Efficient Transfer of C++ Objects in Intel Xeon Phi Coprocessor in Offload Mode
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21340%2F17%3A00316481" target="_blank" >RIV/68407700:21340/17:00316481 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Efficient Transfer of C++ Objects in Intel Xeon Phi Coprocessor in Offload Mode
Original language description
Intel Xeon Phi is a modern coprocessor designed for the high performance computing similar to GPUs by NVidia. TNL (Template Numerical Library) is a library providing abstract layer for accessing multicore CPUs and GPUs in numerical solvers. Our aim is to develop interface for Intel Xeon Phi coprocessor consistent with NVidia CUDA in TNL. In this paper we describe efficient method for bitwise copying of C++ objects similar to NVidia CUDA using Intel offloading extension of C++. As a working example we use the heat equation problem to demonstrate efficiency of the implementation on Intel Xeon Phi Knights Corner and to compare CPU with this coprocessor.
Czech name
—
Czech description
—
Classification
Type
J<sub>ost</sub> - Miscellaneous article in a specialist periodical
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Informatyka w Technologii Materiałów
ISSN
1641-8581
e-ISSN
—
Volume of the periodical
17
Issue of the periodical within the volume
2
Country of publishing house
PL - POLAND
Number of pages
7
Pages from-to
94-100
UT code for WoS article
—
EID of the result in the Scopus database
2-s2.0-85043382238