Breadth-First Search (BFS) Benchmarks

Lucata powers high performance graph analytics with a next generation computing architecture. Performance benchmarks running Breadth-First Search (BFS) on Graph500 datasets using Lucata Pathfinder are below.

Breadth-First Search (BFS) Benchmarks on Lucata

Database Scale (2N)1 Chassis2 Chassis
2043.5154.43
2131.7053.33
2288.40133.83
2367.61119.91
24159.47268.14
2545.1588.01
2646.9789.91
2774.08142.51
2865.72128.94
2972.28133.77
30245.84
* Data in MTEPS (millions of edges traversed per second)

Lucata K-hop Benchmarks (k=6) at Scale 26

K-hop Benchmarks (k=6) on Lucata

The k-hop graph algorithm uses BFS (breadth-first search) to count all the neighbors of a source vertex which are k “hops” away.  For this benchmark, a source vertex is selected and a count of the number of vertices in the graph 6 hops away are counted.

 

 

Database Scale (2N)1 Chassis2 Chassis
2071.1496.23
2137.1667.75
22139.79210.44
23111.19196.32
24264.89452.34
25274.49491.39
26298.28563.89
27260.51466.65
28295.94553.18
29373.99695.75
30554.94
* Data in MTEPS (millions of edges traversed per second)