Slashdot Mirror
Intel Reveals Itanium 2 Glitch
NeoChichiri writes "News.com is running on an article about glitches in Intel's Itanium 2 chips. Even though it doesn't affect all chips, they have still stopped shipments of the new 450 Servers until the problem is resolved. Apparently it has to be 'a specific set of operations in a specific sequence with specific data.' Intel is saying that affects the 900MHz and 1 GHz Itanium 2 chips and that it will not affect the upcoming 1.5 GHz Itanium 2 6M chips." Until the next iteration of chip arrives though, Oliver Wendell Jones writes, "they recommend working around the problem by underclocking the processor to run at 800 MHz instead of its default 900 MHz or 1 GHz."
Because software is a fuckload easier to fix - free downloadable patches, etc.
With hardware like a proccessor, you'd most likely have to actually replace the part that's broken.
I agree that software companies should be held to a higher standard, but they can get away with it because the bugs are easier to fix.
I belong to the ______ generation.
I have to agree with your side note. I make the technology decisions here at my company and have a strict belief when it comes to upgrading. Microsoft OS's I refuse to deploy on our systems until SP1 is released (because we all know its coming sooner or later). We just last month upgraded to Windows XP.
I suppose the same argument can be applied to everything in life. Cars, Televisions, DVD players.. you name it. You just need to get a feel for how things age before you invest in them for long term.
It's called managing expectations, and no one excells at the black art more than Microsoft.
Everyone expected WinXP to be crap, and they were so relieved that it wasn't as bad as they thought they forgot to complain about the problems that do exist, as evidenced by the number of people who say "WinXP is great, compared to Win98 it's very stable and pretty fast, even though I did have to buy a new PC to run it, but that's just progress, isn't it?" when you ask them what they think of it.
Beep beep.
I readily agree. as a software person, it boggles my mind that the hardware doesn't fail hourly. If Microsoft (or Oracle or any software company) were held to the same standards as Intel/AMD, etc, they wouldn't exist. Intel and CPU companies have been work against the immutable laws of physics, whereas software companies only have to manage their own incompetence and beat back their business departments, IMO.
The big problem is when something fails SILENTLY! That's what the BSOD and the Kernel oopsies are! If the system has corrupt data, it is very very bad, worse than losing data. So if the hardware has a bug, then it will pass corrupt data around, and then things fail.....google around for what happens with bad ram, and learn about HAppy Fun Bugs!
Fellowship 9/11
While I do understand your sympathy towards hardware manufacturers, there is one obvious difference between accepting software and hardware bugs. The software bug can be fixed with a patch. The $200 software now works; we can accept that. When the CPU is buggy, the only way that gets corrected is if the manufacturer is willing to replace the CPU. BIG difference.
I agree completely that software products should be set to a higher standard. But we haven't seen integrity in the industry, so all that's left to fix the problem would be to sic the lawyers at them. I don't see that as fixing the problem...
There is no America. There is no democracy. There is only IBM and AT&T and DuPont, Dow, General Electric, and Exxon
...that's why Itanium is not yet in the mass-market. Regardless of the flaws. It's also why my first 64-bit CPU is likely to be an AMD.
I mean, come on. I want 64-bit a lot. An awful lot. I even wanted a redesigned instruction set - something I was please to see Intel had the balls to do with Itanium. The old IA-32 has a lot of baggage and bad design choices. But for crying out loud - $7000 for a single chip?
I kid you not about the $7000 price tag for a single CPU - Itanium 2 is literally 10 times more expensive than AMD's 64-bit Opteron.
This is why, as a life-long fan of Intel, am planning on defecting to AMD with my next machine purchase. To anyone else buying a new machine in the next 6 months: it makes absolutely no sense to get a 32-bit system when vastly more capable and future-proof 64-bit ones can be had for almost the same price as the old 32-bit ones.
This time next year, I reckon that Intel will be steadily loosing market share to new system purchases because of their exhorbitant prices and their complete failure to provide a capable 64-bit platform in the same price range as AMD. Intel haven't even announced a consumer 64-bit chip. AMD's announced six - 2 Opterons, 4 Athlon 64's).
I'm desperately hoping that AMD and Microsoft's marketing machines ramp up to push 64-bit - the sooner the better to punish Intel for not being more pro-active in the marketplace.
>>Unfortunatly this testing can not be done untill there are enough units to test
>>AMD has not had this sort of problem resently
Does that mean they're jealous of Intel's problems and resent not having them?
>>The posts I've read so far, remind me of what a class of 10 year olds would right in criticing
Wow. With your mad spelling and grammar skills you ought to know exactly what 10 year olds are capable of.
But seriously though, Intel sells these chips to a completely different market than AMD. The customers here demand a box that never falls over. IBM and others test like crazy to make sure this stuff doesn't happen with their big chips. You have to remember that these aren't $800 clones here -- rather, big tin -- 6 figure kind of stuff.
Oh, and when has it been customary to give credit to companies for making mistakes? It's like everything else, you have to earn trust. Intel's trying to get into the lucrative big tin market and need to earn the trust of people. So far they're not handling this one well... I'd be super ticked if I had to take down my machines (the ones that I was under the assumption would give me 99.999% uptime) so that I could underclock them to 800MHz. I do supercomputing work and I expect the machines to just run. That's what I paid all that money for, right?
Are you kidding me! If I paid for a server
with a 900 Mhz or 1 Ghz processor, and the
company that produced the processor said that
I had to underclock the chip for it to work
properly I'd ask for a refund. And it one
wasn't forthcoming...
You really are a troll, tonight!
Please read "Sun suffers UltraSparc II cache crash headache [theregister.co.uk]"
This was a problem with the cache RAM and not the CPU itself. It was traced to a supplier (IBM), who was selling a defective product.
In terms of reliability, the Itanium II is no worse than the UltraSPARC series of chips.
There is no data to back this up. I know you don't have it, and I certainly don't have it. The only people who really have it (Intel and Sun) probably won't give it to us, so this ends here.
However, since so many people pay attention to the flaws in Intel chips, they are likely to have less bugs than other chips.
This is not true. Intel is pressured by a time-to-market more than other suppliers, especially with respect to the Pentium line. Sun has obviously decided to delay product launches to work out issues (e.g., UltraSPARC IIIi), because their customers expect reliability over other concerns. Hardware doesn't really follow the "all bugs are shallow" mantra of the Open Source movement, we mainly have to have faith in the manufacturer's simulation and test labs.
In any event, the performance of the Itanium II is at least 1 order of magnitude greater than the UltraSPARC III and (soon) IV.
Do you even know what "order of magnitude" means? You are claiming that, if the UltraSPARC III scores 975 on something that the Itanium II would score 9750??? For a given clock, it is true that the Itanium II is faster than the US III, but by a fraction--not a factor of ten!
Also, the US IV, by definition, will be almost twice as fast as the US III for throughput, because it is two US III chips in one.
You really don't know what the facts are.
Vote in November. You won't regret it.
Don't count on IBM abandoning their RISC chips yet, They power some of IBM's most profitable hardware (AS/400 and RS/6000) platforms.
PHP is the solution of choice for relaying mysql errors to web users.