J
James C. Phillips
Researcher at University of Illinois at Urbana–Champaign
Publications - 82
Citations - 38503
James C. Phillips is an academic researcher from University of Illinois at Urbana–Champaign. The author has contributed to research in topics: Software & Petascale computing. The author has an hindex of 33, co-authored 75 publications receiving 34564 citations. Previous affiliations of James C. Phillips include Marquette University & Michigan State University.
Papers
More filters
Journal ArticleDOI
The challenges of theory-software translation
Caroline Jay,Robert Haines,Daniel S. Katz,Jeffrey C. Carver,Sandra Gesing,Steven R. Brandt,James Howison,Anshu Dubey,James C. Phillips,Hui Wan,Matthew J. Turk +10 more
TL;DR: Systematically investigating how software is constructed and its outputs used within science has the potential to improve the robustness of research software and accelerate progress in its development.
Book ChapterDOI
Avoiding Algorithmic Obfuscation in a Message-Driven Parallel MD Code
James C. Phillips,Robert Brunner,Aritomo Shinozaki,Milind Bhandarkar,Neal Krawetz,Attila Gursoy,Laxmikant V. Kale,Robert D. Skeel,Klaus Schulten +8 more
TL;DR: A hybrid decomposition scheme in which atoms are distributed among processors in regularly sized patches while the work involved in computing interactions between patches is decomposed into independently assignable compute objects, allowing maximum overlap of work and communication without significant programmer effort.
Journal ArticleDOI
Implementation of scientific computing applications on the Cell Broadband Engine
Guochun Shi,Volodymyr Kindratenko,Ivan S. Ufimtsev,Todd J. Martínez,James C. Phillips,Steven Gottlieb +5 more
TL;DR: An effort to implement several traditional high-performance scientific computing applications on the Cell Broadband Engine processor, including molecular dynamics, quantum chromodynamics and quantum chemistry codes, is reported on.
Journal ArticleDOI
Relaxation in a Duffing potential
Surajit Sen,James C. Phillips +1 more
TL;DR: In this paper, the authors recover and extend upon the results of Fronzoni et al. to show analytically, via Mori-Lee theory, that "essentially discrete" (i.e. well defined peaks with finite but small width) temperature-dependent frequencies characterize the autocorrelation functions in a canonical ensemble.