Skip to content

Adding basic skeleton to implement join_cols()

Based on the discussion on the IRC channel with @rcurtin and @zoq I've started implementing join_cols(). Plan is to:

  • implementation of join_cols() using cudaMemcpy() (and the equivalent for OpenCL)
  • write a custom two-way kernel for join_cols() for two objects of different types
  • some quick benchmarking

Merge request reports

Loading