@Robotics Developer: Just to clarify, the Windows division of Msoft will support ARM in its next-gen product. Dileep, who is a thought leader in the division of Msoft that runs big data centers, is more bullish on x86 retaining its dominance in the server-system space than he is on ARM making any big in-roads there anything soon given the huge s/w support issues beyond Windows.
~2/3rds of ARM shipments go into mobile applications. Of, the other 1/3rd, a lot of these units go in the microcontroller area. But there is a pretty respectable amount of "A" profile processors into automotive infotainment, TVs and other home gadgets. Definitely on a path to number 1 in the digital TV space with 3 of the top 4 now shipping ARM Powered platforms. But yes, the point in time where ARM has meaningful market share in applications such as servers and networking infrastructure equipment is years, not months, away.
This perspective is based on my prior experience with embedded applications. If you want a specific answer to your OS question, then you will need to address Microsoft....
The big challenge with the embedded operating system vendors that I have worked with in my last (too many!) years is that the port to a new architecture is a relatively small part of the total cost. The bigger cost is ensuring that software runs with a myriad of applications, supporting the product in the market and then and then continually driven forward (while ensuring that legacy apps will still keep working with the new revision etc).
Thanks for the shout out!
A quick clarification - Marvell has an architecture licence. So the processor core in the Armada-XP device is not the Cortex-A9. It is their own processor. But utilizes the same version of the ARM instruction set as the Cortex-A9
So if I understand the current approach: Microsoft wants to pick up on the ARM based designs with Windows BUT is not interested in ARM based servers. Is there significant differences between porting Windows to ARM platforms and using that port for servers? If the work is similar than the effort is already going to be made (I think?). Just wondering what I missed..
OK a couple insights: ARM now has a full time director level exec working on smoothing the path to the data center for the architecture by assuring solid ports and optimized performance of Java enterprise software, Linux OSes and other key libraries. Tilera has some design wins for its 32-bit, 64-core VLIW part in data centers, but said Top Tier data centers require 64- bit support even for the Web server systems, and Marvell said everyone is evaluating its four-core A9 SoC but no one has made any purchase decisions yet.
Microsoft disclosing their server design to the vendors is really interesting. They are making it open to all and want other small businesses to actually follow a standard solution. This will give great visibility to the supplier of critical components in these servers and could actually result in more sales for the suppliers.
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. Are the design challenges the same as with embedded systems, but with a little developer- and IT-skills added in? What do engineers need to know? Rick Merritt talks with two experts about the tools and best options for designing IoT devices in 2016. Specifically the guests will discuss sensors, security, and lessons from IoT deployments.