Performance Evaluation of Adaptive Routing on Dragonfly-based Production Systems

Autor: Justs Zarins, Sudheer Chunduri, Michele Weiland, Peter Mendygral, Kevin Harms, Yasaman Ghadar, Taylor Groves

Publikováno v: Chunduri, S, Groves, T, Harms, K, Mendygral, P, Zarins, J, Weiland, M & Ghadar, Y 2021, Performance Evaluation of Adaptive Routing on Dragonfly-based Production Systems . in 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS) . pp. 340-349, 35th IEEE International Parallel and Distributed Processing Symposium, Portland, Oregon, United States, 17/05/21 . https://doi.org/10.1109/IPDPS49936.2021.00042
IPDPS

Performance of applications in production environments can be sensitive to network congestion. Cray Aries supports adaptively routing each network packet independently based on the load or congestion encountered as a packet traverses the network. Sof

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a72fac9bdfbff1c35ad866739486aae5
https://www.pure.ed.ac.uk/ws/files/221625888/Performance_Evaluation_CHUNDURI_DOA09012021_AFV.pdf

GPCNeT

Autor: Brian Austin, Sudheer Chunduri, Nathan Wichmann, Nicholas J. Wright, Steven R. Warren, Taylor Groves, Peter Mendygral, Krishna Kandalla, Glenn K. Lockwood, Kalyan Kumaran, Scott Parker, Jacob Balma

Publikováno v: SC

Network congestion is one of the biggest problems facing HPC systems today, affecting system throughput, performance, user experience, and reproducibility. Congestion manifests as run-to-run variability due to contention for shared resources (e.g., f

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::d0c751dd94e9336807a2d598c5ffdc5c
https://doi.org/10.1145/3295500.3356215

CosmoFlow: Using Deep Learning to Learn the Universe at Scale

Autor: Tuomas Kärnä, Lei Shao, Victor W. Lee, Amrita Mathuriya, Nalini Kumar, Simon J. Pennycook, Kristyn Maschhoff, Peter Mendygral, Lawrence Meadows, Jason Sewall, Diana Moise, Prabhat Prabhat, James Arnemann, Michael F. Ringenburg, Siyu He, Shirley Ho, Deborah Bard

Publikováno v: Mathuriya, Amrita; Bard, Deborah; Mendygral, Peter; Meadows, Lawrence; Arnemann, James; Shao, Lei; et al.(2018). CosmoFlow: Using Deep Learning to Learn the Universe at Scale. SC18: International Conference for High Performance Computing, Networking, Storage and Analysis. doi: 10.1109/sc.2018.00068. Lawrence Berkeley National Laboratory: Retrieved from: http://www.escholarship.org/uc/item/6g4145rq
SC

Deep learning is a promising tool to determine the physical model that describes our universe. To handle the considerable computational cost of this problem, we present CosmoFlow: a highly scalable deep learning application built on top of the Tensor

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::678927f228e227083ca2700d4c4a075a
https://escholarship.org/uc/item/6g4145rq

Towards Exascale Simulations of the ICM Dynamo with WENO-Wombat

Autor: Dongsu Ryu, J. M. F. Donnert, Gianfranco Brunetti, Hanbyul Jang, Thomas W Jones, Peter Mendygral

Publikováno v: Galaxies, Vol 6, Iss 4, p 104 (2018)
Galaxies
Volume 6
Issue 4

In galaxy clusters, modern radio interferometers observe non-thermal radio sources with unprecedented spatial and spectral resolution. For the first time, the new data allows to infer the structure of the intra-cluster magnetic fields on small scales

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0b5de01ccfbe19519a1b50006fcda204
http://www.mdpi.com/2075-4434/6/4/104

Acceleration and Evolution of Cosmic Ray Electrons During Radio-Galaxy-Cluster-Shock Encounters

Autor: Chris Nolting, Thomas W Jones, Peter Mendygral, Brian J. O'Neill

Publikováno v: Proceedings of 35th International Cosmic Ray Conference — PoS(ICRC2017).

Radio Galaxies (radio-loud AGNs, or RGs) are common in galaxy cluster media (ICMs). In addition to their potential thermodynamical roles, these RGs may also serve to illuminate important ICM dynamical features, especially ICM shocks. Those interactio

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::a65a4d54b0a531c2eaac35c54cf0f61c
https://doi.org/10.22323/1.301.0276