Slashdot Mirror
IBM Creates World's Fastest Semiconductor Circuits
Todd Heidesch writes: "'IBM announced it has created the world's fastest semiconductor circuit, operating at speeds of over 110 GigaHertz (GHz) and processing an electrical signal in 4.3 trillionths of a second.'
IBM expects the new technology to be pumping out 100 gigabit/sec network switching chips by the end of the year (on an optimistic schedule, I presume)." dr_zeus contributes a link to this Reuters article running on Wired (also fairly thin) on the release, writing: "Granted, this isn't a PC chip, but one wonders how long it will be before we hear 'dude, you've got a 110GHz Dell!'"
Dude, your 110GHz Dell consumes 450kW, and requires its own diesel generator...
The cover has 3 desktop machines 'burning rubber' and racing towards a finish line. The title is something like "Breaking the speed barrier, Intel 386 33MHz!"
It's a neverending journey, this technology trap we find ourselves in.
At 110GHz, light travels less than 3mm in one clock cycle -- less than the width of the processor, I presume. And if it's accessing memory from a RAM chip 10cm away, it'll be waiting close to a hundred clock cycles to get anything back.
is in their ability to save power. From what IBM is saying, is that their chips can be run at say only 20 - 40 ghz and consume a hundred times less power then a chip built with todays processes. So you'll be able to get the same or more processing power out of these chips for less enegry.
At 110 ghz, a PHOTON only moves 2.7mm so figure that the actual signal propagation is like 2/3 the speed of that and you see that the signal can only travel 1.8mm in a clock. So, these chips are not going to be all that great for CPUs at 110 Ghz. Much better for signal processing likein routers or something.
Now I can get rid of my pot-bellied stove and start using my PC, lower emissions, more heat, and a space saver!
That means ~1.29mm at C (speed of light), so about 0.9mm in reality. Wow, those better be some short circuit traces!
And Steve Jobs will still claim that his 2 Ghz G6 is "twice as fast" on some obscure benchmark.
Sometimes it's best to just let stupid people be stupid.
When in engineering school (a couple of years ago) my professor declared that we are moving towards the end of the speed and size improvements of microchips, because soon the assumptions aboout newtonian physics, on which circuit design is based on, will stop being reliable.
Usually you dont have to worry about quantumn effects (electrons tunneling and such things), because there are enough electrons to statisticaly average out the quantumn effects into the classical model.
But when you increase frequency you usually have to decrease the size of the components (so transistors switch faster). But if you decrease size too much you will not have enough electrons passing trough your circuit, to ensure the signal follows classical laws.
Well I guess the quantumn barrier was a lot further than i thought it was.
Or maybe IBM are not decreasing the size of their transistors but increasing voltages to make circuits switch faster.
Did you know that P4 has a couple of pipeline stages that do nothing but propagate signal? (yes, they pipelined the wire ...)
The Raven
The Raven
The article does not clarify what is exactly running at 110GHz - it says a "circuit". Is it a single transistor? Or a series of transistors? Does that include wiring? It is a common misconception that a 110GHz transistor produces a 110GHz chip. A 110GHz transistor would likely produce a 1GHz chip.
OK...
Correct me if I am wrong but aren't we limited by the speed of electrons at some point in the near future. How far can an electron travel in one second? How does this affect die size?
Sure, anyone can shake a stick 110 billion times per second but this doesn't mean that the stick will do anything productive.
As a side note, I think that it would be ironic and appropriate that Intel name their 4.7Ghz chip the "PentiumXT" as a funny play on the AthlonXP and the 1000 fold improvement over the 4.7Mhz XT processors of yore.
Life is the leading cause of death in America.
This article is crap. If you're a real EE who knows about this stuff, please enlighten the rest of us by answering some questions: 1. I'm a little confused. Did IBM demonstrate a networking chip that runs at 110 GHz? Or did they merely demonstrate a ring oscillator type circuit? 2. I was under the impression that, to reach such high speeds, you need something like an HBT. Am I right? Is this circuit based on HBTs? 3. If this circuit is based on HBTs, then why are people talking about Pentiums and Athlons? No way in hell you could implement a VLSI (or rather an ULSI) circuit with HBTs. Am I missing something?
Dear Diary,
Life can be hard if you're a 110GHz computer. It wasn't until my 3.168x10E15th clockcycle that there was a movement on the mouse and I had to present a password-requestor on the screen. That might look nice, but I had to wait several million of clockcycles before I got all the needed information from the memory. Memory is sooo slow these days, I recall stories from previous generations that you could have the data the next clockcycle after you had set the address! The downfall started when but right now it's waiting waiting waiting.
Fortunatly the password typed was wrong, so I had the fun of producing a beep for 44 billion clockcycles. It sounds an impressive length of time, but I got bored after about twenty million clockcycli and I changed the tone-height a hertz or two. That'll teach them to make these stupid mistakes!
Yeah... life is as good as you make of it. Hmm... an interrupt. Hold on. Back. Well, 80 clockcycles for that... Stupid optimized code. How much more before we get another timer-interrupt? Aaargh, still more than 80 billion clockcycles...
bash$
Call me stupid, but why can't they use the same material in PCs to increase the chip speed? Are there some limitations/incompatibilities other than the comparitively slow speeds of memory and I/O (I guess we can all see why I never got very far in that EE major...)
First of all, the IBM transistors are not MOSFETs, the tiny switches used in CPU's and other logic-based circuitry. They are instead heterojunction bipolar transistors (HBTs). HBTs are lightning fast and can be used as low-noise amplifiers for high frequency signals, which makes them great for wireless and Gigabit optical communication applications, but they are relatively large compared to MOSFETs and so are not really suitable for making CPU's. (Notice that the IBM press release never mentions CPU applications, but instead focuses on 100 Gigabit optical communications networks).
Now, you may wonder why SiGe can't be used to make super-fast MOSFETs. The main problem is that MOSFETs require a dielectric, such as SiO2 to act as an insulating layer between the "gate" and the channel. However, attempting to grow a layer of SiO2 on SiGe results in separation of the Ge from the Si, ultimately causing device failure. Currently, people are trying to find ways to deposit new dielectrics with higher dielectric constants, such as ZrO2, to replace the SiO2. Once this is acheived it may be possible to put such a material onto SiGe to allow creation of a MOSFET using this technology. However, development of such high-k dielectric technology is probably 3-4 years away and adaptation of this to SiGe will be a few more years beyond that, so don't expect SiGe-based CPU's anytime soon.
One last thing. I don't understand why IBM gets all the press. Motorola announced 110 GHz HBTs last October. IBM is really not as far ahead of the curve as they would like you to believe.
I see lots of EE types checking in. I'm no EE, not even an E, though I've got a serious affection for DD's anytime I see them and my feet are EEEE wide.
You guys who are saying this is impossible or impractical are in for some real egg on your face, though it's hard to say when.
I managed to spirit one of these out of the IBM labs and they are fast! In fact, they're so fast that you've got to start them up tomorrow in order to do something today, which is ok, because, once they crank, they start delivering yesterday.
Very cool. I just had Isaac Newton help me with a couple of things. By tomorrow, I should be looking up da Vinci, unless I get careless and work my way all the way back to Pythagoras.
Of course, it's tricky staying one step behind the IBM guys. They came by for me yesterday, but I hadn't started up yet. They almost got me last month, but I gave 'em the slip the year before.
You're not limitted by how fast an electron can move, exactly. In fact, electrons move VERY slowly in common situations - the drift velocity in home wiring can be several feet per *second*.
When you shove a few extra electrons in one end of a wire, the charge pushes a few electrons that were already IN the wire down a little. And they push some down a little, and they push some down a little. Just like standing in a tight line at the movies, and shoving the guy in front of you - it takes a little bit of time to propagate all the way down.
So the real question is "If I shove an electron in this end of the conductor, how long before I get one out the other end?" The two things that determine that are (1) the nature of the conductor, and (2) the length of the conductor. By keeping the amount of circuitry on the IC very, very small (which they assuredly did), the propagation time from one end to the other drops proportionately.
However, even beyond just making the die smaller, they are working on making materials propagate the electrical charge more quickly - recently, someone (probably IBM) showed that by using a stressed crystalline lattice, they could significantly decrease the amount of time it took to propagate from one end to the other.
steve
Oh, you're not stuck, you're just unable to let go of the onion rings.
I'd still like to have even that modest potential, which would allow MAC (Multiply ACcumulate) operations at 10MSPS, for digital radio projects, etc. If you decided you need a different feature, just reprogram the fabric.
With today's technology, I don't see why you couldn't have a 4096x4096 grid with 4 way interconnects, running with at least a 1 GHz clock. This could do real time FFT, etc, straight from RF to anything. You could implement a crossbar switch in software for at least 32 streams (being conservative) at the clock rate, in software, with plenty of capacity to spare.
Processor fabric is a powerful concept, but Intel will never implement it, it's too much of a threat to them and their Von Neuman architecture. Someone else has to do it.
--Mike--
That's why copper wires were important - they reduced R. C on the other hand is a different matter - for years and years (untill about 3-4 years ago) no-one cared about the capacitance of wires - because they were usually small compared with the capacitance of gates and the ratios tended to scale down as device features scaled down - everything got faster together
To make matters worse many of our CAD tools have untill quite recently made statistical guesses about wire capacitance which worked OK during things like synthesis (compiling to gates) when the wire capacitance was a small part of the equation, now it does matter and means the the whole structure of synthesis tools will have to change to perform combined synthesis and layout operations in order to create optimal circuits