-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
____/ Mark Kent on Sunday 07 Feb 2010 09:18 : \____
>
>
> Roy Schestowitz <newsgroups@xxxxxxxxxxxxxxx> espoused:
>>
>>
>>
>> ____/ Mark Kent on Friday 05 Feb 2010 16:39 : \____
>>
>>>
>>>
>>> Roy Schestowitz <newsgroups@xxxxxxxxxxxxxxx> espoused:
>>>>
>>>>
>>>>
>>>> Chinaâs Next Supercomputer is using Linux
>>>>
>>>> ,----[ Quote ]
>>>>| China is on its way to make a new indigenous
>>>>| supercomputer build with custom
>>>>| microprocessors developed at the Institute Of
>>>>| Computing Technology. This supercomputer, the
>>>>| petascale Dawning 6000 is a successor of the
>>>>| current fastest supercomputer China has, the
>>>>| Dawning 5000a. The Dawning 5000a has been
>>>>| running on AMD powered microprocessors and
>>>>| Windows HPC Server as itâs OS. The Dawning
>>>>| 5000a ranks 11th in the world. Apart from
>>>>| that, China also holds the #5 supercomputer in
>>>>| the top 500 list.
>>>> `----
>>>>
>>>> http://techie-buzz.com/linux-news/chinas-supercomputer-linux.html
>>>>
>>>
>>> The Dawning 5000a was ranked 19th in the World last November, the last
>>> time the top500.org list was updated.
>>>
>>> This is, to be fair, an incredible achievement for Windows, though. One
>>> wonders how often the nodes crash, and how the overall machine recovers.
>>
>> We once tried Windows clusters over here and it was a disaster. Not much has
>> changed since then. Windows is built by Microsoft alone, not clustering
>> experts like IBM (whose developers write Linux).
>>
>> Microsoft has more or lost lost its ambition in HPC (they rarely mention it).
>> Windows also loses the mobile sector, which is probably the fastest growing.
>>
>
> My mental image of data networks in the future has arbitrarily capable
> terminals (perhaps a pen, a watch?), linked by best connectivity to a
> huge computing clusters which hold data and provide massive computing
> power.
>
> The hard bit is making voice work effectively, though... 3-mode
> networks are the proper solution, but there's a huge amount of
> commercial pressure towards a one-size-fits-all approach, which
> basically is ineffective at best.
Voice is still slower than thought, but it is more precise with a trigger that's
less sensitive. That said, human evolution made us fast communicators and
audiovisual processors, so pseudo-telepathy (mind interpretation with sensors) is
likely too far fetched. It's already possible but only at a crude level... there
are nice video demos of spinning a ball with one's mind after some quick
training phase (a few minutes).
- --
~~ Best of wishes
Roy S. Schestowitz | Watch your step, that soapbox is very slippery
http://Schestowitz.com | Free as in Free Beer | PGP-Key: 0x74572E8E
Cpu(s): 22.6%us, 5.0%sy, 0.1%ni, 70.6%id, 1.3%wa, 0.0%hi, 0.4%si, 0.0%st
http://iuron.com - semantic engine to gather information
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.9 (GNU/Linux)
iEYEARECAAYFAktwqcUACgkQU4xAY3RXLo5lBgCbBD1ixPLwPFYxt+8A3Tg0wUyr
v0kAmwQZ7jaj8VNn5ZNmzAvy/qL9CZNQ
=GpdH
-----END PGP SIGNATURE-----
|
|
