Slashdot Mirror
Is Hyperchip Hype?
Peter Galbraith writes "There was an interview on CBC (here in Canada) last evening about
Hyperchip, a Montreal-based
company that are working on a new type of router that would scale up 1000 times in traffic (so wouldn't be obsolete in less than a year) and would pass packets to their destination in a few hops instead of a dozen or more. Any experts out there think it's hype? Or real?"
The explanation on Hyperchip's "technology" page is pretty thin, but considering they just raised $70 million, I hope they've given more convincing details to their investors.
With a name like HyperChip its got to be a hoax. I it was real it would have a name like RXE-8635P
I think slashdot is broken, my karma is 5 and i post at -1. Whats the deal with that?
Step Two:
Step Three: Profits!
Carousel is a lie!
Maybe details are sparse because they're getting it from the future and they still need to build the time machine...
--- I used to moderate, then I read the -1 articles and decided having to filter through them was not worth it.
No, no. They should have tacked on some more names.
Hyper
Compu
Global
Ultra
Turbo
2002
Now all it needs is some sort of advertising-catchy slogan-type thing.
IBM Guy: Let the UltraGlobalDominatorChip2002 Allow your business to stomp down on the little guy.
Duffman: Oh yeah!
naw, THX-1138 sounds *much* more realistic
I'm here in Montreal, and I applied to go work for them not even a week ago.
:)
I was inadequate
If they can figure that out, they probably have a chance.
Aaron
AaronCameron.net
Am I the only one, or did this make anyone else nostalgic for the mid-90s?
This would have been better suited for the Gnome thread; but its offtopic, nonetheless..
But still, sun is far from fucked - The aftermarket Sun Enterprise systems are selling like hotcakes from 3rd parties - This is bad for sun, but not -all- bad. You buy that 5500? You need support for it. If you get support from Sun, you get to pay an additional premium since you didnt buy it from them or a sun VAR.
Sales of the USIII line are now above the USII line. Sun expects to be in the black by the end of 2q.
Hit Bill Bradfords great site for more details: sunhelp.org
Hrm, blatantly offtopic posts to Slashdot threads to try and drive a stock down.... interesting.
----- sXe
hey I'm an engineering. we've figured out lots of things 1. Beer 2. Sleeping with your eyes open in class 3. Nursing Students
I was at a Pub one evening (I live in Montreal) and I happened to meet their sales manager... ms. Jen Goldfinch. Although I had seen the Hyperchip building on many occasions, I had never inquired as to what they do. After meeting this woman, I was given the impression that their routers are actually in use by some of the big players in the digital pipelines game. She was actually pretty clear on that, although I can't seem to find any exact information concerning their customers on their website. Perhaps some questions to nortel, and qwest folks might clear this up. The only thing that make me dubious about her claim of widespread adoption, would be that if their products are so much "better" (for the lack of a better word) than the competitions, then why is abilene using cisco products? Unfortunately I don't have that kind of time on my hands.
Kind of odd they have nothing on their web site about a Hyperchip. www.cbc.ca
It looks a bit like the PC processor industry - they're pushing the technology to its limits just so that they can claim they're the fastest. What happens when the bandwidth requirements have also scaled 1000 times? There are no overclocking options here folks! On a lighter side - If I had one of thouse routers I might be able to load all those images and flash a bit faster :-)
Follow me
Simple hop count does translate directly into speed. A two hop route plagued with slow nodes might be (and often is) slower than a route that consists of more hops with faster nodes. Sounds like ignorant marketing hype.
Cisco and Juniper can only (currently) route in gigabit speeds.
Other competitors that they will have to deal with: Pluris, IronBridge Networks and Charlotte's Web Networks .
Cisco has had the technology to do their so called 'smart routing' for years. It's called BGP. I have seen it intelligently route packets across the country that only goes across 2, maybe 3 routers. It seems in this "dot-com" era of techies, no one has a clue about routing. There are so very few people who know what to do with a router, and obviously those people aren't working for any commercial ISPs. I used to work networking for the government, and one of our customers had a problem with routing through UUnet. I contacted their router dept and talked to one of their so-called "router engineers" and had to explain to him how to fix an assymetrical route.
Do a traceroute to yahoo.com. Conceivably, you shouldn't have to go more than 5 hops. But with every major corporation creating a string of routers rather than a mesh.... it takes for ever to get there.
I don't have to say anything. Your borderline illiteracy seems to indicate a US citizenship and, in such a case, one of your "free" fellow citizens will stumble along and shoot you before too long anyway. Hopefully he can squint through a haze of crap American beer well enough to get you between the eyes (aiming just south of the NASCAR logo on your hat should be almost perfect).
Plus when you are looking at the forum for more information and you get post like "Sun is Fucked" it kinda boggs down the conversation with information that is not relevant.
We had a project that was probably similar in concept, maybe slightly lower throughput. I don't think the claims are that far fetched.
However, getting one chip working is one thing. Getting an entire box is a whole 'nother trick entirely, as I'm sure they will discover.
They are, obviously short on technical details, but I find no particular reason to disbelieve them. There are a lot of "real" tech companies in Montreal (my ex-company had a branch there), and fewer fakes than other places.
$70million won't last you very long without any other source of revenue. If they are lucky and really, really good, they may have a product out in production in 2-3 years.
Another thing is that article is misleading; they really received $12M in funding, and added another $31M in repayable loans from the Canadian government. Again, the numbers quoted in the article are Canadian dollars, not US.
Several terabit router companies have failed (such as Ironbridge ) and others are having problems, a la Avici along with Nexabit.
For more entertainment, read the article and comments in Light Reading.
It's not the bandwidth, it's the services. Besides, who can afford to provision 65,000 OC-192s?
http://www.hyperchip.com/technology_faq.html
Maybe contact IBM and see if they've been working with HyperChip as per this FAQ.
they claim to have 41 patents issued... I found 3:
I/O and memory bus system for DFPS and units with two or multi-dimensional programmable cell architectures
Efficient direct replacement cell fault tolerant architecture
Fault tolerant data processing system fabricated on a monolithic substrate
From these it appears they are fabricating wafers with lots of semi-independent processing nodes, which are tolerant of failures of some of the nodes (and can therefore take into account chip production glitches on part of the wafer).
This could give them a potentially large performance advantage, if they can do it right.
Posted by an anonymous coward none-the-less... Go figure!
They also have an EETimes story Archived and there is this news item from before the dot-com boom went bust.
Other items include this bit saying we don't need petabit routing anyhow (just wait a few years!). I also spotted this job description from some namesless company.
Basically, this job description says to me, "You will invent the products we need so that we can make lots of bucks off your brains". One of those things, go in with eyes open."It is a greater offense to steal men's labor, than their clothes"
their router is called pbr-1280 is it must be real :)
No? How... odd.
The internet stopped doubling in speed sometime last year. Everyone was banking on having OC48's to large customers (and OC3's to everyone else). One year later and most people are still using NxT1 options, and the core isn't anywhere near overutilized (not anywhere near 10gig. Or 30 gig for that matter, which you can get by running multiple OC-192s in parallel)
So their product is worth about as much as their nearest competitor (Juniper, if they've written their software properly) and they're two years late to the market.
This goes squarely into the category of "Ginger" (the human transporter), Exponential (high speed PPC chips) and the Sinclair C5 solar car. Funds to "Commercialize [their] Carrier-class Super Core Router"? So when do they expect to hit the market? And where will the market be at that time?
Not that it's a bad idea to do something like this. Undoubtably a lot of value is being created in a company like HyperChip. But it's not like they hold the key to a better Internet -- the market will catch up with them even if (and that is a big if) their 1000x figure holds up in the real world.
Pushin' 'n dealin', shovin' 'n stealin'
The same thing is happening on this side of the border. LaurelNetworks is another super-startup company, with a lot of capital, with their guns aimed at the "big boys" of network hardware (Cisco, Juniper, etc.). I did some work with Laurel, and even some work with a micro-startup networking company, BlueWave Networks.
:)
I don't think that there's any hoaxing at all going on here. They're legitimate players with some heavy capital backing them. They also have great engineers and some good technology. It may not be enough, however. What it's going to come down to (IMHO) is the willingness of big ISPs and carriers to adopt technology from a new vendor.
Cisco may not have the best equipment, but everyone and their dog worth their salt in this game knows IOS and how to admin it. You can't say the same of any of the new vendor's products.
We've moved beyond the days of "great ideas" and "great products." Internet routing is a mature market in which the biggest obstacle is now overcome the inertia of the entrenched players.
The anology reminds me of Linux vs. MS, but then again, what doesn't?
From Thier site:
.... and that a packet originates in Boston and is transmitted in red light to the next node, if the light isn't the color for that node, So if red was Richmond, NY and Washington would reflect the red light down the line until it gets to Richmond. This way NY and WAS don't have to convert the signal which saves a lot of time and work. Also this allows Boston to talk to Richmond as 1 hop as far as the software is concerned. Similarly a packet transmitted in Amber light might go all the way to Atlanta before being converted to Electrons.
Accelerating the war are the recent advances in ultra-long-haul optics and optical switches, which are making it practical for routers to place packets on destination-based wavelengths that can take them as close as possible to their final destination in the core, thus eliminating intermediate routing hops and unnecessary O-E-O conversions.
I read this as meaning that you have a strand of fiber that runs from say for example Boston, to NY to Washington to Richmond to Charlotte to Atlanta to
Sounds like a good idea to me since it should work on existing fiber. The real question is how hard and expensive is it to start with two nodes and grow from there.
Slashdot is an anagram for Has Dolts, and I am Dolt number 468543
I say bah, you wait and see when we destroy you with our giant snow machines! mwhahahah, so much cold and snow you'll never dig your way out!
I dunno about him, but I certainly feel better.
Mmmmm. Hunting Vampires while in Band Camp!
Lightreading's article, Hyperchip Hypes Its Hardware, claims that Hyperchip stands out in 2 ways:
1) "It's aiming to create something much more than a bigger, faster, box. It's aiming to create the Internet equivalent of a Class 5 telephone switch, something that would sit at the edge of optical backbones and handle IP connections to tens of thousands of users. Hyperchip's developments would potentially replace entire ISP POPs (points of presence) and would have an aggregate capacity measured in - get this - petabits a second."
2) "Hyperchip is addressing this requirement in a totally different (some would say bizarre) way. It's devoted most of its efforts into adapting supercomputer hardware to deliver the scalability it requires. Software - considered the key to success by most terabit router vendors and users - seems to be of secondary importance to the Montreal based startup."
The article says that trials will start at the end of the year. That should prove interesting...
Look at the graph on the company's white papers. Optical vs. Moore's law. First of all you really can't compare a law and optical. Second of all, they have moores law wrong.
The GeekNights podcast is going strong. Listen!
...my downloads. Kernel source, MP3, and pr0n. That's all we really care about here, right?
Oh, and Half-Life pings. I ran an OC48 up into my treehouse but the ping didn't improve so I went back to an OC3. Then winter came.
...that your first three suggestions are also the first three words of Homer's ebusiness - HyperCompuGlobalMegaNet? (that was later destroyed by an evil Bill Gates)
I used to work for Hyperchip. I don't believe I'm violating my confidentiality agreement by revealing that the name the founder Richard Norman originally wanted was "HyperCorp" but www.hypercorp.com was taken so he settled for Hyperchip instead. The company was founded on the strength of Richard's patents in wafer scale integration and the original business plan included a lot of stuff that was accurately described by the term "hyperchip".
That's 70 million in Canadian funny money so that's about 10 bucks US.
That makes their product different. With Cisco gear, you have a very, very small number of high speed ports available to you in one chassis (and several of these "capabilities" are eaten up when you go with redundant solutions).
The idea behind Hyperchip, that is a supposedly better implementation than Avichi's that preceeded it, is to have a packet switching backplane that is expandable to multiple bays, as opposed to the tiny boxes such as the cisco 12000. Since it is a common backplane, there are fewer "hops".
The real limit is power. The Avici systems used over 400 amps of three phase power per bay, and (I believe) scaled to 16 bays, each one capable of running over 60 OC-192s at line speed.
Hyperchip's unit looks better.
Right now, their just trying to figure out how to market it, and how they can add services inside the box that you wouldn't get otherwise. Think of all the stuff you would like to do to streams of that size, but just can't. Also, think of what to do with packets that are going to full pipes. At OC-192 speeds, you can't hold on to packets. There isn't enough time to put it in to memory.
PS OC-192 can carry approximately 10 Gb/s. Or, over 1.2GB/s (this isn't ethernet, it's sonet) (but will have 10 Gb ethernet interfaces, but they just can't carry as much)
At 10 Gb/s, a 1600 byte packet (for those ethernet fans out there) is on the wire (going across a fixed point)for 160 nanoseconds.
Purebreed Aryans are only found in India (where the European Aryans emigrated from), so perhaps you should go there to get cock.
Please start your boycott as soon as possible.
if its real wheres the working product ? can i buy it ? what does it sell for ? who is going to buy it and in what quantities ? wheres the market ? how will you compete against cisco ironbridge and other vendors ?
The last time this came around on Slashdot, the switch was built out of little micromachined moving mirrors, like the TI video projector.
Hyperchip has not made the big breakthrough to true optical packet switching, and they admit this in their "white paper". That's considered the next big goal in routing. Hyperchip's technology is an interim measure only.
thats one helluva site
any claims of the network core being overloaded in the near future are foolish. go ask any of the large carriers how much dark fiber they have laying in the ground begging for traffic. core routing will be dominated by cisco and juniper for the foreseeable future.
it's easy to say that you have an amazing new technology that will change internet routing. however, ask them who is developing their routing code? is it from scratch? did they buy gated and are just hacking it? there are only a few development groups out there that can do IP routing development from scratch these days... juniper, cisco, probably procket networks and redback networks. they all have people that have written code from scratch.
everyone else is hacking gated. gated has issues. gated doesn't scale. gated is not core router routing software.
i also guarantee that NO carrier, large or small currently has one of these boxes deployed in their production networks.
it's easy to buy into the hype, but these guys will never be a major player... at best nortel will buy them and rename them the opterra blahblah and then kill it off in 18 months.
- create chipset that will allow for a greater number of ports, thereby increasing the limit of data sent down one optical trunk
- design a different network architecture, which is point to point, rather than a ring. This has two benefits. 1. is there are fewer hops between backbone points. 2. the data is placed on the wavelength of the destination, therefore reducing latency and O-E-O conversion
Realistically, it will take a good 8-10 years to deploy this kind of technology for several reasons. Most telco's current use sonet architecture, and running new fiber between the major routing points takes time. Now of course there may already be some fiber laid by Quest or Level3, which the telco's can lease. But changing the entire architecture of the network isn't a trivial thing. Even though hyperchip can build the router, it is likely the actual speeds are far lower than Petabit. Plus, routing traffic at a rate exponentially faster than the rest of the system creates a different set of problems.On the financial side, telco's have already placed orders for hardware and probably won't place orders for petabit routers for atleast another 4-6 years. It takes a tremendous amount of work, fine tuning and maintenance to keep the backbone operating reliably and efficiently. A more fruitful area of research today is intelligent routers, and routing software. We can only go so far with the hardware approach to network congestion. At some point, the network needs to be smarter to alleviate packet corruption and other related issues.
paper weight tomorrow
They are a bunch of socialists, what do you expect?
After working in the networking for some time in a research group, I can say that there have been a lot of companies that have come and gone, offering similar "breakthrough" technologies, raised XX millions of dollars, and then went bankrupt quicker than the time it would take for their hardware to become obsolete.
It's likely that the claim to be able to route up to 1000 times more traffic is only a technology goal for them after they begin producing at least one or more smaller boxes that can't route nearly as much traffic.
And even if the box can route 1000 times more traffic, you have to cope with the Internet being composed of a variety of smaller sub-networks. If AT&T or Verizon upgrades their networks to use these boxes, and you're not on their network, you aren't going to see any gains at all, unless they make equivalent increases in core network bandwidth and you happen to access large majorities of traffic on their network. For the entire Internet to see gains, most of the network providers will need to adopt the box, or similarly capable boxes, and that rollout will take at least three years assuming these boxes become as trendy as "all your base are belong to us", a game that I never came across in my arcading days. What was the redeeming feature, was it a good game, or was the language just so funny that everyone remembered it?
The other thing about the product Hyperchip sells is that it's scalable, so while its maximum routable bandwidth won't make it obsolete in one year, the companies using it will never have that capacity available, they will only expand on an as-needed basis.
It sounds great, but if it does work, Hyperchip will be acquired sooner or later, so the company as it exists now will never live to see the success of the products. Network vendors need to be able to offer much more than a router these days.
The problem is that the backbones need more inter-connects to other companies networks at a local level. For example, living in Davis, CA, my packets from my DSL connection went to Palo Alto, CA because they have to go through ISP's internal network before it reached the backbones to get to my university one block away. If there were more interconnects, there would be less congestion and fewer of these chokehold points. I don't think some fancy piece of software/hardware is going to solve anything when the problem is lack of physical connections.
The biggest trick the devil pulled was letting lawyers become politicians so they can write the laws.
Every time we see a story like this someone has to say "Ooh, ooh! A MAC doesn't NEED fans!"
Do we care? It's a PC case. If you like Apple so much, you shouldn't be reading a story for a PC case!
"Any experts out there think it's hype?"
Say it slowly and the answer is revealed:
Hype-yer-Chip
:]
...proof: first four or five ./ posts were Funny, this doesn't happen every day.
They just closed their fourth round of funding. Note this was 70 million Canadian dollars, US$43 million. Only US$12 million was from venture capitalists, the remaining US$31 million was essentially a loan from the government of Quebec.
These guys have made some pretty wild claims in the past. Their first product was (maybe still is) to be called the PBR 1280. PBR = PetaBitRouter. They claim it scales to ~65000 OC192 ports. That's pretty freaking huge.
We'll see. They claim they're relasing a product later this year.
Multishelf is the new design. Juniper's next gen product, Gibson is multishelf. Alcatel's (not that anyone gives a shit about their IP products) next gen product, the 777, is multishelf. Cisco's and any other core router vendor that still has money is are also building multishelf systems.
The Hyperchip gear is not revelutionary, it simply can control a lot of shelves and ports from a single vantage port. This doesn't mean that single pipes are going to be running at millions of megabits, it means that you can switch large amounts of traffic across your backplane. This isn't a big deal, its just more then anyone needs right now. The rest of the companies will come out with products that can be daisy chained all day long also, but are busy making in between type products to generate revenue in the mean time.
This also has nothing to do with DWDM, because again, we aren't talking about bigger pipes. Just bigger boxes to plug more pipes into. The current pipes are OC192/10Gig-E. They are essentially the same thing and work just fine on networks today. The next step is OC768/40Gig. Currently most core routers are being made with 10 Gb/s slots. The next gen of routers will be made with 40 Gb/s slots. This is the landscape for the next 3 years. This is also perfectly natural and makes sense to anyone that has a clue. Now the statement that its 1000 times "faster" is just marketing and hype. But people that actually buy boxes like this don't give a shit about hype. They put boxes in their labs, test the hell out of them, and if they like them, they will by 100 million dollars worth of them. Simple as that. Let the ignorance continue punks.
They used to be called Netcorp, before they changed their name (they claimed to have a VIPSwitch that never did ship). So, when the product never arrives, change your target (they've actually been around since late 1993, if you count the name change, and have burned through a lot of bucks, even if it is in wimpy $CDN).
Propz to all the strippers in Montreal. They're what's keeping the sky over Canada going dark with American nukes.
But the never found any customers. It turns out that the few people that need very high speed routing don't buy anything but cisco and in that market it won't matter if you have a product thats much better, you'll have poor sales for years before the market will even consider your product.
As far as routing much faster, its not that hard to do. If you stop treating a router as a router and more like a switch, you can speed things up a grat deal with content addressable memory (the stuff used for cache tags). Its very expensive but 8 mb of CAM ram will let you decide which of 16 interfaces a packet goes to within 500 ps after the address bits hit the hardware. You can't do real time route update on this type of system like a cisco but you can still change routes within miliseconds.
The ideas behind the internet are dead when a small business can't dual home. Without routable class C address, that has already happened.
Registrant:
WebBlaster Online (DAVEYJ-DOM)
C/O David J Meier 610 Horicon St.
Horicon, WI 53032
US
Domain Name: DAVEYJ.COM
Administrative Contact, Technical Contact, Billing Contact:
Meier, David (DJM208) daveyj@HUSHMAIL.COM
DaveyJ.Com
610 Horicon St.
Horicon, WI 53032
US
920-485-4568 920-349-3836 920-349-3836
Record last updated on 19-Oct-2001.
Record expires on 05-Nov-2002.
Record created on 05-Nov-1998.
Database last updated on 19-Jan-2002 07:37:00 EST.
Domain servers in listed order:
NS3.ZONEEDIT.COM209.61.140.1
NS5.ZONEEDIT.COM207.41.71.245
That comment was meant for the other thread about the motorless liquid-cooled PC case from Korea. He forgot to pick the wrong window. The real question is, how did it get modded up HERE???
At TerabitCorp, Alan Huang employed what he calls a Galois Network using many standard off-the-shelf routers to create a fault-tolerant, open platform terabit meta-router with some very cool properties. Not sure if the idea ever flew, though...
The antidote for misuse of freedom of speech is more freedom of speech.
-- Molly Ivins
What cretin modded that OFFTOPIC?!?
:)
I'm sorry, but in *my* universe, redheads are never off topic
Anyone of the same oppinion might want to check here.
P.S.
No, parent comment wasn't from me. I wouldn't have bothered going Anonymous.
-
- - You can't take something off the Internet! That's like trying to take pee out of a swimming pool.
Akkkk!
I wanted to get some details on the tech, so I clicked the link to their website and got bombarded by a Flash.
Ok, am I a freak because that website make be want to severly hurt somebody (the inventor of Flash comes to mind), or are the freaks the suits who go to the web site and are impressed by the Flash?
-
- - You can't take something off the Internet! That's like trying to take pee out of a swimming pool.
I guess with the stock-market crash and the effect of the Sept 11th attacks, there must have been quite a bit of pent-up demand for snake-oil stocks.
Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
"Terabit", when describing routers, currently refers to the total capacity of the box, not to actually having terabit connections :-) OC192 is 10 Gbits, and is starting to become a mature technology. OC768 is 40 Gbits; I'm not sure if anybody's routing at that speed yet (probably), but it's not close enough to mature to be practical for anything more than the marketing value of *your* network having the biggest fastest pipe in existence, even if it's only going from San Francisco to San Jose.
Bill Stewart
New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
Going public was fun if you could get investors to go for it (and if you could keep the stock price high until your six-months-can't-sell window was over). Selling out to MS (popularized by Hotmail's $400M or so deal) stopped being fun when the DoJ was threatening to rip MS apart into three companies, none of which were sure they'd want to buy you, so lots of small companies went bust. Selling out to Cisco still looked like fun, because Cisco shares were like cash, only better. Sigh.... the still-mostly-good-old-days.
Bill Stewart
New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
Face it, there's only so much bandwidth demand out there if people stick to text - the reason to use Flash and Streaming Media and MP3 Narrations For Web Pages is so y'all will start using up more bandwidth so people will buy their routers :-)