Menu Content/Inhalt
Tesla C2075 Print
February 2012
The NVIDIA Tesla C2075 companion processor is built for GPU computing. It features 448 application-acceleration cores per board, dramatically increasing performance compared to a traditional workstation. By adding a Tesla companion processor, engineers, designers, and content creation professionals can add over one Teraflop of computing potential to their workstation.

Key Benefits

Fast floating point performance 
  • 515 Gflops (double precision), 1030 Gflops (single precision)
Faster PCIe communication
  • Dual copy engines provides bi-directional PCIe communication
Higher performance on technical applications with large data sets
  • Large, 6GB GDDR5 on-board memory
Higher performance CUDA driver for Windows OS
  • TCC driver reduces CUDA kernel overhead and enables Windows Remote Desktop and Windows Services
Error Correcting Code (ECC) Memory
  • Meets strict requirements for mission critical applications with uncompromised computing accuracy and reliability.
  • Protects register files, L1/L2 caches, shared memory and DRAM


Key Features Applications
> 448 CUDA Cores
> 6GB GDDR5 Memory
> CAE (structural analysis)
> Reservoir simulation
> Molecular Dynamics
> Numerical Analytics
> Computational Visualization (ray tracing) 

Specifications

Specification Description
Generic SKU reference 900-21030-0020-100
Chip Tesla T20A GPU
Package size GPU 42.5 mm x 42.5 mm
Processor clock 1.15 GHz
Memory clock 1.50 Ghz
Memory size 6 GB
Memory I/O 384-bit GDDR5
Memory configuration 24 pcs 64M x 32 GDDR5 SDRAM
External connectors Single port, dual link DVI-I
Internal connectors and headers •8-pin PCI Express power connector
•6-pin PCI Express power connector
•4-pin fan connector
Board power < = 215 W
Thermal cooling solution Custom active fan sink


Return to previous page