IBM has agreed to build a half-depth Xeon server that contains room for optional Nvidia Fermi GPU modules.
The new dx360 M3 server isn't specifically designed around Nvidia's Fermi technology, although the server leaves room for an optional pair of two GPU adapters, which can be either Nvidia's Tesla M2050 or M2070 GPU modules. Still, Nvidia praised the announcement as a validation of its technology.
"IBM's adoption of Tesla for their HPC server line is the most significant milestone in Tesla history," said Andy Keane, general manager of Tesla business at Nvidia, in a statement. "Scientists worldwide can now access the power of Tesla and CUDA from the world leader in technical computing."