Course structure:

This segment of the course is structured as follows:

• Motivation: execution order really matters, even on fairly ``ordinary'' architectures.
• Dependence analysis: how a compiler can analyse array subscript expressions in order to determine whether restructuring would be valid - e.g.
  • Loop interchange
  • Loop fusion
  • Loop reversal
  • Loop parallelisation (for parallel or pipelined machines).
• Loop transformation using unimodular matrices: given the dependence structure, how does the compiler efficiently find the optimum loop transformation?