Intel and Google Data Center E2000 Chip

Intel and Google Data Center E2000 Chip

Google Cloud publishes new C3 Series machines, featuring the Intel E2000 Infrastructure Processing Unit, jointly designed by Google and Intel

Google Cloud and Intel unveiled their data center chip called the E2000, which was jointly designed by both companies.

Intel Corporation announce The development on Tuesday called it “a significant milestone in delivering a programmable platform from start to finish.”

It looks like Google Cloud has released its new C3 series of machines, featuring Intel Xeon processors in private preview and debuting the Intel Infrastructure Processing Unit E2000 (codenamed Mount Evans), which was jointly designed by Google and Intel.

Image: PIUs provide improved security for Intel partners and customers, reduced overheads, and opportunities to free up CPU performance. (credit: Intel)

E2000 . chip

Intel claims that with its unique architectural approach, “C3 machine instances deliver robust performance gains of up to 20 percent over previous-generation C2 instances, enabling high-performance computing and data-intensive workloads.”

She said Google Cloud C3 hardware is also paving the way for a future in which Infrastructure Processing Units (IPUs) are integrated into data centers, accelerating cloud infrastructures and increasing performance.

“We are thrilled to sign the code for the first ASIC Infrastructure Processing Unit with Google Cloud, which has now been launched in the new C3 series of machines,” said Nick McKeown, Intel Senior Vice President and Intel Fellow and General Manager, Network and Edge Group.

“The C3 VMs are the first of their kind in any public cloud, and will run workloads on 4th generation Intel Xeon Scalable processors while securely freeing programmable packet processing to IPUs at 200Gbps line rates,” McKeown added.

“This collaboration between Intel and Google empowers customers with a more secure, resilient, and performing infrastructure,” McKeown said.

Google Cloud has done in detail C3 machine series is here.

chip developments

This isn’t the first time Google has offered its expertise to chip designs.

Google has historically been secretive when it comes to discussing the technology it uses and even designing its data centers.

But the company has long experimented with its own chips.

In 2013, for example, it was reported that it was considering developing its own set of microprocessors for servers, and even discussed the potential development of smartphone chips.

And in 2016, Google revealed that it was making its own chips, designed specifically for machine learning or artificial intelligence (AI).

Then in August 2017, the Google Cloud Platform (GCP) Google Security (Titan) chip began detailing, which was mostly a hardware security device.

In July 2022, Google Cloud announced the first ARM-based virtual machines (VMs) that use chips from US company Ampere Computing for server chips.

Google said at the time that some customers were looking at ARM architecture options to deliver excellent performance per watt efficiency.

Both AWS and Azure already offer ARM-based virtual machines.

But recently, the US Department of Commerce and Google in September this year reached a collaborative research and development agreement, to produce chips that researchers and startups can use to develop new nanotechnology and semiconductor devices.

Google will primarily finance the initial cost of creating the production and will support the first production of the chips, which will be manufactured by SkyWater Technology at the semiconductor foundry in Bloomington, Minnesota.

#Intel #Google #Data #Center #E2000 #Chip

Leave a Comment

Your email address will not be published. Required fields are marked *