Jannah Theme License is not validated, Go to the theme options page to validate the license, You need a single license for each domain name.

Ampere partners with Qualcomm to launch Arm-based AI server

Ampere and Qualcomm aren’t the most obvious partners. After all, both offer Arm-based chips to run data center servers (although Qualcomm’s biggest market remains mobile). But as the two companies announced today, they are now joining forces to offer an AI-focused server that uses Ampere’s processors and Qualcomm’s Cloud AI 100 Ultra AI inference chips to run ( and not train) models.

Like every other chipmaker, Ampere is looking to take advantage of the AI ​​boom. However, the company has always focused on fast and energy-efficient server chips. So while it can use Arm IP to add some of these features to its chips, it’s not necessarily a core competency. That’s why Ampere decided to work with Qualcomm (and SuperMicro to integrate the two solutions), Arm CTO Jeff Wittich told me.

“The idea here is that while I’m going to show you great performance for Ampere CPUs running AI inference on just the CPUs, if you want to scale up to even larger models – multi-100 billion parameter models , for example – like all other workloads, AI is not universal,” Wittich told TechCrunch. “We worked with Qualcomm on this solution, combining our super-efficient Ampere processors to perform many. general tasks that you perform in conjunction with inference, then using their very efficient maps we have a server-level solution.

Image credits: Ampere

As for the partnership with Qualcomm, Wittich said Ampère wants to implement the best solutions on the market.

“(R)very good collaboration we’ve had with Qualcomm here,” he said. “That’s one of the things that we’ve been working on, I think we share a lot of really similar interests, which is why I think it’s really compelling. They’re creating really, really effective solutions and cater to many different segments of the market. We build really, really efficient solutions on the CPU side of the server.

The Qualcomm partnership is part of Ampere’s annual roadmap update. Part of that roadmap is the new 256-core AmpereOne chip, built using a modern 3nm process. These new chips aren’t available to the general public yet, but Wittich says they are factory ready and should be rolled out later this year.

In addition to the additional cores, the defining feature of this new generation of AmpereOne chips is 12-channel DDR5 RAM, which allows Ampere’s data center customers to better adjust their users’ memory access based on their needs.

The sales pitch here is not just about performance, but also about power consumption and the cost of running these chips in the data center. This is especially true when it comes to AI inference, where Ampere likes to benchmark its performance against Nvidia’s A10 GPUs.

Image credits: Ampere

It’s worth noting that Ampere isn’t removing any of its existing chips in favor of these new ones. Wittich pointed out that even these older chips still have plenty of use cases.

Ampere also announced another partnership today. The company is working with NETINT to create a joint solution combining Ampere processors with NETINT’s video processing chips. This new server will be capable of transcoding 360 live video channels in parallel, while also using OpenAI’s Whisper text-to-speech model to caption 40 streams.

“We started on this path six years ago because it is clear that it is the right path,” Renee James, CEO of Ampere, said in today’s announcement. “In the past, low power consumption meant low performance. Ampere proved that this was not true. We pioneered the computing efficiency frontier and delivered performance beyond existing processors in an efficient computing envelope.


Back to top button