• Corpus ID: 61512503

The Graph 500 Benchmark on a Medium-Size Distributed-Memory Cluster with High-Performance Interconnect

@inproceedings{Angel2012TheG5,
  title={The Graph 500 Benchmark on a Medium-Size Distributed-Memory Cluster with High-Performance Interconnect},
  author={Jordan Angel and A. Mayas Flores and Nathaniel C Wardrip and Andrew M. Raim and Matthias K. Gobbert and Richard C. Murphy and David J. Mountain},
  year={2012}
}
While traditional performance benchmarks for high-performance computers measure the speed of arithmetic operations, memory access time is a more useful performance gauge for many large problems today. The Graph 500 benchmark has been developed to measure a computer’s performance in memory retrieval. The Graph 500 implementation considers large, randomly generated graphs, which may be spread across many nodes on a distributedmemory cluster. The benchmark conducts breadth-first searches on these… 
2 Citations
Graph Problems Performance Comparison Using Intel Xeon and Intel Xeon-Phi
TLDR
Two benchmarks focusing on the speed of memory access are examined, one developed in order to measure the computers performance in memory retrieval using the Breadth First Search algorithm on randomly generated graph and the other using the real world data set as an input graph.
DWPE, a new data center energy-efficiency metric bridging the gap between infrastructure and workload
TLDR
The metrics system PUE (sPUE) and Data center Workload Power Efficiency (DWPE) are introduced and sPUE calculates the overhead for operating a given system in a certain data center and DWPE allows for predicting the energy efficiency of different HPC systems in existing HPC data centers, thus making it an ideal approach for guiding HPC system procurement.

References

SHOWING 1-9 OF 9 REFERENCES
Introducing the Graph 500
In the words of Lord Kelvin, “if you cannot measure it, you cannot improve it”. One of the longlasting successes of the Top 500 list is sustained, community-wide floating point performance
Realistic, Mathematically Tractable Graph Generation and Evolution, Using Kronecker Multiplication
TLDR
It is shown that Kronecker graphs naturally obey all the above properties and can rigorously prove that they do so; in fact, it is proved that they can mimic very well several real graphs.
Realistic
  • mathematically tractable graph generation and evolution, using Kronecker multiplication, in: A. Jorge, L. Torgo, P. Brazdil, R. Camacho, J. Gama (Eds.), Knowledge Discovery in Databases: PKDD 2005, Vol. 3721 of Lecture Notes in Computer Science, Springer-Verlag
  • 2005
We sincerely appreciate the additional funding for the students to travel to Supercomputing 2012
  • We sincerely appreciate the additional funding for the students to travel to Supercomputing 2012
URL www.umbc.edu/hpcf
  • URL www.umbc.edu/hpcf
Optimizing the performance of IBM System x and BladeCenter servers using Intel Xeon 5500 series processors
  • Optimizing the performance of IBM System x and BladeCenter servers using Intel Xeon 5500 series processors
  • 2009
Parallel performance studies for an elliptic test problem on the cluster tara
  • Parallel performance studies for an elliptic test problem on the cluster tara
  • 2010
Graph 500 performance on a distributed-memory cluster
  • Tech. Rep
  • 2012
Ang, Introducing the Graph 500, Cray User Group 2010 Proceedings
  • Ang, Introducing the Graph 500, Cray User Group 2010 Proceedings
  • 2010