A Voltage-Controlled, Oscillation-Based ADC Design for Computation-in-Memory Architectures Using Emerging ReRAMs
ACM Journal on Emerging Technologies in Computing Systems, vol. 18, pp. 1–25
Abstract
Conventional von Neumann architectures cannot successfully meet the demands of emerging computation and data-intensive applications. These shortcomings can be improved by embracing new architectural paradigms using emerging technologies. In particular, Computation-In-Memory (CiM) using emerging technologies such as Resistive Random Access Memory (ReRAM) is a promising approach to meet the computational demands of data-intensive applications such as neural networks and database queries. In CiM, computation is done in an analog manner; digitization of the results is costly in several aspects, such as area, energy, and performance, which hinders the potential of CiM. In this article, we propose an efficient Voltage-Controlled-Oscillator (VCO)–based analog-to-digital converter (ADC) design to improve the performance and energy efficiency of the CiM architecture. Due to its efficiency, the proposed ADC can be assigned in a per-column manner instead of sharing one ADC among multiple columns. This will boost the parallel execution and overall efficiency of the CiM crossbar array. The proposed ADC is evaluated using a Multiplication and Accumulation (MAC) operation implemented in ReRAM-based CiM crossbar arrays. Simulations results show that our proposed ADC can distinguish up to 32 levels within 10 ns while consuming less than 5.2 pJ of energy. In addition, our proposed ADC can tolerate ≈30% variability with a negligible impact on the performance of the ADC.
Authors 11
-
Delft University of Technology
Affiliation as printed
Delft University of Technology, Delft, Netherlands
-
Delft University of Technology
Affiliation as printed
Delft University of Technology, Delft, Netherlands
-
Christopher Bengel Aachen
Affiliation as printed
RWTH Aachen University, Aachen, Germany
-
Stefan Wiefels Aachen
Affiliation as printed
RWTH Aachen University, Aachen, Germany
-
Delft University of Technology
Affiliation as printed
Delft University of Technology, Delft, Netherlands
-
Affiliation as printed
Forschungszentrum Juelich GmbH, Peter-Gruenberg Institut (PGI-7), Juelich, Germany
-
Dirk J. Wouters Aachen
Affiliation as printed
RWTH Aachen University, Aachen, Germany
-
Delft University of Technology
Affiliation as printed
Delft University of Technology, Delft, Netherlands
-
Delft University of Technology
Affiliation as printed
Delft University of Technology, Delft, Netherlands
-
IBM (United States) · IBM Research - Thomas J. Watson Research Center
Affiliation as printed
IBM Thomas J. Watson Research Center, Ossining, New York city, USA
-
Delft University of Technology
Affiliation as printed
Delft University of Technology, Delft, Netherlands
Cited by 21 stored of 21
Cited by patents worldwide 10 (Lens.org)
-
IN-MEMORY COMPUTATION DEVICE HAVING AN IMPROVED CURRENT READING CIRCUIT AND CONTROL METHODEP4390935B1 2026-09-16 Active
-
In-memory computation device for implementing at least a multilayer neural networkUS12700438B2 2026-08-04 Active
-
In-memory computation device having an improved current reading circuit and control methodUS12633343B2 2026-05-19 Active
-
In-memory computation device having improved drift compensationUS12462858B2 2025-11-04 Active
-
Signed and binary weighted computation for an in-memory computation systemUS12211582B2 2025-01-28 Active
-
IN-MEMORY COMPUTATION DEVICE HAVING IMPROVED DRIFT COMPENSATIONEP4390934A1 2024-06-26 Pending
-
IN-MEMORY COMPUTATION DEVICE HAVING AN IMPROVED CURRENT READING CIRCUIT AND CONTROL METHODEP4390935A1 2024-06-26 Active
-
DISPOSITIVO DI COMPUTAZIONE IN-MEMORIA AVENTE MIGLIORATA COMPENSAZIONE DI DERIVAIT202200026760A1 2024-06-23 Pending
-
In-memory computation system with drift compensation circuitUS11942144B2 2024-03-26 Active
-
Compensated analog computation for an in-memory computation systemUS11894052B2 2024-02-06 Active