As an add-on to the Intel Xeon 5600 “Westmere” x86 processor news, below is a complete list of the 32-nanometer 5600 processors and how they compare to the 45-nanometer 5500 processors that Intel came out with last year. I got this from the Intel Xeon spec page.
|Processor Number||Intel® QPI Speed||L3 Cache||Processor
|Max Turbo Frequency||Power||Number of Cores||Number of Threads|
|X5680||6.4 GT/s||12MB||3.33 GHz||3.6 GHz||130 W||6||12|
|X5677||6.4 GT/s||12MB||3.46 GHz||3.733 GHz||130 W||4||8|
|X5670||6.4 GT/s||12MB||2.93 GHz||3.333 GHz||95 W||6||12|
|X5667||6.4 GT/s||12MB||3.066 GHz||3.466 GHz||95 W||4||8|
|X5660||6.4 GT/s||12MB||2.8 GHz||3.2 GHz||95 W||6||12|
|X5650||6.4 GT/s||12MB||2.66 GHz||3.066 GHz||95 W||6||12|
|L5640||5.86 GT/s||12MB||2.26 GHz||2.666 GHz||60 W||6||12|
|L5630||5.86 GT/s||12MB||2.13 GHz||2.4 GHz||40 W||4||8|
|L5609||4.8 GT/s||12MB||1.86 GHz||1.866 GHz||40 W||4||4|
|E5640||5.86 GT/s||12MB||2.66 GHz||2.933 GHz||80 W||4||8|
|E5630||5.86 GT/s||12MB||2.53 GHz||2.8 GHz||80 W||4||8|
|E5620||5.86 GT/s||12MB||2.4 GHz||2.666 GHz||80 W||4||8|
|X5570||6.4 GT/s||8MB||2.93 GHz||95 W||4||8|
|X5560||6.4 GT/s||8MB||2.8 GHz||95 W||4||8|
|X5550||6.4 GT/s||8MB||2.66 GHz||95 W||4||8|
|L5530||5.86 GT/s||8MB||2.4 GHz||60 W||4||8|
|L5520||5.86 GT/s||8MB||2.26 GHz||60 W||4||8|
|L5518||5.86 GT/s||8MB||2.13 GHz||60 W||4||8|
|L5508||5.86 GT/s||8MB||2 GHz||38 W||2||4|
|L5506||4.8 GT/s||4MB||2.13 GHz||60 W||4||4|
|E5540||5.86 GT/s||8MB||2.53 GHz||80 W||4||8|
|E5530||5.86 GT/s||8MB||2.4 GHz||80 W||4||8|
|E5520||5.86 GT/s||8MB||2.26 GHz||80 W||4||8|
|E5506||4.8 GT/s||4MB||2.13 GHz||80 W||4||4|
|E5504||4.8 GT/s||4MB||2 GHz||80 W||4||4|
|E5502||4.8 GT/s||4MB||1.86 GHz||80 W||2||2|
For HP’s fiscal quarter ending Jan. 31, HP saw overall growth in the server and storage market, including increases in x86 rack and blade servers, but a sharp drop-off in its Itanium-based hardware. The rundown:
- Enterprise Storage and Servers had $4.4 billion in revenue, up 11% over last year
- Industry Standard Server revenue increased 27%
- Storage decreased 3%
- Business Critical Systems revenue dove 22%
- Blade revenue was up 24%
The full release is here.
IBM Corp. released an announcement letter this week that it will sell a Power7 version of the 595 — the big box — that will support DC power inputs.
The box, as usual, will support running AIX, IBM i and Linux. IBM will sell the box this year, saying the machine will be able to run up to 256 Power7 processor cores. Seeing as the Power7 chip can support up to eight cores per chip, compared to two for Power6, it looks like the Power7 big iron will have an architecture similar to the Power 595, just with Power7 instead of Power6 processors.
IBM unveiled the first of its Power7 servers earlier this week.
One thing I didn’t write about in an article this week about the new Intel Itanium processor, was future Itanium processors.
Since Intel has had a history of missing deadlines when it comes to Itanium, it seems important that they maybe hit one the next time around. The chip giant has been talking for years about its Itanium roadmap, and how solid it is, but the timescales on that roadmap have had a tendency to move around somewhat. So here is what Intel execs had to say about future Itanium processors.
The next Itanium, codenamed Poulson, will jump right from Tukwila’s 60-nanometer architecture to 32 nanometers. It is expected to have at least eight cores, whereas the Tukwila unveiled this week has four. Kirk Skaugen, VP of the Intel Architecture Group, said that Intel is on an “approximate two-year beat rate.” That means Poulson should be out in two years, in 2012.
Following that, Intel plans on releasing a new Itanium chip, codenamed Kittson, two years after Poulson, in 2014. Few details have emerged from the chip other than promises, of course, of improved performance.
Intel will be holding a webcast next Monday, and it appears that it will be announcing its new Itanium processor at the event.
The Santa Clara, Calif. chip giant has said it expects to release the new Itanium, nicknamed Tukwila, in the first quarter this year. Tukwila has been delayed multiple times, and was originally slated to come out in 2007. It will be a 65-nanometer, quad-core chip with hyper-threading technology and integrated memory controllers.
Intel is not confirming whether the webcast on Monday will be for Itanium. But the invitation I received to the webcast said that Kirk Skaugen, VP for Intel Architecture Group, will lead the briefing and be accompanied by Martin Fink, senior VP and GM of business critical servers for HP Software. “Business critical servers” or Business Critical Systems is basically a longer way of saying HP’s Itanium-based Integrity servers, so it looks like it will be an Itanium announcement.
Update, 1:02pm ET:
Just saw this online at Intel’s PR page:
Itanium “Tukwila” Now Gaining Revenue; Q1 Launch Expected
February 2, 2010“Tukwila,” the code name for the newest Itanium processor, has begun revenue shipments. The most advanced Itanium processor yet, “Tukwila” more than doubles the performance of its predecessor and adds a range of new scalability, reliability, and virtualization features. Eighty percent of the Global 100 companies already use Itanium-based servers. The launch of this Itanium mission-critical processor is part of a major push Intel is making into the server processor arena, with several announcements slated for the first half of the year.
According to RedMonk analyst Stephen O’Grady’s blog, in response to a Twitter question about Oracle-Sun’s plans for x86:
A: This is one of the $64,000 questions, in my opinion. Oracle was quite bold yesterday in expressing their disinterest for “commodity markets like x86,” which they were quite content to leave to Dell. It’s rare these days to hear a large systems vendor publicly dismiss x86; VMware’s Paul Maritz, for example, basically said at VMworld the exact opposite. It sounded a lot like, in fact, Scott McNealy in the old days, when he steered Sun away from x86 towards theoretically higher margin but disastrously lower volume SPARC opportunities. And we all know how that turned out, with Sun subsequently bowing to the inevitable and adding support for x86. Could we see a repeat of that history? It’s possible, based on what I heard yesterday, but we’ll see just how aggressive they are on that front.
IDC today is reporting that the x86 server processor market is back on the rebound, growing 14.1% in the fourth quarter of 2009 compared to the third quarter:
“The sequential rise in mainstream and high-end client processors points to the new products, like Core i5 and Athlon II, that Intel and AMD were shipping into the market for the holiday buying season in the fourth quarter,” Shane Rau, director of personal computing semiconducters research at IDC, said. “What’s interesting there is that consumers were there to buy systems based on them and that OEMs were investing in them for future builds. At the same time, the sequential rise in server processors indicates that server OEMs are starting to see corporations come off the sidelines.”
In terms of market share, Intel is still dominating with 89.8% market share, compared to 10.2% for AMD. Though AMD did gain 0.6% market share in the fourth quarter of 2009, Intel gained 3.2% overall for the whole of 2009.
Starting at noon ET today, Oracle will kick off a five-hour event in California that will outline its plans for Sun Microsystems’ technology. Last week, Oracle received approval from the European Commission to buy Sun, a deal estimated to be worth $7.4 billion and one of the biggest in IT in recent years.
I’ll be looking to get details on the following Oracle Sun technologies: UltraSparc, Solaris, Sun’s x86 hardware, Sun’s Modular Datacenter (formerly Blackbox), Sun’s cloud computing (which it announced a month before Oracle’s announcement to buy Sun), and what Oracle will do with Sun’s physical data centers.
My fellow reporters on other sites — SearchOracle.com, SearchServerVirtualization.com, SearchITChannel.com — will be tackling other angles of the acquisition.
The European Commission has approved the Oracle acquisition of Sun Microsystems, representing the last hurdle the database giant had to jump before the deal was done.
It has been nine months since Oracle announced its intention to purchase Sun, but regulatory issues have stymied progress on the deal. The U.S. Department of Justice gave its thumbs-up fairly quickly, but the tougher European Commission took more time. Both agencies wanted to make sure the deal wouldn’t violate antitrust regulations.
The EC ended up focusing much of its time on MySQL, the open source database that Sun bought in 2008. The question was whether Oracle’s acquisition of Sun would eventually quash MySQL. Apparently the EC was convinced enough that it wouldn’t happen, according to its statement:
Although Sun’s share of the database market in terms of revenue is low, as users of MySQL can download and use the database for free, given its open source nature, the Commission’s investigation confirmed MySQL’s position as the leading open source database. The Commission’s investigation therefore focussed on the nature and extent of the competitive constraint that MySQL currently exerts on Oracle and whether this would be affected by the proposed transaction.
The Commission’s in-depth investigation showed that although MySQL and Oracle compete in certain parts of the database market, they are not close competitors in others, such as the high-end segment.
Given the open source nature of MySQL, the Commission also assessed Oracle’s ability and incentive to remove the constraint exerted by MySQL after the merger and the extent to which this constraint could, if necessary, be replaced by other actors on the database market.
The Commission’s investigation showed that another open source database, PostgreSQL, is considered by many database users to be a credible alternative to MySQL and could be expected to replace to some extent the competitive force currently exerted by MySQL on the database market. In addition, the Commission found that ‘forks’ (branches of the MySQL code base), which are legally possible given MySQL’s open source nature, might also develop in future to exercise a competitive constraint on Oracle in a sufficient and timely manner. Given the specificities of the open source software industry, the Commission also took into account Oracle’s public announcement of 14 December 2009 of a series of pledges to customers, users and developers of MySQL concerning issues such as the continued release of future versions of MySQL under the GPL (General Public Licence) open source licence. Oracle has already taken action to implement some of its pledges by making binding offers to third parties who currently have a licensing contract for MySQL with Sun to amend contracts. This is likely to allow third parties to continue to develop storage engines to be integrated with MySQL and to extend the functionality of MySQL.
“I am now satisfied that competition and innovation will be preserved on all the markets concerned,” competition commissioner Neelie Kroes said. “Oracle’s acquisition of Sun has the potential to revitalise important assets and create new and innovative products.”
Some stories we’ve done on the deal:
Red Hat has confirmed that its Red Hat Enterprise Linux (RHEL) operating system version 6 will not be supported on the IntelItanium processor.
The news, broken by The Register shortly before Christmas, presents another chip in the statue that is the EPIC processor. According to the story, Red Hat’s official statement on the matter, according to the story:
Red Hat is committed to protecting Itanium customers’ investments and to providing these customers with enterprise class support for Red Hat Enterprise Linux 5 through March 2014. During this period, Red Hat will provide support, deliver new features, and enable new Itanium hardware in Red Hat Enterprise Linux 5 exclusively in accordance with the published RHEL product lifecycle (http://www.redhat.com/security/updates/errata/). In addition, extended support for Red Hat Enterprise Linux 5 for Itanium is available up to March 2017 from selected OEMs.
The next major release of Red Hat Enterprise Linux (v6) will not provide support for the Itanium architecture; consequently, all Itanium related development will be incorporated into Red Hat Enterprise Linux 5 exclusively.
Although this is certainly not good news for Itanium, it seems as though it presents just another sign of the platform’s slow decline. HP-UX and Windows are the dominant operating systems on Itanium. I don’t know the breakdown of operating systems on Itanium (if you do know, please tell me), but my educated guess is that Linux on Itanium is used mainly in governmental and academic installations.
It should be noted that as far as I know, Novell has not dropped support for Itanium yet, so there is still a viable Linux distro available on that platform. At least for now.
Nevertheless, news like this tends to lead to some hand-wringing and contemplation of Itanium’s initial promise of essentially taking over the chip market. That promise is long gone, and Intel has long since abandoned that claim. Intel, Itanium’s major OEM Hewlett-Packard, and just about everybody on the planet who knows about Itanium, knows that it has found its market in high-end applications and no longer plans on taking over the world. It will most likely continue to decline slowly, with little to no new customers except for those migrating over from old HP PA-RISC architectures.