Advanced Micro Devices may introduce its all-new graphics architecture in late 2015 and then ramp it up in 2016. At least, Mark Papermaster, chief technology officer of AMD, implied on such scenario this week.
Graphics architectures from ATI Technologies and Advanced Micro Devices live active life for about four years and sustain three or four iterations that improve performance and bring in new features. AMD’s graphics core next (GCN) architecture was introduced three years ago and next year it will be time for AMD to announce its successor. Apparently, it looks like this is exactly what the company wants to do. Next year AMD may reveal details about its new architecture and in 2016 it is expected to ramp it up.
“We are not taking the foot off the gas,” said Mr. Papermaster at Barclays global technology conference. You will see continued very, very strong graphics, we will have a refresh that you will see, that we will talk about later in 2015, that we are excited about.”
ATI introduced its first DirectX 9-class graphics architecture (code-named R300) in summer, 2002. The architecture evolved into R420 design in mid-2004 and then into R520 design in late-2005. Around the end of 2006 the company (which was then a part of AMD) unveiled the first details of its TeraScale architecture and launched the first DirectX 10-supporting TeraScale graphics processor (R600) in spring, 2007. The TeraScale survived four major iterations (R600, RV770, R800/Evergreen, R900/Cayman) and even gained DirectX 11 support in 2009. The GCN architecture, which powers current-generation Radeon graphics cards, was unveiled in August, 2011, and then made it to the market in early 2012. Since then, AMD introduced GCN 1.1 and GCN 1.2-compliant graphics processing units and it is expected that next year it will bring additional GCN GPUs to the market.
However, it looks like it is time to move on. The chief technology officer of AMD decided not to talk about graphics processors due in 2015, possibly because they are all based on the GCN architecture, but implied that a major update is coming. If the company follows its traditions, the AMD will first reveal details regarding the architecture, sometimes in 2015, and then will start mass production of actual GPUs in 2016.
Official spokespeople for AMD did not confirm or deny the company’s plans to roll-out the GCN successor any time soon, but given the fact that GCN will turn four in late 2015, it will be time for a major update. Moreover, in 2016 the arch-rival of AMD – Nvidia Corp. – is set to unleash its Pascal architecture that will bring major performance and feature-set advancements, therefore, AMD will have to respond somehow.
At present no details about post-GCN graphics architecture are known. However, expect it to support all the features that DirectX 12 application programming interface brings and some additional capabilities. Development of the post-GCN architecture started around 2010 – 2011, when Eric Demers was the chief technology officer of AMD's graphics products group. After Mr. Demers left AMD in early 2012, AMD hired John Gustafson, a renowned expert in parallel and high-performance computing, who probably had an influence on the development of the architecture. Mr. Gustafson left AMD in 2013, so Raja Kodouri (who returned to AMD from Apple) took the development from where his predecessor left. Therefore, the new architecture will be inspired by three great graphics engineers. AMD’s 2016 graphics processing units are expected to be made using 14nm or 16nm FinFET process technologies at GlobalFoundries and/or Taiwan Semiconductor Manufacturing Co.
Discuss on our Facebook page, HERE.
KitGuru Says: Keeping in mind that AMD does not provide outlook for longer than a year from now and a lot can change in the coming quarters, at present all the assumptions regarding post-GCN AMD GPUs should be considered as speculations. Still, given historical patterns of AMD’s graphics products group and some other factors, AMD will need to announce something new in late 2015 or early 2016.