Authors:
Soumyadip Bandyopadhyay
1
;
Santonu Sarkar
1
and
Kunal Banerjee
2
Affiliations:
1
BITS Pilani and K K Birla Goa Campus, India
;
2
Indian Institute of Technology, India
Keyword(s):
Equivalence Checking, Petri Net based Representation for Embedded Systems (PRES+) Model, Finite State Machine with Datapath (FSMD) Model, High-level Language.
Related
Ontology
Subjects/Areas/Topics:
Distributed and Mobile Software Systems
;
Formal Methods
;
Model Tools
;
Models
;
Paradigm Trends
;
Parallel and High Performance Computing
;
Programming Languages
;
Simulation and Modeling
;
Software Engineering
;
Software Engineering Methods and Techniques
Abstract:
Among the various models of computation (MoCs) which have been used to model parallel programs, Petri net
has been one of the mostly adopted MoC. The traditional Petri net model is extended into the PRES+ model
which is specially equipped to precisely represent parallel programs running on heterogeneous and embedded
systems. With the inclusion of multicore and multiprocessor systems in the domain of embedded systems, it
has become important to validate the optimizing and parallelizing transformations which system specifications
go through before deployment. Although PRES+ model based equivalence checkers for validating such transformations
already exist, construction of the PRES+ models from the original and the translated programs was
carried out manually in these equivalence checkers, thereby leaving scope for inaccurate representation of the
programs due to human intervention. Furthermore, PRES+ model tends to grow more rapidly with the program
size when compared to other MoCs, su
ch as FSMD. To alleviate these drawbacks, we propose a method
for automated construction of PRES+ models from high-level language programs and use an existing translation
scheme to convert PRES+ models to FSMD models to validate the transformations using a state-of-the-art
FSMD equivalence checker. Thus, we have composed an end-to-end fully automated equivalence checker for
validating optimizing and parallelizing transformations as demonstrated by our experimental results.
(More)