Degree of parallelism

About: Degree of parallelism is a research topic. Over the lifetime, 1515 publications have been published within this topic receiving 25546 citations.

In-memory parallelization of join queries over large ontological hierarchies

Abstract: The Resource Description Framework (RDF) data model enables the construction of knowledge graphs over various domains, using ontologies in order to encode information about the domain, and simple statements in the form of subject-predicate-object triples for data representation, facilitating the interlinking and exchange of Web data However, this simplicity comes with the cost of having to execute a large number of joins in order to get the desirable query results, while at the same time large ontological hierarchies complicate the query answering process even more, for systems that provide complete answers with respect to such ontological axioms In this work we present PARJ, an in-memory RDF store which takes into consideration ontological hierarchies during join processing with very low performance overhead, avoiding expensive preprocessing and materialization of implications, and is also amenable to straightforward parallelization Specifically, we present a join implementation that allows to achieve any desired degree of parallelism on arbitrary join queries and RDF graphs stored in memory using compact vertical partitioning We use an adaptive join processing approach, such that we take advantage of complete or even partial ordering of RDF data, which is compactly stored in order to increase spatial locality and keep memory consumption low, coupled with an ID-to-Position vector index used when ordering does not allow for efficient scanning of the input relation Finally, we experimentally show the efficiency and scalability of our proposal

Solving the Constant-Degree Parallelism Alginment Problem

Abstract: We describe an exact algorithm for finding a computation mapping and data distributions that minimize, for a given degree of parallelism, the number of remote data accesses in a distributed memory parallel computer (DMPC). This problem is shown to be NP-hard.

An Algorithm-by-Blocks for SuperMatrix Band Cholesky Factorization

Abstract: We pursue the scalable parallel implementation of the factor- ization of band matrices with medium to large bandwidth targeting SMP and multi-core architectures. Our approach decomposes the computation into a large number of fine-grained operations exposing a higher degree of parallelism. The SuperMatrix run-time system allows an out-of-order scheduling of operations that is transparent to the programmer. Exper- imental results for the Cholesky factorization of band matrices on two parallel platforms with sixteen processors demonstrate the scalability of the solution.

RECEIPT: REfine CoarsE-grained IndePendent Tasks for Parallel Tip decomposition of Bipartite Graphs

Abstract: Tip decomposition is a crucial kernel for mining dense subgraphs in bipartite networks, with applications in spam detection, analysis of affiliation networks etc. It creates a hierarchy of vertex-induced subgraphs with varying densities determined by the participation of vertices in butterflies (2,2-bicliques). To build the hierarchy, existing algorithms iteratively follow a delete-update(peeling) process: deleting vertices with the minimum number of butterflies and correspondingly updating the butterfly count of their 2-hop neighbors. The need to explore 2-hop neighborhood renders tip-decomposition computationally very expensive. Furthermore, the inherent sequentiality in peeling only minimum butterfly vertices makes derived parallel algorithms prone to heavy synchronization. In this paper, we propose a novel parallel tip-decomposition algorithm -- REfine CoarsE-grained Independent Tasks (RECEIPT) that relaxes the peeling order restrictions by partitioning the vertices into multiple independent subsets that can be concurrently peeled. This enables RECEIPT to simultaneously achieve a high degree of parallelism and dramatic reduction in synchronizations. Further, RECEIPT employs a hybrid peeling strategy along with other optimizations that drastically reduce the amount of wedge exploration and execution time. We perform detailed experimental evaluation of RECEIPT on a shared-memory multicore server. It can process some of the largest publicly available bipartite datasets orders of magnitude faster than the state-of-the-art algorithms -- achieving up to 1100x and 64x reduction in the number of thread synchronizations and traversed wedges, respectively. Using 36 threads, RECEIPT can provide up to 17.1x self-relative speedup. Our implementation of RECEIPT is available at this https URL.