Uncle Sam's next big supercomputer might use something more exotic than GPUs

Chip startup NextSilicon's high-performance-computing-focused accelerators get Sandia National Lab's stamp of approval ...
IEEE

Dot-product engine for neuromorphic computing: Programming 1T1M crossbar to accelerate matrix-vector multiplication

An ideal nanoscale memristor crossbar array can naturally carry out vector-matrix multiplication-a computationally expensive task for many important applications-in a single constant time step [2]. By ...
IEEE

MemRaptor: Magnetoresistive Array as Matrix Vector Multiplication and Transcendental Function Operator for NLP Applications

Abstract: Compute-In-Memory (CiM) is emerging as a promising paradigm to design energy-efficient hardware accelerators for AI, addressing the processor-memory data transfer bottleneck. The popularity ...