Complete the code to perform the same algorithm described in a reference implementation on PCU using OpenMP and CUDA respectively.
Budget: $30 – $250 USD
The aim of the assignment is to assess
your ability and understanding, of implementing and optimising parallel algorithms using both
OpenMP and CUDA.
An existing project containing a single threaded implementation of an algorithm has been
provided. This provided starting code also contains functions for validating the correctness
and timing the performance of your implemented algorithms.
You are expected to implement both an OpenMP and a CUDA version of the provided
algorithm, and to complete a report which documents the justification for the techniques you
have used and how profiling and/or benchmarking supports your choices.
your ability and understanding, of implementing and optimising parallel algorithms using both
OpenMP and CUDA.
An existing project containing a single threaded implementation of an algorithm has been
provided. This provided starting code also contains functions for validating the correctness
and timing the performance of your implemented algorithms.
You are expected to implement both an OpenMP and a CUDA version of the provided
algorithm, and to complete a report which documents the justification for the techniques you
have used and how profiling and/or benchmarking supports your choices.