Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / Türkiye

Marie Skłodowska-Curie Action · Ended early

ACROBAT Hardware Acceleration with Tunable SRAM/IMC Voltages

Coordinator
Bilkent Universitesi Vakif, Türkiye
Runs
1 September 2023 to 31 August 2026
Status
Ended early
EU funding
€239k
Total cost
—
Partners
3 organisations in 3 countries
Type
Marie Skłodowska-Curie Action
Grant agreement
101063661

What the project is doing

In the project's own words, from its summary on CORDIS.

Deep Neural Networks (DNNs) are the fundamental component in most artificial intelligence applications. With the increasing number of applications based on artificial intelligence, the performance and energy efficiency of architectures running these algorithms have become crucial, especially for battery-powered platforms. In this work, I propose an energy optimizing memory design framework with a special SRAM/in-memory-computing structure.

It also utilizes datapath optimization techniques like quantization and pruning with a fine-level assignment. Compared to other hardware accelerator studies for DNN processing, in this work, I will show that this special memory design, together with the architectural datapath optimization techniques, will have a much better capability of finding the Pareto optimal point in the energy-accuracy trade-off and increase the profitability of the final design.

Topics

Who is involved

OrganisationCityCountryRole
Bilkent Universitesi VakifBilkent AnkaraTürkiyeCoordinator
Stmicroelectronics Crolles 2 SASCrollesFranceAssociatedpartner
Massachusetts Institute of TechnologyCambridgeUnited StatesAssociatedpartner

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI