Video: Rick Stevens from Argonne on the CANDLE Project for Exascale

Print Friendly, PDF & Email

In this video, Mike Bernhardt from ECP discusses the CANDLE project for Exascale with Rick Stevens from Argonne.

CANDLE is endeavoring to build the software environment for solving very large-scale distributed learning problems on the DOE Leadership Computing platforms. The project aims to facilitate the use of these platforms for solving machine learning problems with a focus on three challenges in cancer research: (1) predicting the response of drugs from cancer cells, (2) analyzing cancer medical records to determine diagnosis and information from unstructured text that could be used to build models for large-scale population response to cancer treatment, and (3) probing the inner workings of cancer biology to help manage simulations of problems and protein mutations associated with cancer cells.

Rick Stevens is associate lab director at Argonne National Laboratory, professor of computer science at the University of Chicago, and principal investigator for the Exascale Computing Project’s (ECP) Cancer Distributed Learning Environment (CANDLE) project. In this video chat with Mike Bernhardt, ECP communications manager, he shares information about, and highlights from, CANDLE, a collaborative effort involving four US Department of Energy (DOE) national laboratories: Argonne, Oak Ridge, Los Alamos, and Lawrence Livermore.

Sign up for our insideHPC Newsletter