---

Parallel algorithm for σ_cond(R)

---

• Recall: uni-processor algorithm for σ_cond(R)
  • One-pass algorithm:

    while ( R has more data blocks ) { read data blocks to fill available buffer; check condition for each tuple in buffers; Move qualifying tuples to output }

    Buffer utilization using M buffers:

  ---

  ---

  ---

  ---

• Parallel algorithm for σ_cond(R)
  • Parallel algorithm for σ_cond(R):

    Each processor executes the uni-processor σcond( ) locally on its fragment of relation R:

    Result:

    The collection (bag) of the output of (at) each processor is the output of σcond(R)

  ---

  ---

  ---

  ---

• Removing duplicates from result
  • If the operation needs to remove duplicates:

    Duplicates can be eliminated locally because: duplicate tuples will always stored at the same processor !!!

  ---

  ---

  ---

  ---

• Performance of the parallel σ_cond
  • Performance of the parallel σ_cond:

    The hash function will scatter the relation R evenly among P processors: Each processor will perform: 1 --- B(R) disk block read operations P

    Therefore:

    The parallel σcond(R) operation will complete in 1/P of the time

    Note:

    The total amount of work performed has not decreased The completion time is reduced because the work is performed in parallel !!!!