HyperTransport vs 3GIO

Format for Printing

Format for printing

Request Reprints


By PoorBloke
April 16, 2002

Posts selected for this feature rarely stand alone. They are usually a part of an ongoing thread, and are out of context when presented here. The material should be read in that light. How are these posts selected? Click here to find out and nominate a post yourself!

This is relevant to a lot of threads that have been going around recently, but I thought it deserved one of its own. If you have been listening to me, you know that one of the reasons that I pay so much attention to INTC is that I find the situation fascinating. Yes, you can make money owning the stock, but I think it is much more important that five or ten years from now, business schools are going to be looking at what INTC is doing right, and what AMD is doing wrong.

INTC has been clearly saying for years what it should be doing, and how it plans to do it. Last fall AMD's CPU strategy fell apart, and they couldn't understand why. Hint: Intel started volume shipments of 0.13u processors about nine months earlier than AMD will. By fall, INTC was ready to aggressively take the fight to AMD if necessary, but it wasn't. INTC could afford to take the time to do it right, because AMD hadn't.

I'm of course referring to the Mustang cancellation, the Thoroughbred delay, pushback, the Barton change to prototype, or whatever, and AMD seriously trying to sell an inferior new product as the greatest thing since sliced bread, and to "ramp production aggressively." If AMD had done a bit more work on the Thoroughbred, had some compilers, and (possibly) add some worthwhile features back in, they would have had a product worth what AMD tried to charge for it. So instead of the Thoroughbred being AMD's salvation, it was branded a loser before it could get started.

And I am not dumping on the chip here. I just did a very serious look at the Alpha 21264 866 MHz, the Athlon 1.33 GHz, and the Pentium 4 1.5 GHz. The most surprising thing was how close in performance they are.

But it is now four months after the promised date of the Thoroughbred introduction, and the necessary software and compiler options don't exist. If AMD had introduced the Thoroughbred in February saying that it was a nice chip, and that they were making it generally available so that every software company could get started on optimizing their applications for it, that would have been acceptable. Better would have been to have an "open" beta release--making the chips available, but waiting until the software is really ready before trying to sell it to users. But AMD promised much more than they delivered, and every time that Intel comes out with a higher speed grade Pentium4 or Celeron, AMD gets battered again.

Speaking of AMD, where is Thoroughbred? And what happened to Mustang? The real answer is in the paragraph above. Everyone who needs Prescotts for product development, compiler tuning, or product verification has all they need. But AMD is not going to formally announce Hammer until they are sure that it really is a better product than what they are selling now, and that this will be obvious to potential buyers. If it never happens for the desktop, tough noogies. If SledgeHammers are better for some servers, and ClawHammers for products from other vendors, fine. AMD have a bad reputation in servers, and reputation is very hard to earn back.

I think that, at least on this board, we are all satisfied that Intel is shipping 0.13u processors in quantity right now. Since OEMs have enough product in the channel, Intel--and the OEMs--have announced it months ago. The mobile chipset for AMD issue has caused delays. (The problem seems to be the lack of decent chipsets. OEMs don't like to lose head-to-head comparisons either.)

And now to the topic of the day, or yesterday, looking at the clock, 3GIO. Intel was very upfront about what it had, and what it was looking to do. I don't know what AMD did with HyperTransport, but they didn't pay attention. They also missed the PCI SIG's involvement. (In case you don't know who the PCI SIG are, they are all the OEMs that matter when trying to drive a new standard into the market). Right now most of them are designing around 3GIO , with the chips to be manufactured by most of the top silicon vendors in the world, I think that they will be used in almost every desktop by 2004.) And AMD seem to have completely missed the involvement of nVidia, ATI, PMC-Sierra, Sun, and others too numerous to mention in the PCI SIG.

Okay, so today (yesterday) 3GIO is a done deal as the new standard for high-speed interconnects. Not only are chipset manufacturers lined up to build processors with 3GIO connections, there is a key compatibility piece on the table, so that boards designed around 3GIO interconnects can use PCI device drivers where that makes sense. With a CPU and 3GIO support and your choice of memory interfaces, you can get a system up, running and out the door easily and simply using an Intel CPU.

When nVidea and/or ATI parts show up, 3GIO based desktop (or deskside) workstations will not only be possible, but will probably have beyond current workstation quality graphics. The price will be steep, but that is why I pointed to Sun (a member of the PCI SIG). 3GIO will probably lower their workstation costs.

So Intel has been busy lining up all the key players so that they could drive the industry towards a new standard. The first was PCI based motherboards, the second, the P6 buss, the third of course, was chipsets with integrated graphics. But by comparison, those were just practice. Intel will redefine, not part of the PC standard, but the whole computer industry: PCs, servers, network switches, and supercomputers for the next five to ten years with 3GIO and Prescott.

So AMD wakes up and says, "Hey guys, guess what. In a few months we plan to come out with a new standard. The Hammer! Take that!"

Huh? Weren't they paying attention? If AMD gets no support from the OS vendors for x86-64 CPUs, no one will pay any attention to AMD's infantile behavior. If you talk to 3GIO, you are in. If you want to talk HyperTransport, go ahead, for low speed devices that makes a lot of sense. Some motherboards will continue to support PCI for years to come. If you prefer ATA, USB, or Firewire, again no problem. There are a lot of nice Southbridge chips around that talk PCI.

So what the paradigm shift to 3GIO does is first, to make migration easy. All the software drivers written to PCI work without any rewrites. Second, it doesn't obsolete anything. (We can argue AGP, but my read is that, at the rate graphics cards have been moving, high-end graphics cards may be the first consumer item to use 3GIO, not the last, and PCI graphics cards are not that shabby.) But third, and most important, if chipsets for MIPS, Alpha, AMD Sledgehammer, Sun UltraSPARC, and other processors are all available with 3GIO interfaces, all of a sudden Intel is the major gorilla.

AMD is a small fish in the PC pond, and Intel is the largest fish in this ocean that includes servers, switches, and supercomputers. Companies looking to bring a new product to market will see the biggest market as the 3GIO market. If AMD stays out, they may be able to define the second largest market. But I doubt it.

If AMD tries to prevent chipset makers from making chipsets which use 3GIO "to talk to the Southbridge" for the Pentium 4, I don't think that can or will happen. Even if they succeed, they will be cutting off their nose to spite their face. And once graphics migrate to 3GIO they won't move back.

So what about HyperTransport? What about it? It was a great idea once upon a time but the problems driving HyperTransport have now been solved, most of them by 3GIO. ;-) PCI is fine for some peripherals, but HyperTransport was going to solve the problems of having too many peripherals for a single PCI bus, and switching between CPUs to get to the one that the device you wanted was on.

3GIO does that, at a much lower cost than HyperTransport, and if needed can be used to build fabrics just like Infiniband. 3GIO is also more flexible. Wide paths permit a much larger bandwidth than Infiniband, narrow paths with the same bandwidth cost significantly less, and even narrower connections are possible. So while 3GIO can co-exist with HyperTransport, I don't see any requirements for it to do so.

So what does Intel get out of all this? With critical mass behind 3GIO, Intel will never again have to worry about motherboard and/or chipset availability. (Well not after about mid-2004, when 3GIO should be dominating everything.) Intel can concentrate on building faster CPUs, and not have to spend as much effort as they do today on other components and issues.

What about AMD? They haven't been hurt yet. If they swallow their pride and build their own 3GIO compatible chipsets, and then design their next CPU generation with direct 3GIO support, they could even come out ahead. But, as I said, AMD doesn't get it.

If AMD tries to fight Intel here, they will lose. No, they have already lost. But at this point, AMD has little or no investment on the losing side, so they should look for a fight they can win. But even better, why pick a fight? Why not make friends and use those relationships to provide better products? Look how well Intel is doing, with exactly that strategy.

Cheers, PB

(Does this sound familiar?)

Become a Complete Fool
Join the best community on the web! Becoming a full member of the Fool Community is easy, takes just a minute, and is very inexpensive.