Update to make multiple instruction issue and different latencies work.

Also change to ref counted DynInst.

SConscript:
    Add branch predictor, BTB, load store queue, and storesets.
arch/isa_parser.py:
    Specify the template parameter for AlphaDynInst
base/traceflags.py:
    Add load store queue, store set, and mem dependence unit to the
    list of trace flags.
cpu/base_dyn_inst.cc:
    Change formating, add in debug statement.
cpu/base_dyn_inst.hh:
    Change DynInst to be RefCounted, add flag to clear whether or not this
    instruction can commit.  This is likely to be removed in the future.
cpu/beta_cpu/alpha_dyn_inst.cc:
    AlphaDynInst has been changed to be templated, so now this CC file
    is just used to force instantiations of AlphaDynInst.
cpu/beta_cpu/alpha_dyn_inst.hh:
    Changed AlphaDynInst to be templated on Impl.  Removed some unnecessary
    functions.
cpu/beta_cpu/alpha_full_cpu.cc:
    AlphaFullCPU has been changed to be templated, so this CC file is now
    just used to force instantation of AlphaFullCPU.
cpu/beta_cpu/alpha_full_cpu.hh:
    Change AlphaFullCPU to be templated on Impl.
cpu/beta_cpu/alpha_impl.hh:
    Update it to reflect AlphaDynInst and AlphaFullCPU being templated
    on Impl.  Also removed time buffers from here, as they are really
    a part of the CPU and are thus in the CPU policy now.
cpu/beta_cpu/alpha_params.hh:
    Make AlphaSimpleParams inherit from the BaseFullCPU so that it doesn't
    need to specifically declare any parameters that are already in the
    BaseFullCPU.
cpu/beta_cpu/comm.hh:
    Changed the structure of the time buffer communication structs.  Now
    they include the size of the packet of instructions it is sending.
    Added some parameters to the backwards communication struct, mainly
    for squashing.
cpu/beta_cpu/commit.hh:
    Update typenames to reflect change in location of time buffer structs.
    Update DynInst to DynInstPtr (it is refcounted now).
cpu/beta_cpu/commit_impl.hh:
    Formatting changes mainly.  Also sends back proper information
    on branch mispredicts so that the bpred unit can update itself.
    Updated behavior for non-speculative instructions (stores, any
    other non-spec instructions): once they reach the head of the ROB,
    the ROB signals back to the IQ that it can go ahead and issue the
    non-speculative instruction.  The instruction itself is updated so that
    commit won't try to commit it again until it is done executing.
cpu/beta_cpu/cpu_policy.hh:
    Added branch prediction unit, mem dependence prediction unit, load
    store queue.  Moved time buffer structs from AlphaSimpleImpl to here.
cpu/beta_cpu/decode.hh:
    Changed typedefs to reflect change in location of time buffer structs
    and also the change from DynInst to ref counted DynInstPtr.
cpu/beta_cpu/decode_impl.hh:
    Continues to buffer instructions even while unblocking now.  Changed
    how it loops through groups of instructions so it can properly block
    during the middle of a group of instructions.
cpu/beta_cpu/fetch.hh:
    Changed typedefs to reflect change in location of time buffer structs
    and the change to ref counted DynInsts.  Also added in branch
    brediction unit.
cpu/beta_cpu/fetch_impl.hh:
    Add in branch prediction.  Changed how fetch checks inputs and its
    current state to make for easier logic.
cpu/beta_cpu/free_list.cc:
    Changed int regs and float regs to logically use one flat namespace.
    Future change will be moving them to a single scoreboard to conserve
    space.
cpu/beta_cpu/free_list.hh:
    Mostly debugging statements.  Might be removed for performance in future.
cpu/beta_cpu/full_cpu.cc:
    Added in some debugging statements.  Updated BaseFullCPU to take
    a params object.
cpu/beta_cpu/full_cpu.hh:
    Added params class within BaseCPU that other param classes will be
    able to inherit from.  Updated typedefs to reflect change in location
    of time buffer structs and ref counted DynInst.
cpu/beta_cpu/iew.hh:
    Updated typedefs to reflect change in location of time buffer structs
    and use of ref counted DynInsts.
cpu/beta_cpu/iew_impl.hh:
    Added in load store queue, updated iew to be able to execute non-
    speculative instructions, instead of having them execute in commit.
cpu/beta_cpu/inst_queue.hh:
    Updated change to ref counted DynInsts.  Changed inst queue to hold
    non-speculative instructions as well, which are issued only when
    commit signals backwards that a nonspeculative instruction is at
    the head of the ROB.
cpu/beta_cpu/inst_queue_impl.hh:
    Updated to allow for non-speculative instructions to be in the inst
    queue.  Also added some debug functions.
cpu/beta_cpu/regfile.hh:
    Added debugging statements, changed formatting.
cpu/beta_cpu/rename.hh:
    Updated typedefs, added some functions to clean up code.
cpu/beta_cpu/rename_impl.hh:
    Moved some code into functions to make it easier to read.
cpu/beta_cpu/rename_map.cc:
    Changed int and float reg behavior to use a single flat namespace.  In
    the future, the rename maps can be combined to a single rename map to
    save space.
cpu/beta_cpu/rename_map.hh:
    Added destructor.
cpu/beta_cpu/rob.hh:
    Updated it with change from DynInst to ref counted DynInst.
cpu/beta_cpu/rob_impl.hh:
    Formatting, updated to use ref counted DynInst.
cpu/static_inst.hh:
    Updated forward declaration for AlphaDynInst now that it is templated.

--HG--
extra : convert_revision : 1045f240ee9b6a4bd368e1806aca029ebbdc6dd3

1 files changed, 51 insertions, 25 deletions

diff --git a/cpu/beta_cpu/rename_map.cc b/cpu/beta_cpu/rename_map.cc
index c234182f0..cb9720d28 100644
--- a/cpu/beta_cpu/rename_map.cc
+++ b/cpu/beta_cpu/rename_map.cc
@@ -3,12 +3,10 @@
 
 // Todo: Consider making functions inline.  Avoid having things that are
 // using the zero register or misc registers from adding on the registers
-// to the free list.
-
-SimpleRenameMap::RenameEntry::RenameEntry()
-    : physical_reg(0), valid(false)
-{
-}
+// to the free list.  Possibly remove the direct communication between
+// this and the freelist.  Considering making inline bool functions that
+// determine if the register is a logical int, logical fp, physical int,
+// physical fp, etc.
 
 SimpleRenameMap::SimpleRenameMap(unsigned _numLogicalIntRegs,
                                  unsigned _numPhysicalIntRegs,
@@ -35,11 +33,12 @@ SimpleRenameMap::SimpleRenameMap(unsigned _numLogicalIntRegs,
 
     //Create the rename maps, and their scoreboards.
     intRenameMap = new RenameEntry[numLogicalIntRegs];
-    floatRenameMap = new RenameEntry[numLogicalFloatRegs];
+    floatRenameMap = new RenameEntry[numLogicalRegs];
 
+    // Should combine this into one scoreboard.
     intScoreboard.resize(numPhysicalIntRegs);
-    floatScoreboard.resize(numPhysicalFloatRegs);
-    miscScoreboard.resize(numMiscRegs);
+    floatScoreboard.resize(numPhysicalRegs);
+    miscScoreboard.resize(numPhysicalRegs + numMiscRegs);
 
     // Initialize the entries in the integer rename map to point to the
     // physical registers of the same index, and consider each register
@@ -59,31 +58,50 @@ SimpleRenameMap::SimpleRenameMap(unsigned _numLogicalIntRegs,
         intScoreboard[index] = 0;
     }
 
+    int float_reg_idx = numPhysicalIntRegs;
+
     // Initialize the entries in the floating point rename map to point to
     // the physical registers of the same index, and consider each register
     // ready until the first rename occurs.
-    for (RegIndex index = 0; index < numLogicalFloatRegs; ++index)
+    // Although the index refers purely to architected registers, because
+    // the floating reg indices come after the integer reg indices, they
+    // may exceed the size of a normal RegIndex (short).
+    for (PhysRegIndex index = numLogicalIntRegs;
+         index < numLogicalRegs; ++index)
+    {
+        floatRenameMap[index].physical_reg = float_reg_idx++;
+    }
+
+    for (RegIndex index = numPhysicalIntRegs;
+         index < numPhysicalIntRegs + numLogicalFloatRegs; ++index)
     {
-        floatRenameMap[index].physical_reg = index + numPhysicalIntRegs;
         floatScoreboard[index] = 1;
     }
 
     // Initialize the rest of the physical registers (the ones that don't
     // directly map to a logical register) as unready.
-    for (PhysRegIndex index = numLogicalFloatRegs;
-         index < numPhysicalFloatRegs;
+    for (PhysRegIndex index = numPhysicalIntRegs + numLogicalFloatRegs;
+         index < numPhysicalRegs;
          ++index)
     {
         floatScoreboard[index] = 0;
     }
 
     // Initialize the entries in the misc register scoreboard to be ready.
-    for (RegIndex index = 0; index < numMiscRegs; ++index)
+    for (RegIndex index = numPhysicalRegs;
+         index < numPhysicalRegs + numMiscRegs; ++index)
     {
         miscScoreboard[index] = 1;
     }
 }
 
+SimpleRenameMap::~SimpleRenameMap()
+{
+    // Delete the rename maps as they were allocated with new.
+    delete [] intRenameMap;
+    delete [] floatRenameMap;
+}
+
 void
 SimpleRenameMap::setFreeList(SimpleFreeList *fl_ptr)
 {
@@ -116,6 +134,8 @@ SimpleRenameMap::rename(RegIndex arch_reg)
             // Update the integer rename map.
             intRenameMap[arch_reg].physical_reg = renamed_reg;
 
+            assert(renamed_reg >= 0 && renamed_reg < numPhysicalIntRegs);
+
             // Mark register as not ready.
             intScoreboard[renamed_reg] = false;
         } else {
@@ -124,7 +144,7 @@ SimpleRenameMap::rename(RegIndex arch_reg)
         }
     } else if (arch_reg < numLogicalRegs) {
         // Subtract off the base offset for floating point registers.
-        arch_reg = arch_reg - numLogicalIntRegs;
+//        arch_reg = arch_reg - numLogicalIntRegs;
 
         // Record the current physical register that is renamed to the
         // requested architected register.
@@ -139,6 +159,9 @@ SimpleRenameMap::rename(RegIndex arch_reg)
             // Update the floating point rename map.
             floatRenameMap[arch_reg].physical_reg = renamed_reg;
 
+            assert(renamed_reg < numPhysicalRegs &&
+                   renamed_reg >= numPhysicalIntRegs);
+
             // Mark register as not ready.
             floatScoreboard[renamed_reg] = false;
         } else {
@@ -160,6 +183,8 @@ SimpleRenameMap::rename(RegIndex arch_reg)
         // so the free list can avoid adding it.
         prev_reg = renamed_reg;
 
+        assert(renamed_reg < numPhysicalRegs + numMiscRegs);
+
         miscScoreboard[renamed_reg] = false;
     }
 
@@ -175,7 +200,7 @@ SimpleRenameMap::lookup(RegIndex arch_reg)
         return intRenameMap[arch_reg].physical_reg;
     } else if (arch_reg < numLogicalRegs) {
         // Subtract off the base FP offset.
-        arch_reg = arch_reg - numLogicalIntRegs;
+//        arch_reg = arch_reg - numLogicalIntRegs;
 
         return floatRenameMap[arch_reg].physical_reg;
     } else {
@@ -196,12 +221,12 @@ SimpleRenameMap::isReady(PhysRegIndex phys_reg)
     } else if (phys_reg < numPhysicalRegs) {
 
         // Subtract off the base FP offset.
-        phys_reg = phys_reg - numPhysicalIntRegs;
+//        phys_reg = phys_reg - numPhysicalIntRegs;
 
         return floatScoreboard[phys_reg];
     } else {
         // Subtract off the misc registers offset.
-        phys_reg = phys_reg - numPhysicalRegs;
+//        phys_reg = phys_reg - numPhysicalRegs;
 
         return miscScoreboard[phys_reg];
     }
@@ -218,13 +243,10 @@ SimpleRenameMap::setEntry(RegIndex arch_reg, PhysRegIndex renamed_reg)
 
         intRenameMap[arch_reg].physical_reg = renamed_reg;
     } else {
-//        assert(arch_reg < (numLogicalIntRegs + numLogicalFloatRegs));
-
-        // Subtract off the base FP offset.
-        arch_reg = arch_reg - numLogicalIntRegs;
+        assert(arch_reg < (numLogicalIntRegs + numLogicalFloatRegs));
 
         DPRINTF(Rename, "Rename Map: Float register %i being set to %i.\n",
-                (int)arch_reg, renamed_reg);
+                (int)arch_reg - numLogicalIntRegs, renamed_reg);
 
         floatRenameMap[arch_reg].physical_reg = renamed_reg;
     }
@@ -234,6 +256,8 @@ void
 SimpleRenameMap::squash(vector<RegIndex> freed_regs,
                         vector<UnmapInfo> unmaps)
 {
+    panic("Not sure this function should be called.");
+
     // Not sure the rename map should be able to access the free list
     // like this.
     while (!freed_regs.empty()) {
@@ -260,16 +284,18 @@ SimpleRenameMap::markAsReady(PhysRegIndex ready_reg)
             (int)ready_reg);
 
     if (ready_reg < numPhysicalIntRegs) {
+        assert(ready_reg >= 0);
+
         intScoreboard[ready_reg] = 1;
     } else if (ready_reg < numPhysicalRegs) {
 
         // Subtract off the base FP offset.
-        ready_reg = ready_reg - numPhysicalIntRegs;
+//        ready_reg = ready_reg - numPhysicalIntRegs;
 
         floatScoreboard[ready_reg] = 1;
     } else {
         //Subtract off the misc registers offset.
-        ready_reg = ready_reg - numPhysicalRegs;
+//        ready_reg = ready_reg - numPhysicalRegs;
 
         miscScoreboard[ready_reg] = 1;
     }