×

Registration

Profile Informations

Login Datas

or login

First name is required!
Last name is required!
First name is not valid!
Last name is not valid!
This is not an email address!
Email address is required!
This email is already registered!
Password is required!
Enter a valid password!
Please enter 6 or more characters!
Please enter 16 or less characters!
Passwords are not same!
Terms and Conditions are required!
Email or Password is wrong!

ARM's New Mali GPU And Machine Learning Chips To Fuel Mainstream Smartphones

ARM Mali and Ethos Chips
Today's smartphones are powerful little devices, particularly at the top end where price tags can extend into four-digit territory. But why should users with deep pockets have all the fun? They shouldn't, and ARM is on a mission to bring features and capabilities once reserved for premium devices into the mainstream sector, with a handful of new processor technologies.

There are four new chips in all. They consist of a Mali-G57 GPU, the Ethos-N57 and Ethos-N37 NPUs, and Mali-D37 DPU. All of these are considered mainstream parts, with the goal of bringing premium experiences to everyday and ultra-efficient consumer devices, though partnerships with companies that license ARM's intellectual property (IP).

"Once the preserve of premium devices, immersive experiences such as AR, high-fidelity gaming, and
new AI-based use cases across mobile and home are now being demanded by the mainstream market.
Giving developers access to high-performance AI and media IP solutions optimized for everyday devices
enables new AI driven use cases, with features such as voice recognition and always-on capabilities, no
longer unique to mobile," ARM explains.

ARM Delivers New Processing IP For Mainstream Devices

ARM Mainstream Processors
The Ethos-N57 and Ethos-N37 are both neural processing units (NPUs), which aim to extend the range of ARM's machine learning (ML) processors to enable artificial intelligence (AI) applications in mainstream devices. Not be overlooked, companies are increasingly leveraging ML hardware (and software) for advanced functions.
This applies not only to smartphones, but other device categories as well, such as game consoles and smart televisions. that's partially where the Mali-D37 display processing unit (DPU) comes into play. ARM claims it's the most energy efficient, smallest area DPU for delivering Full HD 1080p and 2K resolution content.

"AI intelligence is now everywhere from gaming devices to digital TVs (DTVs), and increased compute at
the endpoint is required to allow for these responsive experiences. For example, intelligent experiences
in DTVs range from smart assistant voice commands, real-time translation for shows in another
language, and face recognition to enhance parental controls," ARM says.

ARM Mali-G57
The Mali-G57 GPU is an interesting product because it is the first mainstream GPU based on the company's Valhall architecture. It's the same underlying architecture as found in ARM's higher-end Mali-G77, which itself is a stout design.

Some of the claims are therefore the same. Specifically, ARM says the Mali-G57 offers 30 percent better power efficiency, 30 percent more performance density, and 60 percent better machine learning performance, compared to the Mali-G52 on the same process node.

What this will enable, according to ARM, is VR acceleration and 4K VR performance in mainstream devices. It also supports HDR10 content.

How this all plays out in consumer devices remains to be seen, though it's nice to see ARM attempting to bolster the mainstream segment with advanced capabilities.

Go to Source