TY - JOUR
T1 - ReLOPE
T2 - Resistive RAM-Based Linear First-Order Partial Differential Equation Solver
AU - Ensan, Sina Sayyah
AU - Ghosh, Swaroop
N1 - Publisher Copyright:
IEEE
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020
Y1 - 2020
N2 - Data movement between memory and processing units poses an energy barrier to Von-Neumann-based architectures. In-memory computing (IMC) eliminates this barrier. RRAM-based IMC has been explored for data-intensive applications, such as artificial neural networks and matrix-vector multiplications that are considered as ``soft'' tasks where performance is a more important factor than accuracy. In ``hard'' tasks such as partial differential equations (PDEs), accuracy is a determining factor. In this brief, we propose ReLOPE, a fully RRAM crossbar-based IMC to solve PDEs using the Runge-Kutta numerical method with 97% accuracy. ReLOPE expands the operating range of solution by exploiting shifters to shift input data and output data. ReLOPE range of operation and accuracy can be expanded by using fine-grained step sizes by programming other RRAMs on the BL. Compared to software-based PDE solvers, ReLOPE gains 31.4x energy reduction at only 3% accuracy loss.
AB - Data movement between memory and processing units poses an energy barrier to Von-Neumann-based architectures. In-memory computing (IMC) eliminates this barrier. RRAM-based IMC has been explored for data-intensive applications, such as artificial neural networks and matrix-vector multiplications that are considered as ``soft'' tasks where performance is a more important factor than accuracy. In ``hard'' tasks such as partial differential equations (PDEs), accuracy is a determining factor. In this brief, we propose ReLOPE, a fully RRAM crossbar-based IMC to solve PDEs using the Runge-Kutta numerical method with 97% accuracy. ReLOPE expands the operating range of solution by exploiting shifters to shift input data and output data. ReLOPE range of operation and accuracy can be expanded by using fine-grained step sizes by programming other RRAMs on the BL. Compared to software-based PDE solvers, ReLOPE gains 31.4x energy reduction at only 3% accuracy loss.
UR - http://www.scopus.com/inward/record.url?scp=85097432290&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097432290&partnerID=8YFLogxK
U2 - 10.1109/TVLSI.2020.3035769
DO - 10.1109/TVLSI.2020.3035769
M3 - Article
AN - SCOPUS:85097432290
JO - IEEE Transactions on Very Large Scale Integration (VLSI) Systems
JF - IEEE Transactions on Very Large Scale Integration (VLSI) Systems
SN - 1063-8210
ER -