IBM has selected Nvidia’s Tesla 20-series GPU to power a new line of HPC iDataPlex servers.
According to Dave Turek of Big Blue, Nvidia’s Tesla GPU will provide system “performance boosts” for a number of applications, including energy exploration, science and financial services.
“Nvidia Tesla M2050 is a GPU Computing module integrated into servers that delivers dramatic performance benefits,” explained Turek.
“[In addition], it enables maximum reliability and tight integration with system monitoring and management tools, giving data center IT staff greater choice in how they deploy GPUs.”
Meanwhile, Nvidia spokesperson Andy Keane termed IBM’s adoption of the GPU the “most significant milestone” in Tesla history.
“Scientists worldwide can now access the power of Tesla and CUDA from the world leader in technical computing,” said Keane.
“[Clearly], GPU computing is reaching critical mass. Our CUDA developer toolkit has been downloaded more than 200,000 times…More than 350 universities are teaching CUDA, which enables GPUs to be deployed for supercomputing and other visual computing applications.”
