Matches in UGent Biblio for { <https://biblio.ugent.be/publication/819988#aggregation> ?p ?o. }
Showing items 1 to 33 of
33
with 100 items per page.
- aggregation classification "P1".
- aggregation creator person.
- aggregation creator person.
- aggregation creator person.
- aggregation date "2009".
- aggregation format "application/pdf".
- aggregation hasFormat 819988.bibtex.
- aggregation hasFormat 819988.csv.
- aggregation hasFormat 819988.dc.
- aggregation hasFormat 819988.didl.
- aggregation hasFormat 819988.doc.
- aggregation hasFormat 819988.json.
- aggregation hasFormat 819988.mets.
- aggregation hasFormat 819988.mods.
- aggregation hasFormat 819988.rdf.
- aggregation hasFormat 819988.ris.
- aggregation hasFormat 819988.txt.
- aggregation hasFormat 819988.xls.
- aggregation hasFormat 819988.yaml.
- aggregation isPartOf urn:issn:9781-4133.
- aggregation language "eng".
- aggregation publisher "Association for Computing Machinery (ACM)".
- aggregation rights "I have retained and own the full copyright for this publication".
- aggregation subject "Technology and Engineering".
- aggregation title "Strategies for dynamic memory allocation in hybrid architectures".
- aggregation abstract "Hybrid architectures combining the strengths of general-purpose processors with application-specific hardware accelerators can lead to a significant performance improvement. Our hybrid architecture uses a Java Virtual Machine as an abstraction layer to hide the complexity of the hardware/software interface between processor and accelerator from the programmer. The data communication between the accelerator and the processor often incurs a significant cost, which sometimes annihilates the original speedup obtained by the accelerator. This article shows how we minimise this communication cost by dynamically chosing an optimal data layout in the Java heap memory which is distributed over both the accelerator and the processor memory. The proposed self-learning memory allocation strategy finds the optimal location for each Java object's data by means of runtime profiling. The communication cost is effectively reduced by up to 86% for the benchmarks in the DaCapo suite (51% on average).".
- aggregation authorList BK296975.
- aggregation endPage "220".
- aggregation startPage "217".
- aggregation aggregates 820011.
- aggregation isDescribedBy 819988.
- aggregation similarTo 1531743.1531778.
- aggregation similarTo LU-819988.