IBM Employs NVIDIA’s Tesla M2050 in Its Latest iDataPlex Servers
The GPU computing module integrates into the new iDataPlex dx360 M3 servers. IBM says the technology provides “performance boosts.”
NVIDIA told the press this week that IBM’s latest iDataPlex servers are being build around its own Tesla 20-series GPUs. NVIDIA says IBM’s product is the “the first mainstream high-performance computing systems” to build around the NVIDIA technology.
NVIDIA’s Tesla M2050 is a GPU computing module. The company aims for the product to enable maximum reliability and tight integration with system monitoring and management tools.
According to NVIDIA, GPU computing is reaching critical mass. “More than 350 universities are teaching CUDA, which enables GPUs to be deployed for supercomputing and other visual computing applications,” states an NVIDIA press release submitted to EH Publishing last week.
IBM’s adoption of the Tesla for its HPC server line and iDataPlex dx360 M3 servers is another milestone for NVIDIA. Andy Keane, NVIDIA’s general manager, Tesla business, says it means greater access to the technology. “Scientists worldwide can now access the power of Tesla and CUDA from the world leader in technical computing,” he says.
For IBM’s part, the Tesla product means pushing the envelope in terms of performance. “GPU acceleration provides performance boosts for many applications in energy exploration, science, and financial services,” says IBM vice president, deep computing, Dave Turek. “It is among the significant emerging supercomputer technologies to watch in the years ahead.”