Machine learning and Optimization-guided Compilers for Heterogeneous Architectures (MOCHA)
Closed Pre-Solicitation Posted
This opportunity was awarded. See its 2 award notices in the notice history.
- Solicitation number
- HR001124S0035
- Agency
- Defense Advanced Research Projects Agency Department of Defense
- Responses due
- Set-aside
- No set-aside
Opportunity facts
- NAICS code
- 541715 Research and Development in the Physical, Engineering, and Life Sciences (except Nanotechnology and Biotechnology)
- Points of contact
-
- BAA Coordinator mocha@darpa.mil
Notice details come from SAM.gov. Updated .
About this opportunity
Paragraph 1:
The Defense Advanced Research Projects Agency (DARPA) has issued a pre-solicitation for the "Machine Learning and Optimization-Guided Compilers for Heterogeneous Architectures (MOCHA)" program. The goal of this 36-month research and development effort is to develop a new generation of compiler technology that can optimize performance on heterogeneous computing systems. DARPA seeks proposals that leverage data-driven methods, machine learning, and advanced optimization techniques to rapidly adapt compilers to new hardware with minimal human effort. Proposals should address technical challenges related to compiler front-ends, middle-ends, and back-ends. The evaluation criteria will focus on reducing human effort required for hardware adaptation and improving the performance of compiled code. Proposals are due by October 10, 2024.
Paragraph 2:
This opportunity is not set aside for any particular business size or type. No incumbent contractors are identified. DARPA anticipates making multiple awards in the form of contracts, other transactions, or cooperative agreements, but does not specify an estimated total value or budget range. The MOCHA program is part of DARPA's Broad Agency Announcement HR001124S0035, which outlines a 36-month program structure with annual assessments of increasing technical complexity.
Notice text
Machine Learning and Optimization-Guided Compilers for Heterogeneous Architectures (MOCHA) seeks to build a new generation of compiler technology to realize the full potential performance of heterogenous architectures. MOCHA will develop data-driven methods, Machine Learning, and advanced optimization techniques to rapidly adapt to new hardware components with little human effort and facilitate optimal allocation of computation to heterogeneous components.
Attachments
| File | Type | Posted |
|---|---|---|
| HR001124S0035-Amendment-01.pdf | ||
| HR001124S0035.pdf | ||
| Proposal_Instruction_and_Volume_II_Template__Cost___MOCHA_.docx | DOCX document | |
| Abstract_Instructions_and_Template__MOCHA_CT_BK.docx | DOCX document | |
| Proposal_Summary_Slide__MOCHA_.pptx | PPTX presentation | |
| Associate_Contractor_Agreements__ACA___MOCHA_.docx | DOCX document | |
| DARPA_Standard_Cost_Proposal_Spreadsheet__MOCHA_.xlsx | XLSX spreadsheet | |
| Proposal_Instructions_and_Volume_I_Template_for_Technical_and_Management__MOCHA_.docx | DOCX document |
Notice history
| Notice | Type | Posted |
|---|---|---|
| Machine learning and Optimization-guided Compilers for Heterogeneous Architectures (MOCHA) | Award Notice | |
| Machine learning and Optimization-guided Compilers for Heterogeneous Architectures (MOCHA) | Award Notice | |
| Machine learning and Optimization-guided Compilers for Heterogeneous Architectures (MOCHA) | Pre-Solicitation |
On GovTribe
Work this opportunity on GovTribe
- Track it in your pipeline
- Find teaming partners
- Similar opportunities
- Ask GovTribe AI about this opportunity