Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Pedro Yebenes"'
Autor:
Le, Yanfang, Lee, Jeongkeun, Blendin, Jeremias, Chen, Jiayi, Nikolaidis, Georgios, Pan, Rong, Soule, Robert, Akella, Aditya, Segura, Pedro Yebenes, singhvi, Arjun, Li, Yuliang, Meng, Qingkai, Kim, Changhoon, Arslan, Serhat
State-of-the-art congestion control algorithms for data centers alone do not cope well with transient congestion and high traffic bursts. To help with these, we revisit the concept of direct \emph{backward} feedback from switches and propose Back-to-
Externí odkaz:
http://arxiv.org/abs/2305.00538
Publikováno v:
MASCOTS
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4f71cb6c5e1df7fd02998c2390d43bcb
https://doi.org/10.1109/mascots53633.2021.9614297
https://doi.org/10.1109/mascots53633.2021.9614297
Autor:
Jesus Escudero-Sahuquillo, Pedro Javier Garcia, Pedro Yebenes, Crispín Gómez, Francisco J. Alfaro, Francisco J. Quiles, Jose Rocher-Gonzalez, José Duato
Publikováno v:
ACM Transactions on Architecture and Code Optimization. 16:1-26
Hybrid and direct topologies are cost-efficient and scalable options to interconnect thousands of end nodes in high-performance computing (HPC) systems. They offer a rich path diversity, high bisection bandwidth, and a reduced diameter guaranteeing l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b34513b00eaa4be0522c31c844c35a5e
https://doi.org/10.1145/3319805
https://doi.org/10.1145/3319805
Autor:
Allister Alemania, Pedro Yebenes Segura, Anupama Kurpad, Jan Zielinski, Krzysztof Raszkowski, Roberto Penaranda, Sujoy Senxiv, Steven C. Miller, Ram Huggahalli, Gene Wu, Nan Ni, Malek Musleh, Scott S. Diesing, Curt E. Bruns
Publikováno v:
MASCOTS
The explosive growth in cloud-computing and overall data center system growth has created an unprecedented demand on system architects and designers to continuously develop more complex system networks to effectively satisfy the insatiable appetite t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1258be12a0c7abb8f065fdf250dfa0cc
https://doi.org/10.1109/mascots50786.2020.9285933
https://doi.org/10.1109/mascots50786.2020.9285933
Autor:
Eitan Zahavi, German Maglione-Mathey, Jesus Escudero-Sahuquillo, Pedro Javier Garcia, Pedro Yebenes, Francisco J. Quiles
Publikováno v:
IEEE Transactions on Parallel and Distributed Systems. 29:183-197
Dragonfly topologies are gathering great interest nowadays as one of the most promising interconnect options for High-Performance Computing (HPC) systems. However, Dragonflies contain physical cycles that may lead to traffic deadlocks unless the rout
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e45b2f4a7e33501ef0d219056528a1f6
https://doi.org/10.1109/tpds.2017.2742503
https://doi.org/10.1109/tpds.2017.2742503
Publikováno v:
HiPINEB@HPCA
In post-Dennard scaling energy becomes more and more important. While most components in data-center and supercomputer become increasingly energy-proportional, this trend seems to pass on interconnection networks. Although previous studies have shown
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::67b900e8c419045207f620c5cb4b45c2
https://doi.org/10.1109/hipineb.2019.00009
https://doi.org/10.1109/hipineb.2019.00009
Publikováno v:
The Journal of Supercomputing. 72:4497-4519
The performance of interconnection networks is a challenging issue for High-Performance Computing (HPC) systems, which becomes even more important when the number of interconnected endnodes grows. In that sense, Dragonfly interconnection patterns are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6c0d9fc2aa32b00e4077ca344224bafe
https://doi.org/10.1007/s11227-016-1756-1
https://doi.org/10.1007/s11227-016-1756-1
Autor:
Pedro Javier Garcia, Jesus Escudero-Sahuquillo, Pedro Yebenes, Torsten Hoefler, Francisco J. Quiles
Publikováno v:
Hot Interconnects
Interconnection networks must meet the communication demands of current High-Performance Computing systems. In order to interconnect efficiently the end nodes of these systems with a good performance-to-cost ratio, new network topologies have been pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0dbed4900671045936f8e4b2ed9613bc
https://doi.org/10.1109/hoti.2017.11
https://doi.org/10.1109/hoti.2017.11
Autor:
Jesus Escudero-Sahuquillo, Pedro Javier Garcia, Francisco J. Quiles, Torsten Hoefler, Pedro Yebenes
Publikováno v:
HiPINEB@HPCA
Interconnection network performance becomes a key issue in HPC systems as their size grows. In order to maximize network performance with the minimum quantity of network resources, Slim Fly topology was proposed. It offers a high network bandwidth an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d4d8df7953a8ca9d52d7d4257061b7c4
https://doi.org/10.1109/hipineb.2017.9
https://doi.org/10.1109/hipineb.2017.9
Publikováno v:
HiPINEB@HPCA
Power consumption is one of the most important aspects regarding design and operation of large computing systems, such as High-Performance Computing (HPC) and cloud installations. Various hard constraints exist due to technical, economic and ecologic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aa9807088d436be8d8a4c10b72caf661
https://doi.org/10.1109/hipineb.2016.13
https://doi.org/10.1109/hipineb.2016.13