This title appears in the Scientific Report :
2019
Please use the identifier:
http://dx.doi.org/10.1109/CAHPC.2018.8645891 in citations.
Mainstream vs. Emerging HPC: Metrics, Trade-Offs and Lessons Learned
Mainstream vs. Emerging HPC: Metrics, Trade-Offs and Lessons Learned
Various servers with different characteristics and architectures are hitting the market, and their evaluation and comparison in terms of HPC features is complex and multidimensional. In this paper, we share our experience of evaluating a diverse set of HPC systems, consisting of three mainstream and...
Saved in:
Personal Name(s): | Radulovic, Milan |
---|---|
Asifuzzaman, Kazi / Zivanovic, Darko / Rajovic, Nikola / de Verdiere, Guillaume Colin / Pleiter, Dirk (Corresponding author) / Marazakisl, Manolis / Kallimanis, Nikolaos / Carpenter, Paul / Radojkovic, Petar / Ayguade, Eduard | |
Contributing Institute: |
Jülich Supercomputing Center; JSC |
Published in: |
2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD) : [Proceedings] - IEEE, 2018. - ISBN 978-1-5386-7769-8 - doi:10.1109/CAHPC.2018.8645891 |
Imprint: |
IEEE
2018
|
Physical Description: |
250-257 |
DOI: |
10.1109/CAHPC.2018.8645891 |
Conference: | 2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), Lyon (France), 2018-09-24 - 2018-09-27 |
Document Type: |
Contribution to a book Contribution to a conference proceedings |
Research Program: |
European Exascale Processor Memory Node Design Supercomputer Facility |
Publikationsportal JuSER |
Various servers with different characteristics and architectures are hitting the market, and their evaluation and comparison in terms of HPC features is complex and multidimensional. In this paper, we share our experience of evaluating a diverse set of HPC systems, consisting of three mainstream and five emerging architectures. We evaluate the performance and power efficiency using prominent HPC benchmarks, High-Performance Linpack (HPL) and High Performance Conjugate Gradients (HPCG), and expand our analysis using publicly available specialized kernel benchmarks, targeting specific system components. In addition to a large body of quantitative results, we emphasize six usually overlooked aspects of the HPC platforms evaluation, and share our conclusions and lessons learned. Overall, we believe that this paper will improve the evaluation and comparison of HPC platforms, making a first step towards a more reliable and uniform methodology. |