A bunch of maintenance fixes, the largest of which is getting the PTX simulation to work with CUDA 12. (#95)

* Fixing the formatter to always use a consistent format and running it on the codebase

* Update linux-so-version.txt

* Update Makefile

* A couple of unnecessary files that are lingering around

* Support CUDA 12

* Getting the PTX simulations to work with CUDA 12. The issue is that ptxas added more information (number of barriers and compile time). We have to parse these or lexx/yacc fail.

* Update ptxinfo.l

debug MACRO was ineffective

* Update gpgpusim_check.cmake

Update to make the CUDA version print a warning, not an error and updating the print to be more reflective of what the actual problem is.

8 files changed, 45 insertions, 46 deletions

diff --git a/src/accelwattch/XML_Parse.h b/src/accelwattch/XML_Parse.h
index 176b82f..7017c90 100644
--- a/src/accelwattch/XML_Parse.h
+++ b/src/accelwattch/XML_Parse.h
@@ -40,9 +40,9 @@
 #ifndef XML_PARSE_H_

 #define XML_PARSE_H_

 

-//#ifdef WIN32

-//#define _CRT_SECURE_NO_DEPRECATE

-//#endif

+// #ifdef WIN32

+// #define _CRT_SECURE_NO_DEPRECATE

+// #endif

 

 #include <stdio.h>

 #include <string.h>

diff --git a/src/accelwattch/core.cc b/src/accelwattch/core.cc
index cbaefc7..fe11e05 100644
--- a/src/accelwattch/core.cc
+++ b/src/accelwattch/core.cc
@@ -47,38 +47,39 @@
 #include "const.h"
 #include "io.h"
 #include "parameter.h"
-//#include "globalvar.h"
-// double exClockRate;
+// #include "globalvar.h"
+//  double exClockRate;
 //*********************
-// Operand collector (OC) modelling (Syed Gilani)
+//  Operand collector (OC) modelling (Syed Gilani)
 //*********************
-// The OCs are modelled similar to the GPGPU-Sim v3.x documentation and
-// nVIDIA patents.
-// the OC need the following GPGPU-Sim config options:
+//  The OCs are modelled similar to the GPGPU-Sim v3.x documentation and
+//  nVIDIA patents.
+//  the OC need the following GPGPU-Sim config options:
 //-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) -gpgpu_operand_collector_num_units_sp 6 #
-// number of collector units (default = 4)
-// -gpgpu_operand_collector_num_units_sfu 8 # number of collector units (default
-// = 4) -gpgpu_operand_collector_num_units_mem                    2 # number of
-// collector units (default = 2) -gpgpu_operand_collector_num_units_gen 0 #
-// number of collector units (default = 0)
+//  registers to banks (default = off) -gpgpu_operand_collector_num_units_sp 6 #
+//  number of collector units (default = 4)
+//  -gpgpu_operand_collector_num_units_sfu 8 # number of collector units
+//  (default = 4) -gpgpu_operand_collector_num_units_mem                    2 #
+//  number of collector units (default = 2)
+//  -gpgpu_operand_collector_num_units_gen 0 # number of 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 determine the crossbar size.
@@ -1837,7 +1838,7 @@ MemManU::MemManU(ParseXML* XML_interface, int ithCore_,
   area.set_area(area.get_area() + dtlb->local_result.area);
   // output_data_csv(dtlb.tlb.local_result);
 }
-//#define FERMI
+// #define FERMI
 
 RegFU::RegFU(ParseXML* XML_interface, int ithCore_,
              InputParameter* interface_ip_, const CoreDynParam& dyn_p_,
@@ -2194,7 +2195,7 @@ EXECU::EXECU(ParseXML* XML_interface, int ithCore_,
             bypass.area.set_area(bypass.area.get_area()
     +fpTagBypass->area.get_area());
     }*/
-  }       /* if (coredynp.core_ty==Inorder) */
+  } /* if (coredynp.core_ty==Inorder) */
   else {  // OOO
     if (coredynp.scheu_ty == PhysicalRegFile) {
       /* For physical register based OOO,
diff --git a/src/accelwattch/iocontrollers.h b/src/accelwattch/iocontrollers.h
index 9d6c48a..22df1fb 100644
--- a/src/accelwattch/iocontrollers.h
+++ b/src/accelwattch/iocontrollers.h
@@ -35,9 +35,9 @@
 
 #include "XML_Parse.h"
 #include "cacti/parameter.h"
-//#include "io.h"
+// #include "io.h"
 #include "array.h"
-//#include "Undifferentiated_Core_Area.h"
+// #include "Undifferentiated_Core_Area.h"
 #include <vector>
 #include "basic_components.h"
 
diff --git a/src/accelwattch/logic.cc b/src/accelwattch/logic.cc
index 7f40189..3d3a1a4 100644
--- a/src/accelwattch/logic.cc
+++ b/src/accelwattch/logic.cc
@@ -656,7 +656,7 @@ 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;
diff --git a/src/accelwattch/memoryctrl.h b/src/accelwattch/memoryctrl.h
index 4ac55fc..f065c0a 100644
--- a/src/accelwattch/memoryctrl.h
+++ b/src/accelwattch/memoryctrl.h
@@ -41,9 +41,9 @@
 
 #include "XML_Parse.h"
 #include "cacti/parameter.h"
-//#include "io.h"
+// #include "io.h"
 #include "array.h"
-//#include "Undifferentiated_Core_Area.h"
+// #include "Undifferentiated_Core_Area.h"
 #include <vector>
 #include "basic_components.h"
 
diff --git a/src/accelwattch/processor.cc b/src/accelwattch/processor.cc
index d5c7cdd..a86b96d 100644
--- a/src/accelwattch/processor.cc
+++ b/src/accelwattch/processor.cc
@@ -664,24 +664,22 @@ void Processor::displayDeviceType(int device_type_, uint32_t indent) {
 
   switch (device_type_) {
     case 0:
-      cout << indent_str << "Device Type= "
-           << "ITRS high performance device type" << endl;
+      cout << indent_str
+           << "Device Type= " << "ITRS high performance device type" << endl;
       break;
     case 1:
-      cout << indent_str << "Device Type= "
-           << "ITRS low standby power device type" << endl;
+      cout << indent_str
+           << "Device Type= " << "ITRS low standby power device type" << endl;
       break;
     case 2:
-      cout << indent_str << "Device Type= "
-           << "ITRS low operating power device type" << endl;
+      cout << indent_str
+           << "Device Type= " << "ITRS low operating power device type" << endl;
       break;
     case 3:
-      cout << indent_str << "Device Type= "
-           << "LP-DRAM device type" << endl;
+      cout << indent_str << "Device Type= " << "LP-DRAM device type" << endl;
       break;
     case 4:
-      cout << indent_str << "Device Type= "
-           << "COMM-DRAM device type" << endl;
+      cout << indent_str << "Device Type= " << "COMM-DRAM device type" << endl;
       break;
     default: {
       cout << indent_str << "Unknown Device Type" << endl;
diff --git a/src/accelwattch/xmlParser.cc b/src/accelwattch/xmlParser.cc
index 780d2ad..9f01ebe 100644
--- a/src/accelwattch/xmlParser.cc
+++ b/src/accelwattch/xmlParser.cc
@@ -85,10 +85,10 @@
 #endif
 #include "xmlParser.h"
 #ifdef _XMLWINDOWS
-//#ifdef _DEBUG
-//#define _CRTDBG_MAP_ALLOC
-//#include <crtdbg.h>
-//#endif
+// #ifdef _DEBUG
+// #define _CRTDBG_MAP_ALLOC
+// #include <crtdbg.h>
+// #endif
 #define WIN32_LEAN_AND_MEAN
 #include <Windows.h>  // to have IsTextUnicode, MultiByteToWideChar, WideCharToMultiByte to handle unicode files
 // to have "MessageBoxA" to display error messages for openFilHelper
@@ -3241,7 +3241,7 @@ XMLSTR XMLParserBase64Tool::encode(unsigned char *inbuf, unsigned int inlen,
     *(curr++) = base64EncodeTable[j >> 18];
     *(curr++) = base64EncodeTable[(j >> 12) & 0x3f];
     *(curr++) = base64EncodeTable[(j >> 6) & 0x3f];
-    *(curr++) = base64EncodeTable[(j)&0x3f];
+    *(curr++) = base64EncodeTable[(j) & 0x3f];
     if (formatted) {
       if (!k) {
         *(curr++) = _CXML('\n');
diff --git a/src/accelwattch/xmlParser.h b/src/accelwattch/xmlParser.h
index 71a1f57..b5c0779 100644
--- a/src/accelwattch/xmlParser.h
+++ b/src/accelwattch/xmlParser.h
@@ -163,7 +163,7 @@
 
 // uncomment the next line if you want no support for wchar_t* (no need for the
 // <wchar.h> or <tchar.h> libraries anymore to compile)
-//#define XML_NO_WIDE_CHAR
+// #define XML_NO_WIDE_CHAR
 
 #ifdef XML_NO_WIDE_CHAR
 #undef _XMLWINDOWS