Add kernels broken up over multiple loops

[MrBurmark]

Add version of some kernels that break the iteration space into multiple subdomains and run a loop over each.
The intention is to compare performance when using a single loop to cover all the data or using multiple loops to cover the data.
Kernels to look at first:

• Stream_TRIAD
• Algorithm_REDUCE_SUM
• Basic_INDEXLIST_3LOOP