Deep Learning Based Controller for SSD Acceleration

Project description:

Flash memory is widely-used memory technology, used in disk-on-keys, SSDs, set-top boxes (routers, TVs etc.), cellular SIM, and more. Flash memory requires a unique memory controller, as Flash is block-addressable, has unique error handling correction properties, wear leveling management and more.

Solid-state drive architectures can arrange Flash chips and controller in several topologies: channels, bus-based, full crossbar and more.

There are several new trends in SSDs that should be considered in a storage controller design. The challenges of moving Big Data and unacceptable latency of devices operating. In addition, machine learning is becoming more common in performing specialized tasks such as object detection and classification. The same machine learning techniques can be used to increase drive endurance and reliabilityof flash memory systems.  The use of AI in storage brings the potential to substantially increase endurance and reliability. The use of machine learning in flash drives is in the early stages and will be developed and implemented in many applications.

In this project, the students will implement a design of controller and architecture for solid-state drive that uses AI techniues to improve performance. The implementation includes system matlab modeling, spec and architecture definition, logic design using the Verilog HDL, verification and synthesis.

Project goals:

·         Understanding of controllers architecture and Flash memory background

·         Architecture development, logic design, implementation in verilog HDL, simulation, synthesis and layout.

Prerequisite : Digital Systems and Computer Structure – 044252

Supervisor : Dr. Amit Berman