Beyond hybrids, more Intel nods to AMD?

Beyond hybrids, more Intel nods to AMD?

Summary: Earlier today, I summarized the part of my discussion with Intel's enterprise marketing director Shannon Poulin that had to do with the market requirements for server chips that generate a minimal amount of heat with as little compromise to processing power as possible.  Prowess and heat have always at odds with one another when producing chips.

SHARE:
TOPICS: Processors
8

Earlier today, I summarized the part of my discussion with Intel's enterprise marketing director Shannon Poulin that had to do with the market requirements for server chips that generate a minimal amount of heat with as little compromise to processing power as possible.  Prowess and heat have always at odds with one another when producing chips.  Higher performing chips run hotter and, outside of Moore's Law, which indirectly implies that the heat produced by a given amount of processing horsepower will decrease over time, the main way way to cut back on heat production for a server chip is to ratchet down the number of watts it takes for the chip to run.  In a mobile scenario, you can cut back on heat production through techniques like sleep states when the user isn't as active.  But sleep states and server applications don't exactly mix.  

That discussion took place in the context of a longer briefing about the roadmap that Intel's Digital Enterprise Group is announcing: a roadmap that includes, as News.com's Michael Kanellos points out, an incredibly aggressive push towards predominantly dual core offerings.  In the bigger picture, the announcements by Intel aren't just an acknowledgement of the strategies long pursued by arch-rival AMD; they're proof that Intel can turn its oil tankers (fabrication facilities) around a bit more like motorboats while going on the counterattack.

In the AMD acknowledgement department are two items that go hand-in-hand with each other.  The first is a continued de-emphasis on chip speed (eg: 2.8 Ghz) as a part of the branding and marketing of its microprocessors.  Moving forward, Poulin told me, processors will be numbered (eg: there will be a 7000 series of XEONs) but nothing about the chip's clock speed can be implied from the number.   This, of course, is remarkably similar to a strategy long employed by AMD who has forever argued that clock speed is somewhat meaningless when trying to compare offerings.   To further emphasize its point, AMD would give model numbers to its chips that were not a reflection of their true clock speeds, but rather an implication as to the clock speeds of the Intel chips whose performance they matched (even though AMD's clock speeds were technically slower).   Clockspeeds will continue to be relevant in terms of determining the differences between chips within a single vendor's chip lineup, but they appear to finally be falling by the wayside as a marketing bullet point for differentiation.  That said, you and I both know that the clockspeed will continue to be discussed and often misused by marketers.

The second nod to AMD comes in the form of packaging and branding.  You can't buy just the processor from AMD.  For example, whereas the memory controller is external to Intel's processors, it's integrated into AMD's.  Intel argues that the more modular design lead to more flexibility and easier implementation of supporting technologies (supporting to the processor) as they come along.  AMD argues that it's OK to lock into a less flexible design for a longer period of time if the integration results in certain long term performance benefits from the design.  So, AMD is more of a package deal and Intel is a bit more a la cartesque.   But now, even if only in branding, Intel appears to be leaning more in the direction of the package deal.  Moving forward for example, Poulin told me that if the processor is a 7000 series processor, then the chipset that goes with it will be branded as 7100.  And, taking the packaging one step further, the networking controller will be branded as a 7200.  Said Poulin:

Every new platform gets a name unto itself.  We're moving away from things like gigahertz and cache size and towards a situation where we're focusing more on elements of platform: Virtualization, management, ability to provision.  We are much more focused on features than absolute gigahertz and cache size.  

 

Where have we seen this sort of bundling before?  Although it doesn't use numbers, it seems reminiscent of Intel's Centrino brand.  Centrino  represents  a certain combination of processor, chipset, and networking (one that, if you've been reading my blogs for a while, you'd know that I'm not particularly fond of).   Even so, for servers, it's clearly a step in the perception direction that AMD took a long time ago.  It will be interesting to see where Intel goes with this plan.

In the counterattack department, Poulin didn't mention AMD by name.  But he did make it clear that Intel is more than ready for a 32/64 hybrid world.  Although he said "85" isn't some magic number, Poulin said that 85 percent of the server chips that Intel is shipping now are 64-bit capable and that by the time the end of 2006 rolls around, 85 percent of the chips it's shipping will be dual core as well.  And a significant number of the servers based on these processors will be two-way servers (dual processors).   The net-net implication of dual core two way systems is that with each core designed to simultaneously process two execution threads (due to Intel's Hyperthreading technology) and with two processors each with two cores (for a total of four cores), a 2-way dual core system is theoretically capable of simultaneously handling eight threads. 

But is it enough to slow down AMD's Opteron which, according to a recent Mercury Research survey ,has surged from 7.4 percent marketshare in 2005Q1 to 11.2 percent share in Q2 (numbers that Intel's Poulin disputes on the basis of the methodology behind them)?  That remains to be seen.  Even though Poulin says that most existing applications will derive some benefit out of the brute force of a 2x2x2 system (threads x cores x processors), he admits that developers will need to revisit their applications before they can get the most out of all eight threads -- half of which can be attributed to the Hyperthreading technology.  While developers contemplate that option, AMD isn't exactly waiting.  Its dual core processors are out as well, some of which are married to the 1 GHz version of AMD's Hypertransport bus.  For those not familiar with Hyperthreading or Hypertransport, the two are not to be confused with each other.  They do two entirely different things.  But ultimately, both are designed to improve the same bottom line: system performance.  

Currently, Intel has 17 dual or multi-core projects in development.  While only three of them are in production right now, Poulin said that Intel's plan "is to ramp dual core aggressively."  But, whether or not that dual core push will be enough for Goliath to keep David at bay -- particularly when David is equally committed to a dual core architecture --  remains to be seen.  One thing is for sure.  In terms of AMD approaches to adopt, there isn't much left for Intel to consider.   Unless of course it wants to reconsider what "HT" should stand for. 

Topic: Processors

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.

Talkback

8 comments
Log in or register to join the discussion
  • Offuscation maximus

    Cyrix was the first chipmaker to give up on megahertz numbers and give "equivalent" numbers to InHell chips. AMD scoffed at the idea at the time and happily branded their chips with megahertz numbers. Oh how times have changed! I guess Cyrix had the better idea after all!

    InHell will put two CPU cores on a chip, but NOT a memory controller? Whats' up with that? Sun is trying to eliminate chip interconnects itself - by presumably linking all chips into a "superchip". This "computer on a chip" design is finally becomming a reality.

    I would have to argue that NOT putting a memory controller on a chip is STUPID! Presumably, you have a separate memory controller so that you could swap it out (upgrade) it in the future. Hey dude, UPGRADES ARE DEAD! Every time you want a faster machine (i.e. CPU), you HAVE to buy a new motherboard. Motherboards today are only upgradable so far - and its usually not good enough (if they are older than about 1yr). Example: Buy a AMD64 2800 and the motherboard is capable of going to a AMD64 3500 - BUT a year later, the AMD64 3800 is available and guess what, it has a DIFFERENT SOCKET. Upgrades are dead. Motherboards get upgraded along with CPUs. No need to have a separate memory controller.
    Roger Ramjet
    • amd64's

      just to clarify any athlon confusion, the first gen of x86-64 was the s754, which was 1600Mhz HT bus and chip types are 2800 to 3700, yes it was rather short lived but was supposed to be the socket-a replacement - but socket-a is still alive since it is cheaper and so many people shrug off the 64-bit capability regardless of any
      architectural advantages... was a strange transitional period. Originally there was a 1200Mhz HT version that was shunned by the community!

      the s939 is PCI-E capable (unlike s754), boasts 2GHz HT bus, and chip availability range from 3000 to X2 and beyond!
      ~doolittle~
      • This has nothing to do with slot or socket.

        It depends whether a CHIPSET supports PCI Express or not.

        Have a look at here:
        http://www.abit-usa.com/products/mb/products.php?categories=1&model=293

        nForce 3 doesn't support PCI Express. nForce 4 and ATI Radeon Xpress 200 Series support PCI Express.
        Grayson Peddie
    • On-Die Memory Controller

      There are a few disadvantages to having an on-board memory controller. Look at some high-end Xeon-based servers and you can see features such as RAID and HOT Swap memory which are features of the chipset. You can't implement these when the on-die controller does not support them.

      Of course, next-Gen Optys could adpt these features, for now, AMD has sacrificed some High-availability features and architecture flexibility for raw speed.

      This is not a bad thing necessarily, but it is important to note each chip compant retains some advantage. This keeps these parts from being a commodity.
      JackPastor
  • will be interesting...

    It is going to get really exciting with this engineering race, now that Sun is on with AMD and Apple is iApple. AMD chips currently have a slight headstart with hypertransport built in and virtualization on the horizon...

    the question is what is going to be the FSB replacement for intel?
    Noone seems to know (even intel for that matter)
    ~doolittle~
    • AMD is having 400% performance lead

      Look at the SAP benchmarks, the HP DL585 with 4 Opteron 875 outperforms the latest IBM and Unisys' 16P Xeon 3GHZ/4MB by 20%. That's a 400% performance lead. Opteron beats INTEL across the board, the HP DL585 also outperforms 8P Itanium servers. The performance gap will only increase when AMD goes quad-core.
      sharikou
  • packaging a memory controller?

    [quote]The second nod to AMD comes in the form of packaging and branding. You can't buy just the processor from AMD. For example, whereas the memory controller is external to Intel's processors, it's integrated into AMD's. Intel argues that the more modular design lead to more flexibility and easier implementation of supporting technologies (supporting to the processor) as they come along. [/quote]

    I'm not sure you can call building a memory controller into the processor to be simply a packaging decision, that's an engineering decision. "Packaging" would imply that there is a separate chip involved in memory control, and it gets included with the main chip, the CPU. That is of course the case with Intel processors, but with AMD it's not a separate chip, it's just a part of the main CPU.
    bbbl67
  • INTEL EM64T is slower than 32 bit

    There is an Anandtech benchmark testing INTEL Xeon and Opteron under 64 bit and 32 bit. It finds that INTEL CPU is 15 to 30% slower when running in 64 bit than 32 bit, while AMD Opteron alwayds run by 20-40% faster under 64 bit.
    sharikou