Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Justin Luitjens"'
Publikováno v:
ICASSP
We present an optimized weighted finite-state transducer (WFST) decoder capable of online streaming and offline batch processing of audio using Graphics Processing Units (GPUs). The decoder is efficient in memory utilization, input/output (I/O) bandw
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5b48f9b50be58d6497bd6ddf77c4c8bc
Publikováno v:
INTERSPEECH
We describe initial work on an extension of the Kaldi toolkit that supports weighted finite-state transducer (WFST) decoding on Graphics Processing Units (GPUs). We implement token recombination as an atomic GPU operation in order to fully paralleliz
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5c02449df9d49638eed922c36fe673f2
https://doi.org/10.21437/interspeech.2018-1339
https://doi.org/10.21437/interspeech.2018-1339
Publikováno v:
2016 6th Workshop on Irregular Applications: Architecture and Algorithms (IA3).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cc078cd0b6daaa62699730743f7faa23
https://doi.org/10.1109/ia3.2016.009
https://doi.org/10.1109/ia3.2016.009
Autor:
Justin Luitjens, Martin Berzins
Publikováno v:
Concurrency and Computation: Practice and Experience. 23:1522-1537
Block-structured adaptive mesh refinement (BSAMR) is widely used within simulation software because it improves the utilization of computing resources by refining the mesh only where necessary. For BSAMR to scale onto existing petascale and eventuall
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0b779a09f86eca489050a4e26b186985
https://doi.org/10.1002/cpe.1719
https://doi.org/10.1002/cpe.1719
Publikováno v:
Concurrency and Computation: Practice and Experience. 19:1387-1402
In this paper we consider the scalability of parallel space-filling curve generation as implemented through parallel sorting algorithms. Multiple sorting algorithms are studied and results show that space-filling curves can be generated quickly in pa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ffa7e2f998f520e24e845e1764fa52b7
https://doi.org/10.1002/cpe.1179
https://doi.org/10.1002/cpe.1179
Autor:
Anthony Scudiero, Evgeny Bolotin, Stephen W. Keckler, Oreste Villa, Justin Luitjens, Mike O'Connor, Peng Wang, Paulius Micikevicius, David Nellans, Nikolai Sakharnykh, William J. Dally, Daniel R. Johnson
Publikováno v:
SC
Modern scientific discovery is driven by an insatiable demand for computing performance. The HPC community is targeting development of supercomputers able to sustain 1 ExaFlops by the year 2020 and power consumption is the primary obstacle to achievi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dbb34908898001cd022ab8503f2361af
https://doi.org/10.1109/sc.2014.73
https://doi.org/10.1109/sc.2014.73
Publikováno v:
MTAGS@SC
Uintah is a computational framework for fluid-structure interaction problems using a combination of the ICE fluid flow algorithm, adaptive mesh refinement (AMR) and MPM particle methods. Uintah uses domain decomposition with a task-graph approach for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a6861bb9c1057b2cb88560115ef39723
https://doi.org/10.1109/mtags.2010.5699431
https://doi.org/10.1109/mtags.2010.5699431
Autor:
Martin Berzins, Charles A. Wight, Todd Harman, Qingyu Meng, Joseph R. Peterson, Justin Luitjens
Publikováno v:
Proceedings of the 2010 TeraGrid Conference.
The Uintah Software system was developed to provide an environment for solving a fluid-structure interaction problems on structured adaptive grids on large-scale, long-running, data-intensive problems. Uintah uses a novel asynchronous task-based appr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::de0fa678cd208a695e4a0996db0eb6ac
https://doi.org/10.1145/1838574.1838577
https://doi.org/10.1145/1838574.1838577
Autor:
Martin Berzins, Justin Luitjens
Publikováno v:
IPDPS
Uintah is a highly parallel and adaptive multi-physics framework created by the Center for Simulation of Accidental Fires and Explosions in Utah. Uintah, which is built upon the Common Component Architecture, has facilitated the simulation of a wide
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a42b0effdf7318d7f2ecabee50313b2a
https://doi.org/10.1109/ipdps.2010.5470437
https://doi.org/10.1109/ipdps.2010.5470437
Publikováno v:
Advanced Computational Infrastructures for Parallel and Distributed Adaptive Applications
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::234895bfd0d2f7c6b52e6f49dde4f442
https://doi.org/10.1002/9780470558027.ch10
https://doi.org/10.1002/9780470558027.ch10