[PATCH] D19359: Sparc itineraries support, with LEON3 and LEON4 itineraries added

[James Y Knight via llvm-commits]

jyknight added a comment.

Some test case showing a reordering arising from the instruction latency info would be good.

Also, I'd really like if someone more familiar with scheduling could say whether using InstrItin{Class/Data} is okay to use for new code, or if it should be reworked using the SchedMachineModel scheme. I'm not sure at this point whether the latter should always be used in preference to the former.

Anyone care to comment about that?


Repository:
  rL LLVM

http://reviews.llvm.org/D19359