By using this site, you agree to our updated Privacy Policy and our Terms of Use. Manage your Cookies Settings.
449,312 Members | 1,786 Online
Bytes IT Community
+ Ask a Question
Need help? Post your question and get tips & solutions from a community of 449,312 IT Pros & Developers. It's quick & easy.

Imagine if we can get NVIDIA specs to program THIS 300 TFlops GPUsupercomputer !!

P: n/a
From Google, translated to English from French:

http://www.google.com/translate?u=ht...&hl=en&ie=UTF8

"A hybrid system composed of 1068 CPU octocoeurs new generation, with
48 modules GPU to make a maximum of parallel calculations."

"According to our information, the 1068 processors are indeed Nehalem
eight of hearts, and 48 modules are GPU solutions from NVIDIA Tesla.
This will be in addition to a new generation of Tesla, with a very
high probability of the GT200 chip controllers, and even several for
each module (we imagine two, as in the current solutions Tesla
NVIDIA)."

= = = ================================================== ====== = = =

Can you imagine if NVIDIA would just release the specs so that the
world can directly program into the GPU with Assembly Language !!!
Jun 27 '08 #1
Share this Question
Share on Google+
1 Reply


P: n/a
Interesting, NVIDIA has recently offered an SDK called CUDA that can use you
Workstation GPU as a additional processing platform. This could pave the way
for a PC to use an additional GPU to perform secondary calculations while
the primary one draws the image,. This is the main idea the motivated the
Aegia product.

<hs*****@gmail.comwrote in message
news:19**********************************@1g2000pr g.googlegroups.com...
From Google, translated to English from French:

http://www.google.com/translate?u=ht...&hl=en&ie=UTF8

"A hybrid system composed of 1068 CPU octocoeurs new generation, with
48 modules GPU to make a maximum of parallel calculations."

"According to our information, the 1068 processors are indeed Nehalem
eight of hearts, and 48 modules are GPU solutions from NVIDIA Tesla.
This will be in addition to a new generation of Tesla, with a very
high probability of the GT200 chip controllers, and even several for
each module (we imagine two, as in the current solutions Tesla
NVIDIA)."

= = = ================================================== ====== = = =

Can you imagine if NVIDIA would just release the specs so that the
world can directly program into the GPU with Assembly Language !!!
Jun 27 '08 #2

This discussion thread is closed

Replies have been disabled for this discussion.