Moore’s law is not broken: shock, horror, screaming headline! It will last for a while longer yet - new generations of silicon process will continue to give us more transistors on chips, but that won’t, on its own, give us the increases in performance and decreases in power consumption we have become used to. However, we can utilise those extra transistors, to build multicore processors and more of them, and through heterogeneous computing and appropriate use of domain-specific processors. This will give us the increased performance and improved energy-efficiency we need. These are critical areas for us to concentrate on for the future if we are to continue to lead in energy-efficiency.At ARM, we focus on energy-efficiency: not just making IP blocks that make the best possible use of energy themselves but also that lead to partner SoCs using less energy overall (e.g. by reducing external memory bandwidth). One of today’s exciting technical challenges is heterogeneous computing, and we invest a lot of time working in this area to enable more energy-efficient consumer electronics devices. Consequently, when AMD kindly invited me to give a keynote speech at their Fusion Developer Summit at 12:45, 14th June 2011 at the Meydenbauer Center in Bellevue, I was pleased to accept.
Although somewhat novel on the desktop, heterogeneous computing is not a new area for ARM at all. Since ARM was founded over twenty years ago, ARM’s Partners have made SoCs containing numerous heterogeneous compute engines, including CPUs, and many of these have been used in power-constrained environments. There is a significant industry change happening - most smartphones being launched today now contain multiple multicore CPUs, and increasingly, multicore GPUs as well. ARM has huge experience with multicore processors and we launched the world’s first embedded multicore GPU, the Mali-400MP. In addition to multicores, the SoCs in consumer devices contain different compute engines including domain-specific processors – these are engines designed for very specific types of computation, that I’ve blogged about before. However, lately there has been great interest in leveraging the capabilities of some of these processors for more general-purpose computation (GPU computing, or GPGPU). We believe this has great possibilities to do certain types of computation such as image processing faster and in a much more energy-efficient way, so when we launched the ARM Mali-T604 GPU last year, it was designed not only to be the world's best embedded graphics processor, but also to be the world's best embedded processor for GPU computing.
ARM is the only IP supplier designing CPUs, GPUs, video processors, the system IP (the fabric interconnect that joins systems together and the memory controllers), the tools and the physical IP that enables our partners to build these complex systems. We feel this gives us a unique position in the industry to comment on these issues and that is what I’ll be doing. Here’s a quick video where I introduce my keynote speech.
ARM is a big believer in standards (Khronos OpenGL ES, OpenCL, OpenVG, AMBA, to name but a few), and has contributed extensively to open standards as well as having set standards of our own. Using multicores and heterogeneous computing introduces some challenges of complexity and I’ll be talking about standards and how they can help hide complexity in order to enable ease of development and time to market. Independent software developers need these standards so that they can create the applications that run across multiple platforms. In turn creating the successful developer partner community that is so necessary for all of us, as an industry to thrive.
I hope you’ll find my keynote interesting and I look forward to meeting many of you at the developer summit in Bellevue in June.
What do you think about heterogeneous computing? What are the issues you want to hear about?
Jem is an ARM Fellow and likes to think of himself as "The Godfather" to technical talent in ARM. After spending some time in his youth writing software for satellites and traffic-lights among other fascinating things, Jem spotted the technical inflection point of the mobile industry: graphics, video and other visual computing. As VP of technology in the Media Processing Division of ARM, Jem is busy with a lot of projects involving the future of cool ARM technology, which will revolutionise how people experience and interact with digital devices.
All company and product names appearing in the ARM Blogs are trademarks and/or registered trademarks of ARM Limited per ARM’s official trademark list. All other product or service names mentioned herein are the trademarks of their respective owners.
1 Comments On This Entry
Please log in above to add a comment or register for an account
Page 1 of 1
rightnottobeararms
13 June 2011 - 03:44 PM
How about some direct brain stimulation? I have in mind some nanodevices that connect to your neurons and interface with outside world. You will have thought access to the internet and see if ghadafi is dead or alive or if the queen is still alive. So for every region of the brain a nanointerface will exchange information with the brain neural network. The resistance is futile : you will be integrated. So you could know things instantly and with ease.
Page 1 of 1
»
Blog Tags
»
Recent Entries
»
Search My Blog
»
Recent Comments
-
Jem Davies
on May 11 2012 06:46 AM
ARM Mali-T604: New GPU & Architecture For Highest Performance & Flexibility
-
Sean Lumly
on May 10 2012 10:34 PM
ARM Mali-T604: New GPU & Architecture For Highest Performance & Flexibility
-
Jem Davies
on Apr 26 2012 08:45 AM
ARM Mali-T604: New GPU & Architecture For Highest Performance & Flexibility
-
-


1 Comments






















