Itanium's future: Users believe Intel, not Oracle Who do you believe? Oracle, when it says that Intel will eventually replace the Itanium processor with Xeons, or Intel and its Itanium co-developer HP, when they say there are two more generations of Itaniums coming, and that those processors will be supported for at least a decade. There isn't a lot of consensus on this issue …
Oy, Morgan! Numerical information like this would benefit from piecharts (may be tricky) or tables (shouldn't be *that* tricky for the modern journalist), perhaps with fewer sentences. Carry on like this and I'll cancel my subscription.
There is another slight flaw too; asking existing HP/UX purchasers whether they trust HP/Intel is about as sensible as asking existing Apple purchasers whether Apple kit is overpriced, the audience has largely already made their view clear by making purchases based on HP/UX or Apple.
graphics, graphics, me young whippersnapper !! Back to the VT100 for you, with green screen settings only. Since when did we techies need pitchers to see the information ? Bah, windows, Macs and GUIs, ruined good computing science, ruined I tell you.
As for the rest of your comments, dear boy, let me illuminate your darkness.
it is not only cold out there, but there is not much moola, money, bread or cash. Got it ? Organisations are now considering what will just work. This includes the re-invention of the bureau service, commonly referred to a "cloud computing" Even in big enterprises, moving off previous platforms is happening. Granted moves are slow and quiet. As soon as the CEO smells bonuses for a money saving (at least on the power point slides) platform changes start.
As an Apple purchaser I'm fully aware that the kit is overpriced, though not nearly as much as an Oracle purchaser that Oracle kit is even more overpriced. Support is crippling.
Realistically though I think Itanium has about as much life left in it as Sparc has, just a race to see which one disappears first.
cant help but suspect the plan is eventually to combine the two CPU lines.
Already share common controllers on backplanes. Xeons are becoming serious heavy hardware CPUs. Still got a way to go the beat Power 6 and 7, but Intel, somewhat prodded by AMD, are making better chips over the years.
Simple economics would indicate Intel want to simplify their chip fabrication lines to get scaling economies. Still, I miss the old pa-risc chips. Crap floating point, but reliable and very good business performance and low clock rates, so cool to run in the compute room/data center. Good firmware in the backplane also.
Whether buyers trust Intel or Oracle is besides the point - the total cost of switching hardware is often less than the cost of switching software, particularly for non-trivial applications or anything with tight database integration. Even if Intel keeps producing and supporting Itanium, it won't matter to Oracle customers running on it...a great many will still switch hardware to keep up with Oracle releases, especially as packaged software running against it requires releases x.y of Oracle.
Last time I checked, the OpenVMS roadmap ended somewhere in 2528 since the Pentagon is considered an... uhm... key account? Since all VMS programmers are either dead, retired or sent to train their replacements in India, HP won't port OpenVMS to another platform, ergo, Itanium will be around longer that you would expect.
manufacturers are very optimistic, but i don't think we will be able to go under 16nm until 2040-2050.
So after we will get stuck for decades at 16nm, the only possible way to increase performance will be the massive parallelism, using as many cores as possible. This will require chips with low transistor count, like VLIW. So this could give some hope for Itanium.
With the Itanium and POWER increasing the performance of their cores over the years, increasing the cost of the licensing by core was a fair thing to do, to place CPU architectures on a common footing.
With the SPARC cores being slow (but highly paralleled, providing for competitive socket throughput), it had made sense for a long time to decrease the pricing per-core, but Oracle was more interested in short term profits, at the time, and less interested in the health of that architecture.
Oracle disjoint pricing was a primary driver for people departing from SPARC, before Oracle made the jump to buy a SPARC vendor (i.e. Sun.)
The question remains: will Oracle apply unfair price constraints on other CPU architecture vendors, the way they bloodied Sun by overpricing SPARC licensing, before buying Sun out?
It could be that Itanium will continue for 10 years or more, as a niche market chip. The million dollar question is: Where will HPUX go? It is clear that PA-RISC won't be re-awakened. Itanium cores still won't compete well with x64 Xeon cores, let alone Power 8 (or whatever) cores.
If Oracle dropped Itanium to drive business towards its own Niagara chips, that doesn't seems like a high percentage play. Niagara is fine for easily parallelize-able workloads. It just has some hideous performance for key-task workloads. If Oracle can truly overcome this problem, perhaps Niagara has a future. If not, Larry E is driving business toward x64 and Power.
Oracle has to be careful with cutting off Power. IBM has some database products that can be used with SAP and other key applications. Oracle could find itself losing some sales to some very large companies.
I don't even own a single Intel or x86 CPU but I know their roadmaps have always been trustable.
On the other hand, Oracle does a real spoiled thing. Itanium isn't really some quantum chip or anything. Anything can compile for any CPU. I really don't believe they are doing mad things like pure/unportable ASM or anything. Even if they do, Intel has some huge documentation and huge help to any compiler, from open to closed. They aren't some startup.
You've not watched the Itanium roadmaps then. While Sun canceled a couple of chips, so did Intel with Itanium! Intel has not been within a year of their timelines with any Itanium chip yet... Honest? maybe... Accurate? Absolutely not. If you want details, just do a search on Itanium or Itanic on theregister.
Back when Itanic was being actively backed by Intel and major software vendors, its notoriety as triumph of marketing over CPU design for the sole purpose of bringing the general purpose CPU market under Intel monopoly was pointed out and rightly criticized by all major tech sites, el Reg included.
Then, one company after another stopped supporting it, including Microsoft and Red Hat, and Intel was ostensibly lukewarm towards continued development of Itanium, but all remained fine and well, and attacks on Itanic continued.
Now, when Oracle finally jumped the gun and announced termination of development for Itanic, everyone is suddenly rushing to Itanium's defense (and to bashing Oracle)? Come on! I know that the general attitude of most sites is that Oracle is greater evil than even Microsoft, not to mention hp or Intel (which, bafflingly, is still presented in good light despite the uncovered monopolistic practices), but its gotten ridiculous at this point. Microsoft or Red Hat were never subjected to a fraction of the criticism that's being leveled at Oracle.
Itanium was never a good chip, plain and simple. Intel suggested an ambivalent attitude towards it in the recent years and I can hardly believe it will retain any edge over x86, much less any significant edge. Coupled with dwindling market share, this was expected. But to defend Itanium all of a sudden? I'm baffled.
We really need an angelic/demonic Larry icon...
IBM still holds Itanium as viable for DB2 deployment (potential migration for existing Oracle customers):
http://www-01.ibm.com/software/data/db2/lowerdatabasecosts/
Also, realize that to migrate all Tandem users (e.g. pretty much all of the banking industry) off to a different platform is difficult. Not saying it's impossible, but I would think that would mean the Itanium stays around for some time.
"to migrate all Tandem users (e.g. pretty much all of the banking industry) off to a different platform is difficult. "
Been done several times already. If the system behaves the same way, in particular the software behaves the same way, who cares if it's IA64 Inside or some more marketable alternative.
"IBM still holds Itanium as viable for DB2 deployment"
All other things being equal, would IBM prefer to deploy DB2 on IA64 (on which OS?) or on x86-64 (on any OS they fancy?)?
It's the software that matters (for most of the market, anyway).
The Register 
Biting the hand that feeds IT
Copyright. All rights reserved © 1998–2024
