Linear Algebra-Based Triangle Counting via Fine-Grained Tasking on Heterogeneous Environments : (Update on Static Graph Challenge)

Yaşar, Abdurrahman; Rajamanickam, Sivasankaran; Berry, Jonathan W.; Wolf, Michael M.; Young, Jeffrey; Çatalyürek, Ümit V.

doi:10.1109/hpec.2019.8916233

Cited by 11 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Later, [32], [33], [34] use bitmap to represent the hash bucket which still suffers from high cache pressure. We also notice that Yacsar et al [35], [36], [37], [38] switch between dense and sparse representations of a hash table in their matrix-multiplication effort which is, however, complex in nature.…”

Section: Related Work and Challengesmentioning

confidence: 94%

“…Vertex-centric triangle counting is worse than the edge-centric counterpart on GPUs due to more severe workload imbalance issues [21], [22], [23], [25]. Particularly, vertex-centric design [17], [32], [35], [36], [37] iterates through each vertex, loads the 1-and 2-hop neighbors, and intersects them to arrive at the triangles. Edge-centric design [21], [22], [23], [25] does that for each edge thus only 1-hop neighbors are needed.…”

Section: Related Work and Challengesmentioning

confidence: 99%

“…Merge-path Bitmap Hashing Vertex-centric Edge-centric CPU [13] [17], [27], [30] [26], [29] [17] [35], [36], [37], [38], [46], [47] [48], [49] GPU [13], [21], [22], [23], [24], [50] [43] [33], [34], [51] TRUST [25] [36], [52] [52] TABLE 1: Closely related projects for TRUST.…”

Section: Matrix-multiplication Subgraph Matching Binary-searchmentioning

confidence: 99%

See 2 more Smart Citations

TRUST: Triangle Counting Reloaded on GPUs

Pandey,

Wang,

Zhong

et al. 2021

Preprint

View full text Add to dashboard Cite

Triangle counting is a building block for a wide range of graph applications. Traditional wisdom suggests that i) hashing is not suitable for triangle counting, ii) edge-centric triangle counting beats vertex-centric design, and iii) communication-free and workload balanced graph partitioning is a grand challenge for triangle counting. On the contrary, we advocate that i) hashing can help the key operations for scalable triangle counting on Graphics Processing Units (GPUs), i.e., list intersection and graph partitioning, ii) vertex-centric design reduces both hash table construction cost and memory consumption, which is limited on GPUs. In addition, iii) we exploit graph and workload collaborative, and hashing-based 2D partitioning to scale vertex-centric triangle counting over 1,000 GPUs with sustained scalability. In this work, we present TRUST which performs triangle counting with the hash operation and vertex-centric mechanism at the core. To the best of our knowledge, TRUST is the first work that achieves over one trillion Traversed Edges Per Second (TEPS) rate for triangle counting.

show abstract

Section: Related Work and Challengesmentioning

confidence: 94%

Section: Related Work and Challengesmentioning

confidence: 99%

See 1 more Smart Citation

TRUST: Triangle Counting Reloaded on GPUs

Pandey,

Wang,

Zhong

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…For example, the Kokkos Kernels SpGEMM implementation led to highly optimized implementation of the triangle counting kernel (Wolf et al, 2017). Since then, there are other fast implementations of triangle counting kernels based on Cilk (Yaşar et al, 2018) and using both CPUs and GPUs (Yasar et al, 2019) and distributed memory systems (Acer et al, 2019).…”

Section: Algebraic Approaches For Graph Algorithms and Combinatorial Problemsmentioning

confidence: 99%

EXAGRAPH: Graph and combinatorial methods for enabling exascale applications

Acer

Azad

Boman

et al. 2021

The International Journal of High Performance Computing Applica

Self Cite

View full text Add to dashboard Cite

Combinatorial algorithms in general and graph algorithms in particular play a critical enabling role in numerous scientific applications. However, the irregular memory access nature of these algorithms makes them one of the hardest algorithmic kernels to implement on parallel systems. With tens of billions of hardware threads and deep memory hierarchies, the exascale computing systems in particular pose extreme challenges in scaling graph algorithms. The codesign center on combinatorial algorithms, ExaGraph, was established to design and develop methods and techniques for efficient implementation of key combinatorial (graph) algorithms chosen from a diverse set of exascale applications. Algebraic and combinatorial methods have a complementary role in the advancement of computational science and engineering, including playing an enabling role on each other. In this paper, we survey the algorithmic and software development activities performed under the auspices of ExaGraph from both a combinatorial and an algebraic perspective. In particular, we detail our recent efforts in porting the algorithms to manycore accelerator (GPU) architectures. We also provide a brief survey of the applications that have benefited from the scalable implementations of different combinatorial algorithms to enable scientific discovery at scale. We believe that several applications will benefit from the algorithmic and software tools developed by the ExaGraph team.

show abstract

“…Scalability was demonstrated using up to 1K Cores on a 3.6B edge graph. Another linear algebra-based solution is presented in [61], which offers heterogeneous (CPU-GPU) processing on multi-GPU platforms like the Nvidia DGX.…”

Section: Relation To External Workmentioning

confidence: 99%

TriPoll: Computing Surveys of Triangles in Massive-Scale Temporal Graphs with Metadata

Steil,

Reza,

Iwabuchi

et al. 2021

Preprint

View full text Add to dashboard Cite

Understanding the higher-order interactions within network data is a key objective of network science. Surveys of metadata triangles (or patterned 3-cycles in metadata-enriched graphs) are often of interest in this pursuit. In this work, we develop TriPoll, a prototype distributed HPC system capable of surveying triangles in massive graphs containing metadata on their edges and vertices. We contrast our approach with much of the prior effort on triangle analysis, which often focuses on simple triangle counting, usually in simple graphs with no metadata. We assess the scalability of TriPoll when surveying triangles involving metadata on real and synthetic graphs with up to hundreds of billions of edges. We utilize communication-reducing optimizations to demonstrate a triangle counting task on a 224 billion edge web graph in approximately half of the time of competing approaches, while additionally supporting metadata-aware capabilities.

show abstract

Linear Algebra-Based Triangle Counting via Fine-Grained Tasking on Heterogeneous Environments : (Update on Static Graph Challenge)

Cited by 11 publications

References 10 publications

TRUST: Triangle Counting Reloaded on GPUs

TRUST: Triangle Counting Reloaded on GPUs

EXAGRAPH: Graph and combinatorial methods for enabling exascale applications

TriPoll: Computing Surveys of Triangles in Massive-Scale Temporal Graphs with Metadata

Contact Info

Product

Resources

About