A Tour of Dependable Computing Research in Latin America

Computing technology has become pervasive and with it the expectation for its ready availability when needed, thus basically at all times. Dependability is the set of techniques to build, configure, operate, and manage computer systems to ensure that they are reliable, available, safe, and secure.1 But alas, faults seem to be inherent to computer systems. Components can simply crash or produce incorrect output due to hardware or software bugs or can be invaded by impostors that orchestrate their behavior. Fault tolerance is the ability to enable a system as a whole to continue operating correctly and with acceptable performance, even if some of its components are faulty.3 Fault tolerance is not new; von Neumann himself designed techniques for computers to survive faults.4