Sign in with
Sign up | Sign in

Intel Versus AMD

Intel’s Xeon 7500-Series CPUs Target Enterprise Computing
By

Intel certainly has numbers on its side: more than 90 percent of the server market is x86, and Intel owns more than 80 percent of that pie. AMD had gone from zero percent marketshare in 2003, when it launched the Opteron, to 20 percent in record time, only to fritter that away by delaying the launch of the quad-core Barcelona processor in 2007.

AMD has gotten its mojo back with a series of releases that were on time (or ahead of schedule, in some cases) and delivered decent performance at a lower price than Intel. Slowly, AMD regained its good standing with the major server OEMs, and with each subsequent Opteron launch, has more OEMs.

AMD's latest processor is Magny-Cours, an eight- and 12-core Opteron. The company took the six-core "Istanbul"-era Opteron and connected two of them with a high-speed HyperTransport interconnect. The eight-core design is simply two six-core Opterons with two cores disabled on each.

Those in the technical know will say AMD is being hypocritical by doing this, since that was Intel's solution for its first quad-core Xeons. It took two dual-core processors and "glued" them together on the same die. But Intel's solution was less elegant.

For starters, if a core on one CPU wanted to communicate with the other core, the data would have to go out through the front side bus and back in to the CPU. This was an inefficient design, although Intel still got some decent performance out of those kludgey designs (Intel didn't hesitate to point this out, either). With Magny-Cours, a point-to-point HyperTransport interconnect between the two CPUs is many times faster than the old Xeon solution.Magny-Cours does not use Hyper-Threading (a proprietary Intel technology), but does have 8/12 cores versus the four/six in the Xeon 5600. I bring up the 5600 because AMD has never positioned M-C as a competitor to the Xeon 7500-series; it sees the Intel Xeon 5600 processor family as its primary competitor. Now, the technical argument of two cores vs. one core with two threads is an article in and of itself. Hyper-Threading does maximize the execution of code in one core, getting two threads or processes done with one core. But in the end, AMD will argue cores trump multithreading, and the benchmarks will prove or disprove this.

The 5600 is a two-socket mid-level processor good for the majority of server tasks, whereas the 7500/6500 will be for the mission-critical and high performance markets. That's about the one area where Intel and AMD will meet is in HPC.

Twice per year, the Top500 supercomputer list, a ranking of the fastest known supercomputers in the world, is released and every company involved issues press releases for bragging rights. Both Intel and AMD are targeting HPC with their respective chips. You might see a few on the list that comes out this June, but you will definitely see a bunch of 7500- and Magny-Cours-powered servers on the November list.

Magny-Cours is also aiming to lower the economics of the four-socket market. Dual-processor (2P) servers are fairly economical, but when you go to a quad-processor (4P) server, the price goes up by a factor of four or more. AMD refers to this as the "4P tax" and its goal is to bring the cost of a 4P server down to about double that of a 2P, perhaps even less.

While AMD would love to compete against the Xeon 7500, more likely it will compete with the 5600 in the mid- to upper-mid range of servers, and do so quite adequately at a competitive price.

Ask a Category Expert

Create a new thread in the Reviews comments forum about this subject

Example: Notebook, Android, SSD hard drive

Display all 19 comments.
This thread is closed for comments
  • 3 Hide
    surda , April 8, 2010 7:20 AM
    even though i dont read much about server processors but this just sounds super fast, i like how it has alot of error stages checking so that it stays 24/7 without crashing, but do they really need all that speed for servers? i just gotta say hardware technology is moving very fast these days.

    nice article btw thank you.
  • 0 Hide
    anamaniac , April 8, 2010 7:27 AM
    These chips are absolute beasts! They do run at low frequencies however. (But would you want 130W chips in a 4P/8P box?)
    4 memory channels, 16 DIMMs per CPU, damn. I imagine you'd spend more on the 16GB DDR3 DIMMs than you would the processors though.
    Also nice to hear that these scale well in 4P/8P boxes.

    But I must ask, why are the 7500 chips in 45nm? Is the 32nm process still too immature to make a 2 billion transistor chip with any decent level of success?

    Assuming a 8P box, all CPU's clocked to 3.5GHz (~120GFlop per CPU, ~1TFlops total), you could run a few games purely in software mode and still get good performance. Damn.
  • 2 Hide
    Anonymous , April 8, 2010 8:01 AM
    "In the course of one week, two separate events signaled what may be the end of Intel's grand experiment with RISC architecture. Intel released the Xeon 7500-series processor family, containing many features found in the Itanium, a RISC-based design developed in partnership with Hewlett-Packard, and Microsoft ended its support of Itanium."

    When did Itanium change from being a VLIW architecture to being a RISC architecture?... It was designed to overcome some RISC architecture limitations of the day. XScale was Intel's big RISC mistake...
  • -1 Hide
    RazberyBandit , April 8, 2010 8:31 AM
    I think it's just poor wording. Both portions of that sentence refer to the Xeon-7500. Try it this way:

    "In the course of one week, two separate events signaled what may be the end of Intel's grand experiment with RISC architecture. Intel released the Xeon 7500-series processor family, a RISC-based design developed in partnership with Hewlett-Packard containing many features found in the Itanium, and Microsoft ended its support of Itanium."

    There, all better!
  • 0 Hide
    Anonymous , April 8, 2010 9:02 AM
    How necessary is it to have the error correction circuitry? If it's that important and the normal desktop and server architecture doesn't have it then are we not all accumulating errors in our data and code? With what frequency does this happen in the real world - and is the machine check architecture actually important, or just a bullet point for a sales brochure?
  • 3 Hide
    gglawits , April 8, 2010 5:17 PM
    AMD's Magny-Cours is the better value proposition.
    Compare the AMD 6128 (8 cores, 2.0 GHz, $266 list price) against the Xeon X7550 (8 cores, 2.0 GHz, $2729 list price) and you'll see what I mean. The XEON cost more than 10 times as much! Sure it's faster, but not 10 times faster. Not even 2 times faster.
  • -8 Hide
    cjl , April 8, 2010 5:23 PM
    gglawitsAMD's Magny-Cours is the better value proposition.Compare the AMD 6128 (8 cores, 2.0 GHz, $266 list price) against the Xeon X7550 (8 cores, 2.0 GHz, $2729 list price) and you'll see what I mean. The XEON cost more than 10 times as much! Sure it's faster, but not 10 times faster. Not even 2 times faster.

    You clearly didn't understand a word of this article.
  • 1 Hide
    KlamathBFG , April 8, 2010 7:40 PM
    Also consider the applications that can have their life extended with a new scaled up limit and compare that to the cost of re-engineering those applications and suddenly $2729 a processor sounds cheap $27,900 or in some cases $272,900 would still be cheap.
  • -5 Hide
    idisarmu , April 8, 2010 11:24 PM
    gglawitsAMD's Magny-Cours is the better value proposition.Compare the AMD 6128 (8 cores, 2.0 GHz, $266 list price) against the Xeon X7550 (8 cores, 2.0 GHz, $2729 list price) and you'll see what I mean. The XEON cost more than 10 times as much! Sure it's faster, but not 10 times faster. Not even 2 times faster.


    You sir, are an idiot. RAM is MUCH more expensive than these CPUs. Even 16gb of desktop DDR3 memory costs about $800. Now these mobos generally have more than 4 dimms per cpu- more like 8, so $1600 for RAM makes a $266 CPU seem really really cheap. Now server memory is always more expensive, so I think it would make perfect sense to spend $2000 more in order to have a system with fewer bottlenecks.
  • 3 Hide
    ta152h , April 8, 2010 11:56 PM
    Why comment on the Itanium when you don't know what it is? This doesn't signal the writing on the wall, only 6% of Itanium buyers were using Windows.

    It still has reliability features far exceeding the Nehalem-EX, and they are still greatly supported by the largest computer maker in the world, which, by the way, also was the original designer.

    It's not going anywhere.
  • 2 Hide
    gglawits , April 9, 2010 6:07 PM
    For the two rude Intel fanboys "cjl" and "isisarmu", here's the math:

    Two-socket 16 core Opteron system with 32 GByte RAM:
    Tyan S8230 ... $460 (source: Froogle)
    two Opteron 6128 ... $266 x 2 = $532 (source: AMD)
    sixteen 2GByte DDR3 ECC DIMMs ... $60 x 16 = $1000 (source: Froogle)
    case, P/S, HD ... $400 (estim.)
    Grand total ... $2400 for a 16 core, 32 GByte server ($150 per core)

    Two-socket 16 core Intel "Beckton" system with 32 GByte RAM:
    motherboard ... $478 (assumed price, not available yet)
    two Xeon E6550 ... $2461 x 2 = $4922 (source: Intel)
    sixteen 2GByte DDR3 ECC DIMMs ... $60 x 16 = $1000 (source: Froogle)
    case, P/S, HD ... $400 (estim.)
    Grand total ... $6800 for a 16 core server, more than $400 per core

    Again, nobody doubts that the "Beckton" system will be faster.
    But, hey, $2400 vs. $6800 is a heck of a price difference.
  • -1 Hide
    notty22 , April 9, 2010 11:46 PM
    I think its the AMD fanboy who is not paying attention. Its stated clearly in the article AMD themselves don't see M-C as a competitor to this product.
    Quote:
    AMD has never positioned M-C as a competitor to the Xeon 7500-series; it sees the Intel Xeon 5600 processor family as its primary competitor.

    This does not take a genius to figure out !
    There are countless mission critical scenarios where second best in speed/reliability will cost companies money + get people fired(IT guy who chose the 'better deal' . Financial transactions with the NYSE, Amazon.coms inventory, Credit Card companies customer's accounts......
  • 0 Hide
    Reynod , April 10, 2010 2:59 AM
    I think the point is that N-EX will target much of the market space previously held at the top ... not the middle ... where Beckton sits, and AMD hopes to win back both the low end (2P) and eat into the middle (4P) with their price / power / efficiency strategy ... 6100.

    That's good news for small businesses ... as costs for the low and mid range systems will drop due to competition.

    N-EX based systems will nevertheless cost you an arm, leg, and possibly a kidney ... no competition there to dissuade Intel to drop the price.

    And why should they? Must have cost a squillion on the R&D to make this puppy pass inspection... many engineers toiling into the wee hours.

    Good article ... a tremendous chip too.

  • 0 Hide
    JohnnyLucky , April 10, 2010 11:35 AM
    "Itanium servers were usually multi-million dollar beasts that ran multi-petabyte Oracle databases or line-of-business applications that had to always run."

    petabyte - how many zeroes after the 1?
  • 0 Hide
    goodguy713 , April 10, 2010 1:04 PM
    lol i would love to see gaming bench marks on a system like this
  • -2 Hide
    Anonymous , April 10, 2010 3:24 PM
    We are using 6 Dl580 G5 with two socket 6-core 7400x cpu and 63GB RAM on each server in a single ESX4 cluster. Total 384GB of RAM, ll hooked up to 80 Terabytes of FiberChannel 15k DISKs on a EMC Clariion SAN. There are about 200 virtual machines including Exchange 2007, SQL servers, oracle server, and a large number of application servers running on OS ranging from server 2000, 2003 and server 2008. The CPU load are barely over 30% utilization.

    Imagine if we have these X7500 CPU they would be just sleeping. LOL

    Imagine if I had the X7500 CPU in these
  • 0 Hide
    ossie , April 10, 2010 5:22 PM
    Finally intel comes to the 8P party... where AMD was for almost a decade... alone, with no intel in sight - Opteron 8xx(x) anyone?
    While 8P systems amount to a tiny fraction of the server/workstation market - mostly 2P and some 4P - evolution is always welcomed.
    notty22I think its the AMD fanboy who is not paying attention. Its stated clearly in the article AMD themselves don't see M-C as a competitor to this product. This does not take a genius to figure out !
    ... more wintel fanboy b$. If some THGossip article "states" something, it must be true... right? Wrong.

    Even accustomed with the usual THGossip wintel bias and hype, micro$uxx' relevance in the mission-critical market is more than overblown... they're plain irrelevant.
    No more Itanic support? Good riddance - only gamer loader diehards would've used the crap from redmond anyway.

    jacp1000How necessary is it to have the error correction circuitry? If it's that important and the normal desktop and server architecture doesn't have it then are we not all accumulating errors in our data and code? With what frequency does this happen in the real world - and is the machine check architecture actually important, or just a bullet point for a sales brochure?

    All critical servers/workstations implement ECC. If not, it would be just a russian roulette game, until data corruption or crashes occur.
    It's not about "if" - errors are guaranteed to occur - but about "when" - and how to reliably detect, and correct them, and if uncorrectable ones appear, to take appropriate measures.
    Even if the drm infested games loader doesn't support RAS features, it doesn't mean that serious work shouldn't be done, where they are mandatory.
  • 0 Hide
    K2N hater , April 11, 2010 8:09 PM
    These processors will never show their true potential while running on cheap 1-2U heatsinks and tiny fans that last 1 year at most.
  • 0 Hide
    bentonsl_2010 , April 12, 2010 1:47 PM
    Quote:
    "Itanium servers were usually multi-million dollar beasts that ran multi-petabyte Oracle databases or line-of-business applications that had to always run."

    petabyte - how many zeroes after the 1?



    1 PB = 1,000,000,000,000,000 or 1000 TB's