Zobrazeno 91 - 100
of 408
pro vyhledávání: '"Kessler, Christoph"'
Autor:
Li, Lu, Kessler, Christoph
Publikováno v:
ACM International Conference Proceeding Series; 1/25/2017, p7-12, 6p
SkePU is a C++ template library with a simple and unified interface for expressing data parallel computations in terms of generic components, called skeletons, on multi-GPU systems using CUDA and OpenCL. The smart containers in SkePU, such as Matrix
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______261::e16364d54954fe8a55db19942a7f4a04
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-102578
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-102578
Autor:
Dastgeer, Usman, Kessler, Christoph
In this paper, we describe our work on providing a generic yet optimized GPU (CUDA/OpenCL) implementation for the 2D MapOverlap skeleton. We explain our implementation with the help of a 2D convolution application, implemented using the newly develop
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::704316818f62f6b21c02a39573897315
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-136906
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-136906
The Intel SCC manycore processor supports energy-efficient computing by dynamic voltage and frequency scaling of cores on a fine-grained level. In order to enable the use of that feature in application-level energy optimizations, we report on experim
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::d3e044119d9c7416e6832e3c68533c58
https://hal.archives-ouvertes.fr/hal-00719033
https://hal.archives-ouvertes.fr/hal-00719033
Shared memory multicore processor technology is pervasive in mainstream computing. This new architecture challenges programmers to write code that scales over these many cores to exploit the full computational power of these machines. OpenMP and Inte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::5de03ffd62ddf38d795bd94e7e76baf9
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-93951
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-93951
Performance of manycore processors is limited by programs' use of off-chip main memory. Streaming computation organized in a pipeline limits accesses to main memory to tasks at boundaries of the pipeline to read or write to main memory. The Single Ch
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::386d92f2bf53cdbaffd0c8d0e36dbeb6
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-93421
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-93421
Autor:
Benkner, Siegfried, Pllana, Sabri, Larsson Träff, Jesper, Tsigas, Philippas, Richards, Andrew, Namyst, Raymond, Bachmayer, Beverly, Kessler, Christoph, Moloney, David, Sanders, Peter
Publikováno v:
ParCo
ParCo, Aug 2011, Ghent, Belgium
ParCo, Aug 2011, Ghent, Belgium
International audience; The European FP7 project PEPPHER is addressing programmability and performance portability for current and emerging heterogeneous many-core archi- tectures. As its main idea, the project proposes a multi-level parallel executi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::81b23c8551f487a179f69e91a6a1c015
https://hal.inria.fr/hal-00661320/document
https://hal.inria.fr/hal-00661320/document
Publikováno v:
International conference on Parallel Computing (ParCo)
International conference on Parallel Computing (ParCo), Aug 2011, Gent, Belgium. ⟨10.3233/978-1-61499-041-3-159⟩
International conference on Parallel Computing (ParCo), Aug 2011, Gent, Belgium. ⟨10.3233/978-1-61499-041-3-159⟩
International audience; SkePU is a skeleton programming framework for multicore CPU and multi-GPU systems. StarPU is a runtime system that provides dynamic scheduling and memory management support for heterogeneous, accelerator-based systems. We have
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::c173073798ab96006eb4139813dc818b
https://hal.inria.fr/inria-00606200
https://hal.inria.fr/inria-00606200