Compute-in-memory: State space models; ultra-thin AlScN memory; brain-inspired edge AI.

In his doctoral thesis, Michael Roop develops numerical methods that allow finding physically reliable approximate solutions ...

Government-funded academic research on parallel computing, stream processing, real-time shading languages, and programmable ...

Electronics usually fail under extreme heat, but scientists have now created a memory chip that keeps working at temperatures ...

Researchers at USC's Viterbi School of Engineering have demonstrated an electronic memory device that functions far beyond previously known thermal limits. In experiments, the device remained ...

Abstract: The first-principles approach based on density-functional theory (DFT)/density-functional perturbation theory (DFPT) is widely used in calculations of the systems’ ground state energy, ...

Abstract: NVIDIA Tensor Cores and AMD Matrix Cores (together called Matrix Accelerators) are of growing interest in high-performance computing and machine learning owing to their high performance.