This contains my bachelors thesis and associated tex files, code snippets and maybe more. Topic: Data Movement in Heterogeneous Memories with Intel Data Streaming Accelerator
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 

391 B

implemented

  • 1 to n engines per group
  • 1 to n threads running on one specific core / dsa engine
  • copy inside and across NUMA borders
  • cross-copy: 2 engines copying from their numa domain to the domain of the other
  • all with "packet sizes" of 1KiB, 2KiB, 4KiB, 8KiB, ..., 1GiB
  • all with both CPU and DSA for comparison

missing

  • batch vs single submissions
  • effect of fence/drain