A Non-Volatile All-Spin Non-Binary Matrix Multiplier: An Efficient Hardware Accelerator for Machine Learning

Rahnuma Rahman, Supriyo Bandyopadhyay

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 non-binary matrix multiplier. First, while the crossbar architecture requires N**2 devices to multiply two matrices, we require only two devices regardless of the value of N. Second, while the energy dissipation in the crossbar architecture scales as N**2, in our construct, it scales as N. Each MAC operation can be performed in ~5 ns and the maximum energy dissipated per operation is ~60N aJ. This provides a very useful hardware accelerator for machine learning and artificial intelligence tasks which often involve the multiplication of large matrices. The non-volatility allows the matrix multiplier to be embedded in powerful non-von-Neumann architectures. It also allows all computing to be done at the edge while reducing the need to access the cloud, thereby making artificial intelligence more resilient against cyberattacks.

Knowledge Graph

arrow_drop_up

Comments

Sign up or login to leave a comment