Intel to Acquire Fulcrum Microsystems

[btarunr]

Intel Corporation today announced it signed a definitive agreement to acquire Fulcrum Microsystems Inc., a privately held fabless semiconductor company that designs Ethernet switch silicon for data center network providers.

"Intel is transforming from a leading server technology company to a comprehensive data center provider that offers computing, storage and networking building blocks," said Kirk Skaugen, Intel vice president and general manager, Data Center Group. "Fulcrum Microsystems' switch silicon, already recognized for high performance and low latency, complements Intel's leading processors and Ethernet controllers, and will deliver our customers new levels of performance and energy efficiency while improving their economics of cloud service delivery."

10 Gigabit Ethernet (10GbE) networks are one of the fastest-growing market segments in the data center today. As demand for data continues to increase, there is a growing need for high-performance, low-latency network switches to support evolving cloud architectures and the growth of converged networks in the enterprise. Fulcrum Microsystems designs integrated, standards-based 10GbE and 40 Gigabit Ethernet (40GbE) switch silicon that have low latency and workload balancing capabilities while helping provide superior network speeds.

Cloud computing is driving the convergence of server, storage and network technologies and solutions based around Intel Xeon processor solutions. IP Data Center customers need faster and more flexible networking solutions. The acquisition will fulfill an important component in Intel's strategy to deliver comprehensive data center building blocks, from server processors and technologies to storage and networking.

"Customers in Web, financial services, technical and high-performance computing market segments appreciate the performance advantages Arista offers with our Extensible Operating System combined with switches based on Fulcrum Microsystems silicon," said Andy Bechtolsheim, founder, chief development officer and chairman of Arista Networks. "Fulcrum Microsystems has architecture capabilities ideal for low-latency applications, and we are excited about the future possibilities of this technology as Fulcrum is acquired by Intel, the world's largest semiconductor manufacturer."

Founded in 1999, Fulcrum Microsystems is based in Calabasas, Calif. Additional terms of the transaction were not disclosed. The agreement is subject to the approval of Fulcrum Microsystems shareholders, regulatory approval and satisfaction of customary closing conditions. It is expected to close in the third quarter of 2011.

View at TechPowerUp Main Site

 

[FordGT90Concept]

I don't see why Intel would want them unless it has something to do with Lightpeak/Thunderbolt.

 

[Zudeo]

Damn. Fulcrum agents have Intel? This can't be good. Chuck doesn't approve of this.

In fact, I spoke to him. Here's his reaction.

Not pleased. Not pleased at all.

 

[Zudeo]

On a more serious note, it's probably for the next iteration of Lightpeak. Hopefully for Ivy Bridge or Haswell platforms.

 

[TheMailMan78]

I hear Fulcrum and I think....

So Intel now has a MiG-29?
I sure hope AMD gets a YF-22 soon!

 

[WarraWarra]

If you take the tech that the fulcrum is based on and add it to a cpu for sata replacement you will get what ?
Maybe a future solution for Sandy-E pci-e 4x sata port issues ?

+ you can expand the networking side to catch up with China's current standards and that would be able to handle the normal 10G and once ready 40G data for a country like China.
This should give Intel a fair chance at trying to compete if they can catch up.

PS> USA we think we will have proper 3.5G for mobile phones eventually, this above is default (2008) 10G mobile data and 40G mobile data, you do the math.
Imagine 1.5bilion or is it already 3billion Chinese downloading conservatively at 4G speeds on their 8billion (last count) mobile phones on such a network = how much data ??

Intel can make some money there.

Off Topic:
YF-22 maybe not the best choice, maybe read this post about mig and eurofighter.
http://asian-defence.blogspot.com/2011/06/pakistani-f-16s-shoot-down-raf.html

Funny how this was not on the news here.
LOL someone joked about the Fulcrums - Soviet "Fulcrums" and "Flankers"

 

[TheMailMan78]

If you take the tech that the fulcrum is based on and add it to a cpu for sata replacement you will get what ?
Maybe a future solution for Sandy-E pci-e 4x sata port issues ?

+ you can expand the networking side to catch up with China's current standards and that would be able to handle the normal 10G and once ready 40G data for a country like China.
This should give Intel a fair chance at trying to compete if they can catch up.

PS> USA we think we will have proper 3.5G for mobile phones eventually, this above is default (2008) 10G mobile data and 40G mobile data, you do the math.
Imagine 1.5bilion or is it already 3billion Chinese downloading conservatively at 4G speeds on their 8billion (last count) mobile phones on such a network = how much data ??

Intel can make some money there.

Off Topic:
YF-22 maybe not the best choice, maybe read this post about mig and eurofighter.
http://asian-defence.blogspot.com/2011/06/pakistani-f-16s-shoot-down-raf.html

Funny how this was not on the news here.
LOL someone joked about the Fulcrums - Soviet "Fulcrums" and "Flankers"

The Raptor is not a Eurofighter.

 

[Completely Bonkers]

Intel "bought" a couple of patents and a handful of bright employees. That's all.

 

[micropage7]

Intel "bought" a couple of patents and a handful of bright employees. That's all.

thats the point, what intel needs? they have 'everything'

 

[buggalugs]

Ya i think this is the future for the business environment. A computer in one central location and networked ethernet connected monitors.

Keeps costs down, maintenance down, and security is easier to control.

 

[FordGT90Concept]

The Raptor is not a Eurofighter.

Yup, the F-22 (Y designator is experimental--it is now deployed) in US war games engaged and killed F-18s before they even knew it was in their airspace. The F-22 should never get in a situation where it has to dog fight but, if it does, it has the huge advantage of thrust vectoring over the F-16 and F-18.


@WarraWarra: What does China have to do with anything? China is way behind the "West" in everything except population count.


If this technolgy is aimed at LightPeak/Thunderbolt, the earliest we'll see it is in Ivybridge. Most likely, it won't be until the iteration after that. It takes at least 2 years to deploy technology like that and we are likely within a year from the launch of IvyBridge. I think Intel knows better than try to rush something like that in. More likely, I think Intel sees SATA as not advancing quick enough to keep pace with SSD development so they need a generational leap forward. They could get that generational leap from Fulcrum.

 

[Yukikaze]

I don't see why Intel would want them unless it has something to do with Lightpeak/Thunderbolt.

Probably because Intel wants to provide a complete datacenter solution. The only question is: When will Intel buy a router maker?

 

[entropy13]

it has the huge advantage of thrust vectoring over the F-16 and F-18.

it has the huge advantage of thrust vectoring

advantage of thrust vectoring

thrust vectoring

 

[sneekypeet]

Enough with the aviation references already, can we try to stay on topic?

 

[FordGT90Concept]

Probably because Intel wants to provide a complete datacenter solution. The only question is: When will Intel buy a router maker?

Infiniband? That's the norm right now. It can handle up to 1.5 Tb/s putting Fulcrum's technologies to shame. I still think it has something to do with SATA saturation and/or Lightpeak/Thunderbolt.

 

[Yukikaze]

Infiniband? That's the norm right now. It can handle up to 1.5 Tb/s putting Fulcrum's technologies to shame. I still think it has something to do with SATA saturation and/or Lightpeak/Thunderbolt.

Infiniband is much more expensive than 10GbE at the infrastructure level. While Infiniband has its advantages (most notably in latency), it is not a replacement for Ethernet in every single Datacenter due to its cost. It is however much better for a pure compute cluster.

 

[FordGT90Concept]

But that might be what Intel sees in Fulcrum. Maybe they believe Fulcrum has an answer for how to do Lightpeak (or at least Thunderbolt) cheap(er).

 

[Yukikaze]

But that might be what Intel sees in Fulcrum. Maybe they believe Fulcrum has an answer for how to do Lightpeak (or at least Thunderbolt) cheap(er).

You might be right, but Intel already makes 10GbE solutions and has been doing that for the past few years (since 2007). I believe Intel sees a way to make its existing and future 10GbE solutions cheaper and/or more power efficient. I do not think this has anything to do with TB/LP.