A. Abdelfattah, E. Gendron, D. Gratadour, D. Keyes, H. Ltaief, A. Sevin, and F. Vidal
vol. 8632 of Lecture Notes in Computer Science, Springer, pp. 704-715, (2014)
Multi-object adaptive optics (MOAO) is a novel adaptive optics (AO)
technique dedicated to the special case of wide-field multi-object
spectrographs (MOS). It applies dedicated wavefront corrections to
numerous independent tiny patches spread over a large field of view
(FOV). The control of each deformable mirror (DM) is done individually
using a tomographic reconstruction of the phase based on measurements
from a number of wavefront sensors (WFS) pointing at natural and
artificial guide stars in the field. The output of this study helps the
design of a new instrument called MOSAIC, a multi-object spectrograph
proposed for the European Extremely Large Telescope (E-ELT). We have
developed a novel hybrid pseudo-analytical simulation scheme that allows
us to accurately simulate in detail the tomographic problem. The main
challenge resides in the computation of the tomographic reconstructor,
which involves pseudo-inversion of a large dense symmetric matrix. The
pseudo-inverse is computed using an eigenvalue decomposition, based on
the divide and conquer algorithm, on multicore systems with multi-GPUs.
Thanks to a new symmetric matrix-vector product (SYMV) multi-GPU kernel,
our overall implementation scores significant speedups over standard
numerical libraries on multicore, like Intel MKL, and up to 60% speedups
over the standard MAGMA implementation on 8 Kepler K20c GPUs. At 40,000
unknowns, this appears to be the largest-scale tomographic AO matrix
solver submitted to computation, to date, to our knowledge and opens new
research directions for extreme scale AO simulations.