Data and Computation Abstractions for Dynamic and Irregular Computations
نویسندگان
چکیده
Effective data distribution and parallelization of computations involving irregular data structures is a challenging task. We address the twin-problems in the context of computations involving block-sparse matrices. The programming model provides a global view of a distributed block-sparse matrix. Abstractions are provided for the user to express the parallel tasks in the computation. The tasks are mapped onto processors to ensure load balance and locality. The abstractions are based on the Aggregate Remote Memory Copy Interface, and are interoperable with the Global Arrays programming suite and MPI. Results are presented that demonstrate the utility of the approach.
منابع مشابه
The Parallel Implementation of N - body
This dissertation studies issues critical to e cient N-body simulations on parallel computers. The N-body problem poses several challenges for distributed-memory implementation: adaptive distributed data structures, irregular data access patterns, and irregular and adaptive communication patterns. We introduce new techniques to maintain dynamic irregular data structures, to vectorize irregular ...
متن کاملAutomatic Parallelization of Irregular and Pointer-Based Computations: Perspectives from Logic and Constraint Programming
Abs t r ac t . Irregular computations pose some of the most interesting and challenging problems in automatic parallelization. Irregularity appears in certain kinds of numerical problems and is pervasive in symbolic applications. Such computations often use dynamic data structures which make heavy use of pointers. This complicates all the steps of a parallelizing compiler, from independence det...
متن کاملReliable Scalable Symbolic Computation: The Design of SymGridPar2 pdfsubject=Proceedings of the 28th Symposium On Applied Computing, SAC 2013
Symbolic computation is an important area of both Mathematics and Computer Science, with many large computations that would benefit from parallel execution. Symbolic computations are, however, challenging to parallelise as they have complex data and control structures, and both dynamic and highly irregular parallelism. The SymGridPar framework has been developed to address these challenges on s...
متن کاملProgramming Models, Compilers, and Algorithms for Irregular Data-Parallel Computations
Advances in parallel computing have made it clear that the ability to express computations in a machine-independent manner and the ability to handle dynamic and irregular computations are two necessary features of future programming systems. In this paper, we describe the nested data-parallel model of programming, which has both these capabilities. We present an intermediate-level language call...
متن کاملProgramming with Sociable Resources
We present a model for shared-memory parallel programming that makes shared objects (“resources”) the drivers of heap-manipulating parallel computations. The model aims to syntactically capture patterns of spatial locality in heap updates and to express the maximum amount of logical parallelism in computations. To achieve this, we take a “resources’-eye” view of parallel operations on the heap....
متن کامل