GLITCH PROMPTS INTEL TO RECALL 1.13-GHZ PENTIUMS

September 1, 2000

COMMERCIAL NEWS

New York, N.Y. — Ian Fried reports that Intel has recalled its fastest chip – the 1.13-GHz Pentium III – saying the chip could cause system errors when running certain programs and at a particular temperature.

The problem is with certain circuits of the chip that have been shown to malfunction in laboratory tests under certain conditions, said Intel spokesman Howard High. Intel said it has not received reports from customers of any problems, but the glitch has been noted by some hardware review sites in recent days.

Intel Corp’s Chief Executive Craig Barret said that the company had fallen short in the development of its newest and fastest chip. “We should have done a better job,” he said, speaking to Reuters in Buenos Aires on Tuesday, during his tour of South America. “We know what the problem is and are in the process of fixing it to ship new product.”

“While the financial impact is negligible it makes Intel look bad to their customers,” U.S. Bancorp Piper Jaffray analyst Ashok Kumar wrote in a note to clients. “The company is announcing products they cannot ship, and it turns out, do not even work properly.”

As reported by CNET News.com, Dell Computer and IBM have stopped shipping PCs with the processor. Intel said it will work with those companies to satisfy existing customers.

“Clearly if they want a replacement, then we will replace (it),” High said. “If they want a refund, we’ll accommodate them.” The 1.13-GHz chip began shipping July 31 in limited quantities.

An Intel spokesman said the chip had only shipped to “a handful of customers,” including International Business Machines Corp. and Dell Computer Corp., but declined to comment on exactly how many chips had been shipped.

“We estimate that the company has shipped less than 10,000 units and, as such, the financial toll is negligible,” said Kumar. “Also, given that these products populate high-end systems priced at about $3,000, the opportunity cost is minimal.”

“There can’t be very many – tens of thousands at most,” said Linley Gwennap, principal analyst at The Linley Group. “I wouldn’t be surprised if it was under 10,000.”

Word of the glitch came on the same day that rival Advanced Micro Devices announced shipments of its 1.1-GHz Athlon.

Analysts say competition with AMD may have caused Intel to release a chip that wasn’t ready. “It sounds like Intel may have pushed a little too hard,” said chip analyst Peter Glaskowsky of MicroDesign Resources. “It shows the Pentium III is not really capable of reaching these levels.”

Gwennap noted that Intel did not originally have the 1.13-GHz chip on its road map and has struggled to produce the 1-GHz chip in enough quantity to satisfy customers.

“When you push the clock speed beyond what it was designed to do, you run into problems,” Gwennap said. “They rushed to get the 1-GHz chip out, and they couldn’t produce enough of them.”

Intel said it has identified the cause of the problem and will fix it by redesigning the circuits in question. “It’s probably a couple of months before we get units back into the marketplace,” High said.

Although other Pentium III processors have the same design, Intel said it has not found the same problem in other chips. “We’ve done quite a bit of testing, and we haven’t seen anything,” High said.

Intel said the fact that it had not shipped many of the processors will make the problem easier to remedy than past glitches, such as the bug with the 820 chipset. In that case, computer motherboards with the defective chipset were sold through distributors and available in computers from many retailers.

“We’re kind of early in the process, which is a benefit with something like this,” High said.

Only Dell, IBM and a few European companies had been selling systems with the 1.13-GHz chip. Intel said it is recalling chips that have not yet been sold and has halted its shipments of the processor.

High said various computer hardware review sites began noting a problem with certain kernels of the Linux operating system. Intel at first could replicate the problem only when the chips were operated outside recommended temperature specifications. Over the weekend, it began noticing problems even within the chip’s specifications.

Intel executives said it was too soon to say how much the bug might cost, but the cost will not be material to Intel’s earnings.

While the recall was small in size, it was not the first. In 1995, Intel recalled its first Pentium due to a flaw, in what was cited by then-chief executive Andrew Grove in his book “Only the Paranoid Survive” as a defining event for the company as it became a household name.

Last year, Intel recalled its Intel 820 chipset due to a design flaw in technology provided by Rambus Inc. In May, Intel recalled defective motherboards – the internal chassis that hold memory components in personal computers.

Salomon Smith Barney analyst Jonathan Joseph said that the small size of the current recall made it “no big deal.” “This is not a black eye, this is a nit,” he said. “The magnitude of this recall is infinitesimal. It is in no way comparable to the 1995 Pentium recall.”

But Kumar said the implications of the recall were more serious than its size would suggest. He blamed Intel’s race against AMD to the claim to the fastest chip as part of the problem.

“This is another sign that the 1.13 gigahertz chip is pushing the envelope for an architecture developed for 2 gigahertz speeds,” he said, noting that Intel had missed the transition to copper interconnects on its 0.18 micron process, and was using a core that was five years old.

“Essentially they are pushing an aging architecture to keep pace with AMD’s Athlon, to have bragging rights to the fastest processor,” he said. “Intel should have introduced the P4 a long time ago. Their research and development budget is much larger than AMD’s. That they can’t keep pace with such a small competitor as AMD speaks volumes about the company.”

Intel’s Barret, however, said that the chip’s trouble was not due trying to pace AMD. “I don’t think it was an issue of getting it out before the competition,” he said, adding that the company’s Pentium 4 would be available in October or November.

But Kumar warned Intel’s flawed chip could test the patience of its customers. “Intel having this reoccur on a constant basis is just stretching the relationships with OEMs,” he said, referring to original equipment manufacturers such as IBM and Dell.

However, those computer makers, which both received shipments of the faulty chips, said they did not yet see cause to alter their relationships with Intel.

IBM had begun shipping some Aptiva desktop computers with the chips, a spokesman said. “We don’t know exactly what we are going to replace these chips with right now,” said IBM spokesman Tim Blair, adding that IBM was working on how to get parts back from customers.

Dell Computer Corp. had planned to ship products with the new chip last Friday, and was told by Intel to hold off, a Dell spokesman said.

“We were taking orders starting July 31 and anticipating shipment on August 25, when some of issues began to come up,” said Dell spokesman Tom Kehoe. “We found out on Monday we would not able to ship them at all, so we will be offering a one-gigahertz system to those who have placed orders.”

Dell, which relies solely on Intel for its processors, would not have any material impact on sales or earnings, and was not considering a change in their relationship with Intel, Kehoe said.

In addition to the glitch that forced the recall of the 820 and the delay of the low-end Timna chip, Intel has had delays and performance issues with its forthcoming Itanium chip, which is aimed at high-end servers.

Gwennap noted that Intel’s manufacturing woes over the past year – and AMD’s success – reverse what had been the trend.

“For a long time, Intel was this machine that couldn’t break and AMD couldn’t take two steps without tripping,” Gwennap said. “For the past year, Intel has been having problem after problem, and AMD keeps cranking out more and more chips.”

Gwennap said that while the Pentium III may have hit its limit, Intel will be able to introduce chips at much faster speeds when it debuts the Pentium 4 later this year.

The Pentium 4 design “clearly allows higher clock speeds,” Gwennap said. “That’s one of the reasons they are moving to a new architecture.”

============================================================

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire