A comparison study of the behaviour of equivalent algorithms in fault injection experiments, in parallel superscalar architectures
This work describes an experimental comparison study of the behavior of a set of algorithms in the presence of faults. The algorithms have the characteristic that they belong to the same problem class and solve the matrix exponentiation problem. A number of comparison studies exist in bibliography, with respect to their numerical, conversion and time and space complexity. We use Fault Injection techniques at the compile time, namely software based script fault injection method based on random bit inversion assumption. The system is a fully operating parallel architecture machine with two superscalar processors. The algorithms are studied for their fault tolerance in the presence of a basic fault detection method based on command duplication and exploiting the parallel architecture.
Bibliographic Reference: Oral report given at: The 20th International Conference on Computer Safety, Reliability and Security. Organised by: Erwin Schoitsch, Austrian Research Centers. Held in: Budapest (HU), 26-28 September 2001
Record Number: 200013212 / Last updated on: 2001-03-23
Original language: en
Available languages: en