FastForward seeks partnerships with multiple high-performance computing (HPC) companies to accelerate the R&D of technologies critical to the advancement of extreme-scale computing. Approximately $60 million will be available over two years for accelerated R&D in three technology areas: processors, memory, and storage.
Lawrence Livermore National Laboratory (LLNL) is a Federally Funded Research and Development Center (FFRDC) founded by the University of California in 1952. It is primarily funded by the United States Department of Energy (DOE) and managed and operated by Lawrence Livermore National Security, LLC (LLNS), a partnership of the University of California, Bechtel, Babcock & Wilcox, URS, and Battelle Memorial Institute in affiliation with the Texas A&M University System.
On October 1, 2007 LLNS assumed management of LLNL from the University of California, which had exclusively managed and operated the Laboratory since its inception 55 years before.
FastForward is administered by DOE and contracted through Lawrence Livermore National Security, LLC as part of a seven lab consortium (Argonne National Laboratory, Lawrence Berkeley National Laboratory, Lawrence Livermore National Laboratory, Los Alamos National Laboratory, Oak Ridge National Laboratory, Pacific Northwest National Laboratory, and Sandia National Laboratories).
DOE’s strategic plan calls for ensuring U.S. security and prosperity by using transformative science and technology to address the nation’s energy, environmental, and nuclear challenges. This includes advancing simulation-based scientific discovery by investing in applied mathematics, computer science, and networking tools. These investments will enable the research required to develop Exascale computing platforms and the software environment needed to support DOE energy, science, and security missions. Critical to this R&D effort is the aggressive pursuit of energy-efficient HPC systems.
FastForward was born of the recognition that the broader computing market will drive innovation in a direction that may not meet the needs of the DOE mission. FastForward seeks to fund innovative new and/or accelerated R&D of technologies targeted for use in the next 5–10 years.
Whamcloud, a company composed of HPC storage veterans and well-known Lustre experts, implements and supports Lustre solutions in HPC centers around the world, has been awarded the Storage and I/O Research & Development subcontract for the Department of Energy’s FastForward program. The subcontract scope clearly identifies key R&D necessary for a new object storage paradigm for HPC exascale computing.
The Lustre file system architecture was started as a research project in 1999 by Peter Braam, who was a Senior Systems Scientist at Carnegie Mellon University at the time. Lustre is a parallel distributed file system, generally used for large scale cluster computing. Because Lustre has high-performance capabilities and open licensing, it is often used in super computers. At the present time, fifteen of the top 30 supercomputers in the world have Lustre file systems in them, including the world’s fastest TOP500 supercomputer, IBM Sequoia.
“Whamcloud has the world’s best file system team. Being chosen to lead this consortium in researching exascale issues is a real honor for the entire company. We could not be more excited and confident in this group’s ability to tackle these hard problems,” said Brent Gorda, CEO of Whamcloud. “We look forward to interacting with the community to push high-performance computing forward.”
The developed technology will also address next-generation storage mechanisms required by the Big Data market. The subcontract is set for a two-year schedule through the middle of 2014 and begins immediately.
The subcontract incorporates application I/O expertise from the HDF Group, system I/O and I/O aggregation expertise from EMC Corporation, and scale testing facilities from Cray, teamed with file system, architecture, and project management skills from Whamcloud. All components developed in the project will be open sourced and benefit the entire Lustre community.
“The I/O stack for exascale supercomputing needs a hybrid model that leverages the performance and cost benefits of Flash and Disk, complemented with intelligent software. EMC storage technology is at the core of the exascale I/O stack,” said Percy Tzelnic, Senior Vice President, EMC Fast Data Group. “The selection for research and funding from U.S. government agencies is recognition of EMC’s long-standing storage leadership and presence in the HPC market. EMC is committed to help further the next leap forward in supercomputing — catapulting commercial HPC into the exascale era.”
- Whamcloud, composed of HPC storage veterans and well-known Lustre experts, implements and supports Lustre solutions in HPC centers around the world.
- Whamcloud actively promotes the growth, stability and vendor neutrality of Lustre.