Maynard Handley (name99.delete@this.name99.org) on September 27, 2013 11:30 am wrote:

> > The situation today is very much different from that late 80's and '90s'. Simply
> > saying ARM will win because it is coming up from below just like x86 did to the
> > server RISCs is grossly simplistic as well as almost certainly wrong. The money
> > situation is very different and that determines the winner.
>
> While the money involved is relevant, the more relevant issue is the engineering involved.
> The flaw with x86 is the insane complexity of the designs. This complexity means
> - seven years to design a CPU (and so high latency in responding to changing markets)
> - multiple design teams are required (and have to be paid) to create a new design every year
> ARM is so much simpler (and will be even simpler when people start making ARMv8 only chips) that one can
> mount a serious challenge to Intel from below at VASTLY less expense, and on a VASTLY shorter timescale.

Decades ago (MIPS R2000 vs 386 say) RISC had a distinct advantage in terms
of results for design effort. For any market that needs more than a low frequency
in-order scalar processor the difference drops down to noise levels today as
performance requirements rise to even just current smart phone levels.

Saying an A7 core was vastly easier for Apple to design than the Bay Trail core
was for Intel to design is just sheer nonsense. High performance x86 is a long
solved problem (at Intel if nowhere else) whose solutions continuously improve
based on accumulated knowledge. The portion of a Baytrail SoC dedicated to
x86 decoding that the A7 SoC lacks is ridiculously infinitesimal in terms of the
over all device with multiprocessor cache coherency, OOOE execution cores,
dynamic power management, and all of the non-CPU integrated functionality.


>
> The money situation is different, yes, but not all in Intel's favor. To create a competitive chip
> requires much more expense in labor, and a better quality process. And then to compete requires
> selling that chip at essentially ARM prices. This is not sustainable. I expect Atom has lost zillions
> already, and it's going to get worse if Intel have REALLY done what they have claimed (moved Intel
> to annual tick-tock, with the 5 or 6 or 7 parallel design teams that requires).

Lost zillions? What are you 12 or what?

Nonsense. Atom sold in far higher volumes than Intel ever expected. The versions
sold into embedded control had higher gross margin than its mainstream x86 chips
for PCs.


>
> Intel have two advantages
> - better process
> - substantially more experience in turboing a design from cruising speed to bursts of high speed and back.
> The second is ephemeral. Apple (and for that matter Qualcomm) have been methodically working
> their way through the tools of high speed CPUs. They'll get to turboing soon. (Though before
> then they'll probably do common addressing between CPU and GPU, and HW TM.)
> Better process will remain for a while --- but better process costs, and it costs a LOT.
>

> And Intel aren't even just competing against ARM, they are competing against themselves.
> Every time they make Atom better, they steal market away from their desktop line...
> (They've basically learned nothing from the past. What killed Itanium was the deliberate attempt
> to make it so complex that no-one else could ever copy it --- under the bizarre delusion that
> that same complexity would not affect Intel's attempts to wrestle with this monster.)
>

More horseshit. IPF was uncopyable because of three way patent/IP ownership
between Intel, HP, and a jointly held IP holding company. The complexity that
hindered early implementations was building x86 compatibility into silicon. A
pure IA64 device could have been completed years earlier with much better
performance characteristics.