AMD’s Next-Gen Polaris GPU Architecture To Focus on Efficiency and Pixels
AMD is finally readying to launch their next-gen GPU architecture which is allegedly known as “Polaris.” The new architecture is set to be the company’s first big leap in terms of GPU design since the arrival of their Graphics Core Next in late 2011.
The information comes from HWBattle, which first published an image and then a slide from AMD’s GPUOpen announcement presentation referring to the Polaris Architecture. AMD appears to have named the new architecture after the brightest star in the constellation Ursa Minor, with the banner image stating:
Introducing the Polaris Architecture
Our guiding lights is to power every pixel on every device efficiently. Stars are the most efficient photon generators of our universe. Their efficiency is the inspiration for every pixel we generate.
We don’t have nifty details on the new architecture yet, but the small statement does hint that the Polaris architecture is built with two things in mind, better Pixels and greater efficiency. That means AMD’s first Post-GCN architecture, which will be based on the 14nm process, not only promises to deliver some great power/watt characteristics, but also bring better viewing experiences.
This isn’t the first time we’ve heard the name Polaris referenced by AMD officials. Raja Koduri, head of the Radeon Technologies Group, has already teased the new architecture on Twitter, hinting that an announcement may be coming at CES 2016.
— Raja Koduri (@GFXChipTweeter) November 26, 2015
Kaduri’s referring to Polaris as being 2.5 times “brighter” might be a hint at its performance as compared to the current generation of GCN. But currently, we’re not sure what the “2.5 times” does actually mean. We’ll update you on the topic when more information rolls out. Stay tuned!
Gohar is the lead editor at TechFrag. He has a wide range of interests when it comes to tech but he's currently spending a big chunk of his time writing about privacy, cyber security, and anything policy related.