Cave Creek could be used to replace chips such as Cavium Nitrox and Octeon, Netlogic XLP or Freescale QorIQ used as accelerators. OEMs already using the x86 as a control plane processor could find that switch a way to speed time to market and lower cost.
“There still will be plenty of room for other companies, but many chip vendors who had designs next to Intel processors will get squeezed out,” said Joe Byrne, senior analyst with market watcher the Linley Group (Mountain View, Calif.)
Cave Creek “has good prospects, but we don’t know the details of its performance or power consumption yet, and it definitely will need an assist chip at the high end,” said Byrne. “I think they are targeting the middle market,” he said.
Thanks to its strength in the control plane and in security appliances, Intel is currently the second largest supplier of comms processors next to Freescale, Byrne said.
Intel has had a mixed record in comms chips to date. It sold its network processor business to Netronome in 2007. Later, a security SoC called Tolapi “wasn’t very interesting,” said Steve Price, a marketing director in Intel’s comms infrastructure group.
The Crystal Forest pairing is a follow-on of the recent Jasper Forest platform that paired a Nehalem-class Xeon with a slightly modified server logic chip.
Jasper Forest was “extremely successful,” said Price. “We have dozens of customers and its strong in storage, telecom, edge routers,” he said.
I could see this chip being used to offload packet processing functions from hypervisors or virtual machines. As networking is virtualized into the cloud, the packet processing requirements on cloud servers is increased. Perhaps this is Intel's admission that virtual networking doesn't compete and/or scale on x86. You still need specialized networking hardware.
Yeah, I thought about that, but it doesn't seem like those are going to be as dataplane-intensive as they are talking about here. I guess that if you throw in compression / encryption it might be a worthwhile target for a family of chips that scale to the job.
I think there will be a lot of macro, micro and pico base stations deployed in the next ten years, and Intel would love to see that shift to being an x86 app. It's not as big a market as smartphones for sure, but its significant.
It seems like a real niche market for a mass-market player like Intel. High-end switch fabrics for base stations are sexy, but they wouldn't seem to be a real volume business. You have to wonder if there is a larger market that they are using this to gain entry into at some point.
I love this comment: "Base stations using the chips will still need some external parts such as Viterbi decoders."
Um, last time I checked, nobody makes Viterbi decoder ICs anymore. That function is an IP block that one puts in an SoC.
In the past Intel had the Xscale communication processors and the IXP network processors specially designed for the data plane. However at that time it sold the Xscale to Marvell. Now it seems that Intel returns to the the data plane...
David Patterson, known for his pioneering research that led to RAID, clusters and more, is part of a team at UC Berkeley that recently made its RISC-V processor architecture an open source hardware offering. We talk with Patterson and one of his colleagues behind the effort about the opportunities they see, what new kinds of designs they hope to enable and what it means for today’s commercial processor giants such as Intel, ARM and Imagination Technologies.