Corpus ID: 62327934

Linear Algebraic Primitives for Parallel Computing on Large Graphs

@inproceedings{Barbara2010LinearAP,
  title={Linear Algebraic Primitives for Parallel Computing on Large Graphs},
  author={Santa Barbara},
  year={2010}
}
Linear Algebraic Primitives for Parallel Computing on Large Graphs 
Optimizing Sparse Linear Algebra for Large-Scale Graph Analytics
TLDR
A new class of linear algebra algorithms can efficiently execute sparse matrix-matrix and matrix-vector multiplications on large-scale, shared memory multiprocessor systems, enabling analysts to more easily discern meaningful data relationships, such as those in social networks. Expand
GPU-Based Fast Minimum Spanning Tree Using Data Parallel Primitives
TLDR
This paper proposes a minimum spanning tree algorithm using Prim's approach on Nvidia GPU under CUDA architecture by using new developed GPU-based Min-Reduction data parallel primitive in the key step of the algorithm, higher efficiency is achieved. Expand
Active messages as a spanning model for parallel graph computation
TLDR
This thesis demonstrates that phrasing graph algorithms as collections of asynchronous, concurrent, message-driven fragments of code allows for natural expression of algorithms, flexible implementations leveraging various forms of parallelism, and performance portability--all without modifying the algorithm expressions themselves. Expand
Highly Parallel Sparse Matrix-Matrix Multiplication
TLDR
This work presents the first parallel algorithms that achieve increasing speed ups for an unbounded number of processors, based on two-dimensional block distribution of sparse matrices where serial sections use a novel hypersparse kernel for scalability. Expand
The Combinatorial BLAS: design, implementation, and applications
TLDR
The parallel Combinatorial BLAS is described, which consists of a small but powerful set of linear algebra primitives specifically targeting graph and data mining applications, and an extensible library interface and some guiding principles for future development are provided. Expand
Efficient sparse matrix-matrix multiplication on heterogeneous high performance systems
TLDR
This paper introduces a task based programming model and a runtime supported execution model which provides dynamic load balancing on clusters composed by CPUs and GPUs, allowing better utilization of the system while easing the handling of sparse matrices. Expand
Design and Implementation of GPU-Based Prim's Algorithm
TLDR
This paper proposes a minimum spanning tree algorithm using Prim's approach on Nvidia GPU under CUDA architecture by using new developed GPU-based Min-Reduction data parallel primitive in the key step of the algorithm, higher efficiency is achieved. Expand
Expressing graph algorithms using generalized active messages
TLDR
This paper presents a method of phrasing graph algorithms as collections of asynchronous, concurrently executing, concise code fragments which may be invoked both locally and in remote address spaces and identifies a number of common patterns in these algorithms, and explores how this programming model can express those patterns. Expand
MadLINQ: large-scale distributed matrix computation for the cloud
TLDR
The design and implementation of MadLINQ is described and the system outperforms current state-of-the-art systems by employing two key techniques: exploiting extra parallelism using fine-grained pipelining and efficient on-demand failure recovery using a distributed fault-tolerant execution engine. Expand
On parallelizing matrix multiplication by the column-row method
TLDR
This work presents a surprisingly simple method for "consistent" parallel processing of sparse outer products (column-row vector products) over several processors, in a communication-avoiding setting where each processor has a copy of the input. Expand
...
1
2
...

References

SHOWING 1-10 OF 203 REFERENCES
A Unified Framework for Numerical and Combinatorial Computing
TLDR
The authors describe their efforts to build a common infrastructure for numerical and combinatorial computing by using parallel sparse matrices to implement parallel graph algorithms. Expand
Introduction to algorithms - a creative approach
TLDR
Algorithms Involving Sequences and Sets, Algebraic and Numeric Algorithms, Parallel Al algorithms, and NP-Completeness. Expand
A set of level 3 basic linear algebra subprograms
This paper describes an extension to the set of Basic Linear Algebra Subprograms. The extensions are targeted at matrix-vector operations that should provide for efficient and portableExpand
A Relational Approach to the Compilation of Sparse Matrix Programs
We present a relational algebra based framework for compiling efficient sparse matrix code from dense DO-ANY loops and a specification of the representation of the sparse matrix. We presentExpand
The Parallel BGL : A Generic Library for Distributed Graph Computations
This paper presents the Parallel BGL, a generic C ++ library for distributed graph computation. Like the sequential Boost Graph Library (BGL) upon which it is based, the Parallel BGL applies theExpand
NVIDIA Tesla: A Unified Graphics and Computing Architecture
TLDR
To enable flexible, programmable graphics and high-performance computing, NVIDIA has developed the Tesla scalable unified graphics and parallel computing architecture, which is massively multithreaded and programmable in C or via graphics APIs. Expand
Challenges in Parallel Graph Processing
TLDR
The inter-relationships between graph problems, software, and parallel hardware in the current state of the art are presented and the range of these challenges suggests a research agenda for the development of scalable high-performance software for graph problems. Expand
New abstractions for data parallel programming
TLDR
This paper introduces several dimensions along which is possible to develop more powerful data parallel programming abstractions and presents two simple examples of data parallel programs that make use of operators developed as part of the studies. Expand
An extended set of FORTRAN basic linear algebra subprograms
This paper describes an extension to the set of Basic Linear Algebra Subprograms. The extensions are targeted at matrix-vector operations that should provide for efficient and portableExpand
SUMMA: scalable universal matrix multiplication algorithm
In this paper, we give a straight forward, highly e cient, scalable implementation of common matrix multiplication operations. The algorithms are much simpler than previously published methods, yieldExpand
...
1
2
3
4
5
...