AC/DC is an adaptive method for prefetching data from main memory. The basic prefetch
method divides the memory address space into equal-sized concentration zones (CZones) …

An ideal approach to deal with faults in large-scale distributed systems is to contain the
effects of faults as locally as possible and, additionally, to ensure some type of tolerance …

We pose and study the problem of Byzantine-robust topology discovery in an arbitrary
asynchronous network. The problem is an abstraction of fault-tolerant routing. We formally …

In this dissertation, we defend the thesis that a fault-tolerant program is a composition of a
fault-intolerant program and a set of fault-tolerance components. To validate this thesis, we …

Self-stabilizing protocols can tolerate any type and any number of transient faults. However,
in general, self-stabilizing protocols provide no guarantee about their behavior against …

Self-stabilizing protocols can tolerate any type and any number of transient faults. But self-
stabilizing protocols have no guarantee of their behavior against permanent faults. Thus …

Fault tolerance is a crucial property for recent distributed systems. We propose an algorithm
that solves the census problem (list all processor identifiers and their relative distance) on an …

We mix two approaches of the fault-tolerance: robustness and stabilization. Using these
approaches, we propose leader election algorithms that tolerate both transient and crash …

As a new challenge of containing the unbounded influence of Byzantine processes in self-
stabilizing protocols, this paper introduces a novel concept of strong stabilization. The strong …

A reset of a distributed system is safe if it does not complete\prematurely", ie, without having
reset some process in the system. Safe resets are possible in the presence of certain faults …