Exploiting Redundant Computation in Communication-Avoiding Algorithms for Algorithm-Based Fault Tolerance
Camille Coti · 2016
Communication-avoiding algorithms allow redundant computations to minimize the number of inter-process communications. In this paper, we propose to exploit this redundancy for fault-tolerance purpose. We illustrate this idea with QR factorization of tall and skinny matrices. We give a theoretical evaluation of the number of failures our algorithm can tolerate under different semantics and an experimental evaluation of the performance overhead.