[Beowulf] ARM cpu's and development boards and research
diep at xs4all.nl
Wed Nov 28 08:27:24 PST 2012
On Nov 28, 2012, at 4:30 PM, Prentice Bisbal wrote:
> On 11/27/2012 07:32 PM, Vincent Diepeveen wrote:
>> On Nov 28, 2012, at 12:17 AM, Prentice Bisbal wrote:
>>> On 11/27/2012 03:37 PM, Douglas Eadline wrote:
>>>>> My interest in Arm has been the flip side of balancing flops to
>>>>> bandwidth. A standard dual socket (AMD or Intel) can trivially
>>>>> GigE. One option for improving the flops/network balance is to
>>>>> network bandwidth with Infiniband. Another is a slower,
>>>>> cheaper, cooler
>>>>> CPU and GigE.
>>> I applaud that applause.
>>> What Bill has just described is known as an "Amdahl-balanced
>>> and is the design philosophy between the IBM Blue Genes and also
>>> SiCortex. In my opinion, this is the future of HPC. Use lower power,
>>> slower processors, and then try to improve network performance to
>>> the cost of scaling out. Essentially, you want the processors to be
>>> *just* fast enough to keep ahead of the networking and memory,
>>> but no
>>> faster to optimize energy savings.
>> For HPC the winning concept seems to be increasing corecount at
>> We also see how bluegene couldn't keep its concept - it's having
>> what is it 18+ cores
>> now or so?
> It's not 18+. It's exactly 18 cores. And only 16 are used for
> computation. One is used for operating system overhead, and the
> other is a spare.
> This is exactly in keeping with the Blue Gene Concept, which is
> using low-power processors to conserve energy connected to highly-
> optimized interconnects to create a more balanced system. 'Low-
> power' and 'low core-count' are not the same thing.
Here is what wiki says on the original concept: "Trading the speed of
processors for lower power consumption. Blue Gene/L used low
frequency and low power embedded PowerPC cores with floating point
accelerators.While the performance of each chip was relatively low,
the system could achieve better performance to energy ratio, for
applications that could use larger numbers of nodes."
It's obvious this won't be the case in the future.
It means the future is big fat manycores eating a ton of power for
Arguing then that each core is low power is not relevant - it's not
the original concept of the CPU being low power and embedded
as you can see from the wikisayings.
Also funny is: "System-on-a-chip design. All node components were
embedded on one chip, with the exception of 512 MB external DRAM."
More accurate statement for K20 and Xeon Phi is 'supercomputer on a
chip', and IBM will produce something like that as well.
> Also, the networking for the Blue Gene/Q is quite a bit faster than
> the P's, which is why the Q has 4x as many cores, running at ~2x
> the clockspeed. Someone at IBM must have done the math and came to
> the conclusion that with the increase in communications
> performance, you can increase the performance of an individual node
> by ~8x and still have a balanced system.
More information about the Beowulf