Slashdot Mirror

← Back to Stories (view on slashdot.org)

Intel Allows Release of Full 4004 Chip-Set Details

Posted by timothy on from the cool-move-from-the-valley dept.

mcpublic writes "When a small team of reverse engineers receives the blessing of a big corporate legal department, it is cause for celebration. For the 38th anniversary of Intel's groundbreaking 4004 microprocessor, the company is allowing us to release new details of their historic MCS-4 chip family announced on November 15, 1971. For the first time, the complete set of schematics and artwork for the 4001 ROM, 4002 RAM, 4003 I/O Expander, and 4004 Microprocessor is available to teachers, students, historians, and other non-commercial users. To their credit, the Intel Corporate Archives gave us access to the original 4004 schematics, along with the 4002, 4003, and 4004 mask proofs, but the rest of the schematics and the elusive 4001 masks were lost until just weeks ago when Lajos Kintli finished reverse-engineering the 4001 ROM from photomicrographs and improving the circuit-extraction software that helped him draw and verify the missing schematics. His interactive software can simulate an ensemble of 400x chips, and even lets you trace a wire or click on a transistor in the chip artwork window and see exactly where it is on the circuit diagram (and vice-versa)."

124 comments

  1. Wow! Imagine a Beowulf Cluster by wiredog · · Score: 0, Offtopic

    of Intel 4004s!

    --

    Best Slashdot Co
  2. Awesome! by Anonymous Coward · · Score: 1, Funny

    Maybe that means that computer architecture classes can finally start using real chips to study rather than made up chip designs?

    One of the things I hated most about my computer arch class was that we had to learn about a completely made up system design which didn't translate to ANYTHING in the real world. Oh yeah, and it was RISC. *Snoooreeee*

    1. Re:Awesome! by CityZen · · Score: 1

      I don't think you can get more RISC than the 4004's instruction set. Remember, it's a 4-bit CPU!

    2. Re:Awesome! by m85476585 · · Score: 2, Informative

      Real chips were made up at some point. Computer architecture classes should teach you the concepts, then when you go work for Intel you can find out all about the latest secret architectures, and you can apply what you learned in CA to making them better. Obviously you can't expect Intel to give out schematics for Core i7's or they would quickly go out of business.

    3. Re:Awesome! by ByOhTek · · Score: 1

      Likewise for me, something like "SAM". It was a nice simple case, but not terribly interesting.

      But maybe that's why they do the fake arch - because a real arch would be too complex? At least, that would explain undergraduate classes.

      --
      Self proclaimed typo king, and inventor of the bear destroying coffee table (patent not pending).
    4. Re:Awesome! by tehSpork · · Score: 2, Interesting

      Unfortunately the Intel 4004 is much less sophisticated than even the simplistic models I studied as an undergrad. Not to mention that real chips suffer from real compromises and real problems, something our academic fantasy-land models never had to deal with. The simple models allow the students to learn the important concepts (such as multi-cycle instructions, pipelining, caching) without having to worry about why it was implemented a certain way, the concepts are what counted.

      In my computer architecture classes we at least looked at the IA32 architecture but it was more of a space-filler and not a primary focus, our professor was heavily into MIPS.

    5. Re:Awesome! by CityZen · · Score: 3, Interesting

      I guess I'm wrong. They crammed 45 instructions into the architecture using instruction words of varying width.

    6. Re:Awesome! by Muad'Dave · · Score: 0, Offtopic

      See all the _hardware_ errata at Microchip.com.

      Pentium Floating Point error, anyone?

      There are many issues with CPUs - they are just so well-hidden and/or obscure that you never see them. With the advent of updatable microcode, you'll see fewer flaws that need permanent work-arounds.

      --
      Tiller's Rule: Never use a word in written form that you've only heard and never read. You will end up looking foolish.
    7. Re:Awesome! by seifried · · Score: 0, Offtopic

      Yeah, because there are a lot of microchip pirates with several billion dollars lying around to create a modern chip fab and copy cpu's willy-nilly, putting Intel out of business inside of a few weeks probably (heck, with the speed of modern chip pirates probably a few days!).

    8. Re:Awesome! by loose+electron · · Score: 4, Informative

      For the most part - Newer digital designs are language driven, not schematic driven. The advent of Verilog & VHDL lead to purely digital designs done up in code.

      Some of the special devices are done using transistor level design, but synchronous logic these days is a HDL (hardware description language) followed by gate level synthesis, and then autoplace and auto routing.

      A lot of fine tuning along the way for high performance items does get tweaked a lot but for the most part, digital chips are created as a coding exercise.

      --
      www.effectiveelectrons.com "chips that work" Analog, RF, Mixed Signal
    9. Re:Awesome! by nurb432 · · Score: 1

      IA32?

      Damn kids these days.. Back when i was your age we had 8 bits and appreciated it!

      All kidding aside, learning the Z80 inside and out ( and designing my own 8 bit machine later ) didn't hurt me one bit.

      --
      ---- Booth was a patriot ----
    10. Re:Awesome! by Anonymous Coward · · Score: 0

      All professors are heavily in to MIPS, and you, like me, and everyone else who's taken Introduction to Computer Architecture, know why.

    11. Re:Awesome! by m85476585 · · Score: 0

      Redhat makes most of their money off support and providing a complete system, IIRC. When's the last time you called Intel about your CPU, or install a patch for it?

      Intel is making tons of money off their chips, and they have little competition. There's AMD, but they are only barely keeping up. If the Core i7 schematics were released, any old fab company could start making their own i7's for next to nothing. There would be no R&D to pay for and almost no cost to them other than what actually goes into manufacturing a chip. Maybe they wouldn't use the latest 45 or 32nm process Intel is using, but at 65nm they would still likely function the same (assuming you could fit the die in the standard package), and they would be drop-in replacements for Intel's i7s. Sure they would use a bit more power, but for most people the significantly lower price would be worth it. Lower prices would give Intel less incentive to develop new architectures, and development would slow down.

      Sure, people take RHEL and use it for free (Cent OS), but big companies still go with RHEL for support. And Red Hat is arguably taking something that is already free (Linux) and charging for it, making money off almost nothing. Intel developed their architectures and they are making money off them, so they have absolutely no incentive to give them away for free.

      Proprietary stuff isn't always bad, and it's the "everything should be free" attitude that is keeping Linux from becoming more widespread, with many distros not including proprietary drivers or closed source software at all.

      The people that make this stuff have to be paid if you expect results. A loosely organized group of software or hardware developers can't match a big company that can afford to pay good developers. Furthermore, if no one is paying good developers, college students will have no reason to study to be one, and technology will stagnate.

    12. Re:Awesome! by realityimpaired · · Score: 2

      *repeats a mantra* I will not feed the trolls, I will not feed the trolls....

      Linux is Software. And Red Hat doesn't sell the software, they sell support contracts for the software. You can get RedHat's distribution for free through CentOS and are only paying for technical support and the nice pretty RedHat-specific graphics when you buy RHEL. Nobody is going to make money giving away modern chip designs for anybody else out there to manufacture, because there's no way for them to get an ROI on the development of said architecture. CPU's very rarely need tech. support, and aside from hardware design quirks (which coders simply code around), the only time you have a technical problem with a CPU is when the manufacture is defective and you need to replace the chip.

      The closest anybody in the chip design sector ever comes to what you're advocating is ARM, and they don't give anything away. They design and test, and then license the manufacturing out to 3rd parties. They also vigorously enforce their licensing contracts and copyrights, because people paying them royalties for the use of their designs is the only way that they can make money.

      Fuck. I will not feed the trolls again. I will not feed the trolls again....

    13. Re:Awesome! by realityimpaired · · Score: 1

      Yeah, because there are a lot of microchip pirates with several billion dollars lying around to create a modern chip fab and copy cpu's willy-nilly, putting Intel out of business inside of a few weeks probably (heck, with the speed of modern chip pirates probably a few days!).

      You're being facetious, but you're forgetting that the folks at AMD, NVidia, VIA, IBM, and ARM would all love to get a look at the inner workings and design specifications of the latest Core i7. There's only so much that looking at one under an electron microscope can tell you.... And aside from ARM, those companies all either already have the chip fab facilities, or have the billions of dollars needed to build a chip fab facility. (ARM probably has the money, or at least the credit, to build a chip fab as well, but they make their money licensing designs out to other chip fabs, rather than actually building chips themselves.)

      There's also hundreds of chip fabs around the world that are operated by companies like Samsung, Nokia, Texas Instruments, Sony, NEC, etc., which are currently building ARM-designed chips.

    14. Re:Awesome! by tepples · · Score: 1

      All professors are heavily in to MIPS, and you, like me, and everyone else who's taken Introduction to Computer Architecture, know why.

      I had a feeling about it (see all the 16-bit "KIPS" chips designed by college students after having read through Computer Organization and Design). But I wasn't completely sure that MIPS was the ideal teaching model until it was proven pretty much patent-free by Plasma and Loongson.

    15. Re:Awesome! by dissy · · Score: 5, Interesting

      One of the things I hated most about my computer arch class was that we had to learn about a completely made up system design which didn't translate to ANYTHING in the real world. Oh yeah, and it was RISC. *Snoooreeee*

      That's only because you dropped out before getting to the FPGA classes!

      Any functional CPU design (technically non-functional ones too, for whatever good that would do) can be flashed into an FPGA and become as real as any other silicon chip.

      And identical to psudocode, psudo-chipfab can be translated into any real code/fab language by anyone that knows basic design and the target language. You were supposed to be learning the basic design part, so once you got to using a real language used in the real world, you would have some clue what to do with it.

    16. Re:Awesome! by sexconker · · Score: 1

      4195835 * 3145727 / 3145727 = 4195579 ?

    17. Re:Awesome! by dissy · · Score: 1

      Apparently you couldn't release the internal workings of a system (Linux) and have someone make money from it (Redhat). I agree with you, that would be absurd.

      I noticed out of four targets to apply to, not a single one was Intel.

      What works for one company probably won't work for many others, and one could easily say it will Never work with All others.

    18. Re:Awesome! by dpilot · · Score: 4, Informative

      > If the Core i7 schematics were released, any old fab company could start making their own i7's for next to nothing.

      Wrong.

      Let's even imagine for the moment that you really meant that they'd release the verilog/vhdl, instead of schematics. There are still a few minor problems in the way:

      1 - Intel really does have absolutely top-notch processing capability. Typically their top-end CPU pushes their top-end process for all it's worth, both in performance and capacity. (I'll add the caveat that "all it's worth" is a moving bar, which is why speed bumps and die shrinks come along as a process and design mature.) Chances are most fabs in the world simply won't be able to handle the Core i7 - not enough transistors.

      2 - Let's pretend that you have a fab that can put out bigger-than-postage-stamp sized chips, and they can handle the sheer number of transistors. Most likely you still can't hand over such HDL, push a button, and have a layout come out, even bigger and slower. For one thing, a significant fraction of those transistors are in cache - probably SRAM. HDL doesn't build SRAM, it instantiates it. You need either a compiler or an SRAM design team(s) to get the cache(s) built, and they have to be specifically matched to the interface the HDL is expecting - these aren't garden-variety commodity SRAMs, by any means.

      3 - So let's pretend we have SRAMs too, and that the design we had in our back pocket could be tweaked to meet the interface requirements of the Core i7. We have datapath/dataflow problems. In the first place, those datapaths are highly regular - kind of like bit-slices. A lot like bit slices, in fact. Most likely the design was carefully partitioned into functional blocks, and those functional blocks were further partitioned, etc. Then they were floorplanned with an eye to the final design. Far from the smallest concern was getting all of those bits from point-A to point-B to point-C. These things have some pretty big buses inside, and just about everything is high-performance.

      In short, a schematic, even verilog/vhdl is a far cry from the whole picture. Even in today's push-button world, you don't push-button a thing like the Core i7, or even latest-generation AMD CPUs, to be fair. You need to have a talented, experienced physical design team, and there's as much work there, maybe more, than simply coming up with the logical design. Then again, frequently the logical and physical design may not be that separated - a really tight feedback loop between the two can work well.

      So go back to your super-sized non-optimized chip done with push-button tools - oh and by the way, you may have a hard time finding such tools with enough capacity. The resulting chip won't be a little bigger and a little slower - it'll be a LOT bigger and a LOT slower.

      Does anyone know what the technology was for the 4004? (Is that metal-gate, with double-metal, or polysilicon gate with single-poly, single-metal?)

      --
      The living have better things to do than to continue hating the dead.
    19. Re:Awesome! by Anonymous Coward · · Score: 0

      Intel would sue them into the stone age.

    20. Re:Awesome! by camperdave · · Score: 1

      Did it hurt you eight bits? :-)

      Kidding aside, I was a 6502 guy back in the day. There was a book called "How to build a microcomputer and really understand it" (or something along those lines) that took you through what all the control lines did and how the interrupts worked, etc. That, and the reading through the OS listing for the Atari 400/800 really gave me a firm grasp on how it all fits together.

      I'd really like to get a copy of that book again (loaned it out, never got it back). It had printed circuit layouts, the kind you photocopy onto a circuit board then etch. The book also described these cards that had a handful of diodes and resistors on them. Each card was a hard coded nybble of information. You would plug these cards into one of several edge card slots on the circuit board and program the machine that way.

      --
      When our name is on the back of your car, we're behind you all the way!
    21. Re:Awesome! by Nefarious+Wheel · · Score: 2, Interesting
      Real programmers use wave diagrams - far more subtle than butterflies.

      I have an original hardcopy Intel 4004 User's Guide I nabbed from the 1970 Wescon exhibition. Reading through that - butterflies. Yes, the quantum weather software butterfly would have been an easier IDE.

      --
      Do not mock my vision of impractical footwear
    22. Re:Awesome! by MartinSchou · · Score: 1

      Very true

      One of the extra courses I could take was making our 32 bit MIPS design run on FPGAs. In that class the teachers would give us pre-designed modules for memory controller, IO (keyboard) and video to boot a very simple OS on them.

      Didn't take that course though.

    23. Re:Awesome! by hairyfeet · · Score: 1

      While I wouldn't expect them to give out Core, or hell even the "smoking hot" Netburst P4 (damn that thing was a space heater!) but why not the old x86 designs? I mean is there anybody out there that has a real use for a 286 or 386 except for history class? It would be nice to check out those old designs and I doubt they'd be giving away any trade secrets on Core with chips that old.

      In fact it would be cool, at least IMHO if we could see Intel 386 VS AMD VS Cyrix VS WinChip, just to see how each company went about designing their chips. Maybe somebody should write AMD and see if they have those old plans in the basement somewhere?

      --
      ACs don't waste your time replying, your posts are never seen by me.
    24. Re:Awesome! by bhtooefr · · Score: 1

      Sun's opened the UltraSPARC T1 and T2, although nobody's spun an ASIC from that.

      Alternately, Gaisler Research has the LEON, which is dual-licensed under the GPL and a closed license. Want to use it non-commercially, it's GPL for that, want to use it commercially without giving up the source, you have to pay. And, there's a few SoCs here and there based on it.

    25. Re:Awesome! by Anonymous Coward · · Score: 0

      You're an idiot.

      Please don't post here anymore.

    26. Re:Awesome! by sunspot55 · · Score: 2, Interesting

      Does anyone know what the technology was for the 4004? (Is that metal-gate, with double-metal, or polysilicon gate with single-poly, single-metal?)

      Well, I do look at photomask stacks as part of my job from time to time as a process integration engineer (mask bugs do make it past design rule checking and tapeout sometimes) but I will start with a disclaimer that this chip and process was designed before I was alive.

      It looks from the composite drawing that this is a single poly/single metal/self aligned doped poly/source/drain. That should have existed at the time and to my knowledge no metal gate process has been in wide use because of manufacturability and performance problems. It looks like the red is poly (gates and lines), blue metal, and the green is the source/drain/poly doping diffusion. Whether that was done with implantation or glass doping I'm not sure (again before my time, implant was coming into use but glass doping was much cheaper, if not as controllable). It is kind of nice to see such a simple design.

    27. Re:Awesome! by TheKidWho · · Score: 1

      Can't touch the China i7 though...

    28. Re:Awesome! by dpilot · · Score: 1

      It looked like that to me, too. But then I remembered that I working with a metal gate technology later in the 70's, so I wasn't sure. I agree with the red being gate, blue metal, and green diffusion. I didn't take a lot of time looking at the contacts - now that I think a bit more, the metal-gate technology I was working with in the 70's of course had a gate mask, and I saw no such relief on those images. Doh!

      --
      The living have better things to do than to continue hating the dead.
    29. Re:Awesome! by m85476585 · · Score: 1

      I though AMD was starting to outsource it's fab work to save money. Link

      That means whoever they are outsourcing to probably has 45nm (newest Phenoms) and certainly 65nm capability. Maybe no one with a 45nm process would clone an Intel chip (if all the 45nm fabs are in countries where there would be a risk of lawsuit, for example), but someone with a 65nm process could clone a slightly older Core2Quad, which are still fairly competitive with the i7's.

    30. Re:Awesome! by m85476585 · · Score: 1

      Of course--A graphical schematic with 600 million transistors would be useless.

      Intel probably has a custom HDL compiler/synthesizer, which they use to create the actual gates (or a description of gates they send to be manufactured, to be precise). If someone wanted to make an exact copy of an Intel chip, they would need the output, so a listing of gates and wires and their positions, not the code that went into Intel's compiler/synthesizer (unless they had access to that too). Otherwise there's no way a generic compiler/synthesizer could match the optimizations Intel's does, not to mention any hand tweaking.

    31. Re:Awesome! by Skeptic+Al · · Score: 1

      That is way oversimplifying what is needed to make a competitive chip. If it was that easy, there would be a lot of people doing it, giving Intel a lot more competition than they have. And it wouldn't take ~2-3 years per generation.

      In order to get high performance (== high frequency, and == reasonable die size), you cannot rely completely on automated tools.

    32. Re:Awesome! by Alioth · · Score: 1

      Learning about designing your own CPU from scratch? Snore?

      I think you may be on the wrong course.

      --
      Oolite: Elite-like game. For Mac, Linux and Windows
    33. Re:Awesome! by dpilot · · Score: 1

      Thought about it again. You're right - single-poly self-aligned gate. Of course there would be no gate level visible in relief, because this was a mask shot, not a photo, and there was no visible gate mask level. I actually RTFA just a little, and there are bootstrap loads in there. Layout for bootstrap loads is a dead giveaway for the difference between self-aligned silicon-gate and metal-gate with a gate mask. Just bootstrap loads, though. No Mostek bootstrap drivers, but I'm not sure when those came in.

      --
      The living have better things to do than to continue hating the dead.
    34. Re:Awesome! by commodore64_love · · Score: 1

      IMHO the 400x designs should have fallen into public domain long ago. i.e. The government-granted monopoly on that design revoked after 28 years time (per the original 1790 copyright act).

      --
      "I disapprove of what you say, but I will defend to the death your right to say it." - historian Evelyn Beatrice Hall
    35. Re:Awesome! by TheRaven64 · · Score: 1

      I though AMD was starting to outsource it's fab work to save money

      Not exactly. AMD spun off its fab company (as The Foundry Company) to make it easier for AMD to use multiple companies for production and for The Foundry Company to get business from multiple chip designers. This means that when the fab part of AMD is having problems getting enough capacity on their latest process they can now use their excess capacity on the older process to produce chips for other people and AMD can get other companies to fab their chips.

      --
      I am TheRaven on Soylent News
    36. Re:Awesome! by Hal_Porter · · Score: 1

      So go back to your super-sized non-optimized chip done with push-button tools - oh and by the way, you may have a hard time finding such tools with enough capacity. The resulting chip won't be a little bigger and a little slower - it'll be a LOT bigger and a LOT slower.

      I'm not sure that's true. I read that most of the logic on an Intel chip is synthesized, only a small amount is done by hand. In a way it's a bit like applications - most code is written in a high level language and compiled an the most critical one percent or less is done in assembly. Actually my guess is that now the world is moving from x86 to x64, computers are fast and compilers are so smart that's not true for most mainstream applications and the whole thing is written in a high level language just because no one sees the need to translate a load of hairy x86 assembler into x64.

      Now there are lots of foundries turning out unlicensed x86 cores that won't be imported to the US. And Via is turning out licensed x86 cores that will be sold in the US. AMD is quite a bit behind Intel in high end performance.

      My guess is that Intel are not keen on the designers of these getting their hands on the HDL source code of an i7. It seems if you were a non Intel designer and had access to the code it might well lead to an "Aha" moment, just like a programmer might have one if he or she had access to the source code of a best selling application.

      You say layout needs skills, but what's to stop someone outside the US taking the VHDL, tuning it to a common process and selling it as hard macro to the company that owns the factory?

      --
      echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
    37. Re:Awesome! by dpilot · · Score: 1

      I wasn't so much talking about the detail gate layout as I was the high-level floorplanning. Certainly the design has logical partitioning, but there are occasions where a concise logical partitioning divides things one way, but good physical partitioning wants to be different. A good simplified example would be the classical bitslice. Logically you'd like to have an ALU, a shifter, a register file, and a mux. Physically it works out better to partition into bitslices, each with a 1 (or few) bit adder, a piece of shifter, register file, etc. (Obviously the (partial?) lookahead carry has to bolted in there somewhere, etc)

      There are synthesizable cores sold - Phoronix just had an article about AMD coming out with a new one to compete with Atom. ARM has a whole business model based on them. I don't know whether they're blind pushbutton, or whether they come along with hints on how to guide place and route for best power/performance. Now that I think of it, I know a few people a few floors up that I can ask. I'm in a different part of the business, but not ignorant of that side.

      I'm not saying that HDL source wouldn't be valuable, nor that someone couldn't use it to clone the Core i7. I was saying that you couldn't do a dirt-cheap knockoff using the HDL and practically no engineering, which was what the grandparent post sort-of implied. (Practically no engineering being part of what's needed to make the knockoff dirt-cheap.) Then we didn't even get into characterization and validation.

      --
      The living have better things to do than to continue hating the dead.
    38. Re:Awesome! by Hal_Porter · · Score: 1

      There are synthesizable cores sold - Phoronix just had an article about AMD coming out with a new one to compete with Atom. ARM has a whole business model based on them. I don't know whether they're blind pushbutton, or whether they come along with hints on how to guide place and route for best power/performance. Now that I think of it, I know a few people a few floors up that I can ask. I'm in a different part of the business, but not ignorant of that side.

      Actually most ARM cores are hard macros - i.e. ARM port the CPU to a specific process e.g. the latest TSMC one. Of course you can buy synthesizable cores too - then you get the HDL and it's up to you to do the layout. Those are more expensive. Finally, and most expensive of all you can license the patents on the architecture and make your own chips.

      Qualcomm have an architecture license and built their own ARM from scratch (with help from ARM), I think TI did the synthesis themselves and tweaked the layout. Most ARM licensees from what I've been told use a hard macro. There's a big difference in engineering work between each stage.

      http://www.insidedsp.com/tabid/64/articleType/ArticleView/articleId/238/Qualcomm-Reveals-Details-on-Scorpion-Core.aspx

      Still consider. If the ARM VHDL was released then there are probably hundreds of companies globally that could do what TI did, i.e. synthesize it themselves and tweak the layout. They could then all sell hard cores to lesser companies competing with ARM.

      Even worse there are probably dozens of companies that go the Qualcomm route and do full custom ARMs that outperformed the ones ARM sell. They'd each have their own fork of the architecture.

      Now maybe in the US this would be impossible because of patents, but you could probably get away with it in China, Thailand and quite a few other places where patents are not enforced. Basically it would be very bad for ARM - they'd be confined to countries where patents protected them. Grey imports from the outside would gradually kill them there too. They can't compete with people who have the technology for free and didn't need to pay for the R&D.

      I can see Intel are different because they have the best fabs in the world, but not everyone needs a chip made on those.

      Incidentally the patents on x86 should start to run out soon. My guess is that it will gradually transform into an architecture pretty much anyone can build. AMD will license the x64 extensions to anyone that wants them apparently - they've already done it to Via and Transmeta (Intel has access to AMD patents royalty free).

      Of course that makes x64 a very smart move for AMD in the long run.

      --
      echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
    39. Re:Awesome! by dpilot · · Score: 1

      Back to the "cheap Core i7 clone from the HDL" though, I suspect Core i7 is, or at least was, a stretch for even Intel's fabs. There probably are other fabs in the world that could build it, but not that many. ARM is a much easier target - that's part of its strength. The new small core from AMD will be quite interesting, in that respect.

      --
      The living have better things to do than to continue hating the dead.
    40. Re:Awesome! by mattack2 · · Score: 1

      I mean is there anybody out there that has a real use for a 286 or 386 except for history class?

      Aren't many microcontrollers based on older CPUs than that? e.g. 8 bit microcontrollers.

    41. Re:Awesome! by hairyfeet · · Score: 1

      Actually I think most of those you'll find are built on the classic Zilog Z80 arch. They are extremely low power, used in everything from classic PCs to MIDI designs so the chips are well known, and can be made royalty free with a license from Zilog.

      So if you are looking at the embedded space I'm betting the good old Z80 is what you would find the most. From talking to engineering buds who have worked with it they say it is a sweetheart to program for and use. The only thing i remember the old 286/386 designs used for was older military apps where radiation hardening was required. But even with those knowing how the chips work wouldn't give anyone an advantage with the way those devices are locked down. After all, it isn't like the F16 has an Internet connection.

      --
      ACs don't waste your time replying, your posts are never seen by me.
    42. Re:Awesome! by Hal_Porter · · Score: 1

      Back to the "cheap Core i7 clone from the HDL" though, I suspect Core i7 is, or at least was, a stretch for even Intel's fabs. There probably are other fabs in the world that could build it, but not that many.

      Well but you wouldn't clone an i7 - you'd take some of the clever features and reimplement them in your core. Or just build one i7 core rather than four on a chip. I'd much rather one i7 class core than an Atom in a netbook for example.

      --
      echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
    43. Re:Awesome! by dpilot · · Score: 1

      > Well but you wouldn't clone an i7 - you'd take some of the clever features and reimplement them in your
      > core. Or just build one i7 core rather than four on a chip. I'd much rather one i7 class core than an
      > Atom in a netbook for example.

      Sure you can. But all of those things involve engineering, and teams of engineers. That puts you out of the "cheap knock-off" league that was back at the start of this whole subthread. I'm merely contending that there is no such possible thing as a "cheap Core i7 knock-off" even given the HDL. Anything you could possibly do using that HDL is going to require significant engineering effort, falling out of the "cheap" bucket.

      --
      The living have better things to do than to continue hating the dead.
    44. Re:Awesome! by Hal_Porter · · Score: 1

      > Well but you wouldn't clone an i7 - you'd take some of the clever features and reimplement them in your
      > core. Or just build one i7 core rather than four on a chip. I'd much rather one i7 class core than an
      > Atom in a netbook for example.

      Sure you can. But all of those things involve engineering, and teams of engineers. That puts you out of the "cheap knock-off" league that was back at the start of this whole subthread. I'm merely contending that there is no such possible thing as a "cheap Core i7 knock-off" even given the HDL. Anything you could possibly do using that HDL is going to require significant engineering effort, falling out of the "cheap" bucket.

      You've clearly never been to China. I've been to companies there that employ thousands of engineers and are still firmly in the cheap knock off league. Any of these would be quite capable of taking the VHDL code for an i7 and turning it into a whole range of chips. So long as they sell them in China, they don't care about patents, licenses or copyrights.

      --
      echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
    45. Re:Awesome! by dpilot · · Score: 1

      Never been, probably never will. I'm dealing with co-workers in China right now, but the company is pretty darned stingy with the travel. I've done this particular function 2 or 3 times before without traveling, so I'll manage it this time, too.

      I have a friend who had an anecdote about this that he picked up from a friend years back, when an audio company was moving production to China. His friend "escaped" his handlers and went over to the other end of the building where his products were being produced. There was a knockoff factory producing his product, with a local label, for local consumption - in the very same building. Quality control was sorely missing, which has been in anecdotes galore over the past few years. But that can come, given the will.

      As for "thousands of engineers", I had heard once that in India the employable population of educated engineers was fully employed, and the problem was the massive "backlog" of uneducated masses not ready for skilled employment. This was reinforced when I heard that my employer, while doing no expansion in the US and giving raises between 0% and COLA, was giving double-digit raises in India, for retention. I guess I thought China would be in the same boat. I did hear once that China could absorb every single job in the US, and still have an unemployment problem.

      --
      The living have better things to do than to continue hating the dead.
    46. Re:Awesome! by Hal_Porter · · Score: 1

      Actually the most common model is that people design in Taiwan and manufacture in China. For chips most of the manufacturing is done in Taiwan because good fabs are not allowed to be built in China.

      In fact I'm pretty much convinced there are unlicensed chips being made in Taiwan for the Chinese market. Some products are for export - they have multilingual software and manuals, are FCC approved and have legal licensed chips, but I suspect there are also "Taiwan/China" only designs which are only in Chinese, not approved and probably not licensed.

      This is the reason that companies are unwilling to release source code of course - once you release it it is effectively in the public domain.

      Quality control was sorely missing, which has been in anecdotes galore over the past few years.

      Ha! You're not kidding. Even huge Taiwanese and US companies seem to be perpetually on the edge of a massive crisis which will doom the product, all because the factory can't produce things that work. My guess is the "Taiwan/China" only ones are even worse.

      --
      echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
    47. Re:Awesome! by dpilot · · Score: 1

      What's the environmental situation in Taiwan wrt semiconductor fabs and the electronics industry in general? I know we've had some legacy problems here in the US, and mainland China is probably a nightmare, and I'll guess that Taiwan's not far behind. I have a friend who goes to Taiwan fairly regularly, but never thought to ask him about this.

      --
      The living have better things to do than to continue hating the dead.
    48. Re:Awesome! by Hal_Porter · · Score: 1

      I'm not really sure.

      When Taiwan democratised in 1990 there was a lot of emphasis on environmental issues. Taipei has rather poor air quality compared to Europe or even Japan, though it is much better than Shanghai. From what I've heard Taiwan used to be much more polluted than it is.

      I've been to Hsinchu only a couple of times and it didn't seem smoggy. Of course pollution from semiconductor plants mostly affects groundwater and I have no quick way to check that. My tonsils are quite good smog detectors though.

      To be honest I don't think Taiwan was ever as bad as Mainland China. Chinese speaking societies naturally have laws and bureaucrats to enforce them. Basically the limit is the amount of corruption in society. Singapore, Taiwan and Hong Kong have always had lower levels of corruption than China, though from what I've read Taiwan is quite a bit worse than Singapore.

      Corruption undermines the rule of law because corrupt bureaucrats can be bribed to ignore violations of the rules. This is very bad for environmental regulations. The worst case is you have a kleptocratic society where bureaucrats spend all their time soliciting bribes and only enforce the rules on their enemies. This is pretty much what happened in China.

      My guess is that in Taiwan's dictatorial period there probably was a lot of corruption, poor rule of law and pollution. Afterwards people voted for an environmentalist party and the laws and the rule of law were tightened up. So a clean up is in progress but is not yet complete.

      --
      echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
  3. So in 2047... by CityZen · · Score: 4, Funny

    When we get the Core i7 details, will it seem as quaint as the 4004 does now?

    1. Re:So in 2047... by V!NCENT · · Score: 3, Interesting

      At that point in time retired Intel employees would say: "It was all binary... You know ones and zero's on solicon *audience laughs*, which was a bunch of sand basically. Heh... And at that time we were bumping against the limits of this technology so we decided to bake a multitude of them on a single die. Haha... dear God... can you imagine? *audience laughs* Programming this was, well you can imagine, not so pretty. Taking advantage of this technology was still very hard at that time, but OpenCL largely made up for it, so... Any questions?"
      -"I worked for a RAM company at that time. And I realised that while the CPU was in fact doing everything in parallel, the RAM was actually serialy read out. What was your stand on this?"
      Ühm... *audience laughs* That question is for [person sitting next to the speaker]. *audience laughs harder*

      I think that the Core i7 is a little bit too complex to understand right away. I mean with the 4004 everything was realy, realy basic. It had a design team consisting of four people. Nowadays it takes a whole team to improve it all. So I guess the awnser is no.

      --
      Here be signatures
    2. Re:So in 2047... by Elder+Entropist · · Score: 4, Funny

      I mean with the 4004 everything was realy, realy basic. It had a design team consisting of four people. Nowadays it takes a whole team to improve it all.

      Yes, one person for each bit. Nowadays you need 64 or 128 person teams.

    3. Re:So in 2047... by MobyDisk · · Score: 2, Interesting

      No. (I know the question was rhetorical, but I can't resist answering).

      The 4004 had 2,300 transistors. A college student can create and debug a processor more powerful than that in a semester. It is possible to memorize the entire thing. A Core i7 has around 300 million transistors. Unless human intelligence changes significantly, one human could not memorize and understand 300 million transistors.

    4. Re:So in 2047... by Anonymous Coward · · Score: 1, Insightful

      Suicide: commit it.

    5. Re:So in 2047... by CityZen · · Score: 1

      > Unless human intelligence changes significantly...

      Ah, so now we get to the meat of the matter!

    6. Re:So in 2047... by nschubach · · Score: 1

      How are you supposed to find out if the chip is working right if you don't have enough people to stand or sit based on their current instruction?

      --
      Every time I start to have faith in humanity, I ruin it by driving to work between 7 and 8 am.
    7. Re:So in 2047... by Elder+Entropist · · Score: 1

      That's why Intel's HR department has such a high turnover rate. Scheduling vacation time is a massive headache, let alone the unexpected family emergencies. They've tried to automate it, but there's a lot sitting in the inbox to process at any time.

    8. Re:So in 2047... by Anonymous Coward · · Score: 1, Funny

      And quantum computers require one person per qubit.

      The only problem is they're both working on it and not working on it at the same time ... if you know what I mean.

    9. Re:So in 2047... by frozenray · · Score: 1

      > The only problem is they're both working on it and not working on it at the same time

      I imagine this poses one hell of a problem for middle management when it comes to year-end reviews. I don't know, do they put their developers into boxes containing poison gas flasks linked to geiger counters in order to determine who's slacking off and who's actually working?

      --
      "There are already a million monkeys on a million typewriters, and Usenet is NOTHING like Shakespeare." - Blair Houghton
    10. Re:So in 2047... by Alioth · · Score: 1

      Although a great deal of those transistors will be the same thing over and over again - the cache.

      --
      Oolite: Elite-like game. For Mac, Linux and Windows
  4. A great presentation of it all on YouTube by V!NCENT · · Score: 4, Informative

    Link: http://www.youtube.com/watch?v=j00AULJLCNo

    --
    Here be signatures
  5. Italian business by VincenzoRomano · · Score: 4, Interesting

    It'd be nice to remember that the Italian Business was a good thing in this case at least!

    --
    Maybe Computers will never be as intelligent as Humans.
    For sure they won't ever become so stupid. [VR-1988]
    1. Re:Italian business by Anonymous Coward · · Score: 0

      great man..

      but that last name? ouch.

  6. If one was produced with a 40nm process... by ByOhTek · · Score: 1

    I wonder what clockspeed it would get. I know it's completely useless/pointless, but I'd be interested to see anyway.

    --
    Self proclaimed typo king, and inventor of the bear destroying coffee table (patent not pending).
    1. Re:If one was produced with a 40nm process... by hydromike2 · · Score: 3, Interesting

      better question, how would they physically handle a processor that small, 4004 has 2300 transistors, http://en.wikipedia.org/wiki/Intel_4004 , and the i7 has 731 million transistors at 45nm at 263 mm^2, http://www.legitreviews.com/article/824/1/ , So by those numbers the 4004 on a 45 nm process would have an area of .00082749 mm^2 or 1/317826th the physical size of an i7 die. Disclaimer: this is a very rough calculation, but in any case it is more than 5 orders of magnitude smaller than an i7. On the other hand you could have the king of multicore processors....

    2. Re:If one was produced with a 40nm process... by realityimpaired · · Score: 2, Informative

      Probably the same 740kHz that the original 4004 had.

      The manufacturing process used has nothing to do with the maximum clock speed a chip can achieve. It's about energy bleeding (heat loss) and the transistor density. If you manufacture a 4004 using 1950's-era technology, with actual honest-to-goodness 1mm-thick copper wire and large physical transistor switches, it'd be a *lot* bigger, but it'd achieve the same 740kHz that the design allows for.

      The reason using a smaller manufacturing process translates into a higher clock speed is that the smaller manufacturing process means that each logic gate takes up a smaller amount of space on the die. This means that you can cram more transistors in to the same area of silicon, allowing you to complete more operations per clock cycle. This way, using a 40nm process instead of the original manufacturing process means that you can build a 4004 that takes up a ridiculously small amount of physical space, not that you can magically build one that's faster than the original design. :)

    3. Re:If one was produced with a 40nm process... by MadnessASAP · · Score: 1

      I thought Intel was already doing something like this? It was going to somewhat similar to a Cell processor except with something like 128 Pentium 1 cores on it.

      --
      I may agree with what you say, but I will defend to the death your right to face the consequences of saying it.
    4. Re:If one was produced with a 40nm process... by Anonymous Coward · · Score: 0

      Er, doesn't the speed of light/propagation speed of electrons through a substance mean anything to you? Building smaller transistors means there is less time spent waiting for a signal to cross the circuitry and you can run faster/tighter timing. The propagation speed through discrete components gets limited in clock speed by the length of wires pretty quickly. I didn't even graduate with a CS/EE and I know this stuff...

    5. Re:If one was produced with a 40nm process... by Hatta · · Score: 1

      For that matter, what if you made a CPU with a hundred million of these?

      --
      Give me Classic Slashdot or give me death!
    6. Re:If one was produced with a 40nm process... by mako1138 · · Score: 4, Insightful

      This means that you can cram more transistors in to the same area of silicon, allowing you to complete more operations per clock cycle.

      This is true, but smaller process nodes also produce faster transistors. When you make things on the chip smaller, you have the practical effect of reducing parasitic capacitance in transistors and interconnect. Lower capacitance means a smaller RC time constant (using a first-order model), so logic will work faster. Intel's 45nm process can create an inverter with a delay of less than 5 ps.

      Your statements imply that transistors have a fixed speed, and that the only way to improve performance is parallelism. This is false.

    7. Re:If one was produced with a 40nm process... by Anonymous Coward · · Score: 0

      No, that is an oversimplification.

      It is true that the circuit design of a 4004 would limit the device to 740kHz, but the signal quality should be far above that of the 1970s technology it was originally designed for.

      The size of a transistor is directly related to how long it takes for a carrier (electron or "hole") to transition across the MOSFET from the Drain to Source (or Source to Drain for the "holes"). The smaller the transistor, the faster this occurs. Smaller transistors also hold fewer total charges and therefore need less current flow to change the voltage, so the time to transition between a low voltage to a high or a high to low (0 to 1 or 1 to 0) is now shorter.

      The actual quality of the square waves to represent a 0 or 1 can be pretty abysmal looking to human eyes and still function, so circuit designers would push the operating frequency of their circuit up to take advantage of the improved switching speed of the MOSFET structures that make up their logic gates.

      A straight-from-layout 4004 would probably not operate above 740kHz, because that is the frequency of it's designed oscillator (usually an external crystal of a chosen size placed in a special circuit), but put a higher frequency crystal in, or even use a MOSFET-based oscillator (which, using multiple MOSFETs configured as a self-feeding NOT gate, would be slower than the maximum any one MOSFET could handle) would make the 4004 far, far faster.

    8. Re:If one was produced with a 40nm process... by Anonymous Coward · · Score: 0

      On a chip that's one centimeter across, with an relative permittivity of 4.5 (SiO2), the speed of light isn't a concern.

    9. Re:If one was produced with a 40nm process... by mako1138 · · Score: 1

      This would be an interesting homework problem for a digital design class. First, find the single-cycle instruction that will take the longest amount of time. Then, figure out the critical path. Find the logic delay given a particular modern standard cell library.

    10. Re:If one was produced with a 40nm process... by Dadoo · · Score: 1

      smaller process nodes also produce faster transistors

      I was thinking the same thing. In fact, I'd be inclined to believe that, since the resulting chip would be so small, you could actually get it up to a higher clock speed than a current CPU. However, you wouldn't be able to interface it with anything, because you'd never get I/O signals at that frequency off-chip, without ruining them. You'd need to have at least some memory and some type of I/O controller on the same chip, to make it work.

      --
      Sit, Ubuntu, sit. Good dog.
    11. Re:If one was produced with a 40nm process... by Skeptic+Al · · Score: 1

      And yet, you can't propagate a signal all the way across the chip in one clock cycle.

    12. Re:If one was produced with a 40nm process... by Anonymous Coward · · Score: 0

      Now that it's public, is 4004 going to be the first cubic microprocessor, laid out in 3 dimensions rather than on a flat silicon surface?

      Some researcher somewhere might be tuning his nano assembler for it right now..

    13. Re:If one was produced with a 40nm process... by Anonymous Coward · · Score: 0

      As a materials scientist, let me answer that!

      It would be faster! The smaller distances in the 40nm transistors means that the electrons running across the transistor can send their messages faster, so you can turn them on and off faster (i.e. faster clock speeds) Also it helps having shorter transistors because it decreases the probability for an electron to recombine with a hole and thus signal is lost. Smaller is really much much better in most all regards.

  7. Re: Intel Allows Release of Full 4004 Chip-Set Det by Anonymous Coward · · Score: 1, Funny

    Imagine a beowulf cluster of 4004 emulators...

  8. uh by Anonymous Coward · · Score: 0

    Lajos Kintli finished reverse-engineering the 4001 ROM from photomicrographs

    1. Who is paying for this?

    2. http://xenia.media.mit.edu/~mcnerney/2009-4004/4001-composite-photo.jpg looks nice but tells me little about individual components. What's actually being used as source material?

  9. Diaper lovers by Anonymous Coward · · Score: 0

    Very gross...

  10. So, will it... by filesiteguy · · Score: 3, Funny

    ...run Linux?

    j/k

    This should actually be quite cool. I can see garage-based tinkerers messing with this chip, the registry and even coming up with a retro User Group.

    --
    The Kai's Semi-Updated Website Thingy
    1. Re:So, will it... by maxwell+demon · · Score: 2, Funny

      Can you compile a Linux kernel into 2048 bytes?

      --
      The Tao of math: The numbers you can count are not the real numbers.
    2. Re:So, will it... by mcgrew · · Score: 1

      Yes. Linux will run on anything from a supercomputer to a wristwatch.

      --
      Free Martian Whores!
    3. Re:So, will it... by Anonymous Coward · · Score: 0

      What about a supercomputer on a wristwatch?

    4. Re:So, will it... by Hatta · · Score: 1

      Linux requires at least a 386, always has. I'm not sure there's a UNIX that will run on any 8-bit or earlier processor.

      --
      Give me Classic Slashdot or give me death!
    5. Re:So, will it... by CityZen · · Score: 1

      Linux has been ported to various non-x86 architectures. See: http://www.ibm.com/developerworks/linux/library/l-nonx86.html

      And some folks have even ported a Linux subset to 8086. See: http://elks.sourceforge.net/FAQ-English.html

      Still, it would be quite a small subset to fit on the 4004. Being so small, you could consider it a subset of virtually any OS.

    6. Re:So, will it... by Anonymous Coward · · Score: 0

      There is, or at least was: ELKS: http://elks.sourceforge.net/

      I've had Linux running on an XT clone laptop with that.

    7. Re:So, will it... by haxor.dk · · Score: 1

      Sure, Linux will run on it. Just imagine a whole bunch of blades of these...!!

    8. Re:So, will it... by filesiteguy · · Score: 1

      ROTFL!

      --
      The Kai's Semi-Updated Website Thingy
    9. Re:So, will it... by filesiteguy · · Score: 1

      Wow! 16-bit Linux. That's very geeky indeed.

      (FWIW, my father-in-law, who works as a magazine editor for a technical magaine, used a Leading Edge XT clone until just a few years ago. They switched him finally to a Macintosh, which is his new primary desktop.)

      --
      The Kai's Semi-Updated Website Thingy
  11. Re:Wow! Imagine a Beowulf Cluster by Anonymous Coward · · Score: 5, Funny

    4004 - chip not found.

  12. Old joke for old hardware... by ilsaloving · · Score: 1, Funny

    Imagine a beowulf cluster of these!

    1. Re:Old joke for old hardware... by jones_supa · · Score: 0

      In Soviet Russia, 4004 releases details of you!

  13. 4004.com = 4004 Web Server? by Anonymous Coward · · Score: 1, Funny

    Cruising over to 4004.com gives "page cannot be displayed". While I'm sure it's slashdotted, I can't help but wonder if they used one for their web server......

  14. Dude! by NoYob · · Score: 1

    Imagine a beowulf cluster of these!

    First Post said just that.

    I know that most first posts are GNAA trolls, or something else pretty obtuse, but come on! You're waaaay down here and you honestly thought you'd be the first one to post that?!

    There's already been a "Does it run Linux?" post and if I dug into the -1s, I'm sure there would be a "In Soviet Russia, 4004 processes you!" or some such thing about Cowboy Neal's something using 4004 in the description.

    These are things one learns in the first few days of Slashdotting.

    Man, go and read "Slashdot for Beginners" somewhere on Wikipedia - you know there's GOT to be an article on it somewhere there.

    --
    It's NOT me! It's the meds! I'm on 1000mg of Fukitol.
    1. Re:Dude! by Splab · · Score: 1

      You are of course aware that slashdot presents posts in different order depending on your settings? So while his post might be "way down there" in other views it will show up in the top.

      Perhaps you yourself should go look for that elusive slashdot for beginners...

  15. Re:Wow! Imagine a Beowulf Cluster by Nerdfest · · Score: 2, Interesting

    I just found it ... it was in my programmable calculator from high school (EC-4004 from Radio Shack). Still works too.

  16. Re:Wow! Imagine a Beowulf Cluster by Sillygates · · Score: 1

    Umm......4004, previous post from 2006 not found (noticed)?
    http://hardware.slashdot.org/article.pl?sid=06/11/14/2356255

    --
    I fear the Y2038 bug
  17. Federico Faggin, intel4004.com by Anonymous Coward · · Score: 4, Informative

    http://www.intel4004.com/ goes into much greater detail about Federico Faggin (primary co-developer and project leader), and the story of his accomplishments before and at Intel, his physical signature on all 4000 series chips, Intel's successful attempt to discredit him and patent his invention (the buried gate) that he invented at Fairchild before coming to Intel, and his departure to found Zilog with some members of his older design team.

    Intel has been playing their game their way for a very long time.

    1. Re:Federico Faggin, intel4004.com by apetrelli · · Score: 1

      http://www.intel4004.com/ goes into much greater detail about Federico Faggin (primary co-developer and project leader), and the story of his accomplishments before and at Intel, his physical signature on all 4000 series chips, Intel's successful attempt to discredit him and patent his invention (the buried gate) that he invented at Fairchild before coming to Intel, and his departure to found Zilog with some members of his older design team.

      Intel has been playing their game their way for a very long time.

      It's a pity and a big mistake that such a great engineer did not get a Nobel prize yet. He revolutionized our world.

    2. Re:Federico Faggin, intel4004.com by Alioth · · Score: 1

      The site doesn't make it clear - was Faggin shafted by Intel while working for him (and left to form Zilog as a consequence), or did Faggin leave and start Zilog, and then Intel tried to discredit him as an act of sour grapes?

      --
      Oolite: Elite-like game. For Mac, Linux and Windows
    3. Re:Federico Faggin, intel4004.com by TheRaven64 · · Score: 1

      Engineers don't get Nobel Prizes. The prizes are for science not engineering.

      --
      I am TheRaven on Soylent News
    4. Re:Federico Faggin, intel4004.com by apetrelli · · Score: 1

      Engineers don't get Nobel Prizes. The prizes are for science not engineering.

      In fact I meant nobel for physics. The silicon gate technology, invented by Faggin, is essential for the boost of the microprocessor technology, but it is indeed a physics discovery.

    5. Re:Federico Faggin, intel4004.com by TheRaven64 · · Score: 1

      No, it's an invention. Inventions are engineering, discoveries and theories are science. Process technologies are definitely not scientific discoveries. The photovoltaic effect is a physics discovery, an efficient photovoltaic cell is an engineering invention. The former can get a Nobel Prize, the latter can not.

      --
      I am TheRaven on Soylent News
    6. Re:Federico Faggin, intel4004.com by apetrelli · · Score: 1

      No, it's an invention. Inventions are engineering, discoveries and theories are science. Process technologies are definitely not scientific discoveries.

      It seems that you are right, the Nobel committee emphasize on discoveries over inventions, but this was not the original intention of Alfred Nobel.
      So, if sir Alfred was still alive, he could give the prize to him :-D

  18. Control Systems using 4004 by SwedishChef · · Score: 5, Interesting

    In the very early 70s our engineering group was interested in using the new 4004 to simplify the production of control systems for heavy machinery (windlasses, hydraulic systems, etc). The machinery itself was slightly different from contract to contract and even from item to item within a contract so we had to design a new control system for each unit. When the 4004 came out we were excited to see if we couldn't do it cheaper and faster using a microprocessor.

    We had moved from relays and discrete wiring to CMOS components on printed circuit boards and thought that was a big step. CMOS could be run at 15vdc which meant that the noise inherent in the environments our machinery worked in would not be quite as big a problem.

    Unfortunately we discovered that we had several problems including the limited instruction set and memory capabilities of the 4004 along with the lower voltages needed so we stuck to CMOS until I left a couple of years later.

    Still, the 4004 was my introduction to microprocessors and that changed the course of my career from electronics and electronic control systems to digital control systems and computers.

    It's been an exciting ride, too. I am grateful to have grown up with the technology.

    --
    No one ever had to evacuate a city because the solar panels broke!
    1. Re:Control Systems using 4004 by ConceptJunkie · · Score: 1

      By the time I hit the streets, the 80386 was the hotness and the 486 was just around the corner. I love hearing tales of the trenches from the Good Old Days. As exciting as technology remains to me, working in the field and using it constantly, I still miss the simpler times. Maybe it's because what I know now would have made me a Technology God 20 years ago, or maybe it's just because there was something different about a time where things were changing rapidly but the field was still on a scale where someone could comprehend a significant chunk of everything that was going on. Or maybe it's just that Old Geezer syndrome.

      Anyhow, thanks for the story and might I add, "Bork Bork Bork!"

      --
      You are in a maze of twisty little passages, all alike.
  19. Intel is also world leader on chip fabrication by Anonymous Coward · · Score: 0

    I don't think "any old fab company" would be able to produce a running clone of a core i7, let alone run it at the same speeds. AMD and IBM might be able to but who else?

    1. Re:Intel is also world leader on chip fabrication by Criton · · Score: 1

      UMC's Fab 12i most definitely could produce a a core i7 and same with Hitachi ,and NEC as their fabs are as advanced maybe even more advanced than Intel's. Now China the most likely to make an illegal copy can't copy it outright as their most advanced process I believe is only 90nm. But they too probably could make a slower variant as for comments you can't just scale it yes but they do have fairly capable engineers.

  20. Non commercial use? by serviscope_minor · · Score: 3, Funny

    Available for non commercial use? Are they even entertaining the possibility that somoent might try to profit from the design?

    --
    SJW n. One who posts facts.
    1. Re:Non commercial use? by DerekLyons · · Score: 1

      Given the morbid fascination the geek world often has with retro computing, it's not something I'd ground rule myself.

    2. Re:Non commercial use? by sootman · · Score: 0

      Yes! I intend to use this documentation as a starting point for my own product line. I hope to learn quickly and make more advanced designs, which will also be smaller, and I will compete directly with Intel. I will call my company Advanced Micro Designs.

      --
      Dear Slashdot: next time you want to mess with the site, add a rich-text editor for comments.
  21. Whoopy by Anonymous Coward · · Score: 0

    That's am important piece of intellectual property that is. I doubt anyone could possibly design a 4 bit microprocessor without Intel's help. Good thing they finally got around to putting this 39-40 year old design into the public domain. We need cheap calculators!

  22. it's the full specs now by ChipMonk · · Score: 1

    No need to RTFA for that, did you even bother with the summary?

  23. That takes me back by certsoft · · Score: 1

    Somewhere around 1975 or 1976 I worked at the micro-electronics lab at Point Mugu Naval Air Station. We did a number of projects using a 4004 and those awful 1702 EPROMs. I remember using one to run a X/Y Table and sensor probe to test thick film (might have been thin film) resistor wafers. If a chip wasn't in tolerance a drop of magnetic ink would be dropped on it.

    We used a timeshare service via a Model 33 teletype with acoustic modem to access a 4004 assembler. It would spit out a paper tape that we would use for the EPROM burner system. I think I like Eclipse better.

    1. Re:That takes me back by RyuuzakiTetsuya · · Score: 1

      you must surely agree that compared to Visual Studio, paper tape IS a superior option.

      --
      Non impediti ratione cogitationus.
  24. Useless: Need a car analogy. by Anonymous Coward · · Score: 0

    The parent thread has to be the Yugo of posts.

  25. Great, now I cam make my own calculators... by jameskojiro · · Score: 1

    I just need to make my own chip fab in my garage and hundreds of hazardous chemicals that are sure to get me on DHS's shit list....

    --
    Tsukasa: All I really want, is to be left alone...
  26. Re:Awesome! -- here are some process detalis by mcpublic · · Score: 1

    The 4004 family was fabbed using a 10um pMOS process. Single metal, single poly, self-aligned gate. No depletion. Buried contacts were only used in the 4004 due to density requirements. Pretty sure the rest (4001, 4002, and 4003) used the same process as Intel's SRAMs of the day (e.g. the 1101). Not sure how the diff layer was made. I can ask. Bootstrap loads were used for high-side of push-pull inverters needed to drive big loads. Much to my surprise, diff was used instead of poly for interconnect that couldn't be done in metal.

  27. Re:Awesome! -- here are some process detalis by dpilot · · Score: 1

    I saw both diff and poly stretching around in there, though I didn't notice if the poly was for underpass or just gate reach. Never did pMOS myself, just nmos and cmos. Never used buried contacts either - someone higher-placed got burned by buried contacts before I arrived, and they were politically taken off of our plate. I did see some other designs that used a combination of diff/poly/buried-contact for a lower resistance underpass.

    --
    The living have better things to do than to continue hating the dead.