NVIDIA was the first of four teams to announce that they have been awarded a slice of the DARPA Ubiquitous High Performance Computing [UHPC] program. NVIDIA led a team that also included Cray, Oak Ridge National Lab and six top universities. From the looks of it, they took a page from How to Be the Best at Everything and gathered a team of supercomputing juggernauts. The four-year contract award includes $25 million in funding and a shot at the latter portions of the program [via down selection].
This recognizes NVIDIA’s substantial investments in the field of parallel processing and highlights GPU Computing’s position as one of the most promising paths to exascale computing,” said Bill Dally, NVIDIA’s chief scientist and senior vice president of research, and the team’s principal investigator. “We look forward to collaborating to develop programmable, scalable systems that operate in tight power budgets and deliver increases in performances that are many orders of magnitude above today’s systems.”
The DARPA UHPC program is attacking technical issues that are key to the future of high performance computing, from the embedded terascale to the exascale,” said Steve Scott, Cray’s senior vice president and CTO, and the Cray principal investigator on the team. “We are excited to be working with this team, and we believe the directions we are pursuing will lead to radical improvements to the state-of-the-art in the coming decade.”
The eventual platform developed by the team will crest the exascale mark proposed by the original DARPA agency announcement. From the looks of the team, the universities will perform much of the up-front investigation, especially with respect to software. NVIDIA will likely lead the charge in the core silicon department and Cray will probably handle the platform and RAS features.