ARM says its 64-bit ARMv8 processor architecture is a real contender for servers and PCs. But without an appropriate process from major fab partners to etch the chips, the design doesn't matter all that much. That's why an agreement between the stewards of the ARM designs and Taiwan Semiconductor Manufacturing Corp is vital if …
"...the design benefits between x86 and ARM will have to make up the difference in the manufacturing gap"
I can't imagine that will be too difficult - the x86's internal CISC->RISC translation must be quite a bloat, adding latency to branches, and code density will always be crap thanks to the register non-orthogonality, no matter how clever internal register renaming and other workarounds get at optimising the micro-instructions thereafter.
Agreed that the CISC->RISC translation isn't great but Intel has always done a surprisingly good job competing with RISC, starting with the Pentium Pro which was at least as fast as most RISC chips at the time (which is why nobody is using MIPS or HP-PA etc. anymore) and currently a late-model iWhatever core seems to be at least twice as fast with an integer load per-clock than a late-model ARM code in a new iPad, and must faster than that at floating-point.
I expect things to continue as they are for at least several more years, i.e., ARM winning in mobile thanks to much lower power consumption and Intel winning elsewhere thanks to much higher performance.
You're both missing the point
The big advantage of ARM is not architecture, as there are other RISC processors out there that can beat it at its own game.
The big advantage is the ecosystem, where one can buy an ARM chip from just about anyone, and anyone can join and be fabless too.
That drives the prices down, turning the market into something Intel does not want to be a part of, as they have demonstrated in the past leaving markets when margins became too low.
Your comparison between a core iN and an ARM core is not adequate, the x86 core in the Intel CPU has a bajillion more features (x86 decode, SSEs, AVX, specific decode/encode functions, etc.) and wider computing units on top of a lot more cache and having 64bit support. And they're way more than twice as fast, even if pure DMIPS is about a factor 2 between a core i5 quad and an arm cortex a9 quad like the iPad cpu, you have to remember that's only integer performance and hardly representative of overall performance.
The big reason the Intel cores win that round is because they're much wider and consequently have more IPC than the ARM core which is really really tiny. You could for the purpose of benchmarking include a wider Integer Unit in the ARM core and get exactly the same DMIPS/clock as the Intel, but the CPU would still be quite inadequate.
Either way, there is NO competition between 22nm and 32nm chips, since the first cost MUCH more to produce at the moment, and Intel's process is still far from maturity, as the first Ivy launch demonstrated - let's wait till they get it right and we'll see exactly how far behind TSMC is.
Plus, as the number of bleeding edge -capable foundries shrinks, I wouldn't be surprised to see TSMC emerge as a winner and end up with more fab capital than Intel, which it's worth reminding, is only worth about 20 new fabs right now ( as the costs rise for every additional process - at the moment at least - Intel could very well end up facing too high a capital cost to remain one node ahead).
Intel has the high-end performance advantage, so much so that the fastest x86 chips are similar to POWER (the last big RISC still standing) in performance. However low-power x86 chips aren't nearly as competitive, for example the 32nm Atom doesn't look good at all compared with 40/45nm ARM on either performance or power consumption. So the interesting battle is next year with next-gen 22nm Atoms and 28/20nm ARMs.
One area where ARM has a big advantage (due to the ability to design new CPUs much faster than Intel) is heterogeneous multiprocessing where you combine several really fast cores and a few power efficient ones.
The only good part about ARM in super computing is that ARM cores cost nothing and are good enough to do the very small CPU part that GPUs cannot do.
ARM does not have the ability to design new CPUs much faster. They only have a basic toolkit to help you build stuff with their designs, you'd still be in a lot of trouble if you wanted to create a 16-core arm cortex-a9 because it's not part of the ARM designs (cfr Tilera, took them a while to get all 100 cores plus interconnect on the chip).
I was talking about mobiles and tablets (if you wanted a low power supercomputer you certainly wouldn't use x86 cores or GPUs but a purpose designed ARM core similar to the undisputed #1 BlueGene/Q in the Green500). What you'll see next year is fast Cortex-A15 cores paired up with tiny power efficient Cortex-A7 cores. When you don't do anything CPU intensive it will automatically switch to the A7 core, thus saving power.
ARM already supports up to 8 cores with the A15, so extending that to 16 or more doesn't seem too far fetched. Calxeda designed their own interconnect between chips (like Hypertransport) which is different and more difficult.
But what I really meant with designing cores much faster is that due to the inherent simplicity of RISC it is possible to create new CPU designs with less effort. And it's not just ARM, Qualcomm, Marvell, and AMCC doing the same. This would not be possible if it was x86.
ARM don't make the money to sub TSM for a new plant or really for much of anything. So this must either be PR or ARM have given TSM an exclusive, limited time offer.
Inquiring minds wish to know which it is!
makes for a nice headline but let's face it all ARM can do is encourage fabs to support their ambitions.
There's no way they can match Intels spending power. I'm more interested to hear your views on what tsmc and other fabs will do to counter Intels investment in ASML for next gen fab tech.
Fab Less...Isn't that Welsh for 'Awesome'
Surely its more like 2.6D? Or is "3D" the meaningless hyperbolic suffix du jour, like XP was a few years ago?
FinFET is 3D by comparison to a 2D flat transistor.
The fact that the switching happens on a VERTICAL plane instead of the HORIZONTAL plane where everything else is, does make it have two non-parallel planes, enough to define a volume, which is 3D mkay ?
You're the meaningless hyperbolic suffix du jour I suppose.
- Pic Mars rover 2020: Oxygen generation and 6 more amazing experiments
- Microsoft's Euro cloud darkens: US FEDS can dig into foreign servers
- Boffins spot weirder quantum capers as neutrons take the high road, spin takes the low
- Plug and PREY: Hackers reprogram USB drives to silently infect PCs
- Review Fiat Panda Cross: 'Interesting-looking' Multipla spawn hits UK