1

      What would a chip have to include for VIA to codename it God or Satan?

    3. Re:What would it take? by makapuf · · Score: 5, Funny

      Flash memory (or some storage). Remember JESUS SAVES !

    4. Re:What would it take? by SunnyDaze · · Score: 1

      I would just feel sorry for the next chipset to come out claiming to be bigger the Jesus!

    5. Re:What would it take? by Tony+Hoyle · · Score: 1

      What would a chip have to include for VIA to codename it God or Satan?

      A chip called God would have to be omnoprescent and omniscient.

      So it would be freaking *huge* but have shitloads of memory.

    6. Re:What would it take? by mobby_6kl · · Score: 1

      A BIOS recovery mechanism which, if the BIOS is somehow gutted, allows one to fully recover the system by leaving it off overnight in a sealed closet.

    7. Re:What would it take? by Anonymous Coward · · Score: 2, Funny

      Nah, Just water will do, Jesus can do the rest...

    8. Re:What would it take? by FrankDrebin · · Score: 1

      I'm afraid that would be vaporware.

      --
      Anybody want a peanut?
    9. Re:What would it take? by Drathos · · Score: 1

      Yeah, but Satan scores.

      --
      End of line..
    10. Re:What would it take? by Creepy+Crawler · · Score: 1

      Oh well. Guess it'll take 3 days to recreate that backup set.

      And, Buddha makes incremental backups. Somebody's sig said that.

      --
    11. Re:What would it take? by Eli+Gottlieb · · Score: 1

      So I guess we can't have a "Moses" chip until we build AI to predict the stock market?

    12. Re:What would it take? by Per+Wigren · · Score: 1

      I'd call that one Judas though.

      --
      My other account has a 3-digit UID.
    13. Re:What would it take? by BlueParrot · · Score: 1

      Sure, but Buddha makes incremental backups.

    14. Re:What would it take? by Anonymous Coward · · Score: 0

      Perhaps a random number generator. d20?

  17. I hope not. by celardore · · Score: 1

    I just spend a lot of money on a new motherboard and processor (and every other component to build a new pc). I know it's obsolete the moment you buy it, but cut me some slack.

    1. Re:I hope not. by Sillygates · · Score: 3, Interesting

      It's already obsolete(in terms of size), and this is not news :(
      pico itx is already on the maket, the mainboard is about the same size (1.5ghz [like that means anything], upto 1gb ram):
      http://en.wikipedia.org/wiki/Pico-ITX

      and the transmeta crusoe processor (which implemented x86 in software) has been out for almost a decade now. The sony picturebook has a credit card sized motherboard along the left side of it's case:
      http://images.google.com/images?svnum=10&um=1&q=sony+picturebook&btnG=Search+Images

      --
      I fear the Y2038 bug
    2. Re:I hope not. by dgatwood · · Score: 1

      This is 55mm x 84mm. Pico-ITX is 100 mm x 72mm. Thus, this form factor is a little over half the size of Pico-ITX.

      --

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

  18. More info for x86 in embedded dev. at arstechnica by IYagami · · Score: 5, Informative

    You can find articles about the use of x86 in embedded devices at arstechnica, from Jon Stokes:

    Return of the Son of Pentium in 2008? Intel's new ultramobile processors

    Intel's low-cost "Diamondville" CPU to power OLPC/Eee PC mobile category

    And a very interesting article why processor makers want to extend their architecture to other realms: Beyond the BlackBerry crowd: life in a post-32nm world

  19. Everything by Anonymous Coward · · Score: 1, Insightful

    What would a chip have to include for VIA to codename it Jesus?

    Literally.... *EVERYTHING*.

    Including saving your (and my) miserable soul from going to hell.

  20. Linux by Anonymous Coward · · Score: 0

    Yes, but does it run Linux?

    But seriously. Most awesome mobile phone evar.

  21. Crap idea by EmbeddedJanitor · · Score: 3, Insightful
    Single chip x86: Geode etc are a crap idea. The idea has been done to death and has never caught on. There's no real benefit in them. In the past there was some appeal in x86 because of good, cheap compilers etc. Now there's gcc for everything this advantage has long since disappeared.

    ARM, and at a push MIPS, PowerPC and SH4 own this space. x86 needs to offer something huge to get back in the game.

    --
    Engineering is the art of compromise.
    1. Re:Crap idea by cnettel · · Score: 3, Insightful
      GCC targets everything and still is more heavily optimized for x86. Despite that, it's FAR from the best x86 compiler around, performance-wise. The pool of people with a "can read, cannot write it good without great pain" grasp of x86 assembler is also damn huge.

      Other x86-specific assumptions inherent in code (like atomic writes of different sizes, context switches limited to instruction boundaries) means that a platform porting of seemingly good multithreaded code can cause very subtle bugs. It's even possible to write Java code that is almost impossible to turn into a race condition on x86, but where you might do it on other platforms. You might argue that it's rare or that the code is "bad" and incorrect in the first place, but it's still there.

  22. where to find cheap small LCD by josepha48 · · Score: 1
    I've seen via's pico itx and their smaller 'in design board', and they are pretty cool. When the price comes down a little it will probably start to displace arm. My real question is where do you find small cheap or inexpensive displays to go with these little boards? Something on the order of a 4-5 inch diagonal screen.

    A small board is great, but a 4-5 inch screen would make a killer do it yourself pda / mini-computer.

    --

    Only 'flamers' flame!
    Does slashdot hate my posts?

    1. Re:where to find cheap small LCD by Fishchip · · Score: 1

      I dunno, how much do those in-car DVD players go for now, with the little screen? Couple hundred? I have no kids and no minivan, so I don't keep up on these things much.

    2. Re:where to find cheap small LCD by jweller · · Score: 1

      ebay has replacement PSP screens for around $50 shipped. If you want something smaller there are plenty of chinese video "iPods" you could strip for even less money. search for "tft"

    3. Re:where to find cheap small LCD by kird · · Score: 1

      i have a pico itx on my worktable right now. still building a case for it. the mobo itself is not much bigger than a deck of playing cards but once you attach the cables it is taking up the space of a paperback book.

      --
      ----------- destroy evil immediately!
  23. Why no x86 microcontrollers? by tkw954 · · Score: 1

    Is there a technical reason why there have never really been x86 microcontrollers? RISC chips are readily available at reasonable speeds for $1-$20. Even ignoring A/D functionality, why can't I buy a one-chip floating point x86 number-cruncher for my embedded applications that can match my laptop?

    1. Re:Why no x86 microcontrollers? by nerdyH · · Score: 1

      There are several, but they top out at 333MHz 486 or so. Vortex, DMP Electronics, and other make 'em

    2. Re:Why no x86 microcontrollers? by Windom+Earle · · Score: 2, Informative

      I think you're asking about the 80186 and the 80188, which have had a long history in embedded use. They're not particularly popular anymore. They'd match your laptop if you still use a Toshiba 1000SE, of course.

      Similar parallel offerings from Intel were the 80196 line.

  24. How about a better summary first? by mr_mischief · · Score: 3, Informative

    Yeah, because there haven't been 386, 486, and other systems on a chip and Via doesn't have a 1-watt processor anywhere to be found. This is not the first 1-chip chipset for all of the x86 line. That's bullshit. An SoC is even more integrated than just having the chipset as one chip. Somebody never read the old Computer Shopper before it slimmed down. SoC solutions for x86-compatible systems have been around more than a decade. The summary is bad, because TFA does not say this is a first for the x86 line.

    You're right that even low-powered x86 chips like the C7 and the Geode line are generally no match for ARM and XScale. MIPS I'm not as familiar with for power usage purposes. It'd be nice if that question was answered, but I'm afraid it'd be summarized incorrectly too.

    2005 article on anx86 SoC
    another 2005 article about a different x86 SoC
    2004 product page for an already obsolete x86 SoC
    Linux Devices list of x86 SoC solutions, some dated to 2000
    2000 Register article about the year since Cyrix released an x86 SoC
    Chipslist page showing availability of AMD processor with 80188 features plus DMA, watchdog timer, serial ports, and I/O pins in 1995
    article on the National Semiconductor Geode (the owners of that line before AMD bought it) thin client system-on-chip

    And the best proof of all: an archive of a 1996 story on the AMD Elan,which featured a 386, ISA bus, serial UART, memory controller, power management, and PLL hardware ON ONE CHIP

    1. Re:How about a better summary first? by homer_ca · · Score: 1

      Well, that's a more complete list than I could put together, but here's another x86 SoC that's been used in cheapo consumer wifi routers. Supported by OpenWRT.

  25. x86 should be like slavery in the 1820 by kiyoshilionz · · Score: 4, Insightful

    x86 has its market, the personal computer, but its legacy architecture should not be allowed to spread anywhere it has not already tainted. Remember Why Do We Use x86 CPUs? I thought x86 is something we want to eventually move away from (Remember VAX?), not something we want to spread.

    1. Re:x86 should be like slavery in the 1820 by evilviper · · Score: 4, Insightful

      I thought x86 is something we want to eventually move away from

      You were wrong. x86 isn't particularly impressive, but it's just a CPU, not a war crime.

      It's pretty much inevitable that x86 will move into new areas, as embedded systems need more and more processing power for multimedia, x86 vendors spend more and more of money reducing power consumption, and the economies of software development more and more favor reusing x86 software, rather than spending time on optimizations for the other architectures you use.

      Since Intel can't seem to make money on any architecture other than x86, they've eliminated their StrongArm/XScale line, and are replacing it with ultra-low-powered (sub-1watt) x86-based CPUs. VIA has long be trying to make inroads in the high-power, higher-performance embedded market with their own CPUs as well.
      --
      Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
  26. Didnt Cyrix try this a decade ago? by DJRikki · · Score: 2, Interesting

    With the MediaGX (I think) range? Integrate everything you can think of into the die including sounds and graphics.

    1. Re:Didnt Cyrix try this a decade ago? by thalassinos · · Score: 1

      Cyrix merged with National Semiconductor who subsequently sold Cyrix to VIA Technologies. VIA used the Cyrix name on a chip designed by Centaur Technology, since VIA believed Cyrix had better name recognition than Centaur and VIA.

      National Semiconductor retained the MediaGX design for a few more years, renaming it the Geode and hoping to sell it as an integrated processor. They sold the Geode to AMD in 2003.

  27. Mobile Phone. by crhylove · · Score: 1

    So when can I get my small x86 based phone that when plugged into a USB charger/dock instantly hooks up to a monitor, keyboard and mouse? Laptops are weak compared to this model. Imagine if all over the world was a USB charging docking station where you could use your phone/computer as god intended, with full size mouse, keys, monitor, and while we're at it 5.1 speakers, too. It would ideally run Ubuntu and have a small easy to use touch screen interface for video chat, cell phone, ipod and video/audio recording functionality. Have an SD slot, and be cheap and virtually disposable. Any venture capitalists out there want to help me kill the iPhone, Windows Mobile, and all phones by Sony, Samsung, et al?

    Hit me up.

    --
    I hold very few opinions. I hold information based on observation and fact. If you wish to disagree, please use facts.
    1. Re:Mobile Phone. by jcgf · · Score: 1

      That would be cool, but USB isn't fast enough for all that. Add in DVI and firewire (optional) and you would be smokin.

  28. Pico is also obsolete by markov_chain · · Score: 1

    Surely you meant to bring up the mobile-ITX form factor, which is half the size ;)

    --
    Tsunami -- You can't bring a good wave down!
  29. There goes the neighborhood... by giminy · · Score: 1

    So let's take a von Neumann architecture, which has inherent security problems due to it using the same address space for data and code, and use it to replace the usual DSP (which is superior, in at least the security sense).

    Ah, nothing like ubiquitous insecurity...

    --
    The Right Reverend K. Reid Wightman,
    1. Re:There goes the neighborhood... by CoughDropAddict · · Score: 1

      So let's take a von Neumann architecture, which has inherent security problems due to it using the same address space for data and code

      Oh crap! If only there were a way to partition the address space into data and code parts, and have the processor enforce that! Oh wait, there is.

  30. Whoooosh! by Anonymous Coward · · Score: 0

    That's the sound of the joke flying over your head.

  31. but x86 chips aren't really x86 anyway by Trepidity · · Score: 1

    Modern x86 chips have had fairly non-x86 internals for quite some time. I believe in Intel's line the Pentium Pro marked a shift away from fairly-literal implementations of the ISA to more or less translation: although the x86 ISA is thoroughly CISC, the Pentium Pro is mostly a RISC design.

    They can't be completely decoupled of course, but it's hardly like x86 chips are designed by taking the ISA and literally implementing it in silicon.

  32. x86 everywhere? Naaah ..... by ajs318 · · Score: 1

    The "x86 everywhere" dream is coming to an abrupt halt anytime soon.

    There'll be a new open RISC architecture along soon enough. It's a matter of time before the early-generation ARM patents expire, thus removing one of the barriers preventing wider adoption (it's a nice enough architecture, ARM just got greedy with their licencing). Every instruction being 32 bits long won't matter now memory is so cheap.

    --
    Je fume. Tu fumes. Nous fûmes!
    1. Re:x86 everywhere? Naaah ..... by Ash-Fox · · Score: 1

      Software still requiring x86 will matter though.

      --
      Change is certain; progress is not obligatory.
  33. What? by Jeff+DeMaagd · · Score: 0

    Comparing an instruction set with slavery belittles both subjects.

  34. Re:why is this a troll? by Anonymous Coward · · Score: 0

    Because Slashdot mods are retarded and can't tell the difference between "Troll" and "Offtopic." Fucking retards.

  35. x86 everywhere by Anonymous Coward · · Score: 0

    ...part of their respective missions to drive "x86 everywhere."


    How about off a bridge? Just a thought!
  36. Low cost PC and Media Centers by droopycom · · Score: 1

    This could be of great interest for very low cost PCs or small form factor boxes. Or even auto-PC.

    Today you can buy a motherboard with integrated audio, video, network, sata, usb, etc... the next step is to have everything on 1 System-on-Chip (SoC) rather than multiple chips.

    The motherboard would only have two chips: 1 x86 SoC, 1 flash for your bios. Thats it, then its just a bunch of slot for your DRAM some connectors and your done.

  37. pleasethinkofthechildren tag by cygonik · · Score: 1

    ...perhaps I'm missing something obvious.. ..what is the 'pleasethinkofthechildren' tag for? I mean, it's generally a good idea, but, what's the point of the tag? Are there some posts here that are inappropriate? ..I don't figure it's in reference to the single-chip chipset..?

    --
    I am not an atomic playboy.
    1. Re:pleasethinkofthechildren tag by Anonymous Coward · · Score: 0

      It's obvious you're not a hardware guy! That or you're still in school. All the old timers will get this immediately!

      Traditionally, the board that the main chipsets reside on is called a "motherboard"!

      Thus, any additional hardware is often on it's own board (at least it was in the early "PC" days) and is placed on specialized sockets on the motherboard, such as sound card, video cards, I/O extenders and the like and is called a "child board".

      Get it now?

  38. Ah yes, the one's with theoretical err in them. by Anonymous Coward · · Score: 0

    I'm still looking forward to the Satan and Whore of Babylon chipsets.

    The Satan chipset can divide by zero with a random result to push.

    The Whore of Babylon chipset? I don't know about that. There are two unrelated bridges, one called the Whore chipset of Babylon, and then another called the Babylon Whore chipset.

  39. Re:Great idea, but how far can we take ARM chips? by Blowfishie · · Score: 1
    The new generation of ARM chips (the Cortex series) have "the ability to scale in speed from 600MHz to greater than 1GHz, [using] less than 300mW" link. Further down that page gets you a figure of <0.45mW per MHz (I'll assume "idle" modes reduce the 1,000MHz * 0.45 a bit).

    The key point here is that you can get the best performance/watt around from ARM chips. AMD's Geode series has a 1.5-watt Geode LX900 (600MHz) and a 0.9-watt Geode LX800 (500MHz) (link). Note: AMD's site rates these at higher power (2.6W and 1.8W respectively) here.

    ARM chips have always been more efficient than X86 chips and always will be due to CPU architecture and the way that every instruction is encoded. Each ARM opcode has got a 4-bit conditional field that governs whether that opcode is executed or not. In an IC, you've got quiescent power (always there from the moment you switch on) and dynamic power. Dynamic power comes from switching transistors on and off. If an instruction isn't executed, there is less switching and less power consumption.

    With a "save the planet through electronic design" attitude, I'd love to see a large proportion of X86 desktops replaced with ARM-based machines. Especially when you consider that saving even 1 Watt per PC scales to many thousands of megawatts , especially when you see how many PCs are in use now.

    As ARM CPU speeds increase beyond the point where you can have a modern, complex OS and good office software running at a comfortable speed to the user, isn't that a goal worth aiming for? The practical sides of that dream are daunting. I'd be naive to think that the world will port its software just because it's a good idea to save electricity where possible. A fresh start would be bigger than Haiku in it's ambition. Is it worth it? I'd like to think so. What's 10 years of OS and application development that could make a good dent in global power consumption that would last forever?

  40. x86 architecture alternatives by GordonCopestake · · Score: 1

    I wish people would stop complaining about the x86 architecture (which to be fair is outdated and forced into backwards compatability) and instead put their heads together to build a decent future proof architecture that they can then use virtulization and emulation to run all existing x86 code. As far as i'm aware intel tried to start from scratch with the itanium and nobody brought it. We are FORCED to keep the backwards compatibilty but until we can run all our usual x86 based crap nobody will buy new chip(sets)