Top 10 Intel & AMD Stories Of 2009 - InformationWeek

InformationWeek is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

IoT
IoT
Infrastructure // PC & Servers
News
12/11/2009
01:58 PM
Connect Directly
Facebook
Twitter
RSS
E-Mail
50%
50%

Top 10 Intel & AMD Stories Of 2009

High-profile developments on the processor landscape this year included aggressive multicore designs, research to put data centers on chip, and a surprise antitrust settlement between the dueling semiconductor vendors.

In picking the top processor stories of the past 12 months, it becomes obvious that 2009 was a transitional year for chipmakers. Clearly, the settlement by Intel and AMD of their ongoing antitrust and patent/licensing disputes was the single biggest business story.

On the technical front, there were significant architectural advances--including aggressive multicore designs, low-power CPUs, and research to put data-center-class power on a single chip. Intel unveiled Nehalem and AMD launched Istanbul. Still, it appears to this observer that the best is yet to come, as advanced graphics capabilities are woven more tightly into processors and platforms.

With luck, that'll be the focus of next year's wrap up. Here now are the top 10 chip stories of 2009:

AMD and Intel Settle Antitrust Dispute

In a moment of enlightened business self-interest, Intel and AMD on November 12 suddenly ended years of embittered legal wrangling, in which AMD charged Intel with monopolistic practices and Intel sued AMD over alleged licensing and patent violations. (Or maybe they laid down their virtual arms because AMD has been wracked by losses and Intel figured there was a 50-50 chance it could lose in court.)

The two companies announced an antitrust settlement under which Intel agreed to pay AMD $1.25 billion, and the two also signed a five-year cross-licensing deal.

While the agreement puts an end to face-to-face litigation, a $1.5 billion European Union antitrust fine against Intel still stands, as does a New York State antitrust lawsuit against Intel.

Intel Investigates Data Center On A Chip

While four cores is the standard footprint for production processors (they'll be moving to 6 and 8 cores in 2010), Intel's laboratory silicon takes multicore design well into the double digits. In December, Intel showed off a 48-core CPU. Mostly this was an interesting, experimental chip. Intel emphasized its built-in power management technology and its high-speed on-chip network to speed interprocessor communications.

Presumably because such design bullet-points aren't sexy enough, Intel characterized the processor as a "single-chip cloud computer." In his story, our own Antone Gonsalves wrote that Intel is calling it a cloud computer "because its design resembles the organization of data centers used to support cloud-computing environments that deliver services over the Web."

In my blog, I pointed out that a cloud on a chip -- research item though it may be -- is on a continuum with today's highly virtualized servers. Thus, it isn't anything out of the ordinary, and we may well expect to see such designs in product form in the not too distant future.

I also noted that Intel chief technology officer Justin Rattner had talked about something similar, but broader -- a data center on a chip -- in a recent interview.

Rattner: We just won the best-paper prize in the Symposium on Operating System Principles with our collaborators at Carnegie Mellon on something called FAWN, which stands for "fast arrays of wimpy nodes." It's the idea that, if we could build tomorrow's processors out of arrays of relatively simple cores, we could deliver data-center-class solutions. It would be data centers on chips, and then arrays of those chips.

InformationWeek: Does this set up a possible race between virtual and physical processors, because with the chips you're talking about, you'll have so many physical cores you won't need virtual instances?

Rattner: If an individual core is so inexpensive, why go to all the trouble to virtualize it? Just allocate some number of physical cores to the problem. What we're also trying to understand is, what leads to the most energy-efficient solution? Am I more energy efficient if I take a big core and virtualize it many ways than I would be if I took lots of simple cores and handed them out as the workloads demanded? I can't tell you what the answer is, but things are looking pretty good for the small cores.

We welcome your comments on this topic on our social media channels, or [contact us directly] with questions about the site.
Previous
1 of 4
Next
Comment  | 
Print  | 
More Insights
Commentary
Get Your Enterprise Ready for 5G
Mary E. Shacklett, Mary E. Shacklett,  1/14/2020
Commentary
Modern App Dev: An Enterprise Guide
Cathleen Gagne, Managing Editor, InformationWeek,  1/5/2020
Slideshows
9 Ways to Improve IT and Operational Efficiencies in 2020
Cynthia Harvey, Freelance Journalist, InformationWeek,  1/2/2020
White Papers
Register for InformationWeek Newsletters
Video
Current Issue
The Cloud Gets Ready for the 20's
This IT Trend Report explores how cloud computing is being shaped for the next phase in its maturation. It will help enterprise IT decision makers and business leaders understand some of the key trends reflected emerging cloud concepts and technologies, and in enterprise cloud usage patterns. Get it today!
Slideshows
Flash Poll