Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Andra Hugo"'
Publikováno v:
Parallel Computing. 75:11-27
Recent scheduling heuristics for task-based applications have managed to improve performance by taking into account memory-related properties such as data locality and cache sharing. However, there is still a general lack of tools that can provide in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3dde9a466ce158f811a57138e49ac8f0
https://doi.org/10.1016/j.parco.2018.02.003
https://doi.org/10.1016/j.parco.2018.02.003
Publikováno v:
Supercomputing Frontiers and Innovations. 4
The complex memory hierarchies of nowadays machines make it very difficult to estimate the execution time of the tasks as depending on where the data is placed in memory, tasks of the same type may end up having different performance. Multiple schedu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::28c167c097fe97789d10f46219c7a3da
https://doi.org/10.14529/jsfi170306
https://doi.org/10.14529/jsfi170306
Publikováno v:
Recercat. Dipósit de la Recerca de Catalunya
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
PMAM@PPoPP
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
PMAM@PPoPP
Recent scheduling heuristics for task-based applications have managed to improve their by taking into account memory-related properties such as data locality and cache sharing. However, there is still a general lack of tools that can provide insights
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::90ea37454cf1d21fa4f22250a59a83b5
https://hdl.handle.net/2117/101245
https://hdl.handle.net/2117/101245
Publikováno v:
Euro-Par 2016: Parallel Processing Workshops ISBN: 9783319589428
Euro-Par Workshops
HeteroPar'2016 worshop of Euro-Par
HeteroPar'2016 worshop of Euro-Par, Aug 2016, Grenoble, France
Euro-Par Workshops
HeteroPar'2016 worshop of Euro-Par
HeteroPar'2016 worshop of Euro-Par, Aug 2016, Grenoble, France
International audience; Hybrid computing platforms are now commonplace, featuring a large number of CPU cores and accelerators. This trend makes balancing computations between these heterogeneous resources performance critical. In this paper we propo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0ccbc8c167b82949341f9b13a9cdfb4c
https://doi.org/10.1007/978-3-319-58943-5_5
https://doi.org/10.1007/978-3-319-58943-5_5
Publikováno v:
Parallel Computing
Parallel Computing, Elsevier, 2018
Parallel Computing, 2018
Parallel Computing, Elsevier, 2018
Parallel Computing, 2018
This paper is submitted for review to the Parallel Computing special issue for HCW and HeteroPar 16 workshops; International audience; Hybrid computing platforms are now commonplace, featuring a large number of CPU cores and accelerators. This trend
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::13dc6c144e0f50f086c3031a23799452
https://inria.hal.science/hal-01409965/document
https://inria.hal.science/hal-01409965/document
Publikováno v:
SBAC-PAD
To port applications to GPUs, developers need to express computational tasks as highly parallel executions with tens of thousands of threads to fill the GPU's compute resources. However, while this will fill the GPU's resources, it does not necessari
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8098c9c6a3c56109b48d3cf3f7b9ff9d
https://doi.org/10.1109/sbac-pad.2016.14
https://doi.org/10.1109/sbac-pad.2016.14
Publikováno v:
International Conference on Parallel Processing (ICPP 2014)
43rd International Conference on Parallel Processing
43rd International Conference on Parallel Processing, Sep 2014, Minneapolis, United States. ⟨10.1109/ICPP.2014.57⟩
ICPP
43rd International Conference on Parallel Processing
43rd International Conference on Parallel Processing, Sep 2014, Minneapolis, United States. ⟨10.1109/ICPP.2014.57⟩
ICPP
International audience; —To face the advent of multicore processors and the ever increasing complexity of hardware architectures, pro-gramming models based on DAG-of-tasks parallelism regained popularity in the high performance, scientific computin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4c14beb9664eeb692e226faa342fccb6
https://hal.inria.fr/hal-01101054/file/AHugo.pdf
https://hal.inria.fr/hal-01101054/file/AHugo.pdf
Publikováno v:
Third International Workshop on Accelerators and Hybrid Exascale Systems
Third International Workshop on Accelerators and Hybrid Exascale Systems, May 2013, Boston, United States
International Journal of High Performance Computing Applications
International Journal of High Performance Computing Applications, 2014, 28, pp.285-300. ⟨10.1177/1094342014527575⟩
International Journal of High Performance Computing Applications, SAGE Publications, 2014, 28, pp.285-300. ⟨10.1177/1094342014527575⟩
IPDPS Workshops
Third International Workshop on Accelerators and Hybrid Exascale Systems, May 2013, Boston, United States
International Journal of High Performance Computing Applications
International Journal of High Performance Computing Applications, 2014, 28, pp.285-300. ⟨10.1177/1094342014527575⟩
International Journal of High Performance Computing Applications, SAGE Publications, 2014, 28, pp.285-300. ⟨10.1177/1094342014527575⟩
IPDPS Workshops
Enabling HPC applications to perform efficiently when invoking multiple parallel libraries simultaneously is a great challenge. Even if a uniform runtime system is used underneath, scheduling tasks or threads coming from different libraries over the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b416e5f57975a730326958ae9a78c35a
https://hal.inria.fr/hal-00824514
https://hal.inria.fr/hal-00824514