TY - GEN
T1 - Mainstream vs. Emerging HPC
T2 - 30th International Symposium on Computer Architecture and High Performance Computing, SBAC-PAD 2018
AU - Radulovic, Milan
AU - Asifuzzaman, Kazi
AU - Zivanovic, Darko
AU - Rajovic, Nikola
AU - De Verdiere, Guillaume Colin
AU - Pleiter, Dirk
AU - Marazakisl, Manolis
AU - Kallimanis, Nikolaos
AU - Carpenter, Paul
AU - Radojkovic, Petar
AU - Ayguade, Eduard
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/7/2
Y1 - 2018/7/2
N2 - 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.
AB - 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.
KW - BytelFLOP ratio
KW - HPC
KW - emerging and mainstream architectures
KW - energy efficiency
KW - memory latency and bandwidth
KW - weak vs. strong cores
UR - http://www.scopus.com/inward/record.url?scp=85063164839&partnerID=8YFLogxK
U2 - 10.1109/CAHPC.2018.8645891
DO - 10.1109/CAHPC.2018.8645891
M3 - Conference contribution
AN - SCOPUS:85063164839
T3 - Proceedings - 2018 30th International Symposium on Computer Architecture and High Performance Computing, SBAC-PAD 2018
SP - 250
EP - 257
BT - Proceedings - 2018 30th International Symposium on Computer Architecture and High Performance Computing, SBAC-PAD 2018
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 24 September 2018 through 27 September 2018
ER -