Conference paper Open Access

Global optimization of operand transfer fusion in heterogeneous computing

Kessler, Christoph


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="942" ind1=" " ind2=" ">
    <subfield code="a">2019-12-01</subfield>
  </datafield>
  <controlfield tag="005">20200120171918.0</controlfield>
  <controlfield tag="001">3515961</controlfield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">5448926</subfield>
    <subfield code="z">md5:f658ca9e00a2c91479568f39439dc743</subfield>
    <subfield code="u">https://zenodo.org/record/3515961/files/global_optimization.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-10-22</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="o">oai:zenodo.org:3515961</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Linköping University</subfield>
    <subfield code="a">Kessler, Christoph</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Global optimization of operand transfer fusion in heterogeneous computing</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">801015</subfield>
    <subfield code="a">Enhancing Programmability and boosting Performance Portability for Exascale Computing Systems</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;We consider the problem of minimizing, for a dataflow graph of kernel calls, the overall number of operand data transfers, and thus, the accumulated transfer startup overhead, in heterogeneous systems with non-shared memory. Our approach analyzes the kernel-operand dependence graph and reorders the operand arrays in memory such that transfers and memory allocations of multiple operands adjacent in memory can be merged, saving transfer startup costs and memory allocation overheads.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1145/3323439.3323981</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
145
100
views
downloads
Views 145
Downloads 100
Data volume 544.9 MB
Unique views 136
Unique downloads 97

Share

Cite as