Share This Entry:
I will be attending the 7th Multicore Developers Conference in San Jose next week as I’m speaking on a panel there at the McEnery Convention Center, chaired by Jon Peddie, entitled “How Many Cores Does it Take to Reach the Singularity?”
The ARM Mali-400 MP was the world’s first embedded multicore GPU, and ARM has been designing multicore CPUs for over a decade now, so it is natural that we be there to talk about our experiences and to discuss future technical directions. Currently, with the Mali-T658, we scale to 8 cores. Where does it end? What drives the limits? What does the market need this sort of performance for? I am sure we will have an entertaining time discussing these and other questions.
I hope to see you there - Tuesday March 27th at 4:30 at the Hilton in Alamden Ballroom 1/2.
Watch the video interview below, to find out more about the panel.
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.
Share This Entry:
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
Jem Davies 
30 March 2012 - 10:28 AM
Well, the panel at the Multicore DevCon went well and was great fun. A number of people wanted to know when the singularity (the point at which machines are smarter than humans) would arrive. Pradeep from Intel who is a big fan of the “big data” approach to the problem was very keen on building Exascale supercomputers (with associated power stations) to solve the problem, but I was more interested in when we can have portable devices with such capabilities.
Given that with ARM’s Mali-T658 we already have around 300 GFLOPS of computational capability, and we're ramping fast in terms of scaling that even further with subsequent products, then soon we will have amazing amounts of compute power available in handheld consumer electronics devices.
I think we all agreed with my assertion that it really depended on what problem domain we were referring to, and that within certain domains we had already reached the point where computers were there already. However, a machine that thinks about thinking or even one that can reflect on the process of thinking about thinking was a way off yet. Oh, and our software colleagues have most of the heavy lifting to do…
Given that with ARM’s Mali-T658 we already have around 300 GFLOPS of computational capability, and we're ramping fast in terms of scaling that even further with subsequent products, then soon we will have amazing amounts of compute power available in handheld consumer electronics devices.
I think we all agreed with my assertion that it really depended on what problem domain we were referring to, and that within certain domains we had already reached the point where computers were there already. However, a machine that thinks about thinking or even one that can reflect on the process of thinking about thinking was a way off yet. Oh, and our software colleagues have most of the heavy lifting to do…
Page 1 of 1
My Blog Links
»
Blog Tags
»
Recent Entries
»
ARM Onsite
»
Search My Blog
»
