Deriving structured parallel implementations for numerical methods

TL;DR: Part I - Fundamentals Introduction, Foundations, Programming Language Constructs, Proof, Realisations for Strict Languages,Realisations for Non-Strict Languages Part II - Current Research Areas Data Parallelism, Cost Modelling, Shaping Distributions, Performance Monitoring, Memory Performance of Dataflow Programs.

TL;DR: For an important subclass of structured method parallelism, a scheduling methodology which takes data redistributions between multiprocessor tasks into account is presented which is designed for an integration into a parallel compiler tool.

TL;DR: A coordination model to derive efficient implementations using mixed task and data parallelism is presented and the usefulness of the model is demonstrated by applying it to solution methods for differential equations.

TL;DR: This work describes the use of the BSP cost model to optimise programs, based on skeletons or data-parallel operations, in which program components may have multiple implementations.

TL;DR: The bulk-synchronous parallel (BSP) model is introduced as a candidate for this role, and results quantifying its efficiency both in implementing high-level language features and algorithms, as well as in being implemented in hardware.

TL;DR: A new parallel machine model, called LogP, is offered that reflects the critical technology trends underlying parallel computers and is intended to serve as a basis for developing fast, portable parallel algorithms and to offer guidelines to machine designers.

TL;DR: A model of computation based on random access machines operating in parallel and sharing a common memory is presented and can accept in polynomial time exactly the sets accepted by nondeterministic exponential time bounded Turing machines.

TL;DR: An overview of the MPI initiative and the standard interface is presented, in particular those aspects which merge demonstrated research with common practice.