Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 


Forgot your password?
Close
typodupeerror
×
Technology

New Transmeta Patent 80

Posted by CmdrTaco from the what-the-hell-are-they-doing dept.
deggy writes "Transmeta have a new patent as of the 20th of this month. It seems to basicly concern caching. "Apparatus and a method for storing data already stored at an often utilized memory address in registers local to a host processor and maintain the data in the registers and memory consistent so that the processor may respond more rapidly when a memory address is to be accessed." "
This discussion has been archived. No new comments can be posted.

New Transmeta Patent More

New Transmeta Patent

Comments Filter:
  • From IBM:
    Inventor(s):
    Wing; Malcolm J. , Menlo Park, CA
    Kelly; Edmund J. , San Jose, CA

    Then compare with:
    Simpson; Homer J.
    Moose; Bullwinkle J.

    Jay Ward works for Transmeta! Aliens! Mind
    Control! Bwahahaha!
  • People can be hypocritical; groups can't. In any group, including the Slashdot community, there will be a variety of opinions. Some people like KDE; some like GNOME. Others think they both suck and use Window Maker. It's unreasonable to expect that we all think with the same mind. We don't.

    Look at the people who are in favor of the Transmeta patent. Chances are they have never ever posted their opinion on the "evil" patents. You're looking different people expressing their opinions and treating them like they are the same person!

    That's not hypocracy. That's variety.

  • Perhaps, but not by much.

    You have to point out all the relevant articles you found, and then explain how your product is different than those.

    But, if you just don't point them out...

    The patent office doesn't have nearly the resources it should if it wanted to actually investigate the patent aplications.

    Bleh, the whole fscking process is corrupt and useless, we need another.

    The patent office should only issue patents that are truly unique and innovative, and they should bear the costs of the initial investigation if new evidence should come to light. I mean, they fuck up and some else foots the multi-million dollar bill for it. Pathetic. It's yet another institution that doesn't actually do anything except keep the big (and court-experienced) companies in place and crush start-ups.

  • could someone please explain objectively to me why when Transmeta patent something it's good, but when Microsoft patent it's bad?

    Because many people here think that software patents are bad, whereas hardware patents are OK.

    dylan_-


    --

  • IIRC the USPTO has been making moves to make it harder for anyone to dispute a patent or copyright in the court. Not too long ago they asked congress to change the rules so not only did you have to show prior "art" but you had to show that the patent was "injuriously damaging" to your business. This would make it almost impossible to overturn a USPTO decision. I doubt that the patent office is very fond of the court system because they are often called into question over their decisions and have to defend themselves.

    Just my $0.02..
  • well, www.kernel.org [kernel.org] is being hosted by transmeta, and www.transmeta.com [transmeta.com] is running on Linux :).

  • I agree that the description is way too vague. That is yet another problem with the patent system as it stands. There are patent attorneys who pride themselves on their ability to be vague but sound specific enough to get approval. Often they are the same ones who are experts on making the wroding of any patent sound like any existing device.

  • Does this take money? You bet it does. Piles of it. But think about it: if the patent situation is truly as out of hand as many appear to think, it should be possible to raise lots of money to get the most obvious patents voided. If a patent is truly obvious and is truly burdensome for a large number of people or companies, wouldn't they be willing to be named as parties in a suit? If I were being wronged that badly, I know I certainly would.

    Unfortunatly, companies don't have much inclination to fight unjust patents. If MegaCorp A has a patent on the off switch, and MegaCorp B has a patent on the volume control, they cross license their patents, and carry on as before. It's the little guy who's hurt in software patents, who doesn't have a patent in the bleeding obvious or the money to fight it.

    To me, the patent system was designed to make it possible to reproduce engineering designs. For this it seems to work well. You can make your widgit for n years with protection, then everyone can do it.

    For software, it doesn't seem to work well. There are many reasons for this:

    1) Software is mainly ideas, not implementation. Thinking up the idea of a dancing paperclip is the hard part. Once you've thought of that idea, it's relativily easy to produce a new dancing paperclip.

    2) Software is self documenting. If you have FooBar 99, you can, with sufficent skill, work out how it makes paperclips dance. Thus the documentation of the patent isn't very useful for propegating the knowledge. This is especially true with the very non-standard language that is used in patents.

    3) Software parents are too fine grained. Patents for real processes tend to be large, and useful on their own. A process for making threaded copper pipes. Software patents tend to be small things. Cursors, caches & compression schemes. These aren't useful on their own, but only as part of a large program.

    If we wish to promote human knowledge, we should make reverse engineering explictily legal, regardless of what shrinkwrap licenses say, and eliminate software patents. Copyright is perfectly adequete for protecting intellectual property.

  • Math is patentable.

    I read yesterday that a patent had been awarded to the "inventors" of a system for dividing up the spoils of (e.g.) a divorce.
    The system was supposed to be "provably" THE solution to the generalized distribution of fixed property problem.
    My source is the Columbus Dispatch (sadly) and I can't find an URL. Surely someone with a quicker net connection can back me up?

    Fred
  • Some think all three suck and use explorer.exe :>
    Variety indeed.
  • I think that you are very possibly right here. MIT is doing some work with FPGAS (Field Programmable Gate Arrays) but so is the Oxford University Wolfson Research lab (with which I have links). A us company was recently on slashdot for building a computer using that uses FPGAs which is claimed to be 20,000 times faster than the fastest desktop machine. Are Transmeta trying to do something similar? who knows, but this "publicity stunt" of deliberately not telling us to create hype can only go so far - Transmeta: put us out of our misery. Thanks.
  • Considering that the guy didn't mention the name Linus once in his post I would have to say that your post was just lame. Don't put words into other people's mouths.
  • That's the way it should work.

    However, the US patent office will accept anything if it's wrapped in enough technojargon to make it expensive to evaluate. They're overwhelmed with so many applications that their basic attitude is to pass through essentially everything and let the interested parties go to court, where it is expensive and the decision often goes to the company who can afford the best lawyers. The patent office barely has the manpower to read all the patent applications they receive.

    Sometimes it's depressing to realize just how differently things work in practice than in principle.
  • Anonymous Coward wrote:
    From my point of view, ALL patents are an infringment of free speech and free thought, plain and simple.
    How is making sure that everyone knows the details of an invention an "infringement of free speech and free thought"? The main alternative to patents are trade secrets. How do you think that making everything a trade secret and requiring NDA's from all the engineers involved in a project promotes free speech and thought?

    I think you haven't carefully considered your opinion.

  • ...and they also wouldn't develop inferior and more expensive new drugs and sell them through aggressive marketing campaigns.

    The pharmaceutical industry spends more on marketing than on R&D.
  • Oh, I agree, the patent alludes to ideas that are non-obvious and very interesting.

    But the patent is supposed to describe the mechanism to a degree sufficient for someone else to recreate it. This patent does not seem to follow that requirement.

    If it was actually explicit in what it is describing, and also non-obvious, then I would agree. Now its just vagueness.

    Should vagueness that implies interesting things be sufficient for obtaining a patent?
  • That a patent was awarded doesn't mean it can be upheld. Remember, my basic objection is that the patent office is passing everything through with just a glance and leaving the whole mess for the courts. One of my examples of a gross error was the patenting of a large prime number.
  • FYI: Our product will not give head.

    Well, the Clapton-impression had better be up to snuff, then!

  • Sorry about the title. I've been sitting on that response for the better part of a decade and I finally got a chance to use it. I digress

    TheDullBlade Wrote:

    However, the US patent office will accept anything if it's wrapped in enough technojargon to make it expensive to evaluate. They're overwhelmed with so many applications that their basic attitude is to pass through essentially everything and let the interested parties go to court, where it is expensive and the decision often goes to the company who can afford the best lawyers. The patent office barely has the manpower to read all the patent applications they receive.
    You appear to have a fundamental misunderstanding of the way the patent office works. They aren't supposed to be the final arbiter of what is obvious and what isn't. In order to be worthwhile, a patent must be defended in court.

    Of course their attitude is to let the interested parties slug it out in court, that's the way the system is designed to work, and it works fairly well.

    Does this take money? You bet it does. Piles of it. But think about it: if the patent situation is truly as out of hand as many appear to think, it should be possible to raise lots of money to get the most obvious patents voided. If a patent is truly obvious and is truly burdensome for a large number of people or companies, wouldn't they be willing to be named as parties in a suit? If I were being wronged that badly, I know I certainly would.

    In any case, if it bothers you so much, perhaps you should, on your own initiative, set up a not-for-profit to take the holders of what you consider weak patents to court. Go ahead, try to solicit donations. I even think I might donate to it, for the potential for abuse certainly is there.

    Look. I've been listening to the debate about software patents for longer than a patent lasts and longer than many of the participants here have been alive. In nearly 20 years of debate, it is sad to note that the anti-patent brigade hasn't been able to come up with single workable suggestion about what should replace the current US patent system or any concrete examples of the patent system run amok despite endless claims that this happens all the time. Perhaps it is time for you to show me how the USPTO has harmed me.

    Not that the US patent system is perfect. Like the saying "There is no cause so just that you can't find a flaming asshole who supports it" there is no invention so perfect that you can't find someone harmed by it. However, in the absence of realistic alternatives, it's hard to know what to do.

  • Things are getting out of hand. I can understand patents but it seems that soon it will be dificult to design anything cause you will be bound to stumble on some patent whether knowingly or not. On the other hand I am not so worried about hardware patents as I am about the ones dealing with software ideas and designs.

  • This time, I move we have some posts besides "Patents are stupid, I should patent a biological waste disposal system and sue everybody's ass."

    Of course, that doesn't leave much to say about this article... Never mind. Flame on, Sparky.

  • I've been reading the patent claims; so far it looks like they are patenting an L1 cache with bus snooping and write through (does not that describe every current L1 cache scheme?)


    Claim 13 has more meat in it; it almost makes it sound like they are caching micro-ops from on-the-fly emulation of other instruction sets... but that is very similar to what the K7 is supposed to do! (and possibly Merced x86 mode)


    Sure looks like Transmeta is building a chip intended to be fast at emulating existing processors; I hope they release full documentation on it, it would be fun to design my own instruction set!


  • hopefully this will need a patent !

    why say that ?
    well if they have got the cpu or software to cache the corect things this will mean a signifacant speed up in execution .

    I remeber desighning my program so that the varibles would not be swaped out of level 1 cache and speed up the computation of geomentry

    this has been most evedent in video and games where cache misses are important (yes I know databases but hell I dont write those so cant comment).

    hopefully this chip will allow the editing of video and mpeg

    as well as stunning games


    on a linux box !! ha you dont get to say video and linux much That will change hopefully !!



    a poor student @ bournemouth uni in the UK (a deltic so please dont moan about spelling but the content)

  • Re:I'm not quite sure I understand... (Score:3)

    by AndyB ( 11841 ) on Sunday July 25, 1999 @06:33AM (#1785567)
    I was just trying to grok it too. Best as I can tell, this patent describes setting aside two "special" registers which it uses to cache a memory address and the data at that address.

    The interesting part comes when it detects an access to that memory address - it then goes ahead and rewrites the next block of instructions, so that they use the special data register instead of a memory access to load/store the data (and dealing with keeping memory up to date in the background I guess - the patent seems a bit vague on this, as well as on how it chooses which memory address and data to store in those two registers initially).

    Interesting idea, but I'm worried that the patent may be a bit vague on some points... as given, this method isn't guaranteed to work on SMP systems...

    I'm always interested to know if anyone was able to glean more out of the patent, or find problems with my own description. =)

  • Re:I don't get it. (Score:4)

    by substrate ( 2628 ) on Sunday July 25, 1999 @05:59AM (#1785568)
    In order for real high tech companies (I'm not talking about the AOL's or the amazon.com's of the world) to compete they have to differentiate. To do this means that their principle scientists generate new ideas that give them an edge over the competition. In order to protect their intellectual property its in their best interest to patent it otherwise other companies just feed on the R&D expenditure of the real technology leaders.

    If people and corporations were honest this wouldn't be necessary. They're not, so it is. Certain software patents may make it seem like the patent system is useless but that isn't true. It needs some work, but without the protection that patents and patent litigation affords no company would stick their out to break new ground. It'd be much safer to just wait for somebody else (probably academic institutions) to come up with technology and pilfer it.
  • I find this attitude disturbing; after reading through the claims, it looks like there is very little here that is novel or even interesting.

    This kind of Linus-worship is clouding the judgement of lots of folks on this site. Just because it has to do with Linus/Transmeta DOES NOT mean it is unique, innovative, or novel. They might be working on cool things, but judge them for their accomplishments, not just because Linus happens to work there.
  • I also got the impression they patented every conceivable caching method on their code-morphing system by simply being vague.

    Just to give an example to those that don't know, their method could easily be a write-through or write-back caching policy, depending on how you interpet the speed of keeping the data consistent. Write-through caching updates data in memory immediately, while write-back updates periodicly, with the changes being stored in a buffer. These are two simple (and popular) methodoligies which can be found in many if not all computer engineering texts.

    If it were not limited to their reconfigurable instruction set computer, I'd think they would have some serious issues with prior art (IMO).
  • "Apparatus and a method for storing data already stored at an often utilized memory address in registers local to a host processor and maintain the data in the registers and memory consistent so that the processor may respond more rapidly when a memory address is to be accessed."

    Caching memory addresses in processor registers? So you have:

    Registers -> Processor Cache -> Motherboard Cache?

    Or am I completely wrong (which is probably quite likely)?
  • Here are my guesses.
    1) It's for system-on-a-chip integratation.

    2) It's for a 'self-programming' chip; i.e., the circuits can be 'changed' after manufacturing. I reliable cache for a new instruction set would be very important. (Hi, I'm an x86. Now, I'm a SPARC. Now, I'm an Alpha! :) (Oops! MOV != MOE | LARRY | CURLY. Now, I'm a cow chip because my cache failed :( Please reinsert smoke. )

    Seriously though, I think there's a project at MIT like number 2. (FPGA ?)

    Sorry if I'm incoherent, I just woke up.

  • Patent #9448-220-1036
    Anti-gravity pre-processor for FPU

    Uses tri-parallel unidirectional buffering to achieve velocity sufficient to launch the processor into orbit. By utilitizing a integrated tcp/ip stack and a subminature subspace transmitter, the AGP-FPU can participate in the SETI@Home project and help find those pesky aliens that landed in Roswell some 50 years ago.

    --

  • Hypocrisy? (Score:1)

    by Anonymous Coward
    Ok, could someone explain to me why it is "cool" when Transmeta gets a patent, but "uncool" when anyone else does?

    Thanks.
  • Did you even read the previous posts? A few of them are excited by the possibilities, but many of them are critical of the patent itself. Just because linus works there doesn't mean we'll all blindly accept everything they do as a Good Thing (tm).
  • So they're storing memory contents in registers local to the CPU. Doesn't that describe every other type of caching scheme?

    This seems disturbingly vague: could a patent infringement be filed against Intel for their L1 caches???

    I was under the impression that something could only be patented if there was an innovative step involved, not evolutionary. Where is the innovative step here? Or do American patent laws differ that much from elsewhere?

  • I think the company you're referring to is Starbridge Systems. [starbridgesystems.com] Interesting company, that. A rip off their web page:

    SBS's Hypercomputer systems may be described as massively-parallel, reconfigurable, third-order programmable, ultra-tightly-coupled, fully linearly-scaleable, evolvable, asymmetrical multi-processors which achieve unprecedented benefits in performance, design time, speed, flexibility, power consumption, reliability, size, and cost.

    SBS's Hypercomputer systems already reconfigure themselves on-the-fly (up to 1,000 times per second, i.e. in real time) and they are not bound, as this author suggests, to run a single computationally intensive algorithm. They simultaneously perform multiple tasks previously requiring separate, dedicated (meaning hardwired or fixed) hardware configurations (and usually separate software programs as well) for each separate task. If an electronic system is required to do ten different things, with reconfigurable logic only one programmable chip (an FPGA) is needed, rather than ten hardwired chips (application specific integrated circuits, or ASICs).

    Whatever the hell that means. Basically the jist of what they're saying (as I'm interpreting it) is that their computers are able to be reconfigured in hardware so they're like an infinite number of devices designed specifically to take on an entire task. They'd be more efficient just like Deep Crack was exceptionally fast at its single-purpose job of cracking DES, or a 3D graphics card is fast at rendering graphics - far faster than your average, all-purpose CPU. Could be interesting. (Computer, switch to RC5 mode!)

    Anyone have any other information on this?

    Jonathan Wang

  • Not true. Only the U.S. and the Phillipines follow the "first-to-invent" rule: if I invent something a day before you invent it independently, but wait until a day after you apply for a patent to apply for mine, then I get the patent. _All_ other countries follow the "first-to-apply" rule and would give the patent to you.

    Also, most (but not all) countries follow the so-called "absolute novelty" rule under which publishing the details of an invention makes it unpatentable. Here, you can apply up to 1 year after disclosure. A few countries, such as Canada and Brazil, and Australia's "petty patent" system, agree with us on this one.

    Finally, the U.S. system is much more receptive to non-traditional subject matter, including software patents, than most countries'. You can't blame the Patent and Trademark Office for this: it's mostly the fault of the courts, especially the rabidly pro-patent Federal Circuit. After the _State Street Bank_ case of last year, which basically allowed the patenting of a method of accounting, it seems like just about any idea is now patentable in this country.

  • Re:Patents are not that easy to get. (Score:3)

    by jguthrie ( 57467 ) on Sunday July 25, 1999 @07:17AM (#1785580)
    Anonymous coward wrote:
    What exactly is the deal with patents? Seems to me I should patent "an object of complex design and orgin which allows for passengers to be moved via rapid motion from one point to another" That way I can collect royalties from everyone who uses a plane, train or automobile.
    It helps if you know how the patent process works. I'm currently going through that process for my day job. A patent application has to describe a device or class of devices that has not been invented before and the description of the class of devices has to be described well enough so that someone who is "skilled in the art" can duplicate it without difficulty.

    So, if something has ever been built before, it is not patentable. (This is true even if you were the one building it and you wait to long to file the patent.)

    That puts a damper on your plans to rake in the big bucks from mass-transit manufacturers, doesn't it? People have been moved en masse for thousands of years, so there's lots of "prior art".

    In order to be granted that patent, you have to explain what makes your device different from every other mass-transit device that's ever been built and why those differences are important enough to be afforded patent protection. So, it's not possible to patent, say, an airliner, but it may be possible to patent devices on the airliner. I'm sure that whoever invented retractable landing gear got a patent on the device even though most people today would consider that an "obvious" invention.

    This whole software patent thing has been blown all out of proportion. Patents are there to help promote the free distribution of ideas, not to stifle invention. Some people focus solely on the fact that the patent gives the patent owner a monopoly on those devices, but they conveniently forget that, in order to get a patent on anything, you have to describe that thing in enough detail to duplicate it. Once the patent (assuming it's granted) expires, that information is freely available.

    That works for software as well as for mechanical devices. I've heard the complaint that "software changes too fast so 17 years (or 25 or whatever the laws in your country say) is way too long." Unfortunately for that argument, it simply isn't true. The rapid rate of change in software technology was due to the relative youth of the technology. As software has matured, the rate of change in that technology has become much smaller. It's a lot harder to make fundamental changes in software technology now than it was 20 years ago. That alone means that you'll never see a situation where you can't write a program without violating some patent.

    In fact, if you look, you'll see that patents in any technology follow a similar pattern: They come quickly and cover "obvious" (to posterity) inventions in the beginning and are granted less often and the patents that are granted get more esoteric as time goes on.

    For the patent in question, well, I don't know about you, but I've never heard of a system where the cache contents were addressable as processor registers, which is what the patent covers. In fact, although I'm familiar with a number of processors and I am interested in processor design, I don't think it ever would have occured to me that this would be something useful or worthwhile. That means that I am satisfied, pending the arrival of some notification of "prior art", that the Transmeta guys have truly come up with something new.

  • I agree with you. However, I think it's not so much what the patent says as it is what the patent implies/means. If everyone is right about what this is all about, then I think Transmeta really *is* doing something cool. Otherwise, I think they need to go ahead and disclose what they are working on, just so we aren't hyping a non-product.

    Just my US$.02
  • Starbridge System's HAL was discussed on Slashdot some time ago [slashdot.org] and fairly nicely torn apart. There are certain applications where massive FPGA arrays are quite useful, but it is not nearly as generally applicable as the web page would suggest. In case you don't want to wade through the discussion, the gist is that interchip communication and compiler design are two limiting factors.
    --
  • How true! s/Transmeta/Microsoft/ and see what you get!
  • The MIT project you are thinking of is probably the RAW project [mit.edu]. The web site is a bit sparse - not much more than a list of all of the groups research papers. You can get a bit more info about the project in the latest Scientific American in the section about MIT's Oxygen project (hey the article is actually online too - go read it here [scientificamerican.com]. Note that it is aimed at the general public, so it's on the simplistic side).
  • ...do American patent laws differ that much from elsewhere?

    No, American patent laws aren't that radically different. It's just that somewhere along the way the patent office forgot it's supposed to be following them.

  • Unfortunately here in the US, the patent office has actually stated that they do not have the technical skills or resources to evaluate even a small percentage of patent applications. They just accept them, and let people deal with it in court.

    Sort of makes the concept of patents silly huh?

    Put enough techno-jargon in the application, and you probably could patent a biological waste disposal system (to paraphrase another comment) and sue everyone's ass. In fact not only could you, but that's what the patent office recommends you do.

    The real problem is that it costs an average of a million US dollars to fight a parent through the courts. The trick is, then, to patent something that lots of companies need, and make sure the license cost is under that amount for any individual company. You'll never get sued over it, because its not worth it to the companies, and AFAIK you can't file class-action patent challanges.

    Ah, land of the free, home of the brave.
  • I haven't looked at the patent myself, but it's probably more specific than that. Patents become invalid when there are examples of prior art, so most likely this one doesn't just describe L1 caches, but more specifically some cunning mechanism that can not be found in earlier implementations of L1 caches.

    That is, if this is really about L1 cache-like stuff. I haven't checked myself.

    Of course the title of the patent does not cover the content.

  • Re:Patents are not that easy to get. (Score:3)

    by WNight ( 23683 ) on Sunday July 25, 1999 @07:54AM (#1785594) Homepage
    Patents have a few drawbacks.

    1) You can get one on (it seems) nearly anything, simply by wording it so that it seems somewhat new to the examiner, and then use this patent, and the implied threat of lawsuit, to extort money from rival companies.

    2) Patents need to be (from what I remember) on something that wouldn't be deemed trivial to a compotent member of the profession. (ie, if processors all had six registers, adding one or two, while new, wouldn't be that great of a conceptual leap). But, due to the secret nature of patent proceedings, the idea is not presented to knowledgable members of the profession, so someone less skilled gets to judge what is worthy of a patent.


    Now, specifically about the Transmeta patent...

    I read the patent and it described a current caching system, but using registers, presumably instead of very fast static ram located on the cpu...

    Well, registers aren't very well defined, nor is their use, either in the patent, or in technical literature. In fact, pretty well anything that the CPU can access without an idle cycle can be refered to as a register. Does it matter if your CPU has 128 128b renamable GP registers, or if it has 2k of cache RAM that is addressable as registers with no more delay than an actual register, or in fact, just has 2k of cache ram with no more delay than a register? No, it doesn't. Either way, you're essentially getting 'free' reads of cached data.

    Especially since the Transmeta patent doesn't say that those registers will be program addressable. It's not like they said that the program will be able to look in then to determine what is cached (which would be handy), simply that they are stored as 'registers' instead of 'l1 cache' (Level-n cache being a 'flexible' term itself...)

    Considering that all cache ram works by having some area set asside to hold the data, and some set asside to hold the addresses that the data belongs at, and then some logic to make sure that any data changed gets updated in both ram and cache...

    The only thing they did was call this storage 'registers' instead of 'cache RAM'.

    That sure seems like an example of patenting the blatantly obvious. This sure inspires confidence in the usefulness of the patent system.
  • I don't know about the others here, but for me, what makes me itchy are software patents which are then broadly applied. In general I don't have problems with patents. I do have problems when someone tries to patent 'xor' cursors or the alpha channel or even their business methods.

    The problem is that the patent office appears to have taken the attitude "if we don't understand it, we'll grant the patent and let the lawyers sort it out." The cost to have the lawyers sort it out is more than I'll make in a lifetime of freelance programming...

  • The interest here isn't really about this particular patent. It is more just a piece in the puzzle of just what the f**k Linus is up to at Transmeta. For a guy that bears all in regard to the Linux kernel, Linus is very tightlipped about his work at Transmeta.

  • http://www.starbridgesystems.com/home/mainpage.htm

    The Starbridge Systems computer uses "VIVA", an operating system that reconfigures the CPU on the fly, supposedly allowing huge speed increases.
  • That better not be what they're patenting -- I designed a processor using that a year ago.

    It was a stack processor, every operation single-cycle. The ALU was hooked directly to the top two stack items, so the cycle was relatively fast (i.e. high MHz) because of the lack of need for instruction decoding and register muxing.

    Anyhow, the important part was that memory access had two parts: set address register, and read data register.

    Setting the address reg would start a memory read cycle, and while the cycle was going you could do other things. When you need the data, you would read the data register, and if the memory cycle wasn't finished the processor would stall.

    Net effect: 2-cycle memory access. I also had a fetch-data-and-increment-address mode, of course, which made memory access essentially one-cycle.

    My processor was the simplest and fastest in the class :).

    I like stack-based processors. A pity there are so few of them on the market now -- Novix and Chuck Moore's P21 are the only two I know of. (The P21 is pretty amazing, though).

    -Billy
  • You're right, it was filed in 1996. While it looks like they were definitely working on a microprocessor design in 1996, it has been over 3 years since then, so they may have shifted gears entirely. So while it looks likely that Transmeta is working on a cool CPU design, who knows, they may actually be working on a cool graphics chip design by now.

    -E
  • Quickly though, wasn't their prior patent (on /. a few months ago) about hardware translation of non-native instruction sets? Claim 7 states software translation?
    Anyway, I made it to claim 29 and now my head hurts! I'll read this again in the morning.


    _damnit_
  • Ok, could someone explain to me why it is "cool" when Transmeta gets a patent, but "uncool" when anyone else does?

    Software patents are generally uncool. This looks like a hardware patent though, that's different.
  • First of all, I never said anything was wrong with the concept of patents. Save your straw man arguments for someone who won't recognize them.

    The patent office bloody well does have the responsibility to decide what is obvious and where there is prior art, they just haven't done their job in a long while. Court is supposed to be the appeal process for when the patent office screws up.

    "In order to be worthwhile, a patent must be defended in court." You mean there should be a multi-million dollar lawsuit for every patent? Absurd! The problem here is volume, and the court system is far, far less efficient than even the worst bureaucratic approval system.

    There's no more incentive for anybody to pay the immense lawyer fees to have an invalid patent struck down (thereby freeing everybody to produce the patented device) than there would be for someone to pay for R&D for a product that would automatically go into the public domain.

    As for concrete examples of the shocking idiocy of a patent system run amok: a large prime number patented (equivalent to patenting pi), collected (not engineered) genes patented, a patent on the use of digitized video in games (not a specific mechanism, but the idea), a patent on the idea of XORing a pointer onto a display, et c.

    As for software patents (which we weren't talking about at all), they are rarely enforced and act mostly as a scare tactic against people with smaller legal staffs. The legal foundation of software patents is shakey at best, and copyright, not patent law, is what is used to protect software in real life.

    Not a single workable replacement indeed. Patents are utterly superfluous to software, where copyright law rules. I side with Knuth on this one, algorithms are math (math is typically given as an example of an unpatentable area).
  • Storing frequently utilized data in a L1 cache is not the same as
    using an execution unit resident data/address pair. This patent is
    describing a system where-by the execution unit will cache its own
    data in 'a first register of the execution unit.' Presumably, this
    implies a simple case of one unit of data for the purposes of
    describing the mechanism for the patent. A real processor would
    require a vast quantity of such register pairs.

    The second point under claim 7 is rather interesting. This point is
    repeated in claim 13;

    * software for translating instructions from a target instruction
    set to instructions of the host instruction set;

    The term 'code morphing' makes an appearance in claims 20 and 26;

    * code morphing software for translating programs written for a
    target processor having a second different instruction set into
    instructions of the first instruction set for execution by the
    host processor

    This point is rather confusing. To my reading it implies that the
    data/address register pair may also reference translated code
    sequences which may change, forcing a retranslation, i.e. self
    modifying code.

    * software implemented means responsive to an exception generated by
    the comparator for retranslating into a new code sequence without
    storing memory data in the first register which is frequently
    utilized by the host processor during a code sequence and
    executing the new code sequence.

    My (admittedly non-expert) reading of this document tells me that this
    is not simply a rehash of existing technology. I think the claim that
    this is a bogus patent is a simple knee-jerk reaction, probably the
    result of not having read it and/or not understanding it.

  • It isn't just cache (Score:4)

    by sjames ( 1099 ) on Sunday July 25, 1999 @09:12AM (#1785612) Homepage Journal

    Skimming the patent, a few things indicate that it's not just L1 cache.

    The part about triggering a software exception when an address that is not coherant between memory and cache is accessed is interesting. This fits very well with the idea that they are building a fast instruction set emulator system for a risc processor.

    Over all, it looks like the CPU runs in a virtual memory environment of it's own. That VM is provided by the MMU and a just in time translator in software. The translator may get feedback from the cache incoherance exception to re-order the risc code for the next execution.

    IF That is the case, then it is indeed new and the methods are non-obvious.

  • Ob: patent rant (Score:3)

    by sjames ( 1099 ) on Sunday July 25, 1999 @09:19AM (#1785613) Homepage Journal

    The holders of proper and valid patents should sue the USPTO in mass for devaluing the holding of a patent. At one time, holding many patents lended respect and credibility, now because USPTO will approve nearly anything, it is seen as meaningless or worse by the very people one would want to impress.

  • At one time, holding many patents lended respect and credibility, now because USPTO will approve nearly anything, it is seen as meaningless or worse by the very people one would want to impress.

    True,.. so true.

    For instance, someone who posted earlier mentioned the scene on the back of a mouse when one sees all the patents and patents pending on those things. You'd think that by now, a good deal of the basic qualities of a mouse are generic/already patented.
    Except for those new ergonomic devices that seem to become more and more healthy for your hands... (and I wonder about that sometimes..)

    by now, I'm thinking that patenting something isn't going to prevent someone else from creating the same, or close clone, "thing" as you have... because they can just modify your idea, develop theirs seperately and with a different name, ... etc.. and no one's the worse for it. It's actually nice, b/c then people/companies are developing similar technologies, which they must continue to improve to beat the competition, while making it cheaper so that people will buy it. Which is what's been happening throughout the history of economy anyway.
  • I don't mind the patents (and I'm consistent with my belief that patents help prevent people from stealing the hard-earned resources of small companies that come up with new ideas. If there were no patents, few would invest the resources to come up with new innovations). However, I'm still waiting for transmeta to actually ship a working product in sufficient quantities. If IBM is doing the manufacturing then they have a chance but I'm sure AMD will be the first to tell you how hard it is to compete with intel.

Slashdot Top Deals

It was kinda like stuffing the wrong card in a computer, when you're stickin' those artificial stimulants in your arm. -- Dion, noted computer scientist

Close