RSS
 

Posts Tagged ‘super computing’

NVIDIA® Tesla™ C1060 Computing Processor

19 Jul

If you remember the long gone legendary parallel computing elements known as Transputers, behold.. they have been revived.. 🙂 nVidia have come up with a supercomputing processor that plugs into a PCI-Express slot and gives your computer an astonishing performance capability of more than 933 GFLOPS. It contains a massively parallel 240 core GPU that allows it to achieve such performance at a clock speed of around 1.2GHz.

The NVIDIA® Tesla™ C1060 computing processor board is a PCI Express 2.0 fullheight
(4.376 inches by 10.50 inches) form factor computing add-in card based on
the NVIDIA Tesla T10 graphics processing unit (GPU). This board is targeted as
high-performance computing (HPC) solution for PCI Express systems.
The Tesla C1060 is capable of 933 GFLOPs/s of processing performance and
comes standard with 4 GB of GDDR3 memory at 102 GB/s bandwith.

To add more firepower to your personal super computer, ASUS P6T7 WS Supercomputer motherboard provides 7 PCI express 2.0 slots, so you can actually accomodate as many Teslas in it as your pocket allows.


This amazing feat has been made possible through the groundbreaking computing architecture termed as CUDA by nVidia. CUDA allows a variable number of comoute cores in the system and thus permits extreme scalability to 240 cores and beyond.

The image below shows the CUDA architecture..