[PATCH] D46841: MCSchedModel: Add comments to IssueWidth.

[Jonas Paulsson via Phabricator via llvm-commits]

jonpa added a comment.

With inspiration from your reply, perhaps begin with something like:

The MCSchedModel (in contrast to InstrItineraries) is an abstract machine used for modeling predictable physical machine features. It is built around the notion...

I think this is a very important point.



================
Comment at: include/llvm/MC/MCSchedule.h:203
 struct MCSchedModel {
   // IssueWidth is the maximum number of instructions that may be scheduled in
   // the same per-cycle group.
----------------
Maybe remove this now?


================
Comment at: include/llvm/MC/MCSchedule.h:212
+  //
+  // In practice, IssueWidth is useful to model to the bottleneck between the
+  // decoder (after micro-op expansion) and the out-of-order reservation
----------------
"to model to" -> "to model"



================
Comment at: include/llvm/MC/MCSchedule.h:213
+  // In practice, IssueWidth is useful to model to the bottleneck between the
+  // decoder (after micro-op expansion) and the out-of-order reservation
+  // stations. If the total number of reservation stations is also a bottleneck,
----------------
What happens if there is no bottleneck after decoder - IssueWidth then is typically the decoder capacity?



Repository:
  rL LLVM

https://reviews.llvm.org/D46841