Specification and verification of a MPI implementation for a MP-SoC

Authors:
Umberto Souza Da Costa;Ivan Soares De Medeiros Júnior;Marcel Vinicius Medeiros Oliveira
Affiliations:
Universidade Federal do Rio Grande do Norte, Departamento de Informática e Matemática Aplicada, Natal, RN, Brazil;Universidade Federal do Rio Grande do Norte, Departamento de Informática e Matemática Aplicada, Natal, RN, Brazil;Universidade Federal do Rio Grande do Norte, Departamento de Informática e Matemática Aplicada, Natal, RN, Brazil
Venue:
ICTAC'10 Proceedings of the 7th International colloquium conference on Theoretical aspects of computing
Year:
2010

Citing 12
Cited 0

Communicating sequential processes

Communicating sequential processes
Concurrent scientific computing

Concurrent scientific computing
The Theory and Practice of Concurrency

The Theory and Practice of Concurrency
MPI-The Complete Reference, Volume 1: The MPI Core

MPI-The Complete Reference, Volume 1: The MPI Core
Networks on Chips: A New SoC Paradigm

Computer
SPINning Parallel Systems Software

Proceedings of the 9th International SPIN Workshop on Model Checking of Software
A Study on Communication Issues for Systems-on-Chip

Proceedings of the 15th symposium on Integrated circuits and systems design
Analyzing On-Chip Communication in a MPSoC Environment

Proceedings of the conference on Design, automation and test in Europe - Volume 2
Cache coherency communication cost in a NoC-based MPSoC platform

Proceedings of the 20th annual conference on Integrated circuits and systems design
Formal specification of the MPI-2.0 standard in TLA+

Proceedings of the 13th ACM SIGPLAN Symposium on Principles and practice of parallel programming
Model checking nonblocking MPI programs

VMCAI'07 Proceedings of the 8th international conference on Verification, model checking, and abstract interpretation
An approach to formalization and analysis of message passing libraries

FMICS'07 Proceedings of the 12th international conference on Formal methods for industrial critical systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

System-on-Chip is a solution that integrates several components of a computer into a single chip substrate. Those systems are generally targeted for embedded applications and can increase their processing power by using multiple processors and an on-chip interconnection. STORM is a Multi-Processor System-on-Chip virtual platform which uses a basic implementation of the MPI standard to provide communication among their applications. STORM implements a small set of MPI routines for essential point-to-point and collective communication in order to provide more programmability and portability for the applications of the platform. In this work, we make use of CSP to build a formal model of those MPI routines and eliminate imprecision and ambiguities that may arise from their informal descriptions on the MPI standard. Also, we use the FDR model checker to ensure that the implemented routines have no errors introduced during the development process.