Parallelization
- To get the benefit of cloud computation, your algorithm needs to be
able to run on many machines at the same time.
- It needs to be parallelized.
- Can you do a binary sort in parallel? (Not in a straight forward
manner.)
- How fast can you sort in parallel? (linear)
- There is a lot of work in writing parallel algorithms.
- Mapreduce is a framework for processing parallelizable problems across
huge data sets using a lot of computers. (It's Google'
s.)