Accurate and Energy-Efficient Bit-Slicing for RRAM-Based Neural Networks

Accurate and Energy-Efficient Bit-Slicing for RRAM-Based Neural Networks

Diware, S.S. (TU Delft Computer Engineering)
Singh, A. (TU Delft Computer Engineering)
Gebregiorgis, A.B. (TU Delft Computer Engineering)
Joshi, Rajiv V. (IBM Thomas J. Watson Research Centre)
Hamdioui, S. (TU Delft Quantum & Computer Engineering)
Bishnoi, R.K. (TU Delft Computer Engineering)

Quantum & Computer Engineering

2023

Computation-in-memory (CIM) paradigm leverages emerging memory technologies such as resistive random access memories (RRAMs) to process the data within the memory itself. This alleviates the memory-processor bottleneck resulting in much higher hardware efficiency compared to von-Neumann architecture-based conventional hardware. Hence, CIM becomes an attractive alternative for applications like neural networks which require a huge number of data transfer operations in conventional hardware. CIM-based neural networks typically employ bit-slicing scheme which represents a single neural weight using multiple RRAM devices (called slices) to meet the high bit-precision demand. However, such neural networks suffer from significant accuracy degradation due to non-zero Gmin error where a zero weight in the neural network is represented by an RRAM device with a non-zero conductance. This paper proposes an unbalanced bit-slicing scheme to mitigate the impact of non-zero Gmin error. It achieves this by allocating appropriate sensing margins for different slices based on their binary positions. It also tunes the sensing margins to meet the demands of either high accuracy or energy-efficiency. The sensing margin allocation is supported by 2's complement arithmetic which further reduces the influence of non-zero Gmin error. Simulation results show that our proposed scheme achieves up to 7.3× accuracy and up to 7.8× correct operations per unit energy consumption compared to state-of-the-art.

Computation-in-memory
bit-slicing
neural networks
non-zero Gmin error
conductance variation
nonidealities

http://resolver.tudelft.nl/uuid:71dec77a-bb95-4e9a-86bd-3b39d620d29f

https://doi.org/10.1109/TETCI.2022.3191397

2023-08-07

2471-285X

IEEE Transactions on Emerging Topics in Computational Intelligence, 7 (1), 164 - 177

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

journal article

© 2023 S.S. Diware, A. Singh, A.B. Gebregiorgis, Rajiv V. Joshi, S. Hamdioui, R.K. Bishnoi