inorder: initialize res. req. vectors based on resource bandwidth

first change in an optimization that will stop InOrder from allocating new memory for every instruction's
request to a resource. This gets expensive since every instruction needs to access ~10 requests before
graduation. Instead, the plan is to allocate just enough resource request objects to satisfy each resource's
bandwidth (e.g. the execution unit would need to allocate 3 resource request objects for a 1-issue pipeline
since on any given cycle it could have 2 read requests and 1 write request) and then let the instructions
contend and reuse those allocated requests. The end result is a smaller memory footprint for the InOrder model
and increased simulation performance

1 files changed, 2 insertions, 0 deletions

diff --git a/src/cpu/inorder/resource.hh b/src/cpu/inorder/resource.hh
index bd9ec48ca..7f6cb6642 100644
--- a/src/cpu/inorder/resource.hh
+++ b/src/cpu/inorder/resource.hh
@@ -224,6 +224,8 @@ class Resource {
     /** Mapping of slot-numbers to the resource-request pointers */
     std::map<int, ResReqPtr> reqMap;
 
+    std::vector<ResReqPtr> reqs;
+
     /** A list of all the available execution slots for this resource.
      *  This correlates with the actual resource event idx.
      */