The Message Passing Interface provides an interface for onesided communication as part of the MPI-2 standard. The semantics specified by MPI-2 allow for a number of different implementation avenues, each with different performance characteristics. Within the context of Open MPI, a freely available high performance MPI implementation, we analyze a number of implementation possibilities, includin...

This paper presents a novel deterministic MPI implementation (dMPI) to facilitate the debugging of MPI programs. Distinct from existing approaches, dMPI ensures inherent determinism without using any external support (e.g., logs), which achieves convenience and performance simultaneously. The basic idea of dMPI is to use deterministic logical time to solve message races and control asynchronous...

Message passing algorithms may be viewed from a purely probabilistic or statistical physics perspective. This works describes an alternative, linear algebraic view of message passing in trees. We demonstrate the construction of global belief operators on Markov Chains and Trees and compare these with classical results. By interpreting message passing as finding a global stable solution we wish ...

Honbo Zhou, Al Geist Mathematical Sciences Section Oak Ridge National Laboratory Oak Ridge, TN 37831 fzhou, [email protected] Abstract This paper describes di erent approaches to build faster message passing routes into PVM. One of the recent e orts is to use shared memory based channels to replace the socket-based routes between the PVM daemon and its local tasks. Another e ort is the co...

Constructing a minimal vertex cover of a graph can be seen as a prototype for a combinatorial optimization problem under hard constraints. In this paper, we develop and analyze message-passing techniques, namely, warning and survey propagation, which serve as efficient heuristic algorithms for solving these computational hard problems. We show also, how previously obtained results on the typica...

When data are acquired at multiple points in time, evolutionary clustering can provide insights into cluster evolution and changes in cluster memberships while enabling performance superior to that obtained by independently clustering data collected at different time points. Existing evolutionary clustering methods typically require additional steps before and after the clustering stage to appr...

Some message-passing concurrent systems, such as occam 2, prohibit aliasing of data objects. Communicated data must thus be copied, which can be timeintensive for large data packets such as video frames. We introduce automatic mobility, a compiler optimisation that performs communications by reference and deduces when these communications can be performed without copying. We discuss bounds for ...

Lifted inference, handling whole sets of indistinguishable objects together, is critical to the effective application of probabilistic relational models to realistic real world tasks. Recently, lifted belief propagation (LBP) has been proposed as an efficient approximate solution of this inference problem. It runs a modified BP on a lifted network where nodes have been grouped together if they ...

We extend the generalized approximate message passing (G-AMP) approach, originally proposed for highdimensional generalized-linear regression in the context of compressive sensing, to the generalized-bilinear case, which enables its application to matrix completion, robust PCA, dictionary learning, and related matrix-factorization problems. In the first part of the paper, we derive our Bilinear...