Mira Early Science Program

The goals of the ALCF-2 Early Science Program (ESP) were to prepare key applications for the architecture and scale of Mira, and to solidify libraries and infrastructure that would pave the way for other future production applications.

The 16 Early Science projects are the result of a call for proposals, and were chosen based on computational and scientific reviews. The projects, in addition to promising delivery of exciting new science, are all based on state-of-the-art, petascale, parallel applications. Starting in October 2010, the project teams, in collaboration with ALCF staff and IBM, have undertaken intensive efforts to adapt their software to take advantage of Mira’s Blue Gene/Q architecture, which, in a number of ways, is a precursor to future HPC architectures. Together, the 16 projects span a diverse range of scientific fields, numerical methods, programming models, and computational approaches. The latter include particle-mesh methods, adaptive meshes, spectral methods, Monte Carlo, molecular dynamics, and ab initio computational chemistry methods. These applications also represent a large portion of the ALCF’s current and projected computational workload.

The dedicated Early Science period lasted only a few months (between machine acceptance and commencement of production), during which the ESP projects aimed to burn over 2 billion core-hours on Mira. It was essential that the projects were "ready to run" when the clock started ticking. The long lead time of the Program, and dedicated postdoctoral appointees for most projects, working with ALCF staff, helped make that possible.