Recent advances in matrix computations for extreme-scale computers - Part II of II
For Part I, see MS-Mo-D-11

Date: August 10
Time: 16:00--18:00
Room: 203B

(Note: Click title to show the abstract.)

Li, Xiaoye (Lawrence Berkeley National Laboratory)
Duff, Iain (STFC Rutherford Appleton Laboratory)

Abstract: Numerical linear algebra is at the heart of scientific and industrial
discoveries. The forthcoming arrival of the exascale era provides
tremendous opportunities and challenges for further development of
algorithms and software extreme-scale computing. This minisymposium
emphasizes problem reformulations, algorithm redesigns and
code refactorings for the efficient use of high performance computers.
Topics range from direct methods, iterative methods, preconditioning,
and the emerging fast algorithms for both dense and sparse
algebraic systems. The speakers will present various techniques to reduce
communication, synchronization and memory footprint.
Performance of the new algorithms will be demonstrated on modern manycore
parallel machines.

Numerical methods for linear complementary problem
Yin, Jun-Feng (Tongji Univ.)

Efficient deadlock-free asynchronous approaches for a distributed-memory sparse direct solver
Sid-Lakhdar, Wissam M. (Texas A&M Univ.)
L'Excellent, Jean-Yves (Inria & Univ. of Lyon)
Amestoy, Patrick (INPT-IRIT Univ. of Toulouse)

Fine-grained parallel incomplete LU factorization
Chow, Edmond (Georgia Inst. of Tech.)

Preconditioners and Solvers for CFD Applications on GPU-based Supercomputers
De Sturler, Eric (Virginia Tech)


Code: Type-Date-Time-Room No.
Type : IL=Invited Lecture, SL=Special Lectures, MS=Minisymposia, IM=Industrial Minisymposia, CP=Contributed Papers, PP=Posters
Date: Mo=Monday, Tu=Tuesday, We=Wednesday, Th=Thursday, Fr=Friday
Time : A=8:30-9:30, B=10:00-11:00, C=11:10-12:10, BC=10:00-12:10, D=13:30-15:30, E=16:00-18:00, F=19:00-20:00, G=12:10-13:30, H=15:30-16:00
Room No.: TBA