Conference paper Open Access

Global optimization of operand transfer fusion in heterogeneous computing

Kessler, Christoph


Citation Style Language JSON Export

{
  "DOI": "10.1145/3323439.3323981", 
  "author": [
    {
      "family": "Kessler, Christoph"
    }
  ], 
  "issued": {
    "date-parts": [
      [
        2019, 
        10, 
        22
      ]
    ]
  }, 
  "abstract": "<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>", 
  "title": "Global optimization of operand transfer fusion in heterogeneous computing", 
  "type": "paper-conference", 
  "id": "3515961"
}
43
15
views
downloads
Views 43
Downloads 15
Data volume 81.7 MB
Unique views 42
Unique downloads 15

Share

Cite as