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

Informations projet

Synthara Edge

N° de convention de subvention: 888129

DOI

10.3030/888129

Projet clôturé

Date de signature de la CE 3 Decembre 2019

Date de début 1 Janvier 2020

Date de fin 30 Avril 2020

Financé au titre de

• INDUSTRIAL LEADERSHIP - Innovation In SMEs

Coût total

€ 71 429,00

Contribution de l’UE

€ 50 000,00

Coordonné par

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)

Période du rapport: 2020-01-01 au 2020-04-30

Résumé du contexte et des objectifs généraux du projet

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.

Travail effectué depuis le début du projet jusqu’à la fin de la période considérée dans le rapport et principaux résultats atteints jusqu’à présent

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.

Progrès au-delà de l’état des connaissances et impact potentiel prévu (y compris l’impact socio-économique et les conséquences sociétales plus larges du projet jusqu’à présent)

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