The Combinatorial BLAS: design, implementation, and applications

By Aydin Buluç, John R. Gilbert. The international journal of high performance computing applications, 2011

437 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/c7f82b511ef5bb5c87f8d057e022fe3bd812fcdc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

In Hardware and Architecture

Citations in the corpus

PowerGraph: Distributed Graph-Parallel Computation on Natural Graphs (2012, neutral): “Several [8, 22] have proposed generalized sparse matrix vector multiplication as a basis for graph-parallel computation.”
PowerLyra: Differentiated Graph Computation and Partitioning on Skewed Graphs (2019, background): “Readers might be interested in how the performance of PowerLyra compares to other graph processing systems, even if they adopt different designs, such as graph-parallel abstraction [24, 29, 37, 47, 60], dataflow operators [26], sparse matrix operations [7], or declarative programming [62].”
Handbook of Big Data (2016, background): “Pegasus makes the matrix-vector interpretation explicit [35], as does Combinatorial BLAS [67].”
OuterSPACE: An Outer Product Based Sparse Matrix Multiplication Accelerator (2018, background): “lent in graph analytics, such as breadth-first search [23][24], matching [49], graph contraction [15], peer pressure clustering [54], cycle detection [65], Markov clustering [61], and triangle counting [9].”
Communication optimal parallel multiplication of sparse random matrices (2013, background): “Categories and Subject Descriptors F.2.1 [Analysis of Algorithms and Problem Complexity]: Numerical Algorithms and Problems—Computations on matrices Keywords communication-avoiding algorithms; communication-cost lower bounds; sparse matrix multiplication; random graphs”
GraphX: a resilient distributed graph system on Spark (2013, background): “In response to the growing size and importance of graph data, a range of new large-scale distributed graph-parallel frameworks ( e.g., Pregel [9], PowerGraph [6], and others [5, 3, 11]) have emerged.”
Recent Advances in Graph Partitioning (2013, methodology): “While exascale computing is a challenge for high-end applications, many more applications can proﬁt from GP in cloud computing and using tools for high productivity such as Map/Reduce [DG04], Pregel [MAB + 10], GraphLab [LGK + 12], Combinatorial BLAS [BG11], or Parallel Boost Graph Library [GL05].”
Graphicionado: A high-performance and energy-efficient accelerator for graph analytics (2016, background): “Examples include vertex programming [4, 33, 35, 46], sparse matrix operations [8], graph domain-specific languages [18], and task-based models [23].”
GraphMat: High performance graph analytics made productive (2015, background): “…recent work [28] that has compared different graph frameworks including Giraph [1] and GraphLab [5, 22] which are two popular vertex programming models; CombBLAS [3, 11], a matrix programming model; Socialite [29], a functional programming model; and Galois [26, 4, 25], a task-based abstraction.”
GraphX: Graph Processing in a Distributed Dataflow Framework (2014, background): “Distributed dataflow frameworks have enjoyed broad adoption for a wide variety of data processing tasks, including ETL, SQL query processing, and iterative machine learning.”
Gemini: A Computation-Centric Distributed Graph Processing System (2016, neutral): “A large number of graph-parallel systems [3, 10, 11, 12, 16, 17, 21, 22, 23, 26, 29, 30, 32, 36, 41, 42, 43, 44, 47, 49, 55, 56, 57, 59, 60] have been proposed for efficient processing of graphs with increasing scales.”