Print Email Facebook Twitter Parallel Matrix Multiplication on Memristor-Based Computation-in-Memory Architecture Title Parallel Matrix Multiplication on Memristor-Based Computation-in-Memory Architecture Author Haron, M.A.B. (TU Delft Computer Engineering) Yu, J. (TU Delft Computer Engineering) Nane, R. (TU Delft Computer Engineering) Taouil, M. (TU Delft Computer Engineering) Hamdioui, S. (TU Delft Computer Engineering) Bertels, K.L.M. (TU Delft Quantum & Computer Engineering; TU Delft FTQC/Bertels Lab) Department Quantum & Computer Engineering Date 2016 Abstract One of the most important constraints of today’s architectures for data-intensive applications is the limited bandwidth due to the memory-processor communication bottleneck. This significantly impacts performance and energy. For instance, the energy consumption share of communication and memoryaccess may exceed 80%. Recently, the concept of Computation-in-Memory (CIM) was proposed, which is based on the integration of storage and computation in the same physical location using a crossbar topology and non-volatile resistive-switching memristor technology. To illustrate the tremendous potential of CIM architecture in exploiting massively parallel computation while reducing the communication overhead, we present a communicationefficient mapping of a large-scale matrix multiplication algorithm on the CIM architecture. The experimental results show that, depending on the matrix size, CIM architecture exhibits several orders of magnitude higher performance in total execution timeand two orders of magnitude better in total energy consumption than the multicore-based on the shared memory architecture. Subject Computer architectureThree-dimensional displaysComputational modelingParallel algorithmsTwo dimensional displays To reference this document use: http://resolver.tudelft.nl/uuid:6a9edc28-f90d-44ad-8ba4-63756722617f DOI https://doi.org/10.1109/HPCSim.2016.7568411 Publisher IEEE, Piscataway ISBN 978-1-5090-2088-1 Source 2016 International Conference on High Performance Computing & Simulation (HPCS): 14th Annual Meeting Part of collection Institutional Repository Document type conference paper Rights © 2016 M.A.B. Haron, J. Yu, R. Nane, M. Taouil, S. Hamdioui, K.L.M. Bertels Files PDF 10408497.pdf 973.3 KB Close viewer /islandora/object/uuid:6a9edc28-f90d-44ad-8ba4-63756722617f/datastream/OBJ/view