Loci: a rule-based framework for parallel multi-disciplinary simulation synthesis

Abstract

We present a rule-based framework for the development of scalable parallel high performance simulations for a broad class of scientific applications (with particular emphasis on continuum mechanics). We take a pragmatic approach to our programming abstractions by implementing structures that are used frequently and have common high performance implementations on distributed memory architectures. The resulting framework borrows heavily from rule-based systems for relational database models, however limiting the scope to those parts that have obvious high performance implementation. Using our approach, we demonstrate predictable performance behavior and efficient utilization of large scale distributed memory architectures on problems of significant complexity involving multiple disciplines.

Scaling law and enhancement of lift generation of an insect-size hovering flexible wing

“…The governing equations for the fluid given by equation (2.2) are solved using an in-house three-dimensional, unstructured, pressure-based finite volume solver [34,35] written in a rulebased framework [36]. The geometric conservation law [37] is satisfied [38].…”

Exploring Traditional and Emerging Parallel Programming Models Using a Proxy Application

“…Loci is a C++ framework that implements a declarative logic-relational programming model [18]. The programming model is implicitly parallel and uses relational abstractions to describe distributed irregular data structures.…”

“…A version of LULESH exists for GPUs with an implementation in CUDA [16]. Additionally, we have ported LULESH to four new and emerging programming models: Chapel [17], CHARM++ [10], Liszt [12] and Loci [18]. The Liszt port can generate both a multiprocessor version and a GPU-enabled version.…”

LULESH Programming Model and Performance Ports Overview

“…Loci is a C++ framework that implements a declarative logic-relational programming model that is implicitly parallel and uses relational abstractions to describe distributed irregular data structures [11]. The Loci implementation uses built-in 3D vector data-types to simplify the algorithm description.…”