IBM Analog Hardware Acceleration Kit: A Flexible and Fast PyTorch Toolkit for Simulating ANN Training and Inference on Resistive Crossbar Arrays

Wednesday, February 24, 2021 at 12:00pm to 1:00pm

Virtual Event

Speaker: Malte Rasch, IBM

Memristive crossbar arrays are a promising future technology for accelerating AI workloads, but noise and non-idealities demand for improved algorithmic solutions. We introduce the IBM Analog Hardware Acceleration Kit, a first of a kind open source toolkit to simulate crossbar arrays from within PyTorch, to conveniently estimate the impact of material properties and non-idealities on the accuracy for arbitrary ANNs.

Event Type

Conferences/Seminars/Lectures

Events By Interest

Academic

Events By Audience

Public, MIT Community, Students, Alumni, Faculty, Staff

Events By School

School of Engineering (SoE)

Tags

engineering, MTL

Website

https://www.mtl.mit.edu/events/ibm-an...

Department
Microsystems Technology Laboratories
Contact Email

mbrowncu@mit.edu

Add to my calendar

Recent Activity