Revert "Add additional formatting pass on directories"

This reverts commit ca563ea85ead434e0d579026b5e66e829af5efe5.

18 files changed, 384 insertions, 472 deletions

diff --git a/src/gpgpu-sim/gpu-cache.h b/src/gpgpu-sim/gpu-cache.h
index 9fe14ca..9b9898e 100644
--- a/src/gpgpu-sim/gpu-cache.h
+++ b/src/gpgpu-sim/gpu-cache.h
@@ -1312,9 +1312,9 @@ class baseline_cache : public cache_t {
     const cache_config &m_config;
 
     int m_data_port_occupied_cycles;  //< Number of cycle that the data port
-                                      // remains used
+                                      //remains used
     int m_fill_port_occupied_cycles;  //< Number of cycle that the fill port
-                                      // remains used
+                                      //remains used
   };
 
   bandwidth_management m_bandwidth_management;
diff --git a/src/gpgpu-sim/gpu-sim.h b/src/gpgpu-sim/gpu-sim.h
index a24ceea..40c4482 100644
--- a/src/gpgpu-sim/gpu-sim.h
+++ b/src/gpgpu-sim/gpu-sim.h
@@ -264,11 +264,11 @@ class memory_config {
                    // GDDR5 this is identical to RTPS, if for other DRAM this is
                    // different, you will need to split them in two
 
-  unsigned tCCD;    // column to column delay
-  unsigned tRRD;    // minimal time required between activation of rows in
-                    // different banks
-  unsigned tRCD;    // row to column delay - time required to activate a row
-                    // before a read
+  unsigned tCCD;  // column to column delay
+  unsigned tRRD;  // minimal time required between activation of rows in
+                  // different banks
+  unsigned tRCD;  // row to column delay - time required to activate a row
+                  // before a read
   unsigned tRCDWR;  // row to column delay for a write command
   unsigned tRAS;    // time needed to activate row
   unsigned tRP;     // row precharge ie. deactivate row
@@ -276,7 +276,7 @@ class memory_config {
       tRC;  // row cycle time ie. precharge current, then activate different row
   unsigned tCDLR;  // Last data-in to Read command (switching from write to
                    // read)
-  unsigned tWR;    // Last data-in to Row precharge
+  unsigned tWR;  // Last data-in to Row precharge
 
   unsigned CL;    // CAS latency
   unsigned WL;    // WRITE latency
@@ -628,9 +628,9 @@ class gpgpu_sim : public gpgpu_t {
   std::map<unsigned, watchpoint_event> g_watchpoint_hits;
 
   std::string executed_kernel_info_string();  //< format the kernel information
-                                              // into a string for stat printout
+                                              //into a string for stat printout
   void clear_executed_kernel_info();  //< clear the kernel information after
-                                      // stat printout
+                                      //stat printout
 
  public:
   unsigned long long gpu_sim_insn;
diff --git a/src/gpgpu-sim/mem_latency_stat.h b/src/gpgpu-sim/mem_latency_stat.h
index d733218..21c15ee 100644
--- a/src/gpgpu-sim/mem_latency_stat.h
+++ b/src/gpgpu-sim/mem_latency_stat.h
@@ -90,8 +90,8 @@ class memory_stats_t {
   unsigned int **totalbankreads;     // bankreads[dram chip id][bank id]
   unsigned int **totalbankaccesses;  // bankaccesses[dram chip id][bank id]
   unsigned int *num_MCBs_accessed;   // tracks how many memory controllers are
-                                     // accessed whenever any thread in a warp
-                                     // misses in cache
+                                    // accessed whenever any thread in a warp
+                                    // misses in cache
   unsigned int *position_of_mrq_chosen;  // position of mrq in m_queue chosen
 
   unsigned ***mem_access_type_stats;  // dram access type classification
diff --git a/src/gpgpu-sim/shader.cc b/src/gpgpu-sim/shader.cc
index fc1c1e2..73ea8b3 100644
--- a/src/gpgpu-sim/shader.cc
+++ b/src/gpgpu-sim/shader.cc
@@ -3460,7 +3460,7 @@ void shader_core_ctx::warp_exit(unsigned warp_id) {
   for (unsigned i = warp_id * get_config()->warp_size;
        i < (warp_id + 1) * get_config()->warp_size; i++) {
     //		if(this->m_thread[i]->m_functional_model_thread_state &&
-    // this->m_thread[i].m_functional_model_thread_state->donecycle()==0) {
+    //this->m_thread[i].m_functional_model_thread_state->donecycle()==0) {
     //			done = false;
     //		}
 
diff --git a/src/gpuwattch/XML_Parse.cc b/src/gpuwattch/XML_Parse.cc
index 19d3d44..26115d3 100644
--- a/src/gpuwattch/XML_Parse.cc
+++ b/src/gpuwattch/XML_Parse.cc
@@ -535,7 +535,7 @@ void ParseXML::parse(char* filepath) {
   //	if (sys.Private_L2 && sys.number_of_cores!=sys.number_of_L2s)

   //	{

   //		cout<<"Private L2: Number of L2s must equal to Number of

-  // Cores"<<endl;

+  //Cores"<<endl;

   //		exit(0);

   //	}

 

@@ -563,7 +563,7 @@ void ParseXML::parse(char* filepath) {
   unsigned int OrderofComponents_3layer = 0;

   if (NumofCom_3 > OrderofComponents_3layer) {

     //___________________________get all

-    // system.core0-n________________________________________________

+    //system.core0-n________________________________________________

     if (sys.homogeneous_cores == 1)

       OrderofComponents_3layer = 0;

     else

@@ -2044,8 +2044,9 @@ void ParseXML::parse(char* filepath) {
             if (strcmp(xNode4.getAttribute("name"), "sharedmemory") ==

                 0) {  // find system.core0.sharedmemory

               itmp = xNode4.nChildNode("param");

-              for (k = 0; k < itmp; k++) {  // get all items of param in

-                // system.core0.sharedmemory--sharedmemory

+              for (k = 0; k < itmp;

+                   k++) {  // get all items of param in

+                           // system.core0.sharedmemory--sharedmemory

                 if (strcmp(xNode4.getChildNode("param", k).getAttribute("name"),

                            "sharedmemory_config") == 0) {

                   strtmp.assign(

@@ -2482,7 +2483,7 @@ void ParseXML::parse(char* filepath) {
     }

 

     //__________________________________________Get

-    // system.L1Directory0-n____________________________________________

+    //system.L1Directory0-n____________________________________________

     int w, tmpOrderofComponents_3layer;

     w = OrderofComponents_3layer + 1;

     tmpOrderofComponents_3layer = OrderofComponents_3layer;

@@ -2648,7 +2649,7 @@ void ParseXML::parse(char* filepath) {
     }

 

     //__________________________________________Get

-    // system.L2Directory0-n____________________________________________

+    //system.L2Directory0-n____________________________________________

     w = OrderofComponents_3layer + 1;

     tmpOrderofComponents_3layer = OrderofComponents_3layer;

     if (sys.homogeneous_L2Directories == 1)

@@ -2813,7 +2814,7 @@ void ParseXML::parse(char* filepath) {
     }

 

     //__________________________________________Get

-    // system.L2[0..n]____________________________________________

+    //system.L2[0..n]____________________________________________

     w = OrderofComponents_3layer + 1;

     tmpOrderofComponents_3layer = OrderofComponents_3layer;

     if (sys.homogeneous_L2s == 1)

@@ -3101,7 +3102,7 @@ void ParseXML::parse(char* filepath) {
       }

     }

     //__________________________________________Get

-    // system.L3[0..n]____________________________________________

+    //system.L3[0..n]____________________________________________

     w = OrderofComponents_3layer + 1;

     tmpOrderofComponents_3layer = OrderofComponents_3layer;

     if (sys.homogeneous_L3s == 1)

@@ -3389,7 +3390,7 @@ void ParseXML::parse(char* filepath) {
       }

     }

     //__________________________________________Get

-    // system.NoC[0..n]____________________________________________

+    //system.NoC[0..n]____________________________________________

     w = OrderofComponents_3layer + 1;

     tmpOrderofComponents_3layer = OrderofComponents_3layer;

     if (sys.homogeneous_NoCs == 1)

@@ -3640,7 +3641,7 @@ void ParseXML::parse(char* filepath) {
       }

     }

     //__________________________________________Get

-    // system.mem____________________________________________

+    //system.mem____________________________________________

     if (OrderofComponents_3layer > 0)

       OrderofComponents_3layer = OrderofComponents_3layer + 1;

     xNode3 = xNode2.getChildNode("component", OrderofComponents_3layer);

@@ -3756,7 +3757,7 @@ void ParseXML::parse(char* filepath) {
       exit(0);

     }

     //__________________________________________Get

-    // system.mc____________________________________________

+    //system.mc____________________________________________

     if (OrderofComponents_3layer > 0)

       OrderofComponents_3layer = OrderofComponents_3layer + 1;

     xNode3 = xNode2.getChildNode("component", OrderofComponents_3layer);

@@ -3946,7 +3947,7 @@ void ParseXML::parse(char* filepath) {
       exit(0);

     }

     //__________________________________________Get

-    // system.niu____________________________________________

+    //system.niu____________________________________________

     if (OrderofComponents_3layer > 0)

       OrderofComponents_3layer = OrderofComponents_3layer + 1;

     xNode3 = xNode2.getChildNode("component", OrderofComponents_3layer);

@@ -4004,7 +4005,7 @@ void ParseXML::parse(char* filepath) {
     }

 

     //__________________________________________Get

-    // system.pcie____________________________________________

+    //system.pcie____________________________________________

     if (OrderofComponents_3layer > 0)

       OrderofComponents_3layer = OrderofComponents_3layer + 1;

     xNode3 = xNode2.getChildNode("component", OrderofComponents_3layer);

@@ -4073,7 +4074,7 @@ void ParseXML::parse(char* filepath) {
       exit(0);

     }

     //__________________________________________Get

-    // system.flashcontroller____________________________________________

+    //system.flashcontroller____________________________________________

     if (OrderofComponents_3layer > 0)

       OrderofComponents_3layer = OrderofComponents_3layer + 1;

     xNode3 = xNode2.getChildNode("component", OrderofComponents_3layer);

diff --git a/src/gpuwattch/array.cc b/src/gpuwattch/array.cc
index a50cac6..aca5a8a 100644
--- a/src/gpuwattch/array.cc
+++ b/src/gpuwattch/array.cc
@@ -118,7 +118,7 @@ void ArrayST::optimize_array() {
           10;  // This is the time_dev to be used for next iteration
 
       //		from best area to worst area -->worst timing to best
-      // timing
+      //timing
       if ((((local_result.cycle_time - throughput) <= 1e-10) &&
            (local_result.access_time - latency) <= 1e-10) ||
           (local_result.data_array2->area_efficiency <
@@ -145,8 +145,8 @@ void ArrayST::optimize_array() {
 
         if (l_ip.cycle_time_dev > 10) {  // if not >10 local_result is the last
                                          // result, it cannot be cleaned up
-          temp_res = &local_result;      // Only solutions not saved in the list
-                                         // need to be cleaned up
+          temp_res = &local_result;  // Only solutions not saved in the list
+                                     // need to be cleaned up
           temp_res->cleanup();
         }
       }
@@ -171,36 +171,23 @@ void ArrayST::optimize_array() {
     //		/*According to "Content-Addressable Memory (CAM) Circuits and
     //				Architectures": A Tutorial and Survey
     //				by Kostas Pagiamtzis et al.
-    //				CAM structures can be heavily pipelined and use
-    // look-ahead
-    // techniques,
-    //				therefore timing can be relaxed. But McPAT does not
-    //model
-    // the
-    // advanced
-    //				techniques. If continue optimizing, the area efficiency
-    //will
-    // be
-    // too low
+    //				CAM structures can be heavily pipelined and use look-ahead
+    //techniques,
+    //				therefore timing can be relaxed. But McPAT does not model the
+    //advanced
+    //				techniques. If continue optimizing, the area efficiency will be
+    //too low
     //		*/
     //		//For CAM and FA, stop opt if area efficiency is too low
     //		if (throughput_overflow==true)
-    //			cout<< "Warning: " <<" McPAT stopped optimization on
-    //throughput
-    // for
+    //			cout<< "Warning: " <<" McPAT stopped optimization on throughput for
     //"<< name
-    //				<<" array structure because its area efficiency
-    //is
-    // below
+    //				<<" array structure because its area efficiency is below
     //"<<area_efficiency_threshold<<"% " << endl;
     //		if (latency_overflow==true)
-    //			cout<< "Warning: " <<" McPAT stopped optimization on latency
-    //for
-    //"<<
-    // name
-    //				<<" array structure because its area efficiency
-    //is
-    // below
+    //			cout<< "Warning: " <<" McPAT stopped optimization on latency for "<<
+    //name
+    //				<<" array structure because its area efficiency is below
     //"<<area_efficiency_threshold<<"% " << endl;
     //	}
 
diff --git a/src/gpuwattch/core.cc b/src/gpuwattch/core.cc
index 6b9f0d5..9e9f1ab 100644
--- a/src/gpuwattch/core.cc
+++ b/src/gpuwattch/core.cc
@@ -59,31 +59,31 @@
 //-gpgpu_num_reg_banks                    8 # Number of register banks (default
 //= 8)
 //-gpgpu_reg_bank_use_warp_id                    0 # Use warp ID in mapping
-// registers to banks (default = off)
+//registers to banks (default = off)
 //-gpgpu_operand_collector_num_units_sp                    6 # number of
-// collector units (default = 4)
+//collector units (default = 4)
 //-gpgpu_operand_collector_num_units_sfu                    8 # number of
-// collector units (default = 4)
+//collector units (default = 4)
 //-gpgpu_operand_collector_num_units_mem                    2 # number of
-// collector units (default = 2)
+//collector units (default = 2)
 //-gpgpu_operand_collector_num_units_gen                    0 # number of
-// collector units (default = 0)
+//collector units (default = 0)
 //-gpgpu_operand_collector_num_in_ports_sp                    1 # number of
-// collector unit in ports (default = 1)
+//collector unit in ports (default = 1)
 //-gpgpu_operand_collector_num_in_ports_sfu                    1 # number of
-// collector unit in ports (default = 1)
+//collector unit in ports (default = 1)
 //-gpgpu_operand_collector_num_in_ports_mem                    1 # number of
-// collector unit in ports (default = 1)
+//collector unit in ports (default = 1)
 //-gpgpu_operand_collector_num_in_ports_gen                    0 # number of
-// collector unit in ports (default = 0)
+//collector unit in ports (default = 0)
 //-gpgpu_operand_collector_num_out_ports_sp                    1 # number of
-// collector unit in ports (default = 1)
+//collector unit in ports (default = 1)
 //-gpgpu_operand_collector_num_out_ports_sfu                    1 # number of
-// collector unit in ports (default = 1)
+//collector unit in ports (default = 1)
 //-gpgpu_operand_collector_num_out_ports_mem                    1 # number of
-// collector unit in ports (default = 1)
+//collector unit in ports (default = 1)
 //-gpgpu_operand_collector_num_out_ports_gen                    0 # number of
-// collector unit in ports (default = 0)
+//collector unit in ports (default = 0)
 
 // The total number of collector units and their input ports, and the number of
 // register file banks
@@ -827,22 +827,18 @@ SchedulerU::SchedulerU(ParseXML* XML_interface, int ithCore_,
         // PC is to id the instruction for recover exception.
         // inst is used to map the renamed dest. registers.so that commit stage
         // can know which reg/RRAT to update
-        //				data =
-        // int(ceil((robExtra+coredynp.pc_width
+        //				data = int(ceil((robExtra+coredynp.pc_width
         //+
-        //						coredynp.instruction_length
-        //+
-        // 2*coredynp.phy_ireg_width)/8.0));
+        //						coredynp.instruction_length +
+        //2*coredynp.phy_ireg_width)/8.0));
         data = int(ceil(
             (robExtra + coredynp.pc_width + coredynp.phy_ireg_width) / 8.0));
       } else {
         // in RS based OOO, ROB also contains value of destination reg
-        //				data  =
-        // int(ceil((robExtra+coredynp.pc_width
-        //+
-        //						coredynp.instruction_length
+        //				data  = int(ceil((robExtra+coredynp.pc_width
         //+
-        // 2*coredynp.phy_ireg_width + coredynp.fp_data_width)/8.0));
+        //						coredynp.instruction_length +
+        //2*coredynp.phy_ireg_width + coredynp.fp_data_width)/8.0));
         data = int(ceil((robExtra + coredynp.pc_width +
                          coredynp.phy_ireg_width + coredynp.fp_data_width) /
                         8.0));
@@ -2403,9 +2399,8 @@ RENAMINGU::RENAMINGU(ParseXML* XML_interface, int ithCore_,
                                          // detailed explaintions
         data =
             33;  // int(ceil(coredynp.phy_ireg_width*(1+coredynp.globalCheckpoint)/8.0));
-        //			data
-        //=
-        // int(ceil(coredynp.phy_ireg_width/8.0));
+        //			data							 =
+        //int(ceil(coredynp.phy_ireg_width/8.0));
         out_w = 1;  // int(ceil(coredynp.phy_ireg_width/8.0));
         interface_ip.is_cache = false;
         interface_ip.pure_cam = false;
@@ -2435,44 +2430,42 @@ RENAMINGU::RENAMINGU(ParseXML* XML_interface, int ithCore_,
                 XML->sys.core[ithCore].number_hardware_threads);
         area.set_area(area.get_area() + iFRAT->area.get_area());
 
-        //			//RAHT According to Intel, combine GC with FRAT
-        // is
-        // very costly.
-        //			data
-        //=
-        // int(ceil(coredynp.phy_ireg_width/8.0)*coredynp.num_IRF_entry);
+        //			//RAHT According to Intel, combine GC with FRAT is
+        //very costly.
+        //			data							 =
+        //int(ceil(coredynp.phy_ireg_width/8.0)*coredynp.num_IRF_entry);
         //			out_w                            = data;
         //			interface_ip.is_cache			 =
-        // false;
+        //false;
         //			interface_ip.pure_cam            = false;
         //			interface_ip.pure_ram            = true;
         //			interface_ip.line_sz             = data;
         //			interface_ip.cache_sz            =
-        // data*coredynp.globalCheckpoint;
+        //data*coredynp.globalCheckpoint;
         //			interface_ip.assoc               = 1;
         //			interface_ip.nbanks              = 1;
         //			interface_ip.out_w               = out_w*8;
         //			interface_ip.access_mode         = 0;
         //			interface_ip.throughput          =
-        // 1.0/clockRate;
+        //1.0/clockRate;
         //			interface_ip.latency             =
-        // 1.0/clockRate;
+        //1.0/clockRate;
         //			interface_ip.obj_func_dyn_energy = 0;
         //			interface_ip.obj_func_dyn_power  = 0;
         //			interface_ip.obj_func_leak_power = 0;
         //			interface_ip.obj_func_cycle_t    = 1;
         //			interface_ip.num_rw_ports    = 1;//the extra one
-        // port is for GCs
+        //port is for GCs
         //			interface_ip.num_rd_ports    =
-        // 2*coredynp.decodeW;
+        //2*coredynp.decodeW;
         //			interface_ip.num_wr_ports    = coredynp.decodeW;
         //			interface_ip.num_se_rd_ports = 0;
         //			iFRAT = new ArrayST(&interface_ip, "Int
-        // FrontRAT");
+        //FrontRAT");
         //			iFRAT->area.set_area(iFRAT->area.get_area()+
-        // iFRAT->local_result.area*XML->sys.core[ithCore].number_hardware_threads);
+        //iFRAT->local_result.area*XML->sys.core[ithCore].number_hardware_threads);
         //			area.set_area(area.get_area()+
-        // iFRAT->area.get_area());
+        //iFRAT->area.get_area());
 
         // FRAT floating point
         data = int(ceil(coredynp.phy_freg_width *
@@ -3230,39 +3223,30 @@ void BranchPredictor::displayEnergy(uint32_t indent, int plevel, bool is_tdp) {
          << " W" << endl;
     cout << endl;
   } else {
-    //		cout << indent_str_next << "Global Predictor    Peak Dynamic = "
-    //<<
-    // globalBPT->rt_power.readOp.dynamic*clockRate << " W" << endl;
-    //		cout << indent_str_next << "Global Predictor    Subthreshold
-    //Leakage
-    //=
+    //		cout << indent_str_next << "Global Predictor    Peak Dynamic = " <<
+    //globalBPT->rt_power.readOp.dynamic*clockRate << " W" << endl;
+    //		cout << indent_str_next << "Global Predictor    Subthreshold Leakage =
     //" << globalBPT->rt_power.readOp.leakage <<" W" << endl;
-    //		cout << indent_str_next << "Global Predictor    Gate Leakage = "
-    //<<
-    // globalBPT->rt_power.readOp.gate_leakage << " W" << endl;
-    //		cout << indent_str_next << "Local Predictor   Peak Dynamic = "
-    //<<
-    // L1_localBPT->rt_power.readOp.dynamic*clockRate  << " W" << endl;
-    //		cout << indent_str_next << "Local Predictor   Subthreshold Leakage
-    //=
-    //"
+    //		cout << indent_str_next << "Global Predictor    Gate Leakage = " <<
+    //globalBPT->rt_power.readOp.gate_leakage << " W" << endl;
+    //		cout << indent_str_next << "Local Predictor   Peak Dynamic = " <<
+    //L1_localBPT->rt_power.readOp.dynamic*clockRate  << " W" << endl;
+    //		cout << indent_str_next << "Local Predictor   Subthreshold Leakage = "
     //<< L1_localBPT->rt_power.readOp.leakage  << " W" << endl;
-    //		cout << indent_str_next << "Local Predictor   Gate Leakage = "
-    //<<
-    // L1_localBPT->rt_power.readOp.gate_leakage  << " W" << endl;
+    //		cout << indent_str_next << "Local Predictor   Gate Leakage = " <<
+    //L1_localBPT->rt_power.readOp.gate_leakage  << " W" << endl;
     //		cout << indent_str_next << "Chooser   Peak Dynamic = " <<
-    // chooser->rt_power.readOp.dynamic*clockRate  << " W" << endl;
-    //		cout << indent_str_next << "Chooser   Subthreshold Leakage = "
-    //<<
-    // chooser->rt_power.readOp.leakage  << " W" << endl;
+    //chooser->rt_power.readOp.dynamic*clockRate  << " W" << endl;
+    //		cout << indent_str_next << "Chooser   Subthreshold Leakage = " <<
+    //chooser->rt_power.readOp.leakage  << " W" << endl;
     //		cout << indent_str_next << "Chooser   Gate Leakage = " <<
-    // chooser->rt_power.readOp.gate_leakage  << " W" << endl;
+    //chooser->rt_power.readOp.gate_leakage  << " W" << endl;
     //		cout << indent_str_next << "RAS   Peak Dynamic = " <<
-    // RAS->rt_power.readOp.dynamic*clockRate  << " W" << endl;
+    //RAS->rt_power.readOp.dynamic*clockRate  << " W" << endl;
     //		cout << indent_str_next << "RAS   Subthreshold Leakage = " <<
-    // RAS->rt_power.readOp.leakage  << " W" << endl;
+    //RAS->rt_power.readOp.leakage  << " W" << endl;
     //		cout << indent_str_next << "RAS   Gate Leakage = " <<
-    // RAS->rt_power.readOp.gate_leakage  << " W" << endl;
+    //RAS->rt_power.readOp.gate_leakage  << " W" << endl;
   }
 }
 
@@ -3609,48 +3593,30 @@ void InstFetchU::displayEnergy(uint32_t indent, int plevel, bool is_tdp) {
          << " W" << endl;
     cout << endl;
   } else {
-    //		cout << indent_str_next << "Instruction Cache    Peak Dynamic =
-    //"
-    //<<
-    // icache.rt_power.readOp.dynamic*clockRate << " W" << endl;
-    //		cout << indent_str_next << "Instruction Cache    Subthreshold
-    // Leakage
+    //		cout << indent_str_next << "Instruction Cache    Peak Dynamic = " <<
+    //icache.rt_power.readOp.dynamic*clockRate << " W" << endl;
+    //		cout << indent_str_next << "Instruction Cache    Subthreshold Leakage
     //= " << icache.rt_power.readOp.leakage <<" W" << endl;
-    //		cout << indent_str_next << "Instruction Cache    Gate Leakage =
-    //"
-    //<<
-    // icache.rt_power.readOp.gate_leakage << " W" << endl;
-    //		cout << indent_str_next << "Instruction Buffer   Peak Dynamic =
-    //"
-    //<<
-    // IB->rt_power.readOp.dynamic*clockRate  << " W" << endl;
-    //		cout << indent_str_next << "Instruction Buffer   Subthreshold
-    // Leakage
+    //		cout << indent_str_next << "Instruction Cache    Gate Leakage = " <<
+    //icache.rt_power.readOp.gate_leakage << " W" << endl;
+    //		cout << indent_str_next << "Instruction Buffer   Peak Dynamic = " <<
+    //IB->rt_power.readOp.dynamic*clockRate  << " W" << endl;
+    //		cout << indent_str_next << "Instruction Buffer   Subthreshold Leakage
     //= " << IB->rt_power.readOp.leakage  << " W" << endl;
-    //		cout << indent_str_next << "Instruction Buffer   Gate Leakage =
-    //"
-    //<<
-    // IB->rt_power.readOp.gate_leakage  << " W" << endl;
-    //		cout << indent_str_next << "Branch Target Buffer   Peak Dynamic =
-    //"
-    //<<
-    // BTB->rt_power.readOp.dynamic*clockRate  << " W" << endl;
+    //		cout << indent_str_next << "Instruction Buffer   Gate Leakage = " <<
+    //IB->rt_power.readOp.gate_leakage  << " W" << endl;
+    //		cout << indent_str_next << "Branch Target Buffer   Peak Dynamic = " <<
+    //BTB->rt_power.readOp.dynamic*clockRate  << " W" << endl;
     //		cout << indent_str_next << "Branch Target Buffer   Subthreshold
-    // Leakage = " << BTB->rt_power.readOp.leakage  << " W" << endl;
-    //		cout << indent_str_next << "Branch Target Buffer   Gate Leakage =
-    //"
-    //<<
-    // BTB->rt_power.readOp.gate_leakage  << " W" << endl;
-    //		cout << indent_str_next << "Branch Predictor   Peak Dynamic = "
-    //<<
-    // BPT->rt_power.readOp.dynamic*clockRate  << " W" << endl;
-    //		cout << indent_str_next << "Branch Predictor   Subthreshold
-    //Leakage
-    //=
+    //Leakage = " << BTB->rt_power.readOp.leakage  << " W" << endl;
+    //		cout << indent_str_next << "Branch Target Buffer   Gate Leakage = " <<
+    //BTB->rt_power.readOp.gate_leakage  << " W" << endl;
+    //		cout << indent_str_next << "Branch Predictor   Peak Dynamic = " <<
+    //BPT->rt_power.readOp.dynamic*clockRate  << " W" << endl;
+    //		cout << indent_str_next << "Branch Predictor   Subthreshold Leakage =
     //" << BPT->rt_power.readOp.leakage  << " W" << endl;
-    //		cout << indent_str_next << "Branch Predictor   Gate Leakage = "
-    //<<
-    // BPT->rt_power.readOp.gate_leakage  << " W" << endl;
+    //		cout << indent_str_next << "Branch Predictor   Gate Leakage = " <<
+    //BPT->rt_power.readOp.gate_leakage  << " W" << endl;
   }
 }
 
@@ -4248,12 +4214,11 @@ void SchedulerU::computeEnergy(bool is_tdp) {
   if (!exist) return;
   double ROB_duty_cycle;
   //	ROB_duty_cycle = ((coredynp.ALU_duty_cycle +
-  // coredynp.num_muls>0?coredynp.MUL_duty_cycle:0
-  //			+ coredynp.num_fpus>0?coredynp.FPU_duty_cycle:0))*1.1<1
-  //?
+  //coredynp.num_muls>0?coredynp.MUL_duty_cycle:0
+  //			+ coredynp.num_fpus>0?coredynp.FPU_duty_cycle:0))*1.1<1 ?
   //(coredynp.ALU_duty_cycle + coredynp.num_muls>0?coredynp.MUL_duty_cycle:0
   //					+
-  // coredynp.num_fpus>0?coredynp.FPU_duty_cycle:0)*1.1:1;
+  //coredynp.num_fpus>0?coredynp.FPU_duty_cycle:0)*1.1:1;
   ROB_duty_cycle = 1;
   // init stats
   if (is_tdp) {
@@ -4427,7 +4392,7 @@ void SchedulerU::computeEnergy(bool is_tdp) {
 
     } else if (coredynp.multithreaded) {
       //			set_pppm(pppm_t,
-      // XML->sys.core[ithCore].issue_width,1, 1, 1);
+      //XML->sys.core[ithCore].issue_width,1, 1, 1);
       int_inst_window->power =
           int_inst_window->power_t +
           (int_inst_window->local_result.power + instruction_selection->power) *
@@ -4454,7 +4419,7 @@ void SchedulerU::computeEnergy(bool is_tdp) {
 
     } else if (coredynp.multithreaded) {
       //			set_pppm(pppm_t,
-      // XML->sys.core[ithCore].issue_width,1, 1, 1);
+      //XML->sys.core[ithCore].issue_width,1, 1, 1);
       int_inst_window->rt_power =
           int_inst_window->power_t +
           (int_inst_window->local_result.power + instruction_selection->power) *
@@ -4464,9 +4429,9 @@ void SchedulerU::computeEnergy(bool is_tdp) {
   }
   //	set_pppm(pppm_t, XML->sys.core[ithCore].issue_width,1, 1, 1);
   //	cout<<"Scheduler
-  // power="<<power.readOp.dynamic<<"leakage="<<power.readOp.leakage<<endl;
+  //power="<<power.readOp.dynamic<<"leakage="<<power.readOp.leakage<<endl;
   //	cout<<"IW="<<int_inst_window->local_result.power.searchOp.dynamic *
-  // int_inst_window->stats_t.readAc.access +
+  //int_inst_window->stats_t.readAc.access +
   //    + int_inst_window->local_result.power.writeOp.dynamic *
   //    int_inst_window->stats_t.writeAc.access<<"leakage="<<int_inst_window->local_result.power.readOp.leakage<<endl;
   //	cout<<"selection"<<instruction_selection->power.readOp.dynamic<<"leakage"<<instruction_selection->power.readOp.leakage<<endl;
@@ -5139,11 +5104,11 @@ void LoadStoreU::computeEnergy(bool is_tdp) {
 
   } else {
     //	LSQ->power_t.readOp.dynamic  +=
-    // LSQ->stats_t.readAc.access*(LSQ->local_result.power.searchOp.dynamic +
-    // LSQ->local_result.power.readOp.dynamic)
+    //LSQ->stats_t.readAc.access*(LSQ->local_result.power.searchOp.dynamic +
+    //LSQ->local_result.power.readOp.dynamic)
     //	        +
-    // LSQ->stats_t.writeAc.access*LSQ->local_result.power.writeOp.dynamic;//every
-    // memory access invloves at least two operations on LSQ
+    //LSQ->stats_t.writeAc.access*LSQ->local_result.power.writeOp.dynamic;//every
+    //memory access invloves at least two operations on LSQ
     //	No LSQ in GPUs (Syed)
   }
 
@@ -5979,7 +5944,7 @@ void EXECU::displayEnergy(uint32_t indent, int plevel, bool is_tdp) {
   bool long_channel = XML->sys.longer_channel_device;
 
   //	cout << indent_str_next << "Results Broadcast Bus Area = " <<
-  // bypass->area.get_area() *1e-6 << " mm^2" << endl;
+  //bypass->area.get_area() *1e-6 << " mm^2" << endl;
   if (is_tdp) {
     cout << indent_str << "Register Files:" << endl;
     cout << indent_str_next << "Area = " << rfu->area.get_area() * 1e-6
@@ -6186,15 +6151,15 @@ void Core::computeEnergy(bool is_tdp) {
                coredynp.num_pipelines / num_units,
                coredynp.num_pipelines / num_units);
       //			cout << "IFU = " <<
-      // ifu->power.readOp.dynamic*clockRate  << " W" << endl;
+      //ifu->power.readOp.dynamic*clockRate  << " W" << endl;
       ifu->power = ifu->power + corepipe->power * pppm_t;
       //			cout << "IFU = " <<
-      // ifu->power.readOp.dynamic*clockRate  << " W" << endl;
+      //ifu->power.readOp.dynamic*clockRate  << " W" << endl;
       //			cout << "1/4 pipe = " <<
-      // corepipe->power.readOp.dynamic*clockRate/num_units  << " W" << endl;
+      //corepipe->power.readOp.dynamic*clockRate/num_units  << " W" << endl;
       power = power + ifu->power;
       //			cout << "core = " <<
-      // power.readOp.dynamic*clockRate  << " W" << endl;
+      //power.readOp.dynamic*clockRate  << " W" << endl;
     }
     if (lsu->exist) {
       Pipeline_energy +=
@@ -6207,10 +6172,10 @@ void Core::computeEnergy(bool is_tdp) {
                coredynp.num_pipelines / num_units);
       lsu->power = lsu->power + corepipe->power * pppm_t;
       //			cout << "LSU = " <<
-      // lsu->power.readOp.dynamic*clockRate  << " W" << endl;
+      //lsu->power.readOp.dynamic*clockRate  << " W" << endl;
       power = power + lsu->power;
       //			cout << "core = " <<
-      // power.readOp.dynamic*clockRate  << " W" << endl;
+      //power.readOp.dynamic*clockRate  << " W" << endl;
     }
     if (exu->exist) {
       Pipeline_energy +=
@@ -6224,10 +6189,10 @@ void Core::computeEnergy(bool is_tdp) {
       // cout<<"ExPowerScalingFactor:"<<coredynp.num_pipelines/num_units*coredynp.ALU_duty_cycle<<endl;
       exu->power = exu->power + corepipe->power * pppm_t;
       //			cout << "EXE = " <<
-      // exu->power.readOp.dynamic*clockRate  << " W" << endl;
+      //exu->power.readOp.dynamic*clockRate  << " W" << endl;
       power = power + exu->power;
       //			cout << "core = " <<
-      // power.readOp.dynamic*clockRate  << " W" << endl;
+      //power.readOp.dynamic*clockRate  << " W" << endl;
     }
     if (mmu->exist) {
       Pipeline_energy +=
@@ -6240,10 +6205,10 @@ void Core::computeEnergy(bool is_tdp) {
                coredynp.num_pipelines / num_units);
       mmu->power = mmu->power + corepipe->power * pppm_t;
       //			cout << "MMU = " <<
-      // mmu->power.readOp.dynamic*clockRate  << " W" << endl;
+      //mmu->power.readOp.dynamic*clockRate  << " W" << endl;
       power = power + mmu->power;
       //			cout << "core = " <<
-      // power.readOp.dynamic*clockRate  << " W" << endl;
+      //power.readOp.dynamic*clockRate  << " W" << endl;
     }
 
     power = power + undiffCore->power;
@@ -6311,9 +6276,8 @@ void Core::computeEnergy(bool is_tdp) {
     }
 
     rt_power = rt_power + undiffCore->power;
-    //		cout << "EXE = " << exu->power.readOp.dynamic*clockRate  << " W"
-    //<<
-    // endl;
+    //		cout << "EXE = " << exu->power.readOp.dynamic*clockRate  << " W" <<
+    //endl;
     if (XML->sys.Private_L2) {
       l2cache->computeEnergy(is_tdp);
       // set_pppm(pppm_t,1/l2cache->cachep.executionTime, 1,1,1);
@@ -6472,28 +6436,22 @@ void Core::displayEnergy(uint32_t indent, int plevel, bool is_tdp) {
     //			if (undiffCore->exist)
     //			{
     //				cout << indent_str << "Undifferentiated Core" <<
-    // endl;
+    //endl;
     //				cout << indent_str_next << "Area = " <<
-    // undiffCore->area.get_area()*1e-6<< " mm^2" << endl;
+    //undiffCore->area.get_area()*1e-6<< " mm^2" << endl;
     //				cout << indent_str_next << "Peak Dynamic = " <<
-    // undiffCore->power.readOp.dynamic*clockRate << " W" << endl;
-    ////				cout << indent_str_next << "Subthreshold Leakage =
-    ///"
-    ///<<
-    /// undiffCore->power.readOp.leakage <<" W" << endl;
-    //				cout << indent_str_next << "Subthreshold Leakage
-    //=
+    //undiffCore->power.readOp.dynamic*clockRate << " W" << endl;
+    ////				cout << indent_str_next << "Subthreshold Leakage = " <<
+    ///undiffCore->power.readOp.leakage <<" W" << endl;
+    //				cout << indent_str_next << "Subthreshold Leakage =
     //"
-    //								<<
-    //(long_channel?
-    // undiffCore->power.readOp.longer_channel_leakage:undiffCore->power.readOp.leakage)
+    //								<< (long_channel?
+    //undiffCore->power.readOp.longer_channel_leakage:undiffCore->power.readOp.leakage)
     //<< " W" << endl;
     //				cout << indent_str_next << "Gate Leakage = " <<
-    // undiffCore->power.readOp.gate_leakage << " W" << endl;
-    //				//		cout << indent_str_next << "Runtime Dynamic =
-    //"
-    //<<
-    // undiffCore->rt_power.readOp.dynamic/executionTime << " W" << endl;
+    //undiffCore->power.readOp.gate_leakage << " W" << endl;
+    //				//		cout << indent_str_next << "Runtime Dynamic = " <<
+    //undiffCore->rt_power.readOp.dynamic/executionTime << " W" << endl;
     //				cout <<endl;
     //			}
     //		}
@@ -6507,44 +6465,30 @@ void Core::displayEnergy(uint32_t indent, int plevel, bool is_tdp) {
          << endl;
 
   } else {
-    //		cout << indent_str_next << "Instruction Fetch Unit    Peak Dynamic
-    //=
-    //"
+    //		cout << indent_str_next << "Instruction Fetch Unit    Peak Dynamic = "
     //<< ifu->rt_power.readOp.dynamic*clockRate << " W" << endl;
-    //		cout << indent_str_next << "Instruction Fetch Unit Subthreshold
-    // Leakage = " << ifu->rt_power.readOp.leakage <<" W" << endl;
-    //		cout << indent_str_next << "Instruction Fetch Unit    Gate Leakage
-    //=
-    //"
+    //		cout << indent_str_next << "Instruction Fetch Unit    Subthreshold
+    //Leakage = " << ifu->rt_power.readOp.leakage <<" W" << endl;
+    //		cout << indent_str_next << "Instruction Fetch Unit    Gate Leakage = "
     //<< ifu->rt_power.readOp.gate_leakage << " W" << endl;
-    //		cout << indent_str_next << "Load Store Unit   Peak Dynamic = "
-    //<<
-    // lsu->rt_power.readOp.dynamic*clockRate  << " W" << endl;
-    //		cout << indent_str_next << "Load Store Unit   Subthreshold Leakage
-    //=
-    //"
+    //		cout << indent_str_next << "Load Store Unit   Peak Dynamic = " <<
+    //lsu->rt_power.readOp.dynamic*clockRate  << " W" << endl;
+    //		cout << indent_str_next << "Load Store Unit   Subthreshold Leakage = "
     //<< lsu->rt_power.readOp.leakage  << " W" << endl;
-    //		cout << indent_str_next << "Load Store Unit   Gate Leakage = "
-    //<<
-    // lsu->rt_power.readOp.gate_leakage  << " W" << endl;
-    //		cout << indent_str_next << "Memory Management Unit   Peak Dynamic
-    //=
-    //"
+    //		cout << indent_str_next << "Load Store Unit   Gate Leakage = " <<
+    //lsu->rt_power.readOp.gate_leakage  << " W" << endl;
+    //		cout << indent_str_next << "Memory Management Unit   Peak Dynamic = "
     //<< mmu->rt_power.readOp.dynamic*clockRate  << " W" << endl;
-    //		cout << indent_str_next << "Memory Management Unit Subthreshold
-    // Leakage = " << mmu->rt_power.readOp.leakage  << " W" << endl;
-    //		cout << indent_str_next << "Memory Management Unit   Gate Leakage
-    //=
-    //"
+    //		cout << indent_str_next << "Memory Management Unit   Subthreshold
+    //Leakage = " << mmu->rt_power.readOp.leakage  << " W" << endl;
+    //		cout << indent_str_next << "Memory Management Unit   Gate Leakage = "
     //<< mmu->rt_power.readOp.gate_leakage  << " W" << endl;
     //		cout << indent_str_next << "Execution Unit   Peak Dynamic = " <<
-    // exu->rt_power.readOp.dynamic*clockRate  << " W" << endl;
-    //		cout << indent_str_next << "Execution Unit   Subthreshold Leakage
-    //=
-    //"
+    //exu->rt_power.readOp.dynamic*clockRate  << " W" << endl;
+    //		cout << indent_str_next << "Execution Unit   Subthreshold Leakage = "
     //<< exu->rt_power.readOp.leakage  << " W" << endl;
     //		cout << indent_str_next << "Execution Unit   Gate Leakage = " <<
-    // exu->rt_power.readOp.gate_leakage  << " W" << endl;
+    //exu->rt_power.readOp.gate_leakage  << " W" << endl;
   }
 }
 InstFetchU::~InstFetchU() {
@@ -6867,9 +6811,8 @@ void Core::set_core_param() {
   }
   //	if (coredynp.core_ty==OOO)
   //	{
-  //		cout<<"OOO processor models are being updated and will be
-  // available
-  // in next release"<<endl;
+  //		cout<<"OOO processor models are being updated and will be available
+  //in next release"<<endl;
   //		exit(0);
   //	}
   if (!((coredynp.scheu_ty == PhysicalRegFile) ||
diff --git a/src/gpuwattch/iocontrollers.cc b/src/gpuwattch/iocontrollers.cc
index 6a29add..2425d40 100644
--- a/src/gpuwattch/iocontrollers.cc
+++ b/src/gpuwattch/iocontrollers.cc
@@ -236,7 +236,7 @@ void NIUController::set_niu_param() {
   niup.perc_load = XML->sys.niu.total_load_perc;
   niup.type = XML->sys.niu.type;
   //	  niup.executionTime   =
-  // XML->sys.total_cycles/(XML->sys.target_core_clockrate*1e6);
+  //XML->sys.total_cycles/(XML->sys.target_core_clockrate*1e6);
 }
 
 PCIeController::PCIeController(ParseXML* XML_interface,
@@ -276,7 +276,7 @@ PCIeController::PCIeController(ParseXML* XML_interface,
                1.1 * (interface_ip.F_sz_nm / 65.0);
     //	  //Cadence ChipEstimate using 65nm soft IP;
     //	  frontend_dyn =
-    // 0.27e-9/8*g_tp.peri_global.Vdd/1.1*g_tp.peri_global.Vdd/1.1*(interface_ip.F_sz_nm/65.0);
+    //0.27e-9/8*g_tp.peri_global.Vdd/1.1*g_tp.peri_global.Vdd/1.1*(interface_ip.F_sz_nm/65.0);
     // SerDer_dyn is power not energy, scaling from 10mw/Gb/s @90nm
     SerDer_dyn = 0.01 * 4 * (interface_ip.F_sz_um / 0.09) *
                  g_tp.peri_global.Vdd / 1.2 * g_tp.peri_global.Vdd /
@@ -305,7 +305,7 @@ PCIeController::PCIeController(ParseXML* XML_interface,
                1.1 * (interface_ip.F_sz_nm / 65.0);
     //	  //Cadence ChipEstimate using 65nm soft IP;
     //	  frontend_dyn =
-    // 0.27e-9/8*g_tp.peri_global.Vdd/1.1*g_tp.peri_global.Vdd/1.1*(interface_ip.F_sz_nm/65.0);
+    //0.27e-9/8*g_tp.peri_global.Vdd/1.1*g_tp.peri_global.Vdd/1.1*(interface_ip.F_sz_nm/65.0);
     // SerDer_dyn is power not energy, scaling from 10mw/Gb/s @90nm
     SerDer_dyn = 0.01 * 4 * (interface_ip.F_sz_um / 0.09) *
                  g_tp.peri_global.Vdd / 1.2 * g_tp.peri_global.Vdd /
@@ -387,7 +387,7 @@ void PCIeController::set_pcie_param() {
   pciep.type = XML->sys.pcie.type;
   pciep.withPHY = XML->sys.pcie.withPHY;
   //	  pciep.executionTime   =
-  // XML->sys.total_cycles/(XML->sys.target_core_clockrate*1e6);
+  //XML->sys.total_cycles/(XML->sys.target_core_clockrate*1e6);
 }
 
 FlashController::FlashController(ParseXML* XML_interface,
@@ -507,5 +507,5 @@ void FlashController::set_fc_param() {
   fcp.type = XML->sys.flashc.type;
   fcp.withPHY = XML->sys.flashc.withPHY;
   //	  flashcp.executionTime   =
-  // XML->sys.total_cycles/(XML->sys.target_core_clockrate*1e6);
+  //XML->sys.total_cycles/(XML->sys.target_core_clockrate*1e6);
 }
diff --git a/src/gpuwattch/logic.cc b/src/gpuwattch/logic.cc
index d6937ca..65e3875 100644
--- a/src/gpuwattch/logic.cc
+++ b/src/gpuwattch/logic.cc
@@ -362,8 +362,8 @@ void Pipeline::compute() {
 
   double clock_power_pipereg = num_piperegs * pipe_reg.e_clock.readOp.dynamic;
   //******************pipeline power: currently, we average all the
-  // possibilities of the states of DFFs in the pipeline. A better way to do it
-  // is to consider
+  //possibilities of the states of DFFs in the pipeline. A better way to do it
+  //is to consider
   // the harming distance of two consecutive signals, However McPAT does not
   // have plan to do this in near future as it focuses on worst case power.
   double pipe_reg_power = num_piperegs * (pipe_reg.e_switch.readOp.dynamic +
@@ -578,8 +578,8 @@ FunctionalUnit::FunctionalUnit(ParseXML *XML_interface, int ithCore_,
       // energy = 0.3529/10*1e-9;//this is the energy(nJ) for a FP instruction
       // in FPU usually it can have up to 20 cycles.
       //			base_energy = coredynp.core_ty==Inorder? 0:
-      // 89e-3*3; //W The base energy of ALU average numbers from Intel 4G and
-      // 773Mhz (Wattch)
+      //89e-3*3; //W The base energy of ALU average numbers from Intel 4G and
+      //773Mhz (Wattch)
       //			base_energy
       //*=(g_tp.peri_global.Vdd*g_tp.peri_global.Vdd/1.2/1.2);
       base_energy = 0;
@@ -615,8 +615,8 @@ FunctionalUnit::FunctionalUnit(ParseXML *XML_interface, int ithCore_,
           g_tp.peri_global.Vdd / 2;
       leakage = 0;
       //			base_energy = coredynp.core_ty==Inorder?
-      // 0:89e-3; //W The base energy of ALU average numbers from Intel 4G and
-      // 773Mhz (Wattch)
+      //0:89e-3; //W The base energy of ALU average numbers from Intel 4G and
+      //773Mhz (Wattch)
       //			base_energy
       //*=(g_tp.peri_global.Vdd*g_tp.peri_global.Vdd/1.2/1.2);
       base_energy = 0;
@@ -645,8 +645,8 @@ FunctionalUnit::FunctionalUnit(ParseXML *XML_interface, int ithCore_,
                           inv) *
           g_tp.peri_global.Vdd / 2;
       //			base_energy = coredynp.core_ty==Inorder?
-      // 0:89e-3*2; //W The base energy of ALU average numbers from Intel 4G and
-      // 773Mhz (Wattch)
+      //0:89e-3*2; //W The base energy of ALU average numbers from Intel 4G and
+      //773Mhz (Wattch)
       //			base_energy
       //*=(g_tp.peri_global.Vdd*g_tp.peri_global.Vdd/1.2/1.2);
       base_energy = 0;
@@ -666,7 +666,7 @@ FunctionalUnit::FunctionalUnit(ParseXML *XML_interface, int ithCore_,
     }
     per_access_energy *= 0.5;  // According to ARM data embedded processor has
                                // much lower per acc energy
-  }                            /* if (XML->sys.Embedded) */
+  } /* if (XML->sys.Embedded) */
   else {
     if (fu_type == FPU) {
       num_fu = coredynp.num_fpus;
@@ -705,14 +705,16 @@ FunctionalUnit::FunctionalUnit(ParseXML *XML_interface, int ithCore_,
       if (g_ip->F_sz_nm > 90)
         area_t = 8.47 * 1e6 *
                  g_tp.scaling_factor.logic_scaling_co_eff;  // this is um^2
-      leakage = 37e-3;                                      // area_t
-      // *(g_tp.scaling_factor.core_tx_density)*cmos_Isub_leakage(5*g_tp.min_w_nmos_,
-      // 5*g_tp.min_w_nmos_*pmos_to_nmos_sizing_r, 1,
-      // inv)*g_tp.peri_global.Vdd/2;//unit W
-      gate_leakage = 0;  // area_t
-      // *(g_tp.scaling_factor.core_tx_density)*cmos_Ig_leakage(5*g_tp.min_w_nmos_,
-      // 5*g_tp.min_w_nmos_*pmos_to_nmos_sizing_r, 1,
-      // inv)*g_tp.peri_global.Vdd/2;//unit W
+      leakage =
+          37e-3;  // area_t
+                  // *(g_tp.scaling_factor.core_tx_density)*cmos_Isub_leakage(5*g_tp.min_w_nmos_,
+                  // 5*g_tp.min_w_nmos_*pmos_to_nmos_sizing_r, 1,
+                  // inv)*g_tp.peri_global.Vdd/2;//unit W
+      gate_leakage =
+          0;  // area_t
+              // *(g_tp.scaling_factor.core_tx_density)*cmos_Ig_leakage(5*g_tp.min_w_nmos_,
+              // 5*g_tp.min_w_nmos_*pmos_to_nmos_sizing_r, 1,
+              // inv)*g_tp.peri_global.Vdd/2;//unit W
       // energy = 0.3529/10*1e-9;//this is the energy(nJ) for a FP instruction
       // in FPU usually it can have up to 20 cycles.
       base_energy =
@@ -936,7 +938,7 @@ void FunctionalUnit::displayEnergy(uint32_t indent, int plevel, bool is_tdp) {
   bool long_channel = XML->sys.longer_channel_device;
 
   //	cout << indent_str_next << "Results Broadcast Bus Area = " <<
-  // bypass->area.get_area() *1e-6 << " mm^2" << endl;
+  //bypass->area.get_area() *1e-6 << " mm^2" << endl;
   if (is_tdp) {
     if (fu_type == FPU) {
       cout << indent_str
@@ -1167,11 +1169,10 @@ UndiffCore::UndiffCore(ParseXML *XML_interface, int ithCore_,
   //		double vt=g_tp.peri_global.Vth;
   //		double velocity_index=1.1;
   //		double c_in=gate_C(g_tp.min_w_nmos_,
-  // g_tp.min_w_nmos_*pmos_to_nmos_sizing_r , 0.0, false);
-  //		double c_out= drain_C_(g_tp.min_w_nmos_, NCH, 2, 1,
-  // g_tp.cell_h_def,
-  // false) + drain_C_(g_tp.min_w_nmos_*pmos_to_nmos_sizing_r, PCH, 1, 1,
-  // g_tp.cell_h_def, false) + c_in;
+  //g_tp.min_w_nmos_*pmos_to_nmos_sizing_r , 0.0, false);
+  //		double c_out= drain_C_(g_tp.min_w_nmos_, NCH, 2, 1, g_tp.cell_h_def,
+  //false) + drain_C_(g_tp.min_w_nmos_*pmos_to_nmos_sizing_r, PCH, 1, 1,
+  //g_tp.cell_h_def, false) + c_in;
   //		double w_nmos=g_tp.min_w_nmos_;
   //		double w_pmos=g_tp.min_w_nmos_*pmos_to_nmos_sizing_r;
   //		double i_on_n=1.0;
@@ -1180,16 +1181,15 @@ UndiffCore::UndiffCore(ParseXML *XML_interface, int ithCore_,
   //		double i_on_p_in=1;
   //		double vdd=g_tp.peri_global.Vdd;
 
-  //		power.readOp.sc=shortcircuit_simple(vt, velocity_index, c_in,
-  // c_out,
-  // w_nmos,w_pmos, i_on_n, i_on_p,i_on_n_in, i_on_p_in, vdd);
+  //		power.readOp.sc=shortcircuit_simple(vt, velocity_index, c_in, c_out,
+  //w_nmos,w_pmos, i_on_n, i_on_p,i_on_n_in, i_on_p_in, vdd);
   //		power.readOp.dynamic=c_out*vdd*vdd/2;
 
   //		cout<<power.readOp.dynamic << "dynamic" <<endl;
   //		cout<<power.readOp.sc << "sc" << endl;
 
   //		power.readOp.sc=shortcircuit(vt, velocity_index, c_in, c_out,
-  // w_nmos,w_pmos, i_on_n, i_on_p,i_on_n_in, i_on_p_in, vdd);
+  //w_nmos,w_pmos, i_on_n, i_on_p,i_on_n_in, i_on_p_in, vdd);
   //		power.readOp.dynamic=c_out*vdd*vdd/2;
   //
   //		cout<<power.readOp.dynamic << "dynamic" <<endl;
diff --git a/src/gpuwattch/logic.h b/src/gpuwattch/logic.h
index 9a1d3e6..df00837 100644
--- a/src/gpuwattch/logic.h
+++ b/src/gpuwattch/logic.h
@@ -172,9 +172,9 @@ class Pipeline : public Component {
   double WNANDp;
   double load_per_pipeline_stage;
   //	int  Hthread,  num_thread, fetchWidth, decodeWidth, issueWidth,
-  // commitWidth, instruction_length;
+  //commitWidth, instruction_length;
   //	int  PC_width, opcode_length, num_arch_reg_tag,
-  // data_width,num_phsical_reg_tag, address_width;
+  //data_width,num_phsical_reg_tag, address_width;
   //	bool thread_clock_gated;
   //	bool in_order, multithreaded;
   void compute_stage_vector();
@@ -185,9 +185,9 @@ class Pipeline : public Component {
 // class core_pipeline :public pipeline{
 // public:
 //	int  Hthread,  num_thread, fetchWidth, decodeWidth, issueWidth,
-// commitWidth, instruction_length;
+//commitWidth, instruction_length;
 //	int  PC_width, opcode_length, num_arch_reg_tag,
-// data_width,num_phsical_reg_tag, address_width;
+//data_width,num_phsical_reg_tag, address_width;
 //	bool thread_clock_gated;
 //	bool in_order, multithreaded;
 //	core_pipeline(bool _is_default, const InputParameter
diff --git a/src/gpuwattch/memoryctrl.cc b/src/gpuwattch/memoryctrl.cc
index d0becc4..07e2f77 100644
--- a/src/gpuwattch/memoryctrl.cc
+++ b/src/gpuwattch/memoryctrl.cc
@@ -102,7 +102,7 @@ void MCBackend::compute() {
   // double max_row_addr_width = 20.0;//Current address 12~18bits
   double C_MCB, mc_power, backend_dyn,
       backend_gates;  //, refresh_period,refresh_freq;//Equivalent per bit Cap
-                      // for backend,
+                      //for backend,
   double pmos_to_nmos_sizing_r = pmos_to_nmos_sz_ratio();
   double NMOS_sizing, PMOS_sizing;
 
@@ -535,7 +535,7 @@ MCFrontEnd::MCFrontEnd(ParseXML* XML_interface, InputParameter* interface_ip_,
                 PRT->local_result.area * XML->sys.mc.memory_channels_per_mc);
 
   //***ThreadMasks storage (coalesced threads whose memory requests are
-  // satisfied by each memory access)
+  //satisfied by each memory access)
   /* contents of the thread masks Array
         *  16-bit bit masks for up to 16 memory requests of a warp | Number of
    * pending memory requests (5 bits)
@@ -983,7 +983,7 @@ MemoryController::MemoryController(ParseXML* XML_interface,
     area.set_area(area.get_area() + PHY->area.get_area());
   }
   //+++++++++Transaction engine +++++++++++++++++ ////TODO needs better numbers,
-  // Run the RTL code from OpenSparc.
+  //Run the RTL code from OpenSparc.
   //  transecEngine.initialize(&interface_ip);
   //  transecEngine.peakDataTransferRate = XML->sys.mem.peak_transfer_rate;
   //  transecEngine.memDataWidth = dataBusWidth;
@@ -1023,7 +1023,7 @@ MemoryController::MemoryController(ParseXML* XML_interface,
   ////  //clock
   ////  clockNetwork.init_wire_external(is_default, &interface_ip);
   ////  clockNetwork.clk_area           =area*1.1;//10% of placement overhead.
-  /// rule of thumb
+  ///rule of thumb
   ////  clockNetwork.end_wiring_level   =5;//toplevel metal
   ////  clockNetwork.start_wiring_level =5;//toplevel metal
   ////  clockNetwork.num_regs           = pipeLogic.tot_stage_vector;
@@ -1199,7 +1199,7 @@ void MemoryController::set_mc_param() {
     mcp.reads = XML->sys.mc.memory_reads;
     mcp.writes = XML->sys.mc.memory_writes;
     //+++++++++Transaction engine +++++++++++++++++ ////TODO needs better
-    // numbers, Run the RTL code from OpenSparc.
+    //numbers, Run the RTL code from OpenSparc.
     mcp.peakDataTransferRate = XML->sys.mc.peak_transfer_rate;
     mcp.memRank = XML->sys.mc.number_ranks;
     //++++++++++++++PHY ++++++++++++++++++++++++++ //TODO needs better numbers
@@ -1214,17 +1214,16 @@ void MemoryController::set_mc_param() {
   //	else if (mc_type==FLASHC)
   //	{
   //		mcp.clockRate       =XML->sys.flashc.mc_clock*2;//DDR double
-  // pumped
+  //pumped
   //		mcp.clockRate       *= 1e6;
   //		mcp.executionTime   =
-  // XML->sys.total_cycles/(XML->sys.target_core_clockrate*1e6);
+  //XML->sys.total_cycles/(XML->sys.target_core_clockrate*1e6);
   //
   //		mcp.llcBlockSize
   //=int(ceil(XML->sys.flashc.llc_line_length/8.0))+XML->sys.flashc.llc_line_length;//ecc
-  // overhead
-  //		mcp.dataBusWidth =int(ceil(XML->sys.flashc.databus_width/8.0))
-  //+
-  // XML->sys.flashc.databus_width;
+  //overhead
+  //		mcp.dataBusWidth    =int(ceil(XML->sys.flashc.databus_width/8.0)) +
+  //XML->sys.flashc.databus_width;
   //		mcp.addressBusWidth
   //=int(ceil(XML->sys.flashc.addressbus_width));//XML->sys.physical_address_width;
   //		mcp.opcodeW         =16;
@@ -1233,18 +1232,16 @@ void MemoryController::set_mc_param() {
   //		mcp.reads  = XML->sys.flashc.memory_reads;
   //		mcp.writes = XML->sys.flashc.memory_writes;
   //		//+++++++++Transaction engine +++++++++++++++++ ////TODO needs
-  // better numbers, Run the RTL code from OpenSparc.
+  //better numbers, Run the RTL code from OpenSparc.
   //		mcp.peakDataTransferRate = XML->sys.flashc.peak_transfer_rate;
   //		mcp.memRank = XML->sys.flashc.number_ranks;
-  //		//++++++++++++++PHY ++++++++++++++++++++++++++ //TODO needs
-  // better
-  // numbers
+  //		//++++++++++++++PHY ++++++++++++++++++++++++++ //TODO needs better
+  //numbers
   //		//PHY.memAccesses=PHY.peakDataTransferRate;//this is the max
-  // power
+  //power
   //		//PHY.llcBlocksize=llcBlockSize;
-  //		mcp.frontend_duty_cycle = 0.5;//for max power, the actual
-  // off-chip
-  // links is bidirectional but time shared
+  //		mcp.frontend_duty_cycle = 0.5;//for max power, the actual off-chip
+  //links is bidirectional but time shared
   //		mcp.LVDS = XML->sys.flashc.LVDS;
   //		mcp.type = XML->sys.flashc.type;
   //	}
diff --git a/src/gpuwattch/noc.cc b/src/gpuwattch/noc.cc
index 85fc0a9..bf8d8b5 100644
--- a/src/gpuwattch/noc.cc
+++ b/src/gpuwattch/noc.cc
@@ -357,44 +357,30 @@ void NoC::displayEnergy(uint32_t indent, int plevel, bool is_tdp) {
       cout << endl;
     }
   } else {
-    //		cout << indent_str_next << "Instruction Fetch Unit    Peak Dynamic
-    //=
-    //"
+    //		cout << indent_str_next << "Instruction Fetch Unit    Peak Dynamic = "
     //<< ifu->rt_power.readOp.dynamic*clockRate << " W" << endl;
-    //		cout << indent_str_next << "Instruction Fetch Unit Subthreshold
-    // Leakage = " << ifu->rt_power.readOp.leakage <<" W" << endl;
-    //		cout << indent_str_next << "Instruction Fetch Unit    Gate Leakage
-    //=
-    //"
+    //		cout << indent_str_next << "Instruction Fetch Unit    Subthreshold
+    //Leakage = " << ifu->rt_power.readOp.leakage <<" W" << endl;
+    //		cout << indent_str_next << "Instruction Fetch Unit    Gate Leakage = "
     //<< ifu->rt_power.readOp.gate_leakage << " W" << endl;
-    //		cout << indent_str_next << "Load Store Unit   Peak Dynamic = "
-    //<<
-    // lsu->rt_power.readOp.dynamic*clockRate  << " W" << endl;
-    //		cout << indent_str_next << "Load Store Unit   Subthreshold Leakage
-    //=
-    //"
+    //		cout << indent_str_next << "Load Store Unit   Peak Dynamic = " <<
+    //lsu->rt_power.readOp.dynamic*clockRate  << " W" << endl;
+    //		cout << indent_str_next << "Load Store Unit   Subthreshold Leakage = "
     //<< lsu->rt_power.readOp.leakage  << " W" << endl;
-    //		cout << indent_str_next << "Load Store Unit   Gate Leakage = "
-    //<<
-    // lsu->rt_power.readOp.gate_leakage  << " W" << endl;
-    //		cout << indent_str_next << "Memory Management Unit   Peak Dynamic
-    //=
-    //"
+    //		cout << indent_str_next << "Load Store Unit   Gate Leakage = " <<
+    //lsu->rt_power.readOp.gate_leakage  << " W" << endl;
+    //		cout << indent_str_next << "Memory Management Unit   Peak Dynamic = "
     //<< mmu->rt_power.readOp.dynamic*clockRate  << " W" << endl;
-    //		cout << indent_str_next << "Memory Management Unit Subthreshold
-    // Leakage = " << mmu->rt_power.readOp.leakage  << " W" << endl;
-    //		cout << indent_str_next << "Memory Management Unit   Gate Leakage
-    //=
-    //"
+    //		cout << indent_str_next << "Memory Management Unit   Subthreshold
+    //Leakage = " << mmu->rt_power.readOp.leakage  << " W" << endl;
+    //		cout << indent_str_next << "Memory Management Unit   Gate Leakage = "
     //<< mmu->rt_power.readOp.gate_leakage  << " W" << endl;
     //		cout << indent_str_next << "Execution Unit   Peak Dynamic = " <<
-    // exu->rt_power.readOp.dynamic*clockRate  << " W" << endl;
-    //		cout << indent_str_next << "Execution Unit   Subthreshold Leakage
-    //=
-    //"
+    //exu->rt_power.readOp.dynamic*clockRate  << " W" << endl;
+    //		cout << indent_str_next << "Execution Unit   Subthreshold Leakage = "
     //<< exu->rt_power.readOp.leakage  << " W" << endl;
     //		cout << indent_str_next << "Execution Unit   Gate Leakage = " <<
-    // exu->rt_power.readOp.gate_leakage  << " W" << endl;
+    //exu->rt_power.readOp.gate_leakage  << " W" << endl;
   }
 }
 
diff --git a/src/gpuwattch/processor.cc b/src/gpuwattch/processor.cc
index b5b5cfb..96c3351 100644
--- a/src/gpuwattch/processor.cc
+++ b/src/gpuwattch/processor.cc
@@ -1084,8 +1084,7 @@ void Processor::set_proc_param() {
 
   //	if (procdynp.numCore<1)
   //	{
-  //		cout<<" The target processor should at least have one core on
-  // chip."
+  //		cout<<" The target processor should at least have one core on chip."
   //<<endl;
   //		exit(0);
   //	}
@@ -1136,7 +1135,7 @@ void Processor::set_proc_param() {
   interface_ip.F_sz_um = interface_ip.F_sz_nm / 1000;
 
   //***********This section of code does not have real meaning, they are just to
-  // ensure all data will have initial value to prevent errors.
+  //ensure all data will have initial value to prevent errors.
   // They will be overridden  during each components initialization
   interface_ip.cache_sz = 64;
   interface_ip.line_sz = 1;
diff --git a/src/gpuwattch/processor.h b/src/gpuwattch/processor.h
index c0be8be..326206c 100644
--- a/src/gpuwattch/processor.h
+++ b/src/gpuwattch/processor.h
@@ -176,7 +176,7 @@ class Processor : public Component {
       read_coef = l2array[0]
                       ->unicache.caches->local_result.tag_array2->power.writeOp
                       .dynamic;  //*(32/4); // removed by Jingwen, the scaling
-                                 // of 32/4 is not used in the mcpat
+                                 //of 32/4 is not used in the mcpat
       read_coef +=
           l2array[0]->unicache.caches->local_result.power.writeOp.dynamic;
       read_coef +=
diff --git a/src/gpuwattch/sharedcache.cc b/src/gpuwattch/sharedcache.cc
index d25d1df..147be43 100644
--- a/src/gpuwattch/sharedcache.cc
+++ b/src/gpuwattch/sharedcache.cc
@@ -1106,25 +1106,24 @@ void SharedCache::displayEnergy(uint32_t indent, bool is_tdp) {
 //		  ///cout<<"directory.maxPower=" <<directory.maxPower<<endl;
 //
 //		  directory.maxPower	+=
-// directory.missb.l_ip.num_search_ports*directory.missb.local_result.power.searchOp.dynamic*clockRate;
+//directory.missb.l_ip.num_search_ports*directory.missb.local_result.power.searchOp.dynamic*clockRate;
 //		  ///cout<<"directory.maxPower=" <<directory.maxPower<<endl;
 //
 //		  directory.maxPower	+=
-// directory.ifb.l_ip.num_search_ports*directory.ifb.local_result.power.searchOp.dynamic*clockRate;
+//directory.ifb.l_ip.num_search_ports*directory.ifb.local_result.power.searchOp.dynamic*clockRate;
 //		  ///cout<<"directory.maxPower=" <<directory.maxPower<<endl;
 //
 //		  directory.maxPower	+=
-// directory.prefetchb.l_ip.num_search_ports*directory.prefetchb.local_result.power.searchOp.dynamic*clockRate;
+//directory.prefetchb.l_ip.num_search_ports*directory.prefetchb.local_result.power.searchOp.dynamic*clockRate;
 //		  ///cout<<"directory.maxPower=" <<directory.maxPower<<endl;
 //
 //		  directory.maxPower	+=
-// directory.wbb.l_ip.num_search_ports*directory.wbb.local_result.power.searchOp.dynamic*clockRate;
+//directory.wbb.l_ip.num_search_ports*directory.wbb.local_result.power.searchOp.dynamic*clockRate;
 //
-//		  cc.power.readOp.dynamic = directory.maxPower*scktRatio*8;//8
-// is
-// the memory controller counts
+//		  cc.power.readOp.dynamic = directory.maxPower*scktRatio*8;//8 is
+//the memory controller counts
 //		  cc.power.readOp.leakage =
-// directory.caches.local_result.power.readOp.leakage +
+//directory.caches.local_result.power.readOp.leakage +
 //                                     directory.missb.local_result.power.readOp.leakage
 //                                     +
 //                                     directory.ifb.local_result.power.readOp.leakage
@@ -1141,23 +1140,23 @@ void SharedCache::displayEnergy(uint32_t indent, bool is_tdp) {
 //		  ccTot.area.set_area(cc.area.get_area()*1e-6);
 //		  ccTot.power = cc.power;
 //		  cout<<"DC energy per access" <<
-// cc.power.readOp.dynamic/clockRate/8;
+//cc.power.readOp.dynamic/clockRate/8;
 //	  }
 //	  else if (XML->sys.first_level_dir==1)
 //	  {
 //		  inv_dir.maxPower =
-// inv_dir.caches.local_result.power.searchOp.dynamic*clockRate*XML->sys.domain_size;
+//inv_dir.caches.local_result.power.searchOp.dynamic*clockRate*XML->sys.domain_size;
 //		  cc.power.readOp.dynamic  =
-// inv_dir.maxPower*scktRatio*64/XML->sys.domain_size;
+//inv_dir.maxPower*scktRatio*64/XML->sys.domain_size;
 //		  cc.power.readOp.leakage  =
-// inv_dir.caches.local_result.power.readOp.leakage*inv_dir.caches.l_ip.nbanks*64/XML->sys.domain_size;
+//inv_dir.caches.local_result.power.readOp.leakage*inv_dir.caches.l_ip.nbanks*64/XML->sys.domain_size;
 //
 //		  cc.area.set_area(inv_dir.area*64/XML->sys.domain_size);
 //		  cout<<"CC area="<<cc.area.get_area()*1e-6<<endl;
 //		  cout<<"CC Power="<<cc.power.readOp.dynamic<<endl;
 //		  ccTot.area.set_area(cc.area.get_area()*1e-6);
 //		  cout<<"DC energy per access" <<
-// cc.power.readOp.dynamic/clockRate/8;
+//cc.power.readOp.dynamic/clockRate/8;
 //		  ccTot.power = cc.power;
 //	  }
 //  }
@@ -1174,27 +1173,27 @@ void SharedCache::displayEnergy(uint32_t indent, bool is_tdp) {
 //<<directory.maxPower<<endl;
 //
 //	  		  directory.maxPower	+=
-// directory.missb.l_ip.num_search_ports*directory.missb.local_result.power.searchOp.dynamic*clockRate;
+//directory.missb.l_ip.num_search_ports*directory.missb.local_result.power.searchOp.dynamic*clockRate;
 //	  		  ///cout<<"directory.maxPower="
 //<<directory.maxPower<<endl;
 //
 //	  		  directory.maxPower	+=
-// directory.ifb.l_ip.num_search_ports*directory.ifb.local_result.power.searchOp.dynamic*clockRate;
+//directory.ifb.l_ip.num_search_ports*directory.ifb.local_result.power.searchOp.dynamic*clockRate;
 //	  		  ///cout<<"directory.maxPower="
 //<<directory.maxPower<<endl;
 //
 //	  		  directory.maxPower	+=
-// directory.prefetchb.l_ip.num_search_ports*directory.prefetchb.local_result.power.searchOp.dynamic*clockRate;
+//directory.prefetchb.l_ip.num_search_ports*directory.prefetchb.local_result.power.searchOp.dynamic*clockRate;
 //	  		  ///cout<<"directory.maxPower="
 //<<directory.maxPower<<endl;
 //
 //	  		  directory.maxPower	+=
-// directory.wbb.l_ip.num_search_ports*directory.wbb.local_result.power.searchOp.dynamic*clockRate;
+//directory.wbb.l_ip.num_search_ports*directory.wbb.local_result.power.searchOp.dynamic*clockRate;
 //
 //	  		  cc.power.readOp.dynamic =
-// directory.maxPower*scktRatio*8;//8 is the memory controller counts
+//directory.maxPower*scktRatio*8;//8 is the memory controller counts
 //			  cc.power.readOp.leakage =
-// directory.caches.local_result.power.readOp.leakage +
+//directory.caches.local_result.power.readOp.leakage +
 //	                                     directory.missb.local_result.power.readOp.leakage
 //+
 //	                                     directory.ifb.local_result.power.readOp.leakage
@@ -1216,27 +1215,27 @@ void SharedCache::displayEnergy(uint32_t indent, bool is_tdp) {
 //<<directory1.maxPower<<endl;
 //
 //	  		  directory1.maxPower	+=
-// directory1.missb.l_ip.num_search_ports*directory1.missb.local_result.power.searchOp.dynamic*clockRate;
+//directory1.missb.l_ip.num_search_ports*directory1.missb.local_result.power.searchOp.dynamic*clockRate;
 //	  		  ///cout<<"directory1.maxPower="
 //<<directory1.maxPower<<endl;
 //
 //	  		  directory1.maxPower	+=
-// directory1.ifb.l_ip.num_search_ports*directory1.ifb.local_result.power.searchOp.dynamic*clockRate;
+//directory1.ifb.l_ip.num_search_ports*directory1.ifb.local_result.power.searchOp.dynamic*clockRate;
 //	  		  ///cout<<"directory1.maxPower="
 //<<directory1.maxPower<<endl;
 //
 //	  		  directory1.maxPower	+=
-// directory1.prefetchb.l_ip.num_search_ports*directory1.prefetchb.local_result.power.searchOp.dynamic*clockRate;
+//directory1.prefetchb.l_ip.num_search_ports*directory1.prefetchb.local_result.power.searchOp.dynamic*clockRate;
 //	  		  ///cout<<"directory1.maxPower="
 //<<directory1.maxPower<<endl;
 //
 //	  		  directory1.maxPower	+=
-// directory1.wbb.l_ip.num_search_ports*directory1.wbb.local_result.power.searchOp.dynamic*clockRate;
+//directory1.wbb.l_ip.num_search_ports*directory1.wbb.local_result.power.searchOp.dynamic*clockRate;
 //
 //	  		  cc1.power.readOp.dynamic =
-// directory1.maxPower*scktRatio*64/XML->sys.domain_size;
+//directory1.maxPower*scktRatio*64/XML->sys.domain_size;
 //			  cc1.power.readOp.leakage =
-// directory1.caches.local_result.power.readOp.leakage +
+//directory1.caches.local_result.power.readOp.leakage +
 //	                                     directory1.missb.local_result.power.readOp.leakage
 //+
 //	                                     directory1.ifb.local_result.power.readOp.leakage
@@ -1248,26 +1247,26 @@ void SharedCache::displayEnergy(uint32_t indent, bool is_tdp) {
 //	  		  cc1.area.set_area(directory1.area*64/XML->sys.domain_size);
 //
 //	  		  cout<<"CC
-// area="<<(cc.area.get_area()+cc1.area.get_area())*1e-6<<endl;
+//area="<<(cc.area.get_area()+cc1.area.get_area())*1e-6<<endl;
 //			  cout<<"CC Power="<<cc.power.readOp.dynamic +
-// cc1.power.readOp.dynamic <<endl;
+//cc1.power.readOp.dynamic <<endl;
 //			  ccTot.area.set_area((cc.area.get_area()+cc1.area.get_area())*1e-6);
 //			  ccTot.power = cc.power + cc1.power;
 //	  	  }
 //	  	  else if (XML->sys.first_level_dir==1)
 //	  	  {
 //	  		  inv_dir.maxPower =
-// inv_dir.caches.local_result.power.searchOp.dynamic*clockRate*XML->sys.domain_size;
+//inv_dir.caches.local_result.power.searchOp.dynamic*clockRate*XML->sys.domain_size;
 //	  		  cc1.power.readOp.dynamic =
-// inv_dir.maxPower*scktRatio*(64/XML->sys.domain_size);
+//inv_dir.maxPower*scktRatio*(64/XML->sys.domain_size);
 //	  		  cc1.power.readOp.leakage  =
-// inv_dir.caches.local_result.power.readOp.leakage*inv_dir.caches.l_ip.nbanks*XML->sys.domain_size;
+//inv_dir.caches.local_result.power.readOp.leakage*inv_dir.caches.l_ip.nbanks*XML->sys.domain_size;
 //
 //	  		  cc1.area.set_area(inv_dir.area*64/XML->sys.domain_size);
 //			  cout<<"CC
-// area="<<(cc.area.get_area()+cc1.area.get_area())*1e-6<<endl;
+//area="<<(cc.area.get_area()+cc1.area.get_area())*1e-6<<endl;
 //			  cout<<"CC Power="<<cc.power.readOp.dynamic +
-// cc1.power.readOp.dynamic <<endl;
+//cc1.power.readOp.dynamic <<endl;
 //			  ccTot.area.set_area((cc.area.get_area()+cc1.area.get_area())*1e-6);
 //			  ccTot.power = cc.power + cc1.power;
 //
diff --git a/src/gpuwattch/technology_xeon_core.cc b/src/gpuwattch/technology_xeon_core.cc
index 561f5b5..11bb28e 100644
--- a/src/gpuwattch/technology_xeon_core.cc
+++ b/src/gpuwattch/technology_xeon_core.cc
@@ -1904,8 +1904,8 @@ void init_tech_params(double technology, bool is_tag) {
 
   g_tp.min_w_nmos_ = 3 * g_ip->F_sz_um / 2;
   g_tp.max_w_nmos_ = 100 * g_ip->F_sz_um;
-  g_tp.w_iso = 12.5 * g_ip->F_sz_um;      // was 10 micron for the 0.8 micron
-                                          // process
+  g_tp.w_iso = 12.5 * g_ip->F_sz_um;  // was 10 micron for the 0.8 micron
+                                      // process
   g_tp.w_sense_n = 3.75 * g_ip->F_sz_um;  // sense amplifier N-trans; was 3
                                           // micron for the 0.8 micron process
   g_tp.w_sense_p = 7.5 * g_ip->F_sz_um;   // sense amplifier P-trans; was 6
diff --git a/src/gpuwattch/xmlParser.cc b/src/gpuwattch/xmlParser.cc
index 375236f..810e6fb 100644
--- a/src/gpuwattch/xmlParser.cc
+++ b/src/gpuwattch/xmlParser.cc
@@ -765,9 +765,9 @@ static const char XML_gbk_big5_ByteTable[256] = {
     2, 2, 2, 2, 2, 2, 2, 2,
     2, 2, 2, 2, 2, 2, 2, 1  // 0xf0
 };
-static const char *XML_ByteTable =
-    (const char *)XML_utf8ByteTable;  // the default is
-// "characterEncoding=XMLNode::encoding_UTF8"
+static const char *XML_ByteTable = (const char *)
+    XML_utf8ByteTable;  // the default is
+                        // "characterEncoding=XMLNode::encoding_UTF8"
 #endif
 
 XMLNode XMLNode::emptyXMLNode;
diff --git a/src/gpuwattch/xmlParser.h b/src/gpuwattch/xmlParser.h
index caee181..64f5515 100644
--- a/src/gpuwattch/xmlParser.h
+++ b/src/gpuwattch/xmlParser.h
@@ -391,7 +391,7 @@ typedef struct XMLDLLENTRY XMLNode {
    */
 
   static XMLCSTR getError(XMLError error);  ///< this gives you a user-friendly
-                                            /// explanation of the parsing error
+                                            ///explanation of the parsing error
 
   /// Create an XML string starting from the current XMLNode.
   XMLSTR createXMLString(int nFormat = 1, int *pnSize = NULL) const;
@@ -426,23 +426,23 @@ typedef struct XMLDLLENTRY XMLNode {
   XMLNode getParentNode() const;                    ///< return the parent node
   XMLNode getChildNode(int i = 0) const;            ///< return ith child node
   XMLNode getChildNode(XMLCSTR name, int i) const;  ///< return ith child node
-                                                    /// with specific name
-  ///(return an empty node if
-  /// failing). If i==-1, this
-  /// returns the last XMLNode
-  /// with the given name.
+                                                    ///with specific name
+                                                    ///(return an empty node if
+                                                    ///failing). If i==-1, this
+                                                    ///returns the last XMLNode
+                                                    ///with the given name.
   XMLNode getChildNode(XMLCSTR name, int *i = NULL) const;  ///< return next
-                                                            /// child node with
-  /// specific name
-  ///(return an empty
-  /// node if failing)
+                                                            ///child node with
+                                                            ///specific name
+                                                            ///(return an empty
+                                                            ///node if failing)
   XMLNode getChildNodeWithAttribute(XMLCSTR tagName, XMLCSTR attributeName,
                                     XMLCSTR attributeValue = NULL,
                                     int *i = NULL) const;  ///< return child
-  /// node with specific
-  /// name/attribute
-  ///(return an empty
-  /// node if failing)
+                                                           ///node with specific
+                                                           ///name/attribute
+                                                           ///(return an empty
+                                                           ///node if failing)
   XMLNode getChildNodeByPath(XMLCSTR path, char createNodeIfMissing = 0,
                              XMLCHAR sep = '/');
   ///< return the first child node with specific path
@@ -459,21 +459,21 @@ typedef struct XMLDLLENTRY XMLNode {
   char isAttributeSet(XMLCSTR name)
       const;  ///< test if an attribute with a specific name is given
   XMLCSTR getAttribute(XMLCSTR name, int i) const;  ///< return ith attribute
-                                                    /// content with specific
-  /// name (return a NULL if
-  /// failing)
+                                                    ///content with specific
+                                                    ///name (return a NULL if
+                                                    ///failing)
   XMLCSTR getAttribute(XMLCSTR name, int *i = NULL) const;  ///< return next
-  /// attribute content
-  /// with specific
-  /// name (return a
-  /// NULL if failing)
+                                                            ///attribute content
+                                                            ///with specific
+                                                            ///name (return a
+                                                            ///NULL if failing)
   int nAttribute() const;              ///< nbr of attribute
   XMLClear getClear(int i = 0) const;  ///< return ith clear field (comments)
   int nClear() const;                  ///< nbr of clear field
   XMLNodeContents enumContents(XMLElementPosition i)
       const;  ///< enumerate all the different contents (attribute,child,text,
-              /// clear) of the current XMLNode. The order is reflecting the
-  /// order of the original file/string. NOTE: 0 <= i < nElement();
+              ///clear) of the current XMLNode. The order is reflecting the
+              ///order of the original file/string. NOTE: 0 <= i < nElement();
   int nElement() const;        ///< nbr of different contents for current node
   char isEmpty() const;        ///< is this node Empty?
   char isDeclaration() const;  ///< is this node a declaration <? .... ?>
@@ -515,10 +515,10 @@ typedef struct XMLDLLENTRY XMLNode {
                    XMLElementPosition pos = -1);  ///< Add a new child node
   XMLNode addChild(XMLNode nodeToAdd,
                    XMLElementPosition pos = -1);  ///< If the "nodeToAdd" has
-                                                  /// some parents, it will be
-  /// detached from it's parents
-  /// before being attached to
-  /// the current XMLNode
+                                                  ///some parents, it will be
+                                                  ///detached from it's parents
+                                                  ///before being attached to
+                                                  ///the current XMLNode
   XMLAttribute *addAttribute(XMLCSTR lpszName,
                              XMLCSTR lpszValuev);  ///< Add a new attribute
   XMLCSTR addText(XMLCSTR lpszValue,
@@ -539,41 +539,41 @@ typedef struct XMLDLLENTRY XMLNode {
   XMLCSTR updateName(XMLCSTR lpszName);  ///< change node's name
   XMLAttribute *updateAttribute(XMLAttribute *newAttribute,
                                 XMLAttribute *oldAttribute);  ///< if the
-                                                              /// attribute to
-  /// update is
-  /// missing, a new
-  /// one will be
-  /// added
+                                                              ///attribute to
+                                                              ///update is
+                                                              ///missing, a new
+                                                              ///one will be
+                                                              ///added
   XMLAttribute *updateAttribute(XMLCSTR lpszNewValue,
                                 XMLCSTR lpszNewName = NULL,
                                 int i = 0);  ///< if the attribute to update is
-  /// missing, a new one will be added
+                                             ///missing, a new one will be added
   XMLAttribute *updateAttribute(XMLCSTR lpszNewValue, XMLCSTR lpszNewName,
                                 XMLCSTR lpszOldName);  ///< set lpszNewName=NULL
-                                                       /// if you don't want to
-  /// change the name of the
-  /// attribute if the
-  /// attribute to update is
-  /// missing, a new one
-  /// will be added
+                                                       ///if you don't want to
+                                                       ///change the name of the
+                                                       ///attribute if the
+                                                       ///attribute to update is
+                                                       ///missing, a new one
+                                                       ///will be added
   XMLCSTR updateText(XMLCSTR lpszNewValue, int i = 0);  ///< if the text to
-                                                        /// update is missing, a
-  /// new one will be added
+                                                        ///update is missing, a
+                                                        ///new one will be added
   XMLCSTR updateText(XMLCSTR lpszNewValue,
                      XMLCSTR lpszOldValue);  ///< if the text to update is
-  /// missing, a new one will be added
+                                             ///missing, a new one will be added
   XMLClear *updateClear(XMLCSTR lpszNewContent,
                         int i = 0);  ///< if the clearTag to update is missing,
-                                     /// a new one will be added
+                                     ///a new one will be added
   XMLClear *updateClear(XMLClear *newP, XMLClear *oldP);  ///< if the clearTag
-                                                          /// to update is
-  /// missing, a new one
-  /// will be added
+                                                          ///to update is
+                                                          ///missing, a new one
+                                                          ///will be added
   XMLClear *updateClear(XMLCSTR lpszNewValue,
                         XMLCSTR lpszOldValue);  ///< if the clearTag to update
-  /// is missing, a new one will be
-  /// added
-  /** @} */
+                                                ///is missing, a new one will be
+                                                ///added
+                                                /** @} */
 
   /** @defgroup xmlDelete Deleting Nodes or Attributes
    * @ingroup xmlModify
@@ -589,33 +589,33 @@ typedef struct XMLDLLENTRY XMLNode {
   void deleteAttribute(
       int i = 0);  ///< Delete the ith attribute of the current XMLNode
   void deleteAttribute(XMLCSTR lpszName);  ///< Delete the attribute with the
-                                           /// given name (the "strcmp" function
-  /// is used to find the right
-  /// attribute)
+                                           ///given name (the "strcmp" function
+                                           ///is used to find the right
+                                           ///attribute)
   void deleteAttribute(XMLAttribute *anAttribute);  ///< Delete the attribute
-                                                    /// with the name
-  ///"anAttribute->lpszName"
-  ///(the "strcmp" function is
-  /// used to find the right
-  /// attribute)
+                                                    ///with the name
+                                                    ///"anAttribute->lpszName"
+                                                    ///(the "strcmp" function is
+                                                    ///used to find the right
+                                                    ///attribute)
   void deleteText(
       int i = 0);  ///< Delete the Ith text content of the current XMLNode
   void deleteText(XMLCSTR lpszValue);  ///< Delete the text content "lpszValue"
-                                       /// inside the current XMLNode (direct
-  ///"pointer-to-pointer" comparison is
-  /// used to find the right text)
+                                       ///inside the current XMLNode (direct
+                                       ///"pointer-to-pointer" comparison is
+                                       ///used to find the right text)
   void deleteClear(
       int i = 0);  ///< Delete the Ith clear tag inside the current XMLNode
   void deleteClear(XMLCSTR lpszValue);  ///< Delete the clear tag "lpszValue"
-                                        /// inside the current XMLNode (direct
-  ///"pointer-to-pointer" comparison is
-  /// used to find the clear tag)
-  void deleteClear(XMLClear *p);  ///< Delete the clear tag "p" inside the
-                                  /// current XMLNode (direct
+                                        ///inside the current XMLNode (direct
+                                        ///"pointer-to-pointer" comparison is
+                                        ///used to find the clear tag)
+  void deleteClear(XMLClear *p);        ///< Delete the clear tag "p" inside the
+                                        ///current XMLNode (direct
                                   ///"pointer-to-pointer" comparison on the
-                                  /// lpszName of the clear tag is used to find
-                                  /// the clear tag)
-                                  /** @} */
+                                  ///lpszName of the clear tag is used to find
+                                  ///the clear tag)
+  /** @} */
 
   /** @defgroup xmlWOSD ???_WOSD functions.
    * @ingroup xmlModify
@@ -666,49 +666,49 @@ typedef struct XMLDLLENTRY XMLNode {
   XMLCSTR updateName_WOSD(XMLSTR lpszName);  ///< change node's name
   XMLAttribute *updateAttribute_WOSD(XMLAttribute *newAttribute,
                                      XMLAttribute *oldAttribute);  ///< if the
-                                                                   /// attribute
-  /// to update
-  /// is
-  /// missing, a
-  /// new one
-  /// will be
-  /// added
+                                                                   ///attribute
+                                                                   ///to update
+                                                                   ///is
+                                                                   ///missing, a
+                                                                   ///new one
+                                                                   ///will be
+                                                                   ///added
   XMLAttribute *updateAttribute_WOSD(XMLSTR lpszNewValue,
                                      XMLSTR lpszNewName = NULL,
                                      int i = 0);  ///< if the attribute to
-                                                  /// update is missing, a new
-  /// one will be added
+                                                  ///update is missing, a new
+                                                  ///one will be added
   XMLAttribute *updateAttribute_WOSD(XMLSTR lpszNewValue, XMLSTR lpszNewName,
                                      XMLCSTR lpszOldName);  ///< set
-                                                            /// lpszNewName=NULL
-  /// if you don't want
-  /// to change the
-  /// name of the
-  /// attribute if the
-  /// attribute to
-  /// update is
-  /// missing, a new
-  /// one will be added
+                                                            ///lpszNewName=NULL
+                                                            ///if you don't want
+                                                            ///to change the
+                                                            ///name of the
+                                                            ///attribute if the
+                                                            ///attribute to
+                                                            ///update is
+                                                            ///missing, a new
+                                                            ///one will be added
   XMLCSTR updateText_WOSD(XMLSTR lpszNewValue, int i = 0);  ///< if the text to
-                                                            /// update is
-  /// missing, a new
-  /// one will be added
+                                                            ///update is
+                                                            ///missing, a new
+                                                            ///one will be added
   XMLCSTR updateText_WOSD(XMLSTR lpszNewValue,
                           XMLCSTR lpszOldValue);  ///< if the text to update is
-                                                  /// missing, a new one will be
-  /// added
+                                                  ///missing, a new one will be
+                                                  ///added
   XMLClear *updateClear_WOSD(XMLSTR lpszNewContent,
                              int i = 0);  ///< if the clearTag to update is
-                                          /// missing, a new one will be added
+                                          ///missing, a new one will be added
   XMLClear *updateClear_WOSD(XMLClear *newP,
                              XMLClear *oldP);  ///< if the clearTag to update is
-                                               /// missing, a new one will be
-  /// added
+                                               ///missing, a new one will be
+                                               ///added
   XMLClear *updateClear_WOSD(XMLSTR lpszNewValue,
                              XMLCSTR lpszOldValue);  ///< if the clearTag to
-  /// update is missing, a new
-  /// one will be added
-  /** @} */
+                                                     ///update is missing, a new
+                                                     ///one will be added
+                                                     /** @} */
 
   /** @defgroup xmlPosition Position helper functions (use in conjunction with
    * the update&add functions
@@ -729,7 +729,7 @@ typedef struct XMLDLLENTRY XMLNode {
   XMLElementPosition positionOfChildNode(XMLNode x) const;
   XMLElementPosition positionOfChildNode(XMLCSTR name, int i = 0)
       const;  ///< return the position of the ith childNode with the specified
-              /// name if (name==NULL) return the position of the ith childNode
+              ///name if (name==NULL) return the position of the ith childNode
   /** @} */
 
   /// Enumeration for XML character encoding.
@@ -970,11 +970,11 @@ typedef struct XMLDLLENTRY ToXMLStringTool {
   ToXMLStringTool() : buf(NULL), buflen(0) {}
   ~ToXMLStringTool();
   void freeBuffer();  ///<call this function when you have finished using this
-                      /// object to release memory used by the internal buffer.
+                      ///object to release memory used by the internal buffer.
 
   XMLSTR toXML(XMLCSTR source);  ///< returns a pointer to an internal buffer
-                                 /// that contains a XML-encoded string based on
-                                 /// the "source" parameter.
+                                 ///that contains a XML-encoded string based on
+                                 ///the "source" parameter.
 
   /** The "toXMLUnSafe" function is deprecated because there is a possibility of
    * "destination-buffer-overflow". It converts the string
@@ -1015,16 +1015,16 @@ typedef struct XMLDLLENTRY XMLParserBase64Tool {
   XMLParserBase64Tool() : buf(NULL), buflen(0) {}
   ~XMLParserBase64Tool();
   void freeBuffer();  ///< Call this function when you have finished using this
-                      /// object to release memory used by the internal buffer.
+                      ///object to release memory used by the internal buffer.
 
   /**
    * @param formatted If "formatted"=true, some space will be reserved for a
    * carriage-return every 72 chars. */
   static int encodeLength(int inBufLen,
                           char formatted = 0);  ///< return the length of the
-                                                /// base64 string that encodes a
-                                                /// data buffer of size inBufLen
-                                                /// bytes.
+                                                ///base64 string that encodes a
+                                                ///data buffer of size inBufLen
+                                                ///bytes.
 
   /**
    * The "base64Encode" function returns a string containing the base64 encoding
@@ -1035,9 +1035,9 @@ typedef struct XMLDLLENTRY XMLParserBase64Tool {
    * All returned strings are sharing the same memory space. */
   XMLSTR encode(unsigned char *inByteBuf, unsigned int inByteLen,
                 char formatted = 0);  ///< returns a pointer to an internal
-                                      /// buffer containing the base64 string
-  /// containing the binary data encoded from
-  ///"inByteBuf"
+                                      ///buffer containing the base64 string
+                                      ///containing the binary data encoded from
+                                      ///"inByteBuf"
 
   /// returns the number of bytes which will be decoded from "inString".
   static unsigned int decodeSize(XMLCSTR inString, XMLError *xe = NULL);
@@ -1051,9 +1051,9 @@ typedef struct XMLDLLENTRY XMLParserBase64Tool {
    * @param inString If "instring" is malformed, NULL will be returned */
   unsigned char *decode(XMLCSTR inString, int *outByteLen = NULL,
                         XMLError *xe = NULL);  ///< returns a pointer to an
-  /// internal buffer containing the
-  /// binary data decoded from
-  ///"inString"
+                                               ///internal buffer containing the
+                                               ///binary data decoded from
+                                               ///"inString"
 
   /**
    * decodes data from "inString" to "outByteBuf". You need to provide the size