Will AMD ARM Itself?

By Michael Feldman

April 28, 2011

AMD has been plugging away at the x86 business for nearly 20 years now. In 1982 the company crafted a licensing deal with Intel to become an alternative source of x86 processors for the burgeoning personal computer market — specifically to satisfy IBM’s demands for two sources of CPUs for its new PC offerings. And although AMD has parlayed this into a multi-billion dollar business, Intel has never allowed its smaller competitor to be anything but a secondary choice for x86 parts.

As of the first quarter of 2011, Intel owns 81 percent of the x86 processor space, with AMD a distant second with 18.2 percent. The numbers are not much different than they were in 2010 and are not likely to be much different in 2012, 2013, 2014, and so on. The only thing that has maintained AMD’s viability is the sheer size of the market and Intel’s willingness to keep AMD as a co-dependent partner.

But as AMD proved when it acquired GPU-maker ATI in 2006, it is not adverse to adopting new processor technology when it suits the company’s purpose. Now there’s talk that AMD may be considering a second leap of faith, this time in the direction of the ARM architecture — a low-power CPU design that has become the darling of the mobile computing space. An analysis this week by Peter Clarke for EE Times spells out why a fully-ARMed AMD makes a lot of sense.

To begin with, Clarke argues that playing catch-up with Intel is not the greatest recipe for success, especially now that AMD has gotten out the fab business and can thus no longer compete on that playing field. And — although Clarke didn’t point this out — AMD has lost much of its x86 architectural differentiation when Intel adopted AMD’s system design of integrated memory controllers and a HyperTransport like interconnect in QPI. At least for AMD’s non-GPU business, this forces the company to shrink its margins by trying to undercut its larger rival on price.

But the shorter term rationale for hopping on the ARM bandwagon is to expand AMD’s footprint beyond its x86 base. Today the company doesn’t have viable low-power offerings for the rapidly-growing tablet and mobile device space, and ARM could make for a relatively pain-free path into those markets. And with Microsoft’s endorsement of ARM as a Windows platform, AMD could also create non-x86 offerings for traditional desktops and notebooks. And the company wouldn’t have to jettison its x86 portfolio to do any of this.

Clarke notes that for the cost of a few million dollars and a few percent royalty per processor, AMD would be able to jumpstart its ARM business. From his EE Times article:

….Now it may be that a hard-pressed AMD was simply unable to create designs for all the different sectors and performance profiles in a proliferating PC landscape. But that alone is reason to get off the x86 treadmill and let ARM do some of the heavy lifting. And having missed the tablet computer boom ARM licensing would provide the fastest way for AMD to get a chip to market and make up lost ground.

Beyond that, ARM appears headed to server-land, although according to ARM Holdings president and co-founder Tudor Brown, not for another five years or so. But to my mind, this is yet another reason for AMD to start its ARM adventure now. When ARM Holdings comes up with its anticipated 64-bit design, it’s only a hop, skip and a jump to a fully-fledged server implementation.

In fact, if ARM-based servers are to become a reality, somebody will have to develop those chips, and AMD has the right combo of system engineering smarts and business relationships to make it happen. Some of the happiest days at AMD were when it outflanked Intel with its 64-bit x86 Opteron designs (at a time when Intel believed its new Itanium CPU would take the high ground 64-bit servers). It wouldn’t surprise me if there are some execs at AMD who are dreaming about a repeat performance recast under the ARM umbrella.

A future ARM-based server landscape may be a little trickier to navigate than the x86 one, though. Since the architecture can be licensed by anyone, there’s nothing to prevent any server maker from coming up with its own SoC designs. In fact IBM and Fujitsu already license ARM for other purposes. For that matter, even ARM chip vendors like Samsung and Texas Instruments could start churning out server-grade designs if they could come up with the business.

Calxeda (formerly Smooth-Stone) is getting ready to launch an ARM server based on the current generation 32-bit CPU designs. A 2U enclosure will house up to 120 ARM quad-core nodes, while chewing up only about 5 watts per node (including memory). The company claims a single 2U box will deliver the same throughput as a rack of vanilla x86 servers, reducing power requirements by 90 percent.

For the HPC crowd, NVIDIA has announced its intentions to marry ARM CPUs with it GPU technology. The GPU maker’s “Project Denver” will glue the two architectures together, AMD Fusion-like, and create a family of processors for personal computers, workstations, servers and supercomputers. In fact, if AMD perceives NVIDIA’s ARM formula for heterogenous processors as a threat to its own Fusion processor plans, that would be yet another reason to hedge its bets with ARM.

Fueling some this AMD-ARM speculation is this week’s announcement that ARM fellow and vice president Jem Davies will deliver a keynote at the next AMD Fusion Developer Summit in June. Davies is on tap to discuss ARM’s legacy of heterogeneous computing, its future strategy, and its support of OpenCL.

It’s likely this is nothing more than AMD looking to highlight industry support for hetero computing and OpenCL. But it’s worth noting that ARM products, especially ones with the GPGPU-ready Mali graphics hardware (Mali-400 MP and Mali-604), ostensibly compete with AMD’s Fusion chips. At the Many-core and Reconfigurable Supercomputing Conference held early this month in the UK, Dr. Krisztian Flautner, vice president of research & development at ARM, said the company would be releasing a reference design board that includes an ARM CPU plus a Mali 604 GPU, along with a full OpenCL 1.1 implementation that targets both computing units. So one might wonder why AMD would spotlight such technology at one of its events.

In any case, I think Clarke’s analysis is on target and I’ve got to believe the AMD digerati are mulling over an ARM play. In retrospect, it’s a little surprising they haven’t already pulled the trigger. After 20 years of playing second fiddle to Intel, it’s time for the company to strike out on its own.

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!

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…

Nvidia Appoints Andy Grant as EMEA Director of Supercomputing, Higher Education, and AI

March 22, 2024

Nvidia recently appointed Andy Grant as Director, Supercomputing, Higher Education, and AI for Europe, the Middle East, and Africa (EMEA). With over 25 years of high-performance computing (HPC) experience, Grant brings a 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…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the fi 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