The Co-design Approach for Advances in Software and Hardware (CoDAASH) project focuses on understanding the relationship between algorithms and hardware platforms and how to jointly optimize the software and hardware in order to achieve efficient implementations for applications in materials science, chemistry, and physics. CoDAASH is a joint effort between the University of Tennessee, Knoxville, Iowa State University, University of Texas, El Paso, and the University of California, San Diego, and is funded by the United States Air Force Office of Scientific Research (AFOSR).
ICL’s contribution focuses on expressing certain computational chemistry algorithms in the form of a data flow graph (DAG) and subsequently mapping the DAG representation of the kernels to the hardware platforms. This representation allows for capturing the essential properties of the algorithms (e.g., data dependencies), and enables computation at extreme scale in the era of many-core and highly heterogeneous platforms, by utilizing the hardware components (e.g., CPU or GPU) that perform best for the type of computational task under consideration. The dataflow-based form of these algorithms makes them compatible with next generation task scheduling systems, such as PaRSEC.
Find out more at http://icl.eecs.utk.edu/codaash/