It seems the errata error found in AMD’s Quad Core Opteron (“Barcelona”) did indeed cause a delay in shipments, forcing the company to revise the design and delay volume shipment from this quarter until Q2 of 2008.
Semiconductors are prone to errata errors, which only manifest when the chip is made. They are usually minor and only triggered under specific circumstances, and can often be fixed in the BIOS (define) or with a software fix.
“With this one, we created a software workaround but there was a performance penalty. To fix it the right way required a new revision in silicon,” explained Steve Demski, product marketing manager for Opteron at AMD.
Demski said that the errata bug affects highly threaded applications due to a problem in translation between the L2 and L3 cache on the chip, which resulted in data being overwritten. The results could cause computers to hang. Quad Core Opteron was getting into some customers’ hands but the error had to this point only been seen in lab tests.
AMD had originally said there was no delay in its shipping plans, but Demski said the errata problem did force the company to delay ramping production. “We were hoping to ramp production by now,” he said. Now, the plan is to begin production of updated Quad Core Opterons in the first quarter of 2008 and send them to customers for testing, and barring any problems, begin mass production in Q2 2008.
The decision, as it turns out, wasn’t entirely AMD’s. “Our tier one OEMs didn’t want to go into mass production and risk getting this out into tens of thousands of users of hands,” said Demski. AMD is still selling Quad Core Opteron on a deal by deal basis to major customers, evaluating software in the environment of the customer as they go.
He added that customers that have received Barcelona already have said they are happy with what they received and are not going to wait for the new one. This includes the Sun supercomputer project with the University of Texas/Texas Advanced Computing Center (TACC), which uses the Quad Core Opteron in the massive arrays of blades to power the supercomputer.
James Staten, a senior analyst with Forrester Research, said the inventory supply situation with system builders is so thin that he would not be surprised if they pushed back on AMD. “System manufacturer’s inventory system has changed quite a bit. They try to keep a minimum amount on hand, some times just one to three days’ worth,” he told InternetNews.com.
Often times problems like errata are not found by the chip makers but system manufacturers, and they will tell the vendor to shop shipping because “they don’t want to be stuck with the inventory, nor do they want their rather lengthy inventory process to be stopped for one delay,” he said.
This article was first published on InternetNews.com. To read the full article, click here.
Huawei’s AI Update: Things Are Moving Faster Than We Think
FEATURE | By Rob Enderle,
December 04, 2020
Keeping Machine Learning Algorithms Honest in the ‘Ethics-First’ Era
ARTIFICIAL INTELLIGENCE | By Guest Author,
November 18, 2020
Key Trends in Chatbots and RPA
FEATURE | By Guest Author,
November 10, 2020
FEATURE | By Samuel Greengard,
November 05, 2020
ARTIFICIAL INTELLIGENCE | By Guest Author,
November 02, 2020
How Intel’s Work With Autonomous Cars Could Redefine General Purpose AI
ARTIFICIAL INTELLIGENCE | By Rob Enderle,
October 29, 2020
Dell Technologies World: Weaving Together Human And Machine Interaction For AI And Robotics
ARTIFICIAL INTELLIGENCE | By Rob Enderle,
October 23, 2020
The Super Moderator, or How IBM Project Debater Could Save Social Media
FEATURE | By Rob Enderle,
October 16, 2020
FEATURE | By Cynthia Harvey,
October 07, 2020
ARTIFICIAL INTELLIGENCE | By Guest Author,
October 05, 2020
CIOs Discuss the Promise of AI and Data Science
FEATURE | By Guest Author,
September 25, 2020
Microsoft Is Building An AI Product That Could Predict The Future
FEATURE | By Rob Enderle,
September 25, 2020
Top 10 Machine Learning Companies 2020
FEATURE | By Cynthia Harvey,
September 22, 2020
NVIDIA and ARM: Massively Changing The AI Landscape
ARTIFICIAL INTELLIGENCE | By Rob Enderle,
September 18, 2020
Continuous Intelligence: Expert Discussion [Video and Podcast]
ARTIFICIAL INTELLIGENCE | By James Maguire,
September 14, 2020
Artificial Intelligence: Governance and Ethics [Video]
ARTIFICIAL INTELLIGENCE | By James Maguire,
September 13, 2020
IBM Watson At The US Open: Showcasing The Power Of A Mature Enterprise-Class AI
FEATURE | By Rob Enderle,
September 11, 2020
Artificial Intelligence: Perception vs. Reality
FEATURE | By James Maguire,
September 09, 2020
Anticipating The Coming Wave Of AI Enhanced PCs
FEATURE | By Rob Enderle,
September 05, 2020
The Critical Nature Of IBM’s NLP (Natural Language Processing) Effort
ARTIFICIAL INTELLIGENCE | By Rob Enderle,
August 14, 2020
Datamation is the leading industry resource for B2B data professionals and technology buyers. Datamation's focus is on providing insight into the latest trends and innovation in AI, data security, big data, and more, along with in-depth product recommendations and comparisons. More than 1.7M users gain insight and guidance from Datamation every year.
Advertise with TechnologyAdvice on Datamation and our other data and technology-focused platforms.
Advertise with Us
Property of TechnologyAdvice.
© 2025 TechnologyAdvice. All Rights Reserved
Advertiser Disclosure: Some of the products that appear on this
site are from companies from which TechnologyAdvice receives
compensation. This compensation may impact how and where products
appear on this site including, for example, the order in which
they appear. TechnologyAdvice does not include all companies
or all types of products available in the marketplace.