INTEL SPILLS CHIP DETAILS AT FORUM

August 25, 2000

COMMERCIAL NEWS

San Jose, CA — Executives kicked off the Intel Developer Forum Tuesday with a 2GHz Pentium 4 demo and a charge to developers to work together to create standard building blocks for the Net.

Intel Corp. president and CEO Craig Barrett urged developers to borrow a page from the PC market and work together to create interoperability standards and modular products for Internet infrastructure and the communications markets.

“Our collective task is to make those building blocks play together effortlessly and seamlessly,” Barrett said. “We firmly believe that this innovation and optimization occurs when you build standard building blocks.”

Barrett drove home his point, saying “I want to urge you to cooperate not only with companies like Intel, but with your competitors. Standards will …

help develop our industry much faster than isolated and competing standards.”

As an example of how the industry can work together, Barrett cited the discrepancy between wired and wireless networking. Wired and wireless will work together, he said, However, “the real challenge is to have the same sort of infrastructure created on the wireless side (as the wired side) and have them interact. Clearly multiple contact points to the Net is going to make it more interesting, more valuable, more exciting to the end user.”

Another area of focus for Intel will be peer-to-peer networking, Barrett said. The company will outline ways of sharing resources across a network later in the week. To make his point, Barrett called on Applied MetaComputing LLC, which offers software that allows other companies to share and secure resources across a network.

“The future is … peer-to-peer networking, where you have many computers working together that don’t necessarily trust each other,” said Andrew Grimshaw, president and founder of the Charlottesville, Va., company.

The forum allows software and hardware makers to get the latest peeks inside Intel’s technology. Albert Yu, senior vice president and general manager of Intel’s Microprocessor Products Group, offered an update on Intel processor technology. Yu touched on Intel’s Itanium 64-bit server chip, its mobile processor technology and then made several Pentium 4 demos, including the 2GHz chip.

The demonstration began with a 1.5GHz chip and raised its clock speed to 2GHz. The chip was air cooled, without special cooling technology. “Pentium 4 will be the fastest desktop processor in the world” when it ships, Yu said. Yu also demonstrated a desktop PC with a 1.4GHz Pentium 4 chip and 400MHz Rambus Direct RAM.

The new chip, when compared with the Pentium III, enables higher frame rates in video and more realistic three-dimensional graphics, he said. A 1.5GHz Pentium 4 system was then tested against an 800MHz Pentium III system in video capture. The 1.5GHz Pentium 4 was able to capture more frames of video than the 800MHz Pentium III. When watching the video captured by the Pentium III system, “It’s a little jerky, I have to say,” Yu said. When it comes to Itanium, “We are making solid progress and working toward end-user pilots in the Q4 time frame,” he said.

Yu then demonstrated an Itanium server cluster, running on Linux. Yu showed the “fail over” capabilities of the cluster, which can keep an application running even when one machine in the cluster goes down.

Yu also announced a 1GHz Pentium III Xeon chip for servers, which he said is available now. “We are shipping the very first 1GHz processor for the enterprise,” he said. The 1GHz Xeon chip offers 256KB of Level 2 cache and a 133MHz bus, he said.

The 1GHz Pentium III chip for desktop PCs, however, is still in short supply. It is not expected to show up in corporate systems until next month, sources said. Yu then took a few minutes to highlight Intel’s efforts to develop low-power chips for notebook PCs. While he didn’t mention rival Transmeta Corp. by name, he said, “very often we’re confused by thermal power versus average power. For battery life, it’s average power that matters.”

Intel’s low-power 500MHz mobile Pentium III has typical power consumption of 5.5 watts. However, average power consumed by the chip is about 850 milliwatts when running standard office applications, he said. At the same time, he said, “CPU power is a very small portion of the entire platform.”

Six hours is about the longest battery life offered by a notebook today.

“That’s not good enough,” Yu said. “We need to collectively work to decrease the overall power of the platform.” Some 4900 to 5000 developers are expected at this fall’s Intel Developer Forum.

Intel will ratchet up the speed of its high-end Xeon chips to 1 GHz, the company announced. A 1-GHz CPU has more psychological value than practical utility because of bottlenecks talking to memory and other components in a computer. Nevertheless, the milestone highlights Intel’s ability to continue advancing its manufacturing methods even for Xeon chips, which are sold to more demanding and conservative customers.

Xeons are used primarily in servers, the computers that are the brains of computer networks, said Tom Garrison, director of product marketing for Intel’s 32-bit chips. The chip also is sold for users of workstations, the high-performance desktop computers used by designers, engineers and scientists.

The 1-GHz speed applies only to the models of Xeon that have 256K of secondary cache, the high-speed memory that eases delays that result from talking to ordinary, slower-speed memory. In addition, the 1-GHz chips can be used in two-processor systems. “This is the first gigahertz dual-processor (CPU) in the industry,” Garrison said.

The new Xeons cost $ 719 in quantities of 1,000, spokesman Otto Pipjker said. More expensive Xeons come with as much as 2MB of cache and can be used in four-processor configurations. The right chipset, Intel’s Profusion design, allows two four-processor units to be grouped into an eight-CPU system.

Xeons differ from ordinary Pentium chips because Intel manufactures them for a longer time, a move that accommodates customers’ more careful and protracted software and hardware testing period. Those long qualification times led Intel to cancel an 800-MHz version of the large-cache Xeons, which top out at a speed of 700 MHz.

Intel servers gradually are growing up compared with competing designs from Sun Microsystems, Hewlett-Packard, Compaq Computer and others. A next-generation Xeon code-named “Foster” is due next year that removes many of the bottlenecks that hamper current chips.

Another improvement over regular Pentium chips is a feature that makes it easier to monitor the temperature of the CPU and switch on more fans when necessary. Akamai, a company that speeds the transfer of information around the Internet, plans to buy 300 Xeon-based servers each month, Garrison said.

Intel also filled in the details on the Pentium 4 at its developer forum in San Jose, Calif. this week and will show off new chips for cell phones and handheld computers.

The Pentium 4 will feature a completely new architecture called “NetBurst”

designed to handle tasks – such as data encryption, video compression or Napster-like peer-to-peer networking – that have grown in popularity with the Internet, said Albert Yu, senior vice president of the Intel Architecture Group.

“It will be the highest-performing processor for PCs,” Yu said. “We’re moving into streaming video; speech has become much more commonplace than a year ago. Peer-to-peer has been around for a long time, but it is now being recognized as the computing paradigm of the future.”

New subsystems inside the NetBurst architecture will enable the processor to churn more data at a faster rate, Yu said. A micro-engine called the “Rapid Execution Engine,” for example, will run at twice the speed of the processor and will handle frequently repeated tasks, such as addition and subtraction calculations.

In a preview of the chip at the company’s headquarters, technicians showed how a Pentium 4 computer can rapidly render, or draw, 3D images downloaded from the Internet. That sort of processing power could make it easy for sellers on eBay to post virtual representations of their products, for example.

The chip, which will debut at 1.4 GHz and arrive in the fourth quarter, represents the first complete architectural overhaul of the company’s processor line since 1995, when the original Pentium emerged. It will contain 42 million transistors, compared with 28 million for the Pentium III.

For Intel, the chip’s arrival couldn’t come sooner. Manufacturing missteps and increased competition from Advanced Micro Devices have eroded the chip giant’s once-unassailable dominance in the market for processors for performance PCs.

Ron Smith, general manager of Intel’s wireless computing group, announced a new line of StrongArm chips – small, energy-efficient chips for handhelds and cell phones. Formerly code-named StrongArm 2, the new chips will come out at the end of the year.

“We are going to be introducing a variant of the StrongArm under a new brand name,” the spokesman said.

One of the first customers for the chip may be Palm. The handheld computer leader has already said it plans to adopt processors based on the ARM architecture, a processor design licensed by England’s ARM. StrongArm chips remain one of the most popular versions of the ARM design. Palm prototypes containing 200-MHz StrongArm chips were shown off at technology events earlier this year.

Still, the details surrounding the Pentium 4 will likely be the highlight of the conference. Since last October, chip shortages, combined with AMD’s success with Athlon, have put the company on the defensive in the high end of the market.

Though analysts have expressed varying opinions on how well the Pentium 4 will perform, Yu said the NetBurst architecture will bring several new capabilities to the market.

The Rapid Execution Engine, for example, will “turbocharge a piece of the engine,” Yu said, by shifting repetitive tasks out of the main processing and into a specialized, accelerated computing center inside the chip. The Rapid Execution Engine will then be complemented by an Execution Trace cache, a fast reservoir of memory designed to keep the engine packed with data.

Other features will exist to speed data flow and make it more efficient.

“Advanced Dynamic Execution” will speed processing by allowing the processor to recognize parallel patterns and prioritize tasks. In all, the chip will be capable of handling six instructions per clock cycle over extended periods.

The Pentium III typically handles three.

The chip also comes with 144 new multimedia instructions for better graphics and sound. By rewriting their software with the instructions in mind, software developers will be able to improve application performance.

“The Internet is going from a text kind of thing to something more visual,”

Yu said.

In addition, the Pentium 4 will contain a 20-stage pipeline. The pipeline is a processor’s assembly line. While this means the Pentium 4 will have a line twice the length of the 10-stage Pentium III, the longer pipeline will create room for speeding up the chip.

Whether Intel can manufacture the chip in volume will also be a major question at the conference and beyond, as the company has struggled to produce 1-GHz Pentium IIIs in significant volume.

Yu said the Pentium 4 will be in volume production toward the end of the year. An Intel spokesman said that “hundreds of thousands” of the chips will come out this year.

Historically, that would mean the Pentium 4 will be in shorter supply than when the Pentium II or other new chips came out, but likely in larger quantities than the first 1-GHz Pentium IIIs.

In addition, as with the original Pentium, the basic architecture of the Pentium 4 will become the foundation of the company’s processors for the next five to seven years. Following Moore’s Law, this would lead to chips running at more than 11 GHz in 2006.

“A microarchitecture typically lasts five to seven years, and this one is no exception,” Yu said.

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

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