Non-volatile memory die with deep learning neural network

US11705191B2 · kind B2 · utility

Assignee

• Western Digital Technologies, Inc. · US

Inventors

• Rami Rom · Jerusalem, IL
• Ofir Pele · Hod HaSharon, IL
• Alexander Bazarsky · Holon, IL
• Tomer Eliash · Kfar Sava, IL
• Ran Zamir · Ramat Gan, IL
• Karin Inbar · Ramat HaSharon, IL

Key dates

• Filing date: Aug 18, 2021
• Grant date: Jul 18, 2023
• Expiry date: Aug 18, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/09
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Exemplary methods and apparatus are provided for implementing a deep learning accelerator (DLA) or other neural network components within the die of a non-volatile memory (NVM) apparatus using, for example, under-the-array circuit components within the die. Some aspects disclosed herein relate to configuring the under-the-array components to implement feedforward DLA operations. Other aspects relate to backpropagation operations. Still other aspects relate to using an NAND-based on-chip copy with update function to facilitate updating synaptic weights of a neural network stored on a die. Other aspects disclosed herein relate to configuring a solid state device (SSD) controller for use with the NVM. In some aspects, the SSD controller includes flash translation layer (FTL) tables configured specifically for use with neural network data stored in the NVM.