Scalable Knowledge Graph Analytics at 136 Petaflop/s

Kannan, Ramakrishnan {ramki}; Sao, Piyush; Lu, Hao; Herrmannova, Dasha; Thakkar, Vijay; Patton, Robert; Vuduc, Richard; Potok, Thomas

doi:10.1109/SC41405.2020.00010

Title: Scalable Knowledge Graph Analytics at 136 Petaflop/s

Full Record
Other Related Research

Abstract

We are motivated by newly proposed methods for data mining large-scale corpora of scholarly publications, such as the full biomedical literature, which may consist of tens of millions of papers spanning decades of research. In this setting, analysts seek to discover how concepts relate to one another. They construct graph representations from annotated text databases and then formulate the relationship-mining problem as one of computing all-pairs shortest paths (APSP), which becomes a significant bottleneck. In this context, we present a new high-performance algorithm and implementation of the Floyd-Warshall algorithm for distributed-memory parallel computers accelerated by GPUs, which we call DSNAPSHOT (Distributed Accelerated Semiring All-Pairs Shortest Path). For our largest experiments, we ran DSNAPSHOT on a connected input graph with millions of vertices using 4, 096nodes (24,576GPUs) of the Oak Ridge National Laboratory's Summit supercomputer system. We find DSNAPSHOT achieves a sustained performance of 136×1015 floating-point operations per second (136petaflop/s) at a parallel efficiency of 90% under weak scaling and, in absolute speed, 70% of the best possible performance given our computation (in the single-precision tropical semiring or “min-plus” algebra). Looking forward, we believe this novel capability will enable the mining of scholarly knowledge corpora when embedded and integrated into artificialmore »« less

Authors:

^[1];

^[1]; Lu, Hao ^[1];

^[1]; Thakkar, Vijay ^[2];

^[1]; Vuduc, Richard ^[3];

^[1]

ORNL
Georgia Institute of Technology
Georgia Institute of Technology, Atlanta

Publication Date:: 2020-11-01

Research Org.:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)

OSTI Identifier:: 1798621

DOE Contract Number:: AC05-00OR22725

Resource Type:: Conference

Resource Relation:: Conference: The International Conference on High Performance Computing, Networking, Storage and Analysis (SC'20) - Atlanta, Georgia, United States of America - 11/16/2020 5:00:00 AM-11/19/2020 5:00:00 AM

Country of Publication:: United States

Language:: English

Citation Formats


                    Kannan, Ramakrishnan, Sao, Piyush, Lu, Hao, Herrmannova, Dasha, Thakkar, Vijay, Patton, Robert, Vuduc, Richard, and Potok, Thomas. Scalable Knowledge Graph Analytics at 136 Petaflop/s.  United States: N. p., 2020. 
        Web.  doi:10.1109/SC41405.2020.00010.

Copy to clipboard


                    Kannan, Ramakrishnan, Sao, Piyush, Lu, Hao, Herrmannova, Dasha, Thakkar, Vijay, Patton, Robert, Vuduc, Richard, & Potok, Thomas. Scalable Knowledge Graph Analytics at 136 Petaflop/s.  United States.  https://doi.org/10.1109/SC41405.2020.00010

Copy to clipboard


                    Kannan, Ramakrishnan, Sao, Piyush, Lu, Hao, Herrmannova, Dasha, Thakkar, Vijay, Patton, Robert, Vuduc, Richard, and Potok, Thomas. 2020.  
        "Scalable Knowledge Graph Analytics at 136 Petaflop/s".  United States.  https://doi.org/10.1109/SC41405.2020.00010.  https://www.osti.gov/servlets/purl/1798621.

Copy to clipboard


                    
@article{osti_1798621,

  title        = {Scalable Knowledge Graph Analytics at 136 Petaflop/s},

  author       = {Kannan, Ramakrishnan and Sao, Piyush and Lu, Hao and Herrmannova, Dasha and Thakkar, Vijay and Patton, Robert and Vuduc, Richard and Potok, Thomas},

  abstractNote = {We are motivated by newly proposed methods for data mining large-scale corpora of scholarly publications, such as the full biomedical literature, which may consist of tens of millions of papers spanning decades of research. In this setting, analysts seek to discover how concepts relate to one another. They construct graph representations from annotated text databases and then formulate the relationship-mining problem as one of computing all-pairs shortest paths (APSP), which becomes a significant bottleneck. In this context, we present a new high-performance algorithm and implementation of the Floyd-Warshall algorithm for distributed-memory parallel computers accelerated by GPUs, which we call DSNAPSHOT (Distributed Accelerated Semiring All-Pairs Shortest Path). For our largest experiments, we ran DSNAPSHOT on a connected input graph with millions of vertices using 4, 096nodes (24,576GPUs) of the Oak Ridge National Laboratory's Summit supercomputer system. We find DSNAPSHOT achieves a sustained performance of 136×1015 floating-point operations per second (136petaflop/s) at a parallel efficiency of 90% under weak scaling and, in absolute speed, 70% of the best possible performance given our computation (in the single-precision tropical semiring or “min-plus” algebra). Looking forward, we believe this novel capability will enable the mining of scholarly knowledge corpora when embedded and integrated into artificial intelligence-driven natural language processing workflows at scale.},

  doi          = {10.1109/SC41405.2020.00010},

  url          = {https://www.osti.gov/biblio/1798621},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {2020},

  month        = {11}

}

Copy to clipboard

Conference:

View Conference (1.71 MB)

https://doi.org/10.1109/SC41405.2020.00010

Other availability

Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

Exaflops Biomedical Knowledge Graph Analytics

Conference Kannan, Ramakrishnan {ramki}; Sao, Piyush; Lu, Hao; ...

We are motivated by newly proposed methods for mining large-scale corpora of scholarly publications (e.g., full biomedical literature), which consists of tens of millions of papers spanning decades of research. In this setting, analysts seek to discover relationships among concepts. They construct graph representations from annotated text databases and then formulate the relationship-mining problem as an all-pairs shortest paths (APSP) and validate connective paths against curated biomedical knowledge graphs (e.g., Spoke). In this context, we present Coast (Exascale Communication-Optimized All-Pairs Shortest Path) and demonstrate 1.004 EF/s on 9,200 Frontier nodes (73,600 GCDs). We develop hyperbolic performance models (HYPERMOD), which guidemore »« less
https://doi.org/10.1109/SC41404.2022.00011

Full Text Available
Scalable All-pairs Shortest Paths for Huge Graphs on Multi-GPU Clusters

Conference Sao, Piyush; Lu, Hao; Kannan, Ramakrishnan {Ramki}; ...

We present an optimized Floyd-Warshall (Floyd-Warshall) algorithm that computes the All-pairs shortest path (APSP) for GPU accelerated clusters. The Floyd-Warshall algorithm due to its structural similarities to matrix-multiplication is well suited for highly parallel GPU architectures. To achieve high parallel efficiency, we address two key algorithmic challenges: reducing high communication overhead and addressing limited GPU memory. To reduce high communication costs, we redesign the parallel (a) to expose more parallelism, (b) aggressively overlap communication and computation with pipelined and asynchronous scheduling of operations, and (c) tailored MPI-collective. To cope with limited GPU memory, we employ an offload model, where themore »« less
Full Text Available
A supernodal all-pairs shortest path algorithm

Conference Sao, Piyush; Kannan, Ramakrishnan {ramki}; Gera, Prasun; ...

We show how to exploit graph sparsity in the Floyd-Warshall algorithm for the all-pairs shortest path (Apsp) problem. Floyd-Warshall is an attractive choice for Apsp on high-performing systems due to its structural similarity to solving dense linear systems and matrix multiplication. However, if sparsity of the input graph is not properly exploited, Floyd-Warshall will perform unnecessary asymptotic work and thus may not be a suitable choice for many input graphs. To overcome this limitation, the key idea in our approach is to use the known algebraic relationship between Floyd-Warshall and Gaussian elimination, and import several algorithmic techniques from sparse Choleskymore »« less
https://doi.org/10.1145/3332466.3374533

Full Text Available
Algebraic Algorithms for Betweenness and Percolation Centrality

Journal Article Tumurbaatar, Altansuren; Sottile, Matthew - Journal of Graph Algorithms and Applications

Abstract In this paper, we explored different ways to write the algebraic version of betweenness centrality algorithm. Particularly, we focused on Brandes' algorithm. We aimed for algebraic betweenness centrality that can be parallelized easily. We proposed 3-tuple geodetic semiring as an extension to the usual geodetic semiring with 2-tuples. Using the 3-tuple geodetic semiring, Dijkstra's and Brandes' algorithm, we wrote more concise and general algebraic betweenness centrality (ABC) algorithm which is valid for weighted and directed graphs. We also proposed an alternative version of ABC using the usual geodetic semiring with 2-tuple where we used a simple way to constructmore »« less
https://doi.org/10.7155/jgaa.00558

Full Text Available
Fast estimation of diameter and shortest paths (without matrix multiplication)

Conference Aingworth, D; Chekuri, C; Motwani, R

Consider the problem of computing all-pairs shortest paths (APSP) in an unweighted, undirected graph G with n vertices and m edges. The recent work of Alon, Galil, and Margalit, Alon, Galil, Margalit, and Naor, and Seidel has led to dramatic progress in devising fast algorithms for this problem. These algorithm are based on formulating the problem in terms of matrices with small integer entries and using fast matrix multiplications. They achieve a time bound of O(n{sup {omega}}){sup 1} where {omega} denotes the exponent in the running time of the matrix multiplication algorithm used. The current best matrix multiplication algorithm ismore »« less

Similar Records