Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
In-Memory Computing (IMC) solutions, and particularly bitline computing in SRAM, appear promising as they mitigate one of the most energy consuming aspects in computation: data movement. In this work we propose a fast (2.4Ghz for bitwise operations and 2.4/1.5Ghz for 32/64bit additions respectively), reliable (no read disturb issues) and wide voltage range (from 0.6 to 1V) 6T SRAM-based IMC architecture using local bitlines and a fast carry adder pitched below the memory subarray. We verify the proposed architecture through layout and variability aware simulations in 28nm bulk high performances technology PDK.
David Atienza Alonso, Giovanni Ansaloni, Alexandre Sébastien Julien Levisse, Marco Antonio Rios, Flavio Ponzina