A Non-Volatile All-Spin Non-Binary Matrix Multiplier: An Efficient Hardware Accelerator for Machine Learning
arXiv:2211.06490 · doi:10.1109/TED.2022.3214167
Abstract
We propose and analyze a compact and non-volatile nanomagnetic (all-spin) non-binary matrix multiplier performing the multiply-and-accumulate (MAC) operation using two magnetic tunnel junctions - one activated by strain to act as the multiplier, and the other activated by spin-orbit torque pulses to act as a domain wall synapse that performs the operation of the accumulator. It has two advantages over the usual crossbar-based electronic non-binary matrix multiplier. First, while the crossbar architecture requires N3 devices to multiply two matrices, we require only 2N2 devices. Second, our matrix multiplier is non-volatile and retains the information about the product matrix after being powered off. Here, we present an example where each MAC operation can be performed in ~5 ns and the maximum energy dissipated per operation is ~60Nmax aJ, where Nmax is the largest matrix size. This provides a very useful hardware accelerator for machine learning and artificial intelligence tasks which involve the multiplication of large matrices. The non-volatility allows the matrix multiplier to be embedded in powerful non-von-Neumann architectures, including processor-in-memory. It also allows much of the computing to be done at the edge (of internet-of-things) while reducing the need to access the cloud, thereby making artificial intelligence more resilient against cyberattacks.
arXiv commentA slightly shorter version of this article has been accepted for publication in IEEE Transactions on Electron Devices. The replacement corrects some errors in the previously uploaded version
References in corpus (7)
- Current-driven dynamics of chiral ferromagnetic domain walls
- Large-Scale Optical Neural Networks based on Photoelectric Multiplication
- Spin Hall torque magnetometry of Dzyaloshinskii domain walls
- Proposal for an All-Spin Artificial Neural Network: Emulating Neural and Synaptic Functionalities Through Domain Wall Motion in Ferromagnets
- Energy dissipation and switching delay in stress-induced switching of multiferroic devices in the presence of thermal fluctuations
- Giant Voltage Manipulation of MgO-based Magnetic Tunnel Junctions via Localized Anisotropic Strain: a Potential Pathway to Ultra-Energy-Efficient Memory Technology
- Self-similar Magneto-electric Nanocircuit Technology for Probabilistic Inference Engines