Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Akhil Langer"'
Publikováno v:
OpenSHMEM and Related Technologies. OpenSHMEM in the Era of Exascale and Smart Networks ISBN: 9783031048876
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4c803a776a738cdcfbd0e9c32ad86d82
https://doi.org/10.1007/978-3-031-04888-3_12
https://doi.org/10.1007/978-3-031-04888-3_12
Publikováno v:
IPDPS Workshops
High Performance Computing has been a driving force behind important tasks such as scientific discovery and deep learning. It tends to achieve performance through greater concurrency and heterogeneity, where the underlying complexity of richer topolo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d0eaaf7c81ff67ae16029099704ade31
https://doi.org/10.1109/ipdpsw50202.2020.00104
https://doi.org/10.1109/ipdpsw50202.2020.00104
Publikováno v:
EuroMPI
Triggered operations and counting events or counters are building blocks used by communication libraries, such as MPI, to offload collective operations to the Host Fabric Interface (HFI) or Network Interface Card (NIC). Triggered operations can be us
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b2030e7d074b3866f31c735ccdb474b8
https://doi.org/10.1145/3343211.3343222
https://doi.org/10.1145/3343211.3343222
Publikováno v:
The International Journal of High Performance Computing Applications. 31:451-466
Operating chips at high energy efficiency is one of the major challenges for modern large-scale supercomputers. Low-voltage operation of transistors increases the energy efficiency but leads to frequency and power variation across cores on the same c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e5af3ae9d8df955b7aa3fdeb2d7d9a52
https://doi.org/10.1177/1094342016672082
https://doi.org/10.1177/1094342016672082
Autor:
Esteban Meneses, Bilge Acun, Ehsan Totoni, Osman Sarood, Harshitha Menon, Akhil Langer, Laxmikant V. Kale
Publikováno v:
Computer. 49:30-37
In a design based on the Charm++ parallel programming framework, an adaptive runtime system dynamically interacts with a datacenter's resource manager to control power by intelligently scheduling jobs, reallocating resources, and reconfiguring hardwa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::973d230441c04529af32d48c64f6e7f1
https://doi.org/10.1109/mc.2016.310
https://doi.org/10.1109/mc.2016.310
Autor:
Marc Gamell Balmana, Rashid Kaleem, Alexander Sannikov, María Jesús Garzarán, Dmitry Durnov, Akhil Langer, Surabhi Jain
Publikováno v:
SC
Collective operations are used in MPI programs to express common communication patterns, collective computations, or synchronization. In many collectives, such as MPI_Allreduce, the intra-node component of the collective lies on the critical path, as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1c2d4fdac6e07c36156dde737428950b
https://doi.org/10.1109/sc.2018.00032
https://doi.org/10.1109/sc.2018.00032
Autor:
Alexander Sannikov, Sangmin Seo, Yanfei Guo, Ken Raffenetti, Paul Fischer, Tomislav Janjusic, Thilina Rathnayake, Michael Alan Blocksome, Jithin Jose, Matthew Otten, Hajime Fujita, Sergey Oblomov, Sayantan Sur, Masamichi Takagi, Pavan Balaji, Masayuki Hatanaka, Misun Min, Abdelhalim Amer, Paul Coffman, Wesley Bland, Akhil Langer, Michael Chuvelev, Dmitry Durnov, Charles J. Archer, Min Si, Lena Oden, Gengbin Zheng, Xin Zhao
Publikováno v:
SC
This paper provides an in-depth analysis of the software overheads in the MPI performance-critical path and exposes mandatory performance overheads that are unavoidable based on the MPI-3.1 specification. We first present a highly optimized implement
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::239bcee1cca243a59b43e4761829cc19
https://doi.org/10.1145/3126908.3126963
https://doi.org/10.1145/3126908.3126963
Publikováno v:
IPDPS Workshops
Minimizing energy and power consumption of large scale data centers is one of the biggest challenges faced by the high performance computing community. In an over provisioned data center, nodes are power capped to run below their Thermal Design Power
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b11025df02fef97444e4d3bb2017a789
https://doi.org/10.1109/ipdpsw.2015.129
https://doi.org/10.1109/ipdpsw.2015.129
Publikováno v:
PMAM@PPoPP
Power and energy efficiency is one of the major challenges to achieve exascale computing in the next several years. While chips operating at low voltages have been studied to be highly energy-efficient, low voltage operations lead to heterogeneity ac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::268bd7e4bf2acd026548cec8df495dbe
https://doi.org/10.1145/2712386.2712396
https://doi.org/10.1145/2712386.2712396
Autor:
Udatta S. Palekar, Akhil Langer
Publikováno v:
ICORES
Stochastic program optimizations are computationally very expensive, especially when the number of scenarios are large. Complexity of the focal application, and the slow convergence rate add to its computational complexity. We propose a split-and-mer
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::42100af9423ac588d20459c8d3452047
https://doi.org/10.5220/0005287902180223
https://doi.org/10.5220/0005287902180223