Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Michael J. Levenhagen"'
Publikováno v:
IPDPS
Remote Direct Memory Access (RDMA) capabilities have been provided by high-end networks for many years, but the network environments surrounding RDMA are evolving. RDMA performance has historically relied on using strict ordering guarantees to determ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::34fe129e234d46c4ed79c235e228c467
https://doi.org/10.1109/ipdps49936.2021.00029
https://doi.org/10.1109/ipdps49936.2021.00029
Autor:
James H. Laros, Courtenay T. Vaughan, Michael J. Levenhagen, Andrew J. Younge, Clayton Hughes, Simon D. Hammond, Benjamin Schwaller, Kevin Pedretti, Michael J. Aguilar
Publikováno v:
HPCS
The high performance computing industry is undergoing a period of substantial change. Not least because of fabrication and lithographic challenges in the manufacturing of next-generation processors. As such challenges mount, the industry is looking t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::39bdae4fd8cabf5153ffec5e1ec05dad
https://doi.org/10.1109/hpcs48598.2019.9188171
https://doi.org/10.1109/hpcs48598.2019.9188171
Publikováno v:
Concurrency and Computation: Practice and Experience. 32
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::06f8fb0bed21f83c6d495f27df2fd7fc
https://doi.org/10.1002/cpe.5150
https://doi.org/10.1002/cpe.5150
Autor:
Michael J. Levenhagen, Ron Brightwell, Ryan E. Grant, Matthew G. F. Dosanjh, Anthony Skjellum
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030206550
ISC
ISC
The MPI multithreading model has been historically difficult to optimize; the interface that it provides for threads was designed as a process-level interface. This model has led to implementations that treat function calls as critical regions and pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::80dc0f61330bb15cf611a1efb25c135e
https://doi.org/10.1007/978-3-030-20656-7_17
https://doi.org/10.1007/978-3-030-20656-7_17
Autor:
Ryan E. Grant, Michael J. Levenhagen, James H. Laros, David DeBonis, Stephen L. Olivier, Kevin Pedretti
Publikováno v:
Computer. 49:38-46
Power API--the result of collaboration among national laboratories, universities, and major vendors--provides a range of standardized power management functions, from application-level control and measurement to facility-level accounting, including r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::741c35cf95c92a96e14c8c016593e1ef
https://doi.org/10.1109/mc.2016.308
https://doi.org/10.1109/mc.2016.308
Autor:
Ryan E. Grant, Patrick G. Bridges, Ahmad Afsahi, Whit Schonbein, Michael J. Levenhagen, Matthew G. F. Dosanjh, S. Mahdieh Ghazimirsaeed
Publikováno v:
ICPP
The performance critical path for MPI implementations relies on fast receive side operation, which in turn requires fast list traversal. The performance of list traversal is dependent on data-locality; whether the data is currently contained in a clo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::398199d015e90e900effcbba79f6e5d0
https://doi.org/10.1145/3225058.3225130
https://doi.org/10.1145/3225058.3225130
Autor:
Kevin Pedretti, James H. Laros, Michael J. Levenhagen, Lee Ward, Stephen L. Olivier, Andrew J. Younge, Ryan E. Grant
Publikováno v:
IPDPS Workshops
Large-scale HPC systems increasingly incorporate sophisticated power management control mechanisms. While these mechanisms are potentially useful for performing energy and/or power-aware job scheduling and resource management (EPA JSRM), greater unde
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ae54b319820eb6f0b50c0036706779e0
https://doi.org/10.1109/ipdpsw.2018.00117
https://doi.org/10.1109/ipdpsw.2018.00117
Autor:
Andrew J. Younge, Michael J. Levenhagen, Ryan E. Grant, Kevin Pedretti, Stephen L. Olivier, Lee Ward, James H. Laros
Publikováno v:
IGSC
Advanced power measurement capabilities are becoming available on large scale High Performance Computing (HPC) deployments. There exist several approaches to providing power measurements today, primarily through in-band (e.g. RAPL) and out-of-band me
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fb898d6a6d7f2b55d53a273558713e20
https://doi.org/10.1109/igcc.2017.8323587
https://doi.org/10.1109/igcc.2017.8323587
Autor:
Kevin Pedretti, Stephen L. Olivier, David DeBonis, Michael J. Levenhagen, James H. Laros, Suzanne M. Kelly, Ryan E. Grant
Measuring and controlling the power and energy consumption of high performance computing systems by various components in the software stack is an active research area [13, 3, 5, 10, 4, 21, 19, 16, 7, 17, 20, 18, 11, 1, 6, 14, 12]. Implementations in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ee2b8bb65e6480123583ba1a50b6d26
https://doi.org/10.2172/1331358
https://doi.org/10.2172/1331358
Autor:
Taylor Groves, Simon D. Hammond, Dorian Arnold, Ryan E. Grant, Michael J. Levenhagen, Scott Hemmer
Publikováno v:
CLUSTER
Exascale networks are expected to comprise a significant part of the total monetary cost and 10-20% of the power budget allocated to exascale systems. Yet, our understanding of current and emerging workloads on these networks is limited. Left ignored
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::512d2af9430addd7ecb71db9385406a8
https://doi.org/10.1109/cluster.2016.52
https://doi.org/10.1109/cluster.2016.52