I think the ARM family will continue and grow, as expected it is moving into the 64 bit world and will continue to multiply the cores and increase processor clock speed. On a slightly related note: Digital Equipment Corporation was a major player for quite awhile but fell prey to a number of factors (mostly self inflicted IMHO). DEC got complacent, grew too many layers (adding cost), ignored the PC market for too long, was too slow to react to market forces/needs; these are some of the reasons why DEC is not more. I am sure there were other reasons as well, I never worked at DEC but loved the company anyway (had a lot of friends that worked there). It was sad to see them fail, but the lessons learned can and should be applied to ARM and any other company. I like the comment about competing with yourself, that makes a lot of sense!
For better or worse, the computer sector became a commodity. From high-performance down to tablets and phones and embedded systems there just isn't a lot of space for hardware differentiation. Linux, contrary to what some people think, has taken over under the covers---partly because of price but mostly because it is flexible and simple both in the technical and business sense.
In order to compete Intel will have to figure out a way to commoditize it's products, by making low-power, highly integrated and inexpensive SoCs. They certainly aren't there now---if you want to argue that point, please show me an Intel platform capable of running Linux that sells for $30. ARM can do that, but Intel currently can't yet.
I would say, yes.
Dual-core is a must as the time progresses(less than a year, I guess).
The users of the mobile are performing more work on the device than ever before and hence having a 2 core processor in the device is very lucrative for the responsiveness of the device to keep the user keep using the device(mobile, pads, ...) for a longer time in day.
Peter : a thoughtful discussion, perhaps you would like to comment / write more in future about following scenarios :
1. Apple & QC depending less and less on ARM / "Imagination" and doing much more themselves from ground up in order to distinguish
2. The second tier ( nVidia / Samsung ) shifting their strategy ( i,e. playing the more cores game to going the same way as Apple / QC ie, improving on ARM design )
3. Would Intel ever develop a credible low - power alternative to ARM and gain marketshare ( even if at a lower margin than x86 monopoly )
4. How about up and comers like Media Tek / Hua wei ? which of above 3 scenarios would suit them best?
Excellent points all. I am with Danny.
These are reasons why:
1)Qualcomm is buying display companies.
2)The IP battle is moving to PowerVR versus Mali versus Others
3) What else is on-board the SoC including the modem counts for a lot.
4) 3-D packaging and TSVs for maximizing memory bandwidth and minimizing power consumption of that bandwidth is high priority.
Very good synthesis of the CPU core market, Peter! I really appreciate.
I am just surprised by the comments made: many high level position about the evolution of the CPU market, the SC industry and so on... but nobody has simply noticed that a great % of ARM success is due to the solid ECOSYSTEM that the company has built, year after year.
Building such an ECOSYSTEM will be pretty difficult to duplicate, would take 10+ years... and is probably the reason why ARM will stay the leader, and consolidate.
Blog Make a Frequency Plan Tom Burke 17 comments When designing a printed circuit board, you should develop a frequency plan, something that can be easily overlooked. A frequency plan should be one of your first steps ...