Google set to make its own energy efficient ARM Server chip

Do you have a question? Post it now! No Registration Necessary

Translate This Thread From English to

Threaded View
Google set to make its own energy efficient ARM Server chip
-----------------------------------------------------------

http://www.valuewalk.com/2013/12/google-inc-goog-considers-face-off-with-intel-corporation-intc/

Typically Intel chips waste 90% of the power that goes into
a data center as heat. And Google is fed up and wants an
alternative for the millions of servers that it has.
What better than purchase an ARM license and build
your own ARM server chips? :)
It will be possible to expand the data centers to tens of millions of servers
and still clock in with less wasted energy.

The biggest speed restriction is the DDR cycle time that limits CPU
to about 10MHz operating speed. No matter whose chips are used.
So may as well go for the more energy efficient ARM chips.

Google could use this opportunity to break into the hardware business
to power its tablets and netbooks by making the chip with
one single header file that names every register and every bit field
and then selling the chip and the header file to the Linux and open
source community. Every single open sourced project is likely to switch to using
the Google ARM chip within days. If google then brought out a second
chip, it would take hours to days to change that one single header
file and get all the previous work up and running on the new ARM chip again.

If google played their cards right, they will own the entire ARM server
market, tablet market, and Linux ARM chip based market.
With that power, they can squeeze out the patent trolls like appile
and microshaft by denying them any further markets because it will
all be taken up by cheap Linux gadgets and open source projects
that complete for attention at every niche at every level of competition.

In fact any open source project can make their own SoC with single
header file and storm the entire market. It does not have to be google.
It could be Ubuntu, or Mint, or one of the numerous other distro makers.
All they need is about USD 2 million in the bank, with a bit crown funding
perhaps, and never have to look back after taking their first orders.


Re: Google set to make its own energy efficient ARM Server chip
Quoted text here. Click to load it

I'm curious: where does the other 10% go?  Is Google creating matter
with it?

--  
Grant

Re: Google set to make its own energy efficient ARM Server chip
Grant Edwards wrote:


Quoted text here. Click to load it
intel-corporation-intc/
Quoted text here. Click to load it

10% of the chips do the real computing at any one time.

Re: Google set to make its own energy efficient ARM Server chip
7 wrote:
Quoted text here. Click to load it


So Madman Muntz them other 90% offa the board. Problem solved.

--  
Les Cargill

Re: Google set to make its own energy efficient ARM Server chip
Quoted text here. Click to load it

So the actual claim is that 90% of the power is wasted.  Add the
specifier "as heat" implies (to me) that the other 10% is converted
into something other than heat.

100% of the power in a data center turns into heat.

The question ultimiately is how much of that energy consumption could
be avoided while accomplishing the descired task.

--  
Grant Edwards               grant.b.edwards        Yow! I feel better about
                                  at               world problems now!
We've slightly trimmed the long signature. Click to see the full one.
Re: Google set to make its own energy efficient ARM Server chip
Quoted text here. Click to load it

Actually I suspect it is far higher than that. The theoretical maximum
is completely reversible computing, which should in principle create no
heat at all. That tends to be very slow.  Next is to argue that each
 erasure costs kT of energy.
Again they are far far far less efficient than that. Even 1kT per bit
operation would imply only 10^-21J/bit operation. Assuming 64 bit words
and 10GHz operation, that would still only imply 10^(-9) watts of power
consumption. Instead what we get is something like 100W so, that is
99.99999999% of the power going into heat rather than useful
computations.  


Quoted text here. Click to load it

Useful work.  One could call a computer a kind of refrigerator, you feed
in random bits in the memory (max entropy), and you get the output out
at zero entropy (the result of the calculation).
Quoted text here. Click to load it

Actually no, some of it goes into reducing the entropy of the system.  

Quoted text here. Click to load it

Re: Google set to make its own energy efficient ARM Server chip

Quoted text here. Click to load it



But surely that's only temporary.  Does entropy continue to be reduced
indefinitly for as long as a computer is being run?  Or does it reach
some sort of "average" level and from then on you're just
transitioning between different configurations of similar entropy?

--  
Grant Edwards               grant.b.edwards        Yow! You can't hurt me!!
                                  at               I have an ASSUMABLE
We've slightly trimmed the long signature. Click to see the full one.
Re: Google set to make its own energy efficient ARM Server chip
Quoted text here. Click to load it
As I said, in theory a computer can be run reversibly.-- ie it need
spend no energy. Unfortunately this occurs only for a perfectly
issolated computer and infinitely slowly. computers we have now use
irreversible operations like mad to stabilise the memories and the
operations, and alow them to operate quickly. My estimate was for
1KT/bit operation which is about the minimum we could imagine for
irreversible computation. But real computers are more than a  billion times
worse than that if my calculation is right.  




Re: Google set to make its own energy efficient ARM Server chip
unruh wrote:

Quoted text here. Click to load it


I see where the conversation is going.
What I meant was relative to an ARM chip.

If rebuilt using digital equivalent of quantum computer,
which requires another 5% extra silicon, then computing
power would increase x10 to x100 with 5% extra consumption.
So the power saving would be astronomical, or equivalently
the throughput is much greater, but since
a lot of software would have to be rewritten, the trade off in benefit
is not easy to work out until the software world catches up.

Regardless of Intel or ARM, the throughput is limited by
page cycle times of DDR which hasn't improved since the 80's and stuck
at 10MHz. The ARM wins because the quiescent drain is much lower despite
both CPUs having the same DDR limit.
Digital version of quantum computers will get over that,
but normal software can't work on such computers.


Re: Google set to make its own energy efficient ARM Server chip
Quoted text here. Click to load it

Of course that's what you meant. :) And that sounds about right to me.

However, the laws of Usenet require that even slightly vague
statements be interpreted in the manner that provides the most fuel
for a good debate (and the more esoteric the resulting discussion, the
better).

--  
Grant Edwards               grant.b.edwards        Yow! It's OKAY -- I'm an
                                  at               INTELLECTUAL, too.
We've slightly trimmed the long signature. Click to see the full one.
Re: Google set to make its own energy efficient ARM Server chip
unruh wrote:

Quoted text here. Click to load it


I see where the conversation is going.
What I meant was relative to an ARM chip.

If rebuilt using digital equivalent of quantum computer,
which requires another 5% extra silicon, then computing
power would increase x10 to x100 with 5% extra consumption.
So the power saving would be astronomical, or equivalently
the throughput is much greater, but since
a lot of software would have to be rewritten, the trade off in benefit
is not easy to work out until the software world catches up.

Regardless of Intel or ARM, the throughput is limited by
page cycle times of DDR which hasn't improved since the 80's and stuck
at 10MHz. The ARM wins because the quiescent drain is much lower despite
both CPUs having the same DDR limit.
Digital version of quantum computers will get over that,
but normal software can't work on such computers.


Re: Google set to make its own energy efficient ARM Server chip
unruh wrote:

Quoted text here. Click to load it


I see where the conversation is going.
What I meant was relative to an ARM chip.

If rebuilt using digital equivalent of quantum computer,
which requires another 5% extra silicon, then computing
power would increase x10 to x100 with 5% extra consumption.
So the power saving would be astronomical, or equivalently
the throughput is much greater, but since
a lot of software would have to be rewritten, the trade off in benefit
is not easy to work out until the software world catches up.

Regardless of Intel or ARM, the throughput is limited by
page cycle times of DDR which hasn't improved since the 80's and stuck
at 10MHz. The ARM wins because the quiescent drain is much lower despite
both CPUs having the same DDR limit.
Digital version of quantum computers will get over that,
but normal software can't work on such computers.


Re: Google set to make its own energy efficient ARM Server chip
unruh wrote:

Quoted text here. Click to load it


I see where the conversation is going.
What I meant was relative to an ARM chip.

If rebuilt using digital equivalent of quantum computer,
which requires another 5% extra silicon, then computing
power would increase x10 to x100 with 5% extra consumption.
So the power saving would be astronomical, or equivalently
the throughput is much greater, but since
a lot of software would have to be rewritten, the trade off in benefit
is not easy to work out until the software world catches up.

Regardless of Intel or ARM, the throughput is limited by
page cycle times of DDR which hasn't improved since the 80's and stuck
at 10MHz. The ARM wins because the quiescent drain is much lower despite
both CPUs having the same DDR limit.
Digital version of quantum computers will get over that,
but normal software can't work on such computers.


Re: Google set to make its own energy efficient ARM Server chip
Quoted text here. Click to load it

Four repeats of the same response probably was a bit excessive, despite
your annoyance.
What I was saying was that relative to the "theoretical" ideal there is
still HUGE room for improvement in the efficiency of the cpus. While
some of that slack would certainly be lost to practicalities, that still
leaves a lot of room for improvement.  

Quoted text here. Click to load it

Then I am not sure what you mean. Are you saying that a typical ARM chip
is 10 times as efficient as an Intel chip? What does your "90%" mean?
Quoted text here. Click to load it

No, that would be the job of the compiler, not the software.  

Quoted text here. Click to load it

Not sure either what you mean by "digital versions of quantum
computers".  
Quoted text here. Click to load it

Re: Google set to make its own energy efficient ARM Server chip
unruh wrote:

Quoted text here. Click to load it
with-intel-corporation-intc/
Quoted text here. Click to load it

Blame my service provider / ignore it.
90% of their revenue goes to servicing
debts and 10% to customer service. Between 6 and 9pm there is no
bandwidth to speak of so it all keeps retrying.

Quoted text here. Click to load it

Afraid not old chap.
The whole structure of writing programs is different.
There might be a way to do it with a compiler
that some clever boffin could work out.
I used to think something like VHDL could not exist
because hardware and software were so different.
Shows how wrong one can get. :)


Quoted text here. Click to load it

Analog computers are different from digital computers.
Digital versions of analogue computers can be made.

Digital computers are different from quantum computers.
Digital versions of quantum computers can be made.


Re: Google set to make its own energy efficient ARM Server chip
Quoted text here. Click to load it

A quantum computer is not an analog computer. It uses bits to represent
numbers just like any other digitial computer does. That those bits can
be in a superpostion of states, or that they can be entangled with other
bits does not make it analog.
It is certainly true that a  quantum computer working on a problem which
can be sped up by quantum computation, behaves differently from a
classical computer, but just as for classical digital computers, a
quantum computer has a few operations which are universal. Ie, any
quantum computation can be implimented by repeated application of that
minimal set of operations.  

The key feature as far as energy efficiency is concerned is that  
quantum operations must  in general be reversible which means that
intheory they require no energy to run. That is of course not true in
practice, but they need very very little energy to run.  

Note that attempting to simulate quantum operations on a classical
digitial computer might be what you refer to, but that would be a
completely stupid thing to do, since the memory and time requirements
would be far  greater than even any classical computer solving the
same problem-- it would offer no advantage at all
.  
Quoted text here. Click to load it

Re: Google set to make its own energy efficient ARM Server chip
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA256

unruh wrote:
Quoted text here. Click to load it

Current quantum computers function at very low temperatures. I'm using the  
word "function" liberally :). The energy needed for cooling makes it very  
energy inefficient.

That said, it seems some progress has been recently made for preventing  
decoherence of qbits at room temperature. If this work is confirmed, it  
could open the door to very energy efficient high density data storage,  
maybe even some kind of long lived RAM that only needs to be refreshed every  
few minutes or more.  

Also, if this work can be extended to coherent quantum operations at room  
temperature then we may see in a few decades the integration of quantum co-
processors or specialized cores in main stream CPU.

General quantum CPUs are very unlikely in the the next several decades due  
to the complexity of programming such a beast for general computing. Even  
simple mathematical algorithms have been difficult to test in current  
quantum computer with few qbits.

Quoted text here. Click to load it

The only use I know for simulating quantum systems on non-quantum computers  
is physical simulations, particles, materials, or molecular simulations.

Regards.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.10 (GNU/Linux)

iF4EAREIAAYFAlKvxT8ACgkQGQjO2ccW76qfVgEAgfWQtjfoUAh+6qn8VpagWXS9
x31+RW9z0rADMJKitf4A/1Bsv9fxbvnSuLOIp3fvrY9sGwuAJKmIg/AChbglK4j+
=rMPd
-----END PGP SIGNATURE-----


Re: Google set to make its own energy efficient ARM Server chip
Quoted text here. Click to load it

Far less so than current cpus. As you say, quantum computers do not
exist. I am discussing theory, not experiment.

Quoted text here. Click to load it

It would be nice. On the other hand, the way you make qbits last a long
time at room temperature is to make sure that they do not interact with
anything. Since reading and writing IS interacting with something, you
preferrably never write or read to these bits.  
On the other hand as I mentioned, current computers are horrible energy
hogs, so even a little bit could give huge savings.  


Quoted text here. Click to load it

See above.


The problem is that quantum computers really are not better than
ordinary computers except on a small subset of tasks. One might be
simulation of quantum systems (eg atoms getting together to form
molecules), or perhaps some decision processes ( finding the most
efficient or lowest cost process amongst an exponentially large number
of possibilities), both of which would be useful. On the other hand, for
doing your taxes or writing your letters, they are liable to be pretty
useless.


Quoted text here. Click to load it

It is a HUGE industry. Pharmaceuticals for example. And they are
horribly slow, and can only simulate a very few number of components.

Re: Google set to make its own energy efficient ARM Server chip
unruh wrote:

Quoted text here. Click to load it


The last paragraph is a collection of sweeping statements :)

Not particularly true as what you are referring to is a simulation
of a quantum computer. I'm talking about direct behavioural
implementations of quantum behaviour in the logic gates and
ways to making use of that to solve practical problems.
A half way house between a real quantum computer and a simulation
of a quantum computer.
The product of that is computing devices with 10x to 100x performance
enhancement over a digital computer in exchange for 5% extra silicon.



Re: Google set to make its own energy efficient ARM Server chip
Quoted text here. Click to load it

Reference please.  
There is no "halfway house". And where you get that 10x to 100x
improvement I do not know.  
Entanglement is a harsh mistress.

Quoted text here. Click to load it

Site Timeline