SBIR/STTR Research Award

Peregrine Falcon - Modular Multi-Mission Processing for Spacecraft

Award identifier 5fb7c720ea35c22472c634023629b4fd0c3628828e5aa8db5da6e2d070c0974eAwarding agency Department of Defense · Air Force

Award amount

$1,888,929

Program and phase

SBIR · Phase II – Direct to Phase II

Award year

2025

Explore This Research Award in CaptureIQ

Research the technology, evaluate the recipient and agency, identify related opportunities, and explore potential follow-on work with CaptureIQ.

Award details

Awarding agency
Department of Defense
Branch
Air Force
Recipient company
ZEPHYR COMPUTING SYSTEMS, INC.
Proposal award date
2025-08-04
Contract end date
2027-06-05
UEI
X4KRHRTF83C6
Solicitation number
24.3
Topic code
SF243-D015

Research abstract

To meet the demands of modern space missions, there is a need for a general purpose computing system that can be used on a variety of platforms for a variety of use cases. This enables rapid development and deployment of new missions, which is not possible if each mission requires a custom-design computing solution. The commercial industry is already following this trend.  We propose to develop an SDA-specific variant of our Falcon GPU, build prototypes, and complete a comprehensive test campaign, resulting in a flight-ready design at TRL 6. This standardized design will reduce lead times for new hardware from 1-2 years to 3-4 weeks. With the modifications proposed here, the new design will be ready to integrate with many satellite buses used for current and future SDA missions. Additionally, this design will enable easily scaling the level of computing power or redundancy on a per mission basis, by adding more modules. This technique of building clusters of high-performance computers is in widespread use for ground-based computing. We will extend this practice to SDA-specific spacecraft. Thus SDA missions can add additional computing capabilities as required.  Falcon is Colossus’ latest high performance GPU-based data processor. It includes a 12-core ARM Cortex A78AE CPU, a 2048-core Ampere GPU, 64 Tensor Cores, a vision processor, integrated data storage, and basic connectivity. For more advanced connectivity or extra features, the Falcon design integrates an add-on board. Just like swapping out a graphics card on a desktop computer on Earth, this allows customization without changing the design of the core system. The work plan to build a SDA-specific variant of Falcon will focus on a new add-on board for these missions. We will interview several manufacturers of SDA satellites, as well as members of SDA, and compile a list of features and connectivity requirements. That will inform the design of a new add-on board for these missions. This add-on board will support a super-set of these requirements, even if not all features or connections are used on all missions.

Technology keywords

Not reported

Other awards by this recipient

Verified by the same UEI. These are other public SBIR/STTR award pages, not a merged company record.

Awards with the same topic code

Verified by an exact topic code match. This is not a text-similarity match.

Research funding history

3 SBIR/STTR records share this UEI (2022–2025). Reported award amounts total $2,931,552. Reported amounts are not federal obligations.

Phases: Phase II, Phase I, Phase II – Direct to Phase II

Agencies: National Aeronautics and Space Administration, Department of Defense

Agency intelligence

Department of Defense

Back to SBIR/STTR Research Awards

Don't take our word for it. Ask AI about RFPCapture.

See what leading AI assistants have to say about RFPCapture and CaptureIQ.

Gemini opens without a prefilled question. The question is copied to your clipboard when the button works. You can also copy it here:

What is RFPCapture.com and its CaptureIQ platform from Smart Logic AI? How does it help federal contractors discover opportunities, evaluate bid/no-bid decisions, research government contracts, and prepare proposals? How does it compare with other federal capture platforms? Use independent sources where available.