All the latest UK technology news, reviews and analysis

AMD’s next-gen APUs to boost performance with unified memory

30 Apr 2013
AMD Fusion chip

AMD aims to unlock the performance potential of its APU chips by enabling the CPU and GPU cores to have access to a unified memory space, driving development of applications that can use both types of core.

Announced today, heterogeneous uniform memory access (Huma) will enable both CPU and GPU processes to allocate memory from anywhere within the available memory space.

It is set to debut in the third-generation accelerated processing units (APUs) codenamed Kaveri, set for release in the second half of 2013.

Huma is intended to make it easier for programmers to create apps that use both types of core and eliminate the need for special APIs, according to AMD. The technology will thus move closer to delivering on the promise of what AMD calls the Heterogeneous System Architecture (HSA).

All AMD's APUs since the first generation launched back in 2011 have used separate memory spaces for the CPU and GPU cores. To take advantage of the GPUs capabilities to handle parallel workloads, developers had to use the CPU to move data to the GPU's memory space, then retrieve the results after calculation.

Under Huma, the CPU can just pass a pointer to the GPU that tells it where in the unified memory space to find the data, which simplifies the process and boosts performance by eliminating the need to move data around.

"HSA's revolutionary memory architecture is a new standard for high-speed GPU access to the system memory and removing the obstacle of having the GPU 'starved for data," said AMD's Sasa Marinkovic, writing on the company's blog.

HSA will empower software developers to innovate and unleash new levels of performance and functionality on modern devices, Marinkovic added, and will lead to powerful new experiences such as visually rich, intuitive, human-like interactivity.

The new approach also improves cache coherency, according to AMD, as both the CPU and GPU caches can see an up-to-date view of data across the memory space.

  • Comment  
  • Tweet  
  • Google plus  
  • Facebook  
  • LinkedIn  
  • Stumble Upon  
Daniel Robinson

Daniel Robinson is technology editor at V3, and has been working as a technology journalist for over two decades. Dan has served on a number of publications including PC Direct and enterprise news publication IT Week. Areas of coverage include desktops, laptops, smartphones, enterprise mobility, storage, networks, servers, microprocessors, virtualisation and cloud computing.

More on Processors
What do you think?
blog comments powered by Disqus

IT curriculum poll

With coding now compulsory in schools, how important are digital skills for the next generation of school leavers?

Popular Threads

Powered by Disqus
V3 Security Summit

V3 Security Summit Day 2: Botnet, skills and BYOD intelligence incoming

Keep V3 bookmarked for news updates on all the key security concerns and topics facing businesses

Updating your subscription status Loading

Get the latest news (daily or weekly) direct to your inbox with V3 newsletters.

newsletter sign-up button

Getting started with virtualisation

Virtualisation can help you reduce costs, improve application availability, and simplify IT
management. However, getting started can be challenging


Converting big data and analytics insights into results

Successful leaders are infusing analytics throughout their organisations to drive smarter decisions, enable faster actions and optimise outcomes

SQL QlikView Developer (SQL, Qlikview, Agile, PHP, Java, Linux)

SQL QlikView Developer (SQL, Qlikview, Agile, PHP, Java...

Automation Test Analyst (C# Platform, Selenium, Automation, XML

Automation Test Analyst (C# Platform, Selenium, Automation...

Python Front Office Developer Quant

The purpose of the role is to work closely with traders...

Junior C++ Developer - Algo Trading

My client- one of the most successful high frequency...
To send to more than one email address, simply separate each address with a comma.