AMD confirms delay of 2.4ghz Phenom due to TLB errata

V

Vertigo Acid

2(-log[H+])4u
Joined
May 31, 2003
Messages
12,410
The Inq has details on exactly why AMD's flagship Phenom 9700 processor launch will be delayed. Seems that problems in the Translation Lookaside Buffer (TLB). Intel had problems with their TLB earlier this year, but were able to fix the problem with a microcode update. As this isn't possible on AMD's platform, they simply have to recall the processors.

This problem was found during speed-binning the B2 revision processors, and this was the cause for the Phenom FX 3.0 GHz delay. It turns out that some CPUs running at 2.4 GHz or above in some benchmarking combinations, while all four cores are running at 100% load, can cause a system freeze.
Click to expand...
 
UICompE02 said:
Not to be picky, but shouldn't TLB be 'Translation Lookaside Buffer"?
Click to expand...

Yeah, it should...when I read it I knew there was something wrong with it, it sounded weird, but couldn't remember the proper term...Translation is the word.
 
that suck AMD just cant catch a break damn
oh well hope this gets fixed soon i would like to see how this stacks up with the C2Qs
 
When it rains, it pours.

Don't worry, B3 will fix everything. :p
 
Well that explains why all the high end Phenoms suddenly dissapeared off of AMD's roadmaps. Can't wait to see how the B3's perform... :D
 
Here's the first that popped into my head, if you have a lower clocked phenom and you overclock it above 2.4ghz is it going to create this problem?
 
munkle said:
Here's the first that popped into my head, if you have a lower clocked phenom and you overclock it above 2.4ghz is it going to create this problem?
Click to expand...

It depends... I think based on the article they revised the chip.. and then noticed the problems so i imagine its possible the problems werent their in the first gens?
 
Intel fanboys cannt say shit, the Core2 errata is HUGE!
87+ bugs in the first revision, and 67+ and the 2nd stepping.

I have a feeling people are going to get the cheap 5000+ Black, or the 6400+ and put them on the new MSI/Giga-Byte 790FX chipset mainboards with the new 3850.3870's and have some cheap, low heat, low power, and high FPS FUN!
 
temporalwar said:
Intel fanboys cannt say shit, the Core2 errata is HUGE!
87+ bugs in the first revision, and 67+ and the 2nd stepping.

I have a feeling people are going to get the cheap 5000+ Black, or the 6400+ and put them on the new MSI/Giga-Byte 790FX chipset mainboards with the new 3850.3870's and have some cheap, low heat, low power, and high FPS FUN!
Click to expand...



Yes,but Intel did not need to pull chips form the shelf to fix it.And damn,does it ever pour when it rains !? Its coming down in buckets right now over AMD.
 
temporalwar said:
Intel fanboys cannt say shit, the Core2 errata is HUGE!
87+ bugs in the first revision, and 67+ and the 2nd stepping.

I have a feeling people are going to get the cheap 5000+ Black, or the 6400+ and put them on the new MSI/Giga-Byte 790FX chipset mainboards with the new 3850.3870's and have some cheap, low heat, low power, and high FPS FUN!
Click to expand...

Actually they can say that intel can just update microcode to fix it, while amd has to pull the chips. Either way this is bad news for amd.
 
temporalwar said:
Intel fanboys cannt say shit, the Core2 errata is HUGE!
87+ bugs in the first revision, and 67+ and the 2nd stepping.

I have a feeling people are going to get the cheap 5000+ Black, or the 6400+ and put them on the new MSI/Giga-Byte 790FX chipset mainboards with the new 3850.3870's and have some cheap, low heat, low power, and high FPS FUN!
Click to expand...
As Manny said, Intel didn't have to issue a recall and a delay. Every processor has errata.
 
munkle said:
Actually they can say that intel can just update microcode to fix it, while amd has to pull the chips.
Click to expand...

The INQ is full of crap. This site has some good info, as posted by a commenter on the INQ article:

http://www.securiteam.com/securityreviews/5FP0M1PDFO.html

Modern x86 microprocessors from Intel and AMD contain a feature known as "microcode update", or as the vendors prefer to call it, "BIOS update". Essentially the processor can reconfigure parts of its own hardware to fix bugs ("errata") in the silicon that would normally require a recall.

This is done by loading a block of "patch data" created by the CPU vendor into the processor using special control registers. Microcode updates essentially override hardware features with sequences of the internal RISC-like micro-ops (uops) actually executed by the processor. They can also replace the implementations of microcoded instructions already handled by hard-wired sequences in an on-die microcode ROM.

AMD's U.S. Patent 6438664 ("Microcode patch device and method for patching microcode using match registers and patch routines") goes into substantial detail on this.

Typically microcode update blocks are stored in the BIOS flash ROM and loaded into the processor as the system boots. They can also be loaded by the operating system; for instance, Linux contains a microcode device driver for Intel chips.
Click to expand...
 
AMD can microcode update as well however the problem must have been too serious to fix in a microcode update alone.

Looks like phenom will be a value only if overclocking on a budget. I can't see why the OEMs should get excited unless AMD deals seriously under intel.
 
You must log in or register to reply here.
Back
Top