What happens when everyone is designing their SoCs with cores licensed from ARM? Where's the differentiation?
Time was when a great many companies had their own processor architectures. It was a pinnacle of electronic and semiconductor achievement and many digital engineers wanted to have a crack at designing one and feeling the glow of watching software execute on an electronic machine of their own devising.
As we know, success breeds volume and volume provides cash to keep chip development riding the down escalator that is Moore's Law.
Intel has been successful as has ARM. Other architectures are available, as well as multiple implementers. And then there is the application-specific specialization of processors for such things as graphics rendering and other activities.
The system-on-chip era, where the processor is just one part of a larger application-specific chip, changed the business dynamic. Gradually, more and more companies have started to gain time-to-market and cost advantages over their competition by licensing a pre-developed processor core from MIPS, ARC, ARM, Imagination and some others. But of these, ARM has been the most successful by far.
But what happens when everyone is designing their SoCs with cores licensed from ARM? Where is the differentiation? Where is the time to market advantage?
One could argue that there is scope for differentiation in how the system-chip is put together, and that the cores are like the bricks of a house. For example, Nvidia has built a quad-core Cortex-A15 system-chip for mobile applications called Tegra 4, which integrates a fifth processor for low-power standby operation. Samsung's Exynos 5 Octa is also a quad-core Cortex-A15 design but one that adopts fully the "big-little" power saving approach with a quad-core Cortex-A7. But is that enough differentiation?
If you are using ARM-defined cores and ARM processor optimization packages to develop your chips. you are essentially on the same time-to-market line as everybody else in the world, unless you are one of the lead partners that helps ARM develop the core in the first place. And if you are helping develop the core in the first place maybe you would do better developing that for yourself alone under an architecture license.
This argument could be one of the reasons we are starting to see a rush of ARM architecture licensees coming forward, although it is interesting to note this is predominantly (exclusively?) with companies based in the western hemisphere.
The best known is probably Apple. But Qualcomm has also developed its own ARM-compatible processing architecture called Krait. Broadcom recently announced it had taken architectural licensees for both the ARMv7 and the 64-bit capable ARMv8 instruction set architectures. As ARM moves up to 64-bit computing, the number of architectural licenses seems to have increased with Applied Micro and Cavium both going down the route that allows differentiation at both the processor core and the system-chip level.
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.