Communication Optimizations for Irregular Scientiic Computations on Distributed Memory Architectures 3
نویسندگان
چکیده
This paper describes a number of optimizations that can be used to support the eecient execution of irregular problems on distributed memory parallel machines. These primitives (1) coordinate inter-processor data movement, (2) manage the storage of, and access to, copies of oo-processor data, (3) minimize interprocessor communication requirements and (4) support a shared name space. We present a detailed performance and scalability analysis of the communication primitives. This performance and scalability analysis is carried out using a workload generator, kernels from real applications and a large unstructured adaptive application (the molecular dynamics code CHARMM).
منابع مشابه
Runtime Support for Portable Distributed Data Structures
Multipol is a library of distributed data structures designed for irregular applications , including those with asynchronous communication patterns. In this paper, we describe the Multipol runtime layer, which provides an eecient and portable abstraction underlying the data structures. It contains a thread system to express computations with varying degrees of parallelism and to support multipl...
متن کاملIntegrating Software Pipelining and Graph Scheduling for Iterative Scientific Computations
Graph scheduling has been shown eeective for solving irregular problems represented as directed acyclic graphs(DAGs) on distributed memory systems. Many scientiic applications can also be modeled as iterative task graphs(ITGs). In this paper, we model the SOR computation for solving sparse matrix systems in terms of ITGs and address the optimization issues for scheduling ITGs when communication...
متن کاملOptimizing Irregular Data Accesses for Cluster and Multicore Architectures
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission....
متن کاملMassively Parallel Computing: Mathematics and Communications Libraries Massively Parallel Computing: Mathematics and Communications Libraries
Massively parallel computing holds the promise of extreme performance. The utility of these systems will depend heavily upon the availability of libraries until compilation and run{ time system technology is developed to a level comparable to what today is common on most uniprocessor systems. Critical for performance is the ability to exploit locality of reference and eeective management of the...
متن کاملHeuristic Algorithms for Scheduling Iterative Task Computations on Distributed Memory Machines
Many partitioned scientiic programs can be modeled as iterative execution of computational tasks, represented by iterative task graphs (ITGs). In this paper, we consider the symbolic scheduling of ITGs on distributed memory architectures with nonzero communication overhead without searching the entire iteration space. An ITG may or may not have dependence cycles and we propose heuristic algorit...
متن کامل