I think another important fact to remember is that the programming and execution models are quite different for a CPU and a GPU. CPU is still a much more sequential than GPU code which is massively parallel.
' "offer security features to protect 1080p HD content for streaming applications." People will find workarounds for these kinda protection in matter of days, after the release. IMO this is pointless.'
You have to consider this issue from their side to understand the motivation. It's really just a pitch directly to the content creators since Intel is the one that created HDCP and then charges everyone US1000+ for device key sets. The only way they can get more people to adopt and pay up is to offer some benefit and that means making more content readily available.
@Luting, the reason why they didnt do it before is quite simple. CPUs x86 based systems, GPUs fpga based systems. GPUs became more complex and hard to code than CPUs. However as ARM is pushing hard, intel/amd needs to find out different approach and solutions to get business back. thats the reason why we see different approaches
Future of computing is in FPGA where you can embed hundreds of processor into one single chip.
Firstly, it has been long time that even low end PC/laptop will have graphic accelerator. Don't know why takes so long for AMD/INTEL to realize that.
Secondly, if GPU is already integrated into CPU, why not simply expand CPU instruction to support all GPU instructions? This will make programming model a lot simpler. Putting two cores in one die only solves cost & power issue, not programming issue.
It is very important for the CPU vendors to actullay integarate the GPU's into the main processors. These new CPU's will definitely bring down the total cost of complete multimedia PC with good graphics. But what is the imapct of these products on the sales of Nvidia or ATi.
What are the engineering and design challenges in creating successful IoT devices? These devices are usually small, resource-constrained electronics designed to sense, collect, send, and/or interpret data. Some of the devices need to be smart enough to act upon data in real time, 24/7. Specifically the guests will discuss sensors, security, and lessons from IoT deployments.