Conference paper Open Access

Global optimization of operand transfer fusion in heterogeneous computing

Kessler, Christoph


JSON-LD (schema.org) Export

{
  "description": "<p>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.</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "Link\u00f6ping University", 
      "@type": "Person", 
      "name": "Kessler, Christoph"
    }
  ], 
  "headline": "Global optimization of operand transfer fusion in heterogeneous computing", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2019-10-22", 
  "url": "https://zenodo.org/record/3515961", 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.1145/3323439.3323981", 
  "@id": "https://doi.org/10.1145/3323439.3323981", 
  "@type": "ScholarlyArticle", 
  "name": "Global optimization of operand transfer fusion in heterogeneous computing"
}
46
20
views
downloads
Views 46
Downloads 20
Data volume 109.0 MB
Unique views 44
Unique downloads 19

Share

Cite as