Brain inspired AI processing technology allowing for edge computing that transforms “non-smart chips” into “smart” chips

Project Information

Synthara Edge

Grant agreement ID: 888129

DOI

10.3030/888129

Project closed

EC signature date 3 December 2019

Start date 1 January 2020

End date 30 April 2020

Funded under

• INDUSTRIAL LEADERSHIP - Innovation In SMEs

Total cost

€ 71 429,00

EU contribution

€ 50 000,00

Coordinated by

SYNTHARA AG
Switzerland

Periodic Reporting for period 1 - Synthara Edge (Brain inspired AI processing technology allowing for edge computing that transforms “non-smart chips” into “smart” chips)

Reporting period: 2020-01-01 to 2020-04-30

Summary of the context and overall objectives of the project

The aim of the project was to ascertain the technical, commercial, legal and financial viability of Synthara Edge and to determine the next actions to ensure that it reaches adequate maturity for successful market entry and guaranteed industry competitiveness.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

Feedback from potential customers enabled us to validate the product specifications for the go-to-market minimum viable product and develop a comprehensive work plan detailing the activities to be done during the EIC project. We also validated our value chain, acquiring expressions of interest for validation and possible early use cases from several potential customers. A technical risk management strategy was also developed.

Synthara designed a comprehensive go-to-market strategy that involves running a Semi-IP business model in parallel with a fabless business model for market validation and early revenue generation. We carried out a competitor analysis of against existing and emerging technologies and generated a commercial risk management plan.

Synthara conducted a freedom to operate analysis, which confirms that there are no restrictions on the commercialization of the Synthara Edge. Synthara also identified additional potential IP and management strategies.

We generated a comprehensive budget based on the anticipated work laid out in the EIC project work plan and developed 5-year financial projections for Synthara Edge post-project completion.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

Synthara Edge is the first solution in the world that combines event-driven computation with von Neumann style inference neural network engine generating dramatically improve energy efficiency metric. Our solutions only compute when there is meaningful data compared to traditional ASICs run on a clock and perform hundreds of millions of calculations per second even when there is no data to process. Synthara Edge enables an algorithm-driven approach to hardware design. This enables us to offer our customers 10x better energy-efficiency than competitors even with cheaper and older CMOS fabrication processes.

shows the components of Synthara Edge and their respective functionalities within the co-processor