Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

Summary: Oracle has decided to stop developing software for Intel's Itanium chip because it thinks the processor is "nearing the end of its life." Hewlett-Packard screams and Intel reiterates support for the Itanium. Here's what it all means.

SHARE:

Oracle has decided to stop developing software for Intel's Itanium chip because it thinks the processor is "nearing the end of its life." Hewlett-Packard screams and Intel reiterates support for the Itanium.

Intel's Itanium chip has never been the cool kid on the block. It was launched with a lot of hubbub years ago as a way for Hewlett-Packard Unix to upend IBM mainframes.

Let's use our trusty decoder ring to figure out what's going on.

Oracle says:

Intel management made it clear that their strategic focus is on their x86 microprocessor and that Itanium was nearing the end of its life.

Both Microsoft and Red Hat have already stopped developing software for Itanium. HP CEO Leo Apotheker made no mention of Itanium in his long and detailed presentation on the future strategic direction of HP.

What it means: Look folks, Itanium is targeted at the Unix market, which kind of stinks right now relative to the growth Linux and Windows Server. We have our own flavor of Unix called Solaris that we want to push (on our own chips by the way). This isn't Baskin & Robbins!

Oracle says:

After multiple conversations with Intel senior management Oracle has decided to discontinue all software development on the Intel Itanium microprocessor.

What it means: If you project out a few years, we see no future in the Itanium chip. OK, we read between the lines on an Intel briefing, but we're calling our shot now.

HP says:

HP today reiterated that it will continue the development and innovation of Itanium-based Integrity server platforms with its HP-UX operating system using a roadmap that extends more than 10 years.

What it means: Damn Oracle sucks at coopetition. They're trying to kill HP-UX.

HP says:

HP will continue to support customers running existing versions of Oracle software on Itanium-based Integrity servers, both existing and future platforms, during the same timeframe. Last year, HP launched the industry’s most modern mission-critical architecture in more than a decade. This constitutes the longest published roadmap of any UNIX vendor in the industry.

What it means: Has anyone asked Oracle about Sun's roadmap? Go ahead, we dare you.

HP says:

HP moved ahead into second position in the UNIX market while Sun lost share and fell back into third since Oracle announced it would acquire Sun in April of 2009. It is clear that Oracle customers are voting with their purchasing decisions against the Sun platform. This latest Oracle action of disinformation is clearly an attempt to force customers into purchasing Sun servers in a desperate move to slow their declining market share.

What it means: Oracle is trying to sell its stack. Don't fall for it kids. Email Oracle gcp-customerfeedback_us@oracle.com so the company can ignore you.

Intel says:

As a result of recent announcements from Oracle, Intel is taking this opportunity to directly reiterate its plans for the Itanium processor.  “Intel’s work on Intel Itanium processors and platforms continues unabated with multiple generations of chips currently in development and on schedule,” said Paul Otellini, president and CEO of Intel Corporation “We remain firmly committed to delivering a competitive, multi-generational roadmap for HP-UX and other operating system customers that run the Itanium architecture.”

What it means: Well we want to sell you more chips. We don't care if they are called Itanium, Xeon or Potato chips.

Topics: Oracle, Hardware, Hewlett-Packard, Intel, Processors

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

Talkback

53 comments
Log in or register to join the discussion
  • RE: Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

    Itanic has been a disaster from the day it shipped. Great for a few applications but highly limited. Hopefully this will help kill it off.
    oldsysprog
    • That is like saying the Space Shuttle has been a disaster!

      @oldsysprog
      It takes specialized hardware to handle certain tasks. That does not make it a disaster!
      kd5auq
      • RE: Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

        @kd5auq Yeah, the Shuttle has experienced 2 disasters, Challenger and Columbia, and there are 2 more chances for disaster. While it has accomplished its mission to lift heavy equipment to build a space station, its time has come and gone. It's time to retire the remaining fleet.
        mschafer555
      • RE: Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

        @kd5auq, besides killing over a dozen people with its flaws, the promised cost of under a half a billion per launch it instead turned out to be $1.3B over life of program. Yes, the Itanic is like the shuttle.
        admail@...
    • true

      @oldsysprog

      copied form the wikipedia

      "The first Itanium processor, codenamed Merced, was released in 2001. Although its speed would have been impressive had it been introduced on time in 1999, it ran only half as fast as the contemporary x86-based Pentium 4.[1]"
      magallanes
      • RE: Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

        @magallanes Once again we encounter what is presumably a Gen X'er who has no clue about total throughput numbers. Clock speed is only one indicator of performance, and has absolutely no bearing on total throughput, HA, DR, multi-threading, multi-pathing for I/O, ECC for all memory systems, redundancy, etc., etc., etc., nor the stability of any particular application by OS and platform comparisons. If X86 could viably run the world, it would already be doing so. 30 years of X86, and yet Unix and Z systems still abound. Hmmmm.....maybe the folks making decisions to continue down the Unix or Z path know something you and many of your colleagues don't. Next time you are standing at your ATM waiting for cash, or better yet, next time you need to dial 911, be glad they understand some things that you clearly don't.
        ShesAllOverIT
    • RE: Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

      @oldsysprog is an Oracle tool
      dixonrf
    • RE: Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

      @oldsysprog, I kind of agree. I remember getting our first Itanium units. They ran so hot we didn't dare stack them on top of each other even though they were rack mounts. I'm sure the extra cooling costs and electricity running the loud fans has really surpassed the much cooler running x86 & pa-risc processors as far as costs of operating them. Newer Itaniums are better but at least for the Windows world one has to wonder why you'd bother with an Itanium. For HP-UX that's a different matter.<br><br>As for Oracle I hate the way they're ruining Sun. Sun was slowly doing that themselves but the pace has quickened. They expect expensive service contracts for everything, and their partner program makes it difficult even for developers and partners. Try downloading a video driver for a 6 year old Sun x86 box (ultra 20). They expect you to buy a service contract. Goodbye Sun. I liked you at one time. Not to mention that things that were once free are all gone. "guess what, you were able to download security updates for your 5 year old server yesterday, but now you have to buy an expensive hardware service contract to get em - for every machine". No thanks, we'll just buy x86 based systems and run Linux or Windows on them. It'll be much cheaper and a whole lot less hassle.
      SMparky
  • Funny decoder ring :)

    Thanks for the translation! I think the Itanium is / was a great chip, but no one really needs it. PowerPC, UltraSparc dominate the RISC side and X86 dominates the CISC side. The DEC Alpha was also a great chip. Had the Itanium done a decent job of running x86 then it might have been a compelling platform...
    DevGuy_z
    • RE: Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

      @DevGuy_z

      Actually Power dominates the RISC side. SPARC is just dead. The computing power of SPARC even with SPARC VII+ is about 20% of the computing power from IBM's POWER chip and at the same price. Can you believe this??? The UNIX servers are going away, let's face it. Looking at the data from 2002 when UNIX had 10% shipments to 2009 when they had 3.5% of shipments is a clear trend. This data comes from Gartner by the way. x86/x64 is the only platform with viability.
      mikies
      • RE: Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

        @mikies LOL.

        I believe you're a bit behind the curve. Take a look at the T1, T2, T3 and T3 plus processors. They are far superior than anything Intel can muster and probably won't ever catch up, since Sun has been doing multi-core way before Intel did. Sun invented multi-core, and have always had the superior processors. They just sucked at marketing it. I would say 16 cores by 8 threads per core would out perform any Intel processor. Just thought you might need to know.
        rpollard@...
      • RE: Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

        @mikies actually if you look at the numbers and disregard speed I think ARM dominates the RISC market. It seems that nearly every low power unit is built with ARM these days, at least the ones that are not tied to Intel in some way.
        balsover
      • RE: Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

        @mikies
        I suggest you catch up on SPARC cpus, they are the worlds fastest on some aspects, didnt you knew? For instance, TPC-C with a score of 30 million tmpc - the world record is done using SPARCs. POWER has no chance here, POWER does not scale. IBMs largest Unix P795 server has 32 cpus, IBMs largest Mainframe has 24 cpus. That is clear proof of scaling problems. Recently, IBM had to rewrite AIX to get it to handle P795. AIX could not handle as few as 256 threads on the P795 without a major rewrite. IBM's main commodity servers have never scaled well.

        There are other benchmarks where the Niagara T3 is the worlds fastest, crushing the POWER7 as well. Just read the wikipedia article if you want to see them benches.
        Orvar
    • RE: Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

      rpollard@...
      No rpollard, the Ultrasparc platform is even deader than Itanium and mikies was talking about Power not Itanium... Sun/Oracle is down to 5.9% of the hardware server market...
      Having a more powerful processor isn't worth a hill of beans, if your utilization rates suck because you aren't virtualizing workloads on the same machine in separate images.

      The question is WHEN will IBM Power start their decline. Power systems showed a VERY modest increase, over the last year, but overall the traditional UNIX systems have gone down the toilet in the last 4-5 years as a whole in terms of server market share and both Itanium and Sparc have been losing major shares.
      So while HP and Sun try and quibble over the shrinking pie... IBM has been planning their strategy out for several years down the road.
      scotth_z
      • RE: Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

        @scotth_z
        Of course Oracles Unix market share declined in the turmoil of bying Sun. Now the trend will reverse big time. Sun had 35.000 customers. Oracle has 350.000 customers. Oracle will make sure they switch to Solaris, but it takes time. You can not expect Oracle to turn the ship in half a year or so. But wait and see.

        Earlier there was only technical advantages to use Solaris, but Larry will make sure there are business advantages as well to use Solaris. :o)
        Orvar
    • RE: Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

      @DevGuy_z
      True that! I agree. (Was a fan of Alpha, the greatest of all ;).
      mousebooster
  • RE: Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

    VIVA PERON!!
    sfberli
  • It coulda been different

    This is another example of how the Wintel platform has become a boat anchor, stifling innovation. IBM and Apple tried to escape the x86 orbit with the PowerPC chip, Acorn tried to escape with the ARM design (they may still get the last laugh) and Intel intended the Itanium to replace x86.

    Instead here we are in 2010 still running Windows on 386's.
    Robert Hahn
    • RE: Time for the decoder ring: Oracle ends Itanium support, ruckus ensues

      @Robert Hahn
      How has it stifled innovation? All of the "cool" and "innovative" that you hear about nowadays are iPhone/iPad and Android phones/tablets -- both ARM based and neither Windows.
      PB_z
    • A good thing to remember, Mr. Hahm

      @Robert Hahn
      If you are unsure of the subject matter being discussed, then ask questions and learn, do not comment as though you know.
      :|
      Tim Cook