MODIFICATION
A -- Ubiquitous High Performance Computing (UHPC) - Amendment 1
- Notice Date
- 3/10/2010
- Notice Type
- Modification/Amendment
- NAICS
- 541712
— Research and Development in the Physical, Engineering, and Life Sciences (except Biotechnology)
- Contracting Office
- Other Defense Agencies, Defense Advanced Research Projects Agency, Contracts Management Office, 3701 North Fairfax Drive, Arlington, Virginia, 22203-1714
- ZIP Code
- 22203-1714
- Solicitation Number
- DARPA-BAA-10-37
- Archive Date
- 8/30/2010
- Point of Contact
- Dr. William Harrod,
- E-Mail Address
-
DARPA-BAA-10-37@darpa.mil
(DARPA-BAA-10-37@darpa.mil)
- Small Business Set-Aside
- N/A
- Description
- The purpose of this amendment is to modify page 23, as there was a typo regarding an incorrect reference to TA2. Also, please note that the Initial Closing Date for proposal submission has been moved back to 16 April 2010, and that the Final Closing Date for the is 30 August 2010. See highlights in amended document. Mod 1 The purpose of this amendment is to modify page 23, as there was a typo regarding an incorrect reference to TA. Also, please note that the Initial Closing Date for proposal submission has been moved back to 16 April 2010, and that the Final Closing Date for the is 30 August 2010. See highlights in amended document. Solicitation DARPA is soliciting innovative research proposals in the area of computer system research and development. Proposed research should investigate innovative approaches that enable revolutionary advances in science, devices, or systems. Specifically excluded is research that primarily results in evolutionary improvements to the existing state of practice. To address these concerns the UHPC program will pursue, but will not be limited to: 1) development and optimization of ExtremeScale architectures, technologies, execution models, and the critical co-design of hardware and software; 2) low-energy architectures and protocols for logic, memory, data access, and data transport; 3) dynamic systems that adapt to achieve optimal application execution goals; 4) dependable computer systems including resiliency and security at all system levels; 5) concurrency management and the efficient use of massively parallel resources; 6) locality-aware architectures to reduce data movement; 7) self-aware OS that manages real-time performance, dependability and system resources. The UHPC program will develop solutions for radically new computer systems that overcome energy efficiency, dependability, and programmability challenges. The UHPC vision includes: Efficiency: New system-wide (hardware and software) technology approaches to minimize energy dissipation per operation and maximize energy efficiency, without sacrificing scalability to ultra-high performance DoD applications. Programmability: Develop new scalable system architectures and technologies that do not require application programmers to explicitly manage system complexity, in terms of architectural attributes with respect to data locality and concurrency, to achieve performance, time to solution and other goals. Dependability: Develop a system-wide approach to achieve dependability through fault management techniques enabling an application to execute correctly through both failures and attacks, and to protect the confidentiality and integrity of information, while achieving the user's goals. These goals could include performance, time to solution, energy efficiency or power consumption. Dependability across all levels of a UHPC System Design that is nearly transparent to the user and hardware performance. To realize this vision requires reinventing how computers process and manage data and how applications are developed and executed. UHPC System Designs that merely pursue evolutionary development will not be considered. The UHPC Program will pursue research and development efforts that will explore the technologies and architectures required to enable the development of revolutionary computing systems and overcome "business as usual" advances. Scaling current technology and justifying this approach with feature size reduction arguments cannot accomplish the goals of the program. This can only be achieved via dedicated investment, hardware-software co-design, integrated design techniques that utilize open innovation. Since creating an open innovation environment will be a critical element throughout the UHPC program and heavily weighted in all program evaluations, it should be an important consideration in team formation and plans for working with researchers outside of the proposed team. It must be noted that innovation for the sake of innovation will not be sufficient; proposers must demonstrate the viability, applicability and value to the overall UHPC System Design. Computers based on a UHPC System Designs will deliver extreme scale performance for modern DoD computational applications. It is assumed that system designs developed under this program will be scalable to systems ranging from embedded terascale systems up through at least single cabinet petascale configurations. Full Broad Agency Announcement (BAA) is attached.
- Web Link
-
FBO.gov Permalink
(https://www.fbo.gov/spg/ODA/DARPA/CMO/DARPA-BAA-10-37/listing.html)
- Record
- SN02087736-W 20100312/100310234549-e3a44e960cb467ac9a55ca6fad573ce3 (fbodaily.com)
- Source
-
FedBizOpps Link to This Notice
(may not be valid after Archive Date)
| FSG Index | This Issue's Index | Today's FBO Daily Index Page |