Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Rengan Xu"'
Autor:
Valeriu Codreanu, Don D. Smith, Pei Yang, Srinivas Varadharajan, Vikram A. Saletore, Can Karakus, Derya Cavdar, John A. Lockman, Lucas A. Wilson, Rengan Xu, Alexander Sergeev, Damian Podareanu, Quy Ta, Victor Suthichai
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030206550
ISC
ISC
Neural machine translation - using neural networks to translate human language - is an area of active research exploring new neuron types and network topologies with the goal of dramatically improving machine translation performance. Current state-of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::51fb54170ef55b38d1f2243777ad22cc
https://doi.org/10.1007/978-3-030-20656-7_2
https://doi.org/10.1007/978-3-030-20656-7_2
Publikováno v:
PMBS@SC
The recent explosion in the popularity of Deep Learning (DL) is due to a combination of improved algorithms, access to large datasets and increased computational power. This had led to a plethora of open-source DL frameworks, each with varying charac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c457abbf010568ef9cdcfbe74176ddd8
https://doi.org/10.1109/pmbs.2018.8641600
https://doi.org/10.1109/pmbs.2018.8641600
Autor:
Sunita Chandrasekaran, Xiaonan Tian, Barbara Chapman, Rengan Xu, Yonghong Yan, Deepak Eachempati
Publikováno v:
Concurrency and Computation: Practice and Experience. 28:537-556
Manycore accelerators have the potential to significantly improve performance of scientific applications when offloading computationally intensive program portions to accelerators. Directive-based high-level programming models, such as OpenACC and Op
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::38098331889149f2c96852db1af9729c
https://doi.org/10.1002/cpe.3648
https://doi.org/10.1002/cpe.3648
Publikováno v:
Scientific Programming, Vol 2015 (2015)
Existing studies show that using single GPU can lead to obtaining significant performance gains. We should be able to achieve further performance speedup if we use more than one GPU. Heterogeneous processors consisting of multiple CPUs and GPUs offer
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d6e6d90ebfdf4f7dcbbd191c75086658
https://doi.org/10.1155/2015/621730
https://doi.org/10.1155/2015/621730
Autor:
Sunita Chandrasekaran, Michael Wolfe, Seyong Lee, Barbara Chapman, Jung-Won Kim, Rengan Xu, Xiaonan Tian
Publikováno v:
IPDPS Workshops
Programming accelerators today usually requires managing separate virtual and physical memories, such as allocating space in and copying data between host and device memories. The OpenACC API provides data directives and clauses to control this behav
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::40fecacf82e2809c5fee611aa8395a17
https://doi.org/10.1109/ipdpsw.2017.85
https://doi.org/10.1109/ipdpsw.2017.85
This chapter shows how a directive-based model can make it possible for application scientists to “keep” their codes, accelerate them with reduced programming effort, and achieve performance equal to or better than that obtained using hand-writte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3b5e7a3878062f57b43a3b6a059b2fe9
https://doi.org/10.1016/b978-0-12-410397-9.00008-1
https://doi.org/10.1016/b978-0-12-410397-9.00008-1
Publikováno v:
ICPP
Using compiler directives to program accelerator-based systems through APIs such as OpenACC or OpenMP has increasingly gained popularity due to the portability and productivity advantages it offers. However, when comparing the performance typically a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9b23c742e90539308502dfe7074be204
https://doi.org/10.1109/icpp.2016.72
https://doi.org/10.1109/icpp.2016.72
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319413204
HPC developers aim to deliver the very best performance. To do so they constantly think about memory bandwidth, memory hierarchy, locality, floating point performance, power/energy constraints and so on. On the other hand, application scientists aim
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::112dbcc818dddc0dfac2c40ce1330cbf
https://doi.org/10.1007/978-3-319-41321-1_1
https://doi.org/10.1007/978-3-319-41321-1_1
Autor:
William C. Brantley, Pavel Shelepugin, Mathew E. Colgrove, Alexey Titov, Brian Whitney, Maxim Perminov, Wen-mei W. Hwu, John A. Stratton, Wolfgang E. Nagel, Matthias S. Müller, Robert Henschel, Barbara Chapman, Huian Li, Ke Wang, Guido Juckeland, G. Matthijs van Waveren, Huiyu Feng, Kalyan Kumaran, Rengan Xu, Alexander Grund, Shuai Che, Kevin Skadron, Sunita Chandrasekaran, Sandra Wienke
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319172477
PMBS@SC
PMBS@SC
Hybrid nodes with hardware accelerators are becoming very common in systems today. Users often find it difficult to characterize and understand the performance advantage of such accelerators for their applications. The SPEC High Performance Group (HP
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4f16ba24979fe772afdb84334cbad894
https://doi.org/10.1007/978-3-319-17248-4_3
https://doi.org/10.1007/978-3-319-17248-4_3