Principal Investigator Charles Leiserson
Co-investigator Robert Miller
Project Website http://www.nsf.gov/awardsearch/showAward?AWD_ID=1533644&HistoricalAwards=false
Project Start Date October 2015
Project End Date September 2018
Scientists developing compute-intensive multicore applications find it difficult to parallelize their code, a problem that is exacerbated if they wish to take maximum advantage of the potential provided by cloud computing. Part of the problem is that bad codes cause the generation of incorrect hypotheses while reading, writing, and debugging code, wasting time, energy, and resources.
This research plans to meld advanced profiling methods for multithreaded programming with modern user-interface technology to produce a highly usable open-source integrated development environment (IDE) for the performance-engineering of multicore software applications in the cloud. The goal is to provide programmers with continuous profile data for scalability and other performance profiling relevant to parallel programming. They plan to embed an IDE into a profiling framework to produce a profile-centric IDE, continuously providing performance feedback so that developers can see and compare the results of recent runs of their program as they edit their code.
The project has the potential to enable science-based performance engineering of multicore applications in the cloud. The vast majority of computer users, not just expert computer scientists, will be able to develop highly efficient parallel software applications, broadly impacting every computing application in every walk of life. The software produced by this project will be made freely available to anyone on the World Wide Web using a liberal open-source license.