Parallel Computing Technologies 

Abstract: Data replication is a common method used to improve the performance of data access in distributed systems. In this paper, two dynamic replication algorithms, Simple Bottom-Up (SBU) and Aggregate Bottom-Up (ABU), are proposed for the multi-tier Data Grid. A multi-tier Data Grid simulator called DRepSim is developed for studying the performances of the dynamic replication algorithms. The simulation results show that both algorithms can reduce the average response time of data access greatly compared to the static replication method. ABU can achieve great performance improvements for all access patterns even if the available storage size of the replication server is very small. Comparing the two algorithms to Fast Spread dynamic replication strategy, ABU proves to be superior. As for SBU, although the average response time of Fast Spread is better in most cases, Fast Spread's replication frequency is too high to be applicable in the real world.

Abstract: This paper presents a very simple consensus protocol that converges in a single communication step in favorable circumstances. Those situations occur when "enough" processes propose the same value. ("Enough" means "at least (n-f)" where f is the maximum number of processes that can crash in a set of n processes.) The protocol requires f < n/3. It is shown that this requirement is necessary. Moreover, if all the processes that propose a value do propose the same value, the protocol always terminates in one communication step. It is also shown that additional assumptions can help weaken the f < n/3 requirement to f < n/2.

Abstract: We introduce the νSPI-calculus that strengthens the notion of "perfect symmetric cryptography" of the spi-calculus by taking time into account. This involves defining an operational semantics, defining a control flow analysis (CFA) in the form of a flow logic, and proving semantic correctness. Our first result is that secrecy in the sense of Dolev-Yao can be expressed in terms of the CFA. Our second result is that also non-interference in the sense of Abadi can be expressed in terms of the CFA; unlike Abadi we find the non-interference property to be an extension of the Dolev-Yao property.

Abstract: This paper presents SKiPPER, a programming environment dedicated to the fast prototyping of parallel vision algorithms on MIMD-DM platforms. SKiPPER is based upon the concept of algorithmic skeletons, i.e. higher order program constructs encapsulating recurring forms of parallel computations and hiding their low-level implementation details. Each skeleton is given an architecture-independent functional (but executable) specification and a portable implementation as a generic process template. The source program is a purely functional specification of the algorithm in which all parallelism is made explicit by means of composing instances of selected skeletons, each instance taking as parameters the application specific sequential functions written in C. SKiPPER compiles this specification down to a process graph in which nodes correspond to sequential functions and/or skeleton control processes and edges to communications. This graph is then mapped onto the target topology using a third-party CAD software (SynDEx). The result is a dead-lock free, optimized (but still portable) distributed executive, which SKiPPER finally turns into executable code for the target platform. The initial specification, written in ML language, can also be executed on any sequential platform to check the correctness of the parallel algorithm. The applicability of SKiPPER concepts and tools has been demonstrated by parallelising several realistic real-time vision applications both on a multi-DSP platform and a network of workstations. It is here illustrated with a real-time vehicle detection and tracking application.