Intel and HP Commit $10 billion to Boost Itanium 272
YesSir writes "Support for the high-end processor that has had difficulties catching on is coming in from its co-developers Intel and HP. 'The 10 billion investment is a statement that we want to accelerate as a unified body' said Tom Kilroy, general manager of Intel’s digital enterprise group."
Last Gasp for Big Iron? (Score:5, Insightful)
So as I'm reading this there's a big plug for AMD Opteron just below the article. This would appear to me to be the threat to the Itanium, the same which effectively has killed big iron -- inexpensive commodity hardware. Sink a few thousand into Opteron systems and run what you already have, or sink far larger amounts into some gobble-de-gook system which won't run, except under software emulation, what your multiprocessor system does. Sorry HP/Intel and everyone else dumping money down this rabbit hole, I think you've lost the plot. Today's super computers are parallel computing down with 64bit Gen x86 processors, like the AMD Opteron. The glue is in the software, not in big fat chunks of expensive silicon.
if still not convinced, i might have a few meg of core to sell you
tisk tisk (Score:5, Insightful)
Re:Why? (Score:2, Insightful)
Re:Last Gasp for Big Iron? (Score:4, Insightful)
Here is the problem (Score:5, Insightful)
Short Intel now (Score:5, Insightful)
Uhh, it could hardly lose share could it? If it lost any share the product wouldn't exist. What, did they double their share from 1 to 2 users?
Ten billion is an awful lot to throw away on this loser chip.
I mean, few people actually WANT to run a different chip (and thus a different OS and versions of apps) in their data centre, compared to their desktops. They used to do it, because it was necessary. Now it isn't necessary, so people don't want to do it. Intel's only hope is to try and get people to use it EVERYWHERE, on their desktops too. But there aint no hope of that either.
The point is? (Score:3, Insightful)
Let me get this straight (Score:5, Insightful)
Re:Last Gasp for Big Iron? (Score:2, Insightful)
What Intel and HP need to do is admit that the chip is a waste and just let it die, like dumpy the waste man from Drawn Togehter you can hear the Itanium say "KILL ME"
Re:Itanium vs. Ultrasparc T1 (Score:2, Insightful)
The UltraSPARC T1, if Sun can market it well, is the ultimate webserver, database server, and J2EE CPU. I'm extremely interested to see how many T1 servers Sun sells.
Re:Last Gasp for Big Iron? (Score:4, Insightful)
Itanium isn't dead yet (Score:3, Insightful)
It seems the finally found the market:
Last week Intel went back on x86 compatibility, only software emulation [com.com]. Makes sense, the market for Itanium is big iron. It is way to expensive for anything less. And the users better run 64-bit Itanium optimized code to get their money's worth.
Microsoft trashed all Itanium plans for the small and mid segment. They will support Itanium only where it makes sense in their product line, just Windows Server,
Intel's Motherboards supporting both Xeon and Itanium have now been postponed to 2009. This makes sense too, Itanium customers won't be interested in saving a few thousand bucks on commodity motherboards.
And finally 10 billion $ pumped in; good news. I'd think Itanium will be back, by 2008. Architecturally, it is nothing to laugh at atleast. It is just that it lacked everything else, platform-compiler-apps support.
$10 billion? I don't think so (Score:3, Insightful)
Assuming that each Itanium chip retails for roughly $1,000, Intel/HP could simply give away 10,000,000 chips for the investment they're making. Do they really think that there will be enough demand for these chips between now and 2010 to make up for that kind of marketing expense?
I have a hard time believing they will actually spend anything near this amount on marketing, even if the campaign is successful.
Re:Last Gasp for Big Iron? (Score:2, Insightful)
Clusters are only really good for embarassingly parallel problems. The interconnects just can't be as fast as a local bus.
How's this for an alternative: "Commodity Big Iron"?
Why can't a supercomputer be based largely on off-the-shelf CPUs, RAM, Drives, etc.? I know important pieces are missing, but it should be possible to open this stuff up, and have it become a commodity.
Re:I hope this works. (Score:2, Insightful)
ad 1: Compilers can improve easily, with a recompile. this remark I consider extremely naive and it really, really hurts your credibility. The fact that a compiler can be recompiled does not mean it also automatically improves its logic. The problem with all the compilers for Itanium is in the logic, not in the execution. Recompiling the compiler without improving the logic might give you a faster compiler, certainly not a better one.
In order to improve compilers for Itanium the prefetch and scheduling logic in the compilers and assemblers needs to be vastly improved. Especially optimization for data-dependent branches requires a lot of additional work.
ad.2
A
B huh? Are you mixing up RISC and VLIW (EPIC) designs?
ad.3 The only reason Itanium has good SPEC performance is because the benchmark is completely deterministic in its execution. Itanium greatly (like: insanely) benefits from repeated compile-execute-profile iterations of the benchmark. Real world performance doesn't come close. Only numerical codes with very well understood branches can hope to approach those SPEC rates.
ad.4 I suggest the following literature first: Hennesey and Patterson, Computer Architecture (Morgan Kaufmann); Patterson and Hennesey, Computer Organization and Design (Morgan Kaufmann); Sima and Fountain and Kacsuk, Advanced Computer Architectures (Addison Wesley); Lilja, Measuring computer performance (cambridge); Jain, the art of computer systems performance analysis (wiley)
$10 billion all itanic chips ever sold?? (Score:3, Insightful)
Re:Here is the problem (Score:3, Insightful)
What they want you to know now is that Itanium is not, repeat not a competitor for Xeon, Opteron, or the x86 architecture. Itanium's market is in high-end "mission critical computing" and as a replacement for RISC chips (meaning Power and Sparc).
Where once they pushed the 64-bitness of the chip, the x64 extensions have muddied the waters somewhat, so they're not really talking about that anymore. What they are selling are the high-availability features that make Itanium competitive with the aforementioned RISC chips.
The advantage they are touting vs. the competition is openness. If you want a Sparc system you have to go to Sun, and you have to choose from the Sparc systems that Sun offers and the support packages that Sun offers (or maybe Fujitsu, just to blur the point a little bit). With Itanium you have several suppliers -- including Fujitsu, HP, Hitachi, SGI, Unisys, and the other companies in the Itanium Solutions Alliance. Each of those is free to provide its own support packages and terms of service. You also have a few choices of operating systems, including Windows, Linux, and HP/UX, while the only OS that currently runs on Sparc is Solaris.
Believe it or not, it's actually not that bad of a product story. Sooner or later, everybody who's on RISC chips right now is going to want to upgrade their hardware. If they're dead set against the x86 platform then they have three options. One option is to buy the latest version of whatever they're already using. A second option is to jump ship -- Sparc to Power or vice versa. Itanium gives them a third option, with the backing of Intel and a bunch of other prominent hardware vendors.
And then there's always the other, more established Itanium market: running great big SQL Server databases. Believe it or not, there's a fair amount of people who want to do that.
Re:AMD64 (Score:3, Insightful)
I don't see the point of writing a super-compiler that can schedule C code at compile time, when processors can do that just fine at runtime. I think its far more interesting to focus on writing super-compilers that can make high-level languages perform better.
Re:Why? (Score:1, Insightful)
Huh?, IA64 is a new architecture.
It is good that the x86 hardware unit is out of the die now.
It has hampered the design and speed of the CPU.
Aw, jeez... (Score:4, Insightful)
AMD is starting to kick Intel's pants in the most lucrative arena, small- and medium-sized servers. Instead of trying to compete technologically in that area (as opposed to just marketing), they're throwing good money after bad into a failing/failed architecture which only makes sense for a few highly-specialized applications. If it weren't for the fact that most holders of Intel stock know next to nothing about the industry, I would expect a cry for a change of leadership.
Sure, there are a few supercomputing-type applications where the Itanium really, really shines - but they're sufficienty specialized that Intel just doesn't move a very large number of CPUs.
Like I've said before, Intel is in a bind because of its own laziness and arrogance. Look at one of the primary advantages of the A64/Opteron architecture - the on-die memory controller. More memory bandwidth, lower latencies, and a memory subsystem that scales with the number of CPUs. Big-iron vendors proved that technology long before AMD decided to use it. Yet Intel has always enjoyed the superior manufacturing side of the business - if *anyone* could afford to have put those extra transistors on the die, it was Intel. Since they're almost always a step ahead of AMD in making smaller transistors, they had the *ability* to do something along those lines long before AMD did - but relied on the old tradition of more megahertz and lots of marketing. I don't think that this move is much different, they're putting their efforts in the wrong direction.
steve
Re:Last Gasp for Big Iron? (Score:5, Insightful)
You are overall sort of right about that. It's just science isn't standing still and most of new algorithms are specifically invented to be parallelized.
Most problems of physics are solved with matrices. And matrices are of course are easy to parallelize. And physics - is the only who are buying most of big iron anyway.
Nowadays, most of the weather prediction tasks, astronomical tasks, optical tasks, micromeasurements tasks are also optimzed for clusters - not big iron. It's not about top performace - it's about price/performance ratio. For the same money people can buy cluster with e.g. 10 times more raw performance to run unoptimal (e.g. 2-3 times slower) algorithms - but task are done quicker. And cheaper. Yeah, clusters have higher latencies - but they are still dominated by batch jobs, not interactive jobs. Big Iron has better interconnects - but the redundant interconnects take lion share of such system costs.
In fact, the main reason why this have happened (clusters took over big iron) is the RAM prices. In my versity times (early-mid 90s), we all were occupied with shared memory problem: RAM was very expensive. Now people go to general store, pick several 1GB nics, pick several GBs of RAM, and pay a nickel for all that.
Ask anyone in Computer Science now, everyone started throwing RAM at latency problems of clusters. It does look bad on paper and in theory. But in practice it just works.
P.S. On-topic. IA-64 has great performance. But again, on price/performance scale it loses immediately to Intel's own Xeons and AMD's Opterons. Intel constantly refuses to amend its Itanic focus from features to focus on more affordable prices. The story line was quite well covered by The Register. Check posted links.
Re:Itanium vs. Ultrasparc T1 (Score:3, Insightful)
people dont buy it (Score:2, Insightful)
Itanium is a great processor (Score:4, Insightful)
The first problem is one of marketing. HP/Compaq is a screwed-up company, the merger of two wholy incompatible companies that could never work together properly. Put this together with the fact that they canceled Alpha, another great processor, and you can see that selling Itanium is more about politics than engineering. The next problem is pricing. For a single-chip solution, Itanium is awesome, if you don't count the fact that you could buy multiple Opterons for that price and achieve more performance with properly threaded code.
There are, of course, technical problems. Itanium is a heat monster. They didn't design it with power consumption and heat dissipation in mind. Did you know that the Itanium's top speed isn't limited by wire delays like it is in most other chips? No. It could actually run a lot faster, were it not for the fact that they can't get the heat off the chip fast enough. Another problem is the compilers. Static scheduling has its limitations, but the real limitation is that Itanium compilers can't manage to do even decent scheduling. It's too complicated. Much of Itanium's performance is theoretical. Given a small piece of C code, you can recode it in assembly and get it to run 10 times faster. If only the compilers were as smart as the assembly coder.
Itanium was a great idea. It's just being executed poorly, and the R&D is being put into the wrong place. The architecture is there. It's great. Now, get the price down, design it for lower heat dissipation, and get some people working on that damn compiler!
My guess on direction (Score:3, Insightful)
Re:Last Gasp for Big Iron? (Score:3, Insightful)