Check in of various updates to the CPU. Mainly adds in stats, improves

branch prediction, and makes memory dependence work properly.

SConscript:
    Added return address stack, tournament predictor.
cpu/base_cpu.cc:
    Added debug break and print statements.
cpu/base_dyn_inst.cc:
cpu/base_dyn_inst.hh:
    Comment out possibly unneeded variables.
cpu/beta_cpu/2bit_local_pred.cc:
    2bit predictor no longer speculatively updates itself.
cpu/beta_cpu/alpha_dyn_inst.hh:
    Comment formatting.
cpu/beta_cpu/alpha_full_cpu.hh:
    Formatting
cpu/beta_cpu/alpha_full_cpu_builder.cc:
    Added new parameters for branch predictors, and IQ parameters.
cpu/beta_cpu/alpha_full_cpu_impl.hh:
    Register stats.
cpu/beta_cpu/alpha_params.hh:
    Added parameters for IQ, branch predictors, and store sets.
cpu/beta_cpu/bpred_unit.cc:
    Removed one class.
cpu/beta_cpu/bpred_unit.hh:
    Add in RAS, stats.  Changed branch predictor unit functionality
    so that it holds a history of past branches so it can update, and also
    hold a proper history of the RAS so it can be restored on branch
    mispredicts.
cpu/beta_cpu/bpred_unit_impl.hh:
    Added in stats, history of branches, RAS.  Now bpred unit actually
    modifies the instruction's predicted next PC.
cpu/beta_cpu/btb.cc:
    Add in sanity checks.
cpu/beta_cpu/comm.hh:
    Add in communication where needed, remove it where it's not.
cpu/beta_cpu/commit.hh:
cpu/beta_cpu/rename.hh:
cpu/beta_cpu/rename_impl.hh:
    Add in stats.
cpu/beta_cpu/commit_impl.hh:
    Stats, update what is sent back on branch mispredict.
cpu/beta_cpu/cpu_policy.hh:
    Change the bpred unit being used.
cpu/beta_cpu/decode.hh:
cpu/beta_cpu/decode_impl.hh:
    Stats.
cpu/beta_cpu/fetch.hh:
    Stats, change squash so it can handle squashes from decode differently
    than squashes from commit.
cpu/beta_cpu/fetch_impl.hh:
    Add in stats.  Change how a cache line is fetched.  Update to work with
    caches.  Also have separate functions for different behavior if squash
    is coming from decode vs commit.
cpu/beta_cpu/free_list.hh:
    Remove some old comments.
cpu/beta_cpu/full_cpu.cc:
cpu/beta_cpu/full_cpu.hh:
    Added function to remove instructions from back of instruction list
    until a certain sequence number.
cpu/beta_cpu/iew.hh:
    Stats, separate squashing behavior due to branches vs memory.
cpu/beta_cpu/iew_impl.hh:
    Stats, separate squashing behavior for branches vs memory.
cpu/beta_cpu/inst_queue.cc:
    Debug stuff
cpu/beta_cpu/inst_queue.hh:
    Stats, change how mem dep unit works, debug stuff
cpu/beta_cpu/inst_queue_impl.hh:
    Stats, change how mem dep unit works, debug stuff.  Also add in
    parameters that used to be hardcoded.
cpu/beta_cpu/mem_dep_unit.hh:
cpu/beta_cpu/mem_dep_unit_impl.hh:
    Add in stats, change how memory dependence unit works.  It now holds
    the memory instructions that are waiting for their memory dependences
    to resolve.  It provides which instructions are ready directly to the
    IQ.
cpu/beta_cpu/regfile.hh:
    Fix up sanity checks.
cpu/beta_cpu/rename_map.cc:
    Fix loop variable type.
cpu/beta_cpu/rob_impl.hh:
    Remove intermediate DynInstPtr
cpu/beta_cpu/store_set.cc:
    Add in debugging statements.
cpu/beta_cpu/store_set.hh:
    Reorder function arguments to match the rest of the calls.

--HG--
extra : convert_revision : aabf9b1fecd1d743265dfc3b174d6159937c6f44

1 files changed, 61 insertions, 3 deletions

diff --git a/cpu/beta_cpu/bpred_unit.hh b/cpu/beta_cpu/bpred_unit.hh
index 71191f5b7..53c7146c5 100644
--- a/cpu/beta_cpu/bpred_unit.hh
+++ b/cpu/beta_cpu/bpred_unit.hh
@@ -4,9 +4,15 @@
 
 // For Addr type.
 #include "arch/alpha/isa_traits.hh"
+#include "base/statistics.hh"
+#include "cpu/inst_seq.hh"
 
 #include "cpu/beta_cpu/2bit_local_pred.hh"
+#include "cpu/beta_cpu/tournament_pred.hh"
 #include "cpu/beta_cpu/btb.hh"
+#include "cpu/beta_cpu/ras.hh"
+
+#include <list>
 
 /**
  * Basically a wrapper class to hold both the branch predictor
@@ -18,34 +24,86 @@
  * object, and be able to call the constructors on the BP and BTB.
  */
 template<class Impl>
-class DefaultBPredUnit
+class TwobitBPredUnit
 {
   public:
     typedef typename Impl::Params Params;
+    typedef typename Impl::DynInstPtr DynInstPtr;
+
+    TwobitBPredUnit(Params &params);
+
+    void regStats();
+
+    bool predict(DynInstPtr &inst, Addr &PC);
+
+    void squash(const InstSeqNum &squashed_sn, const Addr &corr_target,
+                bool actually_taken);
 
-    DefaultBPredUnit(Params &params);
+    void squash(const InstSeqNum &squashed_sn);
+
+    void update(const InstSeqNum &done_sn);
 
     bool BPLookup(Addr &inst_PC)
     { return BP.lookup(inst_PC); }
 
+    unsigned BPReadGlobalHist()
+    { return 0; }
+
     bool BTBValid(Addr &inst_PC)
     { return BTB.valid(inst_PC); }
 
     Addr BTBLookup(Addr &inst_PC)
     { return BTB.lookup(inst_PC); }
 
-    void BPUpdate(Addr &inst_PC, bool taken)
+    // Will want to include global history.
+    void BPUpdate(Addr &inst_PC, unsigned global_history, bool taken)
     { BP.update(inst_PC, taken); }
 
     void BTBUpdate(Addr &inst_PC, Addr &target_PC)
     { BTB.update(inst_PC, target_PC); }
 
   private:
+    struct PredictorHistory {
+        PredictorHistory(const InstSeqNum &seq_num, const Addr &inst_PC,
+                         const bool pred_taken)
+            : seqNum(seq_num), PC(inst_PC), predTaken(pred_taken),
+              globalHistory(0), usedRAS(0), wasCall(0), RASIndex(0),
+              RASTarget(0)
+        { }
+
+        InstSeqNum seqNum;
+
+        Addr PC;
+
+        bool predTaken;
+
+        unsigned globalHistory;
+
+        bool usedRAS;
+
+        bool wasCall;
+
+        unsigned RASIndex;
+
+        Addr RASTarget;
+    };
+
+    std::list<PredictorHistory> predHist;
 
     DefaultBP BP;
 
     DefaultBTB BTB;
 
+    ReturnAddrStack RAS;
+
+    Stats::Scalar<> lookups;
+    Stats::Scalar<> condPredicted;
+    Stats::Scalar<> condIncorrect;
+    Stats::Scalar<> BTBLookups;
+    Stats::Scalar<> BTBHits;
+    Stats::Scalar<> BTBCorrect;
+    Stats::Scalar<> usedRAS;
+    Stats::Scalar<> RASIncorrect;
 };
 
 #endif // __BPRED_UNIT_HH__