User Name
Password
AppleNova Forums » Apple Products »

64 errors in Core D/S - come again ?


Register Members List Calendar Search FAQ Posting Guidelines
64 errors in Core D/S - come again ?
Thread Tools
m4hl3r
Member
 
Join Date: Jan 2006
 
2006-01-25, 11:10

I've just read, that's there's a estimate of 34 errors on the new Core Duo - Solo chip form Intel.

"Releasing a brand new processor with 34 known errors seems almost criminal to me, especially..." - said RickGeek on January 23th.

Link to Geek.com

http://geek.com/news/geeknews/2006Ja...0123034350.htm

I've read it at www.geek.com, but is that reliable source - anyone?

Even though they might be easy to fix, I'm glad that I decided not to buy a MacBook Pro - .. yet.

34 errors is quite a lot, that's not a "whoops, we missed that one."
Quite a start for Intel.

Oops, wrong number in the headline - whoops, missed that one - sorry.
  quote
chucker
 
Join Date: May 2004
Location: near Bremen, Germany
Send a message via ICQ to chucker Send a message via AIM to chucker Send a message via MSN to chucker Send a message via Yahoo to chucker Send a message via Skype™ to chucker 
2006-01-25, 11:19

I'm not sure it's a lot. Can we have a comparison to other major CPUs?
  quote
m4hl3r
Member
 
Join Date: Jan 2006
 
2006-01-25, 11:26

Quote:
Originally Posted by chucker
I'm not sure it's a lot. Can we have a comparison to other major CPUs?
Dunno.. Anyone ? But again, 34 seems like a lot - to me at least.
  quote
Bryson
Rocket Surgeon
 
Join Date: Feb 2005
Location: The Canadark
 
2006-01-25, 11:32

The comparison on the site is that the Pentium 4 has been found to have 65 errors in total in the time it's been out. No idea how fast they were found, though.
  quote
spotcatbug
Veteran Member
 
Join Date: May 2004
Location: Clayton, NC
 
2006-01-25, 11:32

According to the linked article, the Pentium 4 has 65 known errata with no plans for correction. There's a comparison. At least 34 is less than 65.

[edit] Bryson beat me. Anyway, only 14 of the 34 errors are "show stoppers".

Ugh.
  quote
m4hl3r
Member
 
Join Date: Jan 2006
 
2006-01-25, 11:40

Quote:
Originally Posted by spotcatbug
According to the linked article, the Pentium 4 has 65 known errata with no plans for correction. There's a comparison. At least 34 is less than 65.
Well.. Yes, but still? Seems strange to me. The 64 (it's not 65, it's 64, just found a article - in Danish, not much help for you I guess.) errors on M wasn't serious, one 1 was. And that was fixed on the next versions. The article also says, that's it not normal there's a new prossesor without flaws. But it also says, that the 34 might create some problems for the useres , but nothing serious -

Still - I don't get it. Why release a chip with flaws, 64 and 34 is quite a lot to miss.. Not a "whoops, missed that one - again"
  quote
scratt
Veteran Member
 
Join Date: Jul 2004
Location: M-F: Thailand Weekends : F1 2010 - Various Tracks!
Send a message via Skype™ to scratt 
2006-01-25, 11:44

As people have already said... It depends on the errors.. Heck every floating point operation on a modern computer is an 'error' in real terms.

But I have read that some of these are quite fundamental flaws.

That is dissapointing.

Out of interest how do Intel chips measure against PowerPC chips in terms of errors? Not stirring (well not much), just curious...

I may yet snag one of the last 12" PowerPC PBs before they discontinue them.... Hang having a machine I can test Universal Binaries on - I want one of them 12" suckers!

'Remember, measure life by the moments that take your breath away, not by how many breaths you take'
Extreme Sports Cafe | ESC's blog | scratt's blog | @thescratt
  quote
chucker
 
Join Date: May 2004
Location: near Bremen, Germany
Send a message via ICQ to chucker Send a message via AIM to chucker Send a message via MSN to chucker Send a message via Yahoo to chucker Send a message via Skype™ to chucker 
2006-01-25, 11:45

Quote:
Originally Posted by m4hl3r
The 64 (it's not 65, it's 64, just found a article - in Danish, not much help for you I guess.) errors on M wasn't serious, one 1 was.
Pentium 4 != Pentium M

Quote:
Still - I don't get it. Why release a chip with flaws, 64 and 34 is quite a lot to miss.. Not a "whoops, missed that one - again"
Neither software nor hardware can be released without flaws. It's simply too uneconomic.
  quote
Bryson
Rocket Surgeon
 
Join Date: Feb 2005
Location: The Canadark
 
2006-01-25, 11:45

For comparison, the PPC970FX (Or G5) has 24 errors and the G4 (7447) has 36.

(God bless Google!)
  quote
m4hl3r
Member
 
Join Date: Jan 2006
 
2006-01-25, 11:48

Ok Bryson, didn't you read the reply above you ?

Was anyone of them fundamental flaws ? Or just "easy to fix flaws ?
  quote
m4hl3r
Member
 
Join Date: Jan 2006
 
2006-01-25, 11:51

Quote:
Originally Posted by chucker
Pentium 4 != Pentium M
Neither software nor hardware can be released without flaws. It's simply too uneconomic.
I agree, but 34 - 64 and so on ( all the numbers mentioned ), that seems like quite a lot.. But again, if the Macs just work, isn't that good enough ? No reports of malfunctional iMac, Acer TravelMate or whatsoever. Or have there been any ?
  quote
scratt
Veteran Member
 
Join Date: Jul 2004
Location: M-F: Thailand Weekends : F1 2010 - Various Tracks!
Send a message via Skype™ to scratt 
2006-01-25, 11:52

Read the article.. Two things stick in my mind..

Quote:
Still, the Core Duo and Core Solo processors are just out of the gates, and this high number of immediate errata should leave one a little chilled, I'd say. Releasing a brand new processor with 34 known errors seems almost criminal to me, especially with some of the more obnoxious ones highlighted above.
A few of the errors allow potential security flaws, and a few could really screw with your noodle...
  quote
Bryson
Rocket Surgeon
 
Join Date: Feb 2005
Location: The Canadark
 
2006-01-25, 11:55

Quote:
Originally Posted by m4hl3r
Ok Bryson, didn't you read the reply above you ?
You mean the one entirely unrelated to what I just posted? Not sure what your point is.

Quote:
Was anyone of them fundamental flaws ? Or just "easy to fix flaws ?
I'm afraid I don't understand enough about the nature of the errors to answer that. Anyone with more CPU nous can find the documents at the IBM and Freescale websites.
  quote
m4hl3r
Member
 
Join Date: Jan 2006
 
2006-01-25, 11:56

I'm starting to feel sorry for them who just bought / ordered a new Intel Mac.. This is not quite the "Intel Start" I was hoping for.. But, let's see, this whole thing might just be .. bs ? Does anyone know if Geek.com is a reliable source ?
  quote
m4hl3r
Member
 
Join Date: Jan 2006
 
2006-01-25, 11:57

Quote:
Originally Posted by Bryson
You mean the one entirely unrelated to what I just posted? Not sure what your point is.



I'm afraid I don't understand enough about the nature of the errors to answer that. Anyone with more CPU nous can find the documents at the IBM and Freescale websites.
I ment the 2 posts above you, my bad.
  quote
Bryson
Rocket Surgeon
 
Join Date: Feb 2005
Location: The Canadark
 
2006-01-25, 11:59

Quote:
Neither software nor hardware can be released without flaws. It's simply too uneconomic.
That? I made no comment, just answered:

Quote:
Out of interest how do Intel chips measure against PowerPC chips in terms of errors? Not stirring (well not much), just curious...
  quote
m4hl3r
Member
 
Join Date: Jan 2006
 
2006-01-25, 12:04

Never mind Bryson .. my bad.. Not quite sure what I was thinking .. Just blaim me
  quote
ssdd108
Member
 
Join Date: Nov 2005
Location: Las Vegas, NV
 
2006-01-25, 12:10

NOTHING is released without flaws. Processors released with errata is nothing new and this web site knows it. The geek.com article is taking advantage of the situation. Using this to throw mud on Apple and Intel(or just Intel). Keep in mind Intel's transition to 65nm and the fact that its processors are FAR more complex than AMD or IBM.

If your computer works what does it matter? Are you going to pick a fight with someone? My G5 has 24 errors and your CoreDuo has 34 ha!

This reminds me of a thread a few days ago about a guy who thought his Powerbook G4 was crap because the new Intel notebooks will be shipping soon. If you are waiting for perfection you will be waiting an eternity.

Real artists ship.
  quote
scratt
Veteran Member
 
Join Date: Jul 2004
Location: M-F: Thailand Weekends : F1 2010 - Various Tracks!
Send a message via Skype™ to scratt 
2006-01-25, 12:13

Was it Intel or AMD (I think it was Intel) who had that fundamental maths error on their chips which was catastrophic? This is ancient history I am talking about now..

If I remember correctly AMD cleaned up then, as their version of the chip did not have the error.. Proving once and for all in a double whammy that they were not just copying silicon...

Quote:
The Pentium did have one really famous problem, however. In 1994 there was a major flap in the media about an error the Pentium's ability to divide. Like the 486 before it, Pentium chips included a floating-point unit (FPU) to speed math calculations. Earlier Intel chips did all their arithmetic using integers. Programs that used floating-point numbers (non-integers like 2.5 or 3.14) needed to tell the chip how to divide them using integer arithmetic. The Pentium included these instructions in the chip itself in their FPUs, greatly speeding up numerical calculations. This was also the reason the Pentium was more complex and expensive than it's predecessors. The problem for Intel was that all Pentiums manufactured for almost a year had division errors built into the FPU, causing it to divide certain floating-point numbers incorrectly. At that time, many software packages, including many that used floating-point numbers, were not written to take advantage of an FPU, so they didn't show the error. Also, only certain numbers divided incorrectly. As a result, most people never personally experienced the problem.

The most famous example of the "Divide by Pentium" error could be observed by dividing 4,195,835 by 3,145,727, discovered by Tim Coe of Vitesse Semiconductors. The correct value is 1.33382 (to 5 decimal places) while the flawed Pentium's floating-point unit computed 1.33374, a relative error of 0.006 percent. While this wouldn't be a problem for calculating your checkbook balance, it was of some interest to some college mathematics professors, including Thomas Nicely, a math professor at Lynchburg College in Virginia. Professor Nicely was computing the sum of the reciprocals of a large collection of prime numbers on his Pentium-based computer. Checking his computation, he found the result differed significantly from theoretical values. He got correct results when running the same program on a computer with a 486 CPU and eventually isolated the error to the Pentium itself. After getting no real response from Intel to his initial inquiries, and after checking his facts, Nicely posted a general notice on the Internet asking others to confirm his findings. Things rolled swiftly downhill from there, including newscasts on CNN. In response to publicity about the problem, Intel announced that "an error is only likely to occur [about] once in nine billion random floating point divides," and that "an average spreadsheet user could encounter this subtle flaw once in every 27,000 years of use."

Unfortunately for Intel, their pronouncements did not engender great confidence in the computing faithful. While the chance of accidentally entering a pair of "bad inputs" was low, the Pentium's output for those inputs would be wrong every single time. Many people complained that without completely repeating calculations on other computers, they would not be able to tell if their calculations were actually falling victim to the error. As a result of the furor, IBM halted shipment on Pentium-based computers within a month and announced that "Common spreadsheet programs, recalculating for 15 minutes a day, could produce Pentium-related errors as often as once every 24 days." While PCs were only a small percentage of IBM's business and the announcement may have been motivated by someone with a mainframe background looking for any reason to cast aspersions on the PC, it sent a shockwave though the computing world.

Intel's original policy, when it finally publicly accepted responsibility for the problem, was to replace Pentium chips only for those who could explain their need of high accuracy in complex calculations. Of course, pretty much everyone decided that they fell into that category and the complaints rolled in. It took less than a month for Intel to realize that they would be far better off losing a little money than losing their entire reputation. They finally relented and gave away free replacement Pentiums for any owner who asked for one.

Since then, the PC chip race, both in price and performance, has been ratcheting up between Intel and AMD. While the initial Pentiums ran at 75MHz and 90MHz, systems with chips running at over 1GHz are commonplace now. The current race is to produce commercially viable 2GHz chips. To really understand just how far CPUs have evolved, we will close this section of our history tour with a brief comparison of processor speeds through the years.

'Remember, measure life by the moments that take your breath away, not by how many breaths you take'
Extreme Sports Cafe | ESC's blog | scratt's blog | @thescratt
  quote
chucker
 
Join Date: May 2004
Location: near Bremen, Germany
Send a message via ICQ to chucker Send a message via AIM to chucker Send a message via MSN to chucker Send a message via Yahoo to chucker Send a message via Skype™ to chucker 
2006-01-25, 12:16

Quote:
Originally Posted by ssdd108
NOTHING is released without flaws. [..] If you are waiting for perfection you will be waiting an eternity. Real artists ship.
What they said.
  quote
chucker
 
Join Date: May 2004
Location: near Bremen, Germany
Send a message via ICQ to chucker Send a message via AIM to chucker Send a message via MSN to chucker Send a message via Yahoo to chucker Send a message via Skype™ to chucker 
2006-01-25, 12:18

Quote:
Originally Posted by scratt
Was it Intel or AMD (I think it was Intel) who had that fundamental maths error on their chips which was catastrophic? This is ancient history I am talking about now..

If I remember correctly AMD cleaned up then, as their version of the chip did not have the error.. Proving once and for all in a double whammy that they were not just copying silicon...
Yeah, that was Intel, with the original Pentium. Cf. Wikipedia.
  quote
Luca
ಠ_ರೃ
 
Join Date: May 2004
Location: Minnesota
 
2006-01-25, 12:19

I think that was the Pentium II, scratt. EDIT: Whoops, guess it was the original Pentium.

That said, I think it's disappointing how little context there is in this thread. Even though we do have numbers for some other processors, I really have no idea how serious these errors are or how serious processor errata are in general.
  quote
scratt
Veteran Member
 
Join Date: Jul 2004
Location: M-F: Thailand Weekends : F1 2010 - Various Tracks!
Send a message via Skype™ to scratt 
2006-01-25, 12:27

Havng read through the erratta I would say a few years ago these problems would have bugged me.. I was working on beta silicon, and on first gen chips in machine code, writing right up from driver level to high end system level packages. That's because I could see these problems impacting on my code at a low level...

However, now that I have become this monster of OOP and C++ (God I hate myself) I really don't give two hoots, as other's are going to find and experience these problems way before I do. With the beauty of the internet you can pretty much guarantee that it'll be out in the ether within an hour from some anorak in Minsk who's got more gear than the NSA. He'll have fixed it, not released the fix, made a few thousand billion rubles from selling a virus that exploits it to retired KGB, and then posted the fix and a laa dee daa account of how clever he is on P2P networks and IRC, and promtply been blown up by Mossad, working for the US Secret Service, funded by M$.

So, no, in real terms I don't think it's too much to get worked up about, but its a bit embarressing for Intel, and I suspect we'll find more.

To balance that a bit most of the erratta have been owned up to, and only experienced by Intel themselves. Got to give them points for honesty I suppose...

'Remember, measure life by the moments that take your breath away, not by how many breaths you take'
Extreme Sports Cafe | ESC's blog | scratt's blog | @thescratt
  quote
Powerdoc
Cat's Dreamlands
 
Join Date: May 2004
 
2006-01-25, 13:02

Yes the G4 and G5 where not bug free.
At the difference of IBM, Intel has a more transparent communication. Intel is more willing to communicate on such flaws, than some others companies.
  quote
Posting Rules Navigation
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

vB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Post Reply

Forum Jump
Thread Tools

« Previous Thread | Next Thread »

All times are GMT -5. The time now is 10:06.


Powered by vBulletin®
Copyright ©2000 - 2024, Jelsoft Enterprises Ltd.
Copyright ©2004 - 2024, AppleNova