[ep2to2ep1] check.cc : finally copy ep1 to ep2 as-is including getCom…

…piler

This also requires adding Process::getCompiler to ep2 CPPProcess.cc/h.

Now check.cc is identical in both epoch2 and epoch1
(and runTest.cc is almost identical, except for the test name).
Will now include PR madgraph5#144 for single precision in epoch1,
and will copy check.cc again (and runTest.cc with some changes).

Epoch2 baseline remains epoch2 C++ 1.10e6, cuda 6.6e8

time ./check.exe -p 2048 256 12
***********************************************************************
NumBlocksPerGrid            = 2048
NumThreadsPerBlock          = 256
NumIterations               = 12
-----------------------------------------------------------------------
FP precision                = DOUBLE (nan=0)
Complex type                = STD::COMPLEX
RanNumb memory layout       = AOSOA[4]
Momenta memory layout       = AOSOA[4]
Random number generation    = CURAND (C++ code)
OMP threads / `nproc --all` = 1 / 4
MatrixElements compiler     = gcc (GCC) 9.2.0
-----------------------------------------------------------------------
NumberOfEntries             = 12
TotalTime[Rnd+Rmb+ME] (123) = ( 7.968041e+00                 )  sec
TotalTime[Rambo+ME]    (23) = ( 7.643061e+00                 )  sec
TotalTime[RndNumGen]    (1) = ( 3.249804e-01                 )  sec
TotalTime[Rambo]        (2) = ( 1.928639e+00                 )  sec
TotalTime[MatrixElems]  (3) = ( 5.714422e+00                 )  sec
MeanTimeInMatrixElems       = ( 4.762018e-01                 )  sec
[Min,Max]TimeInMatrixElems  = [ 4.760149e-01 ,  4.765775e-01 ]  sec
-----------------------------------------------------------------------
TotalEventsComputed         = 6291456
EvtsPerSec[Rnd+Rmb+ME](123) = ( 7.895863e+05                 )  sec^-1
EvtsPerSec[Rmb+ME]     (23) = ( 8.231592e+05                 )  sec^-1
EvtsPerSec[MatrixElems] (3) = ( 1.100979e+06                 )  sec^-1
***********************************************************************
NumMatrixElements(notNan)   = 6291456
MeanMatrixElemValue         = ( 1.372152e-02 +- 3.269516e-06 )  GeV^0
[Min,Max]MatrixElemValue    = [ 6.071581e-03 ,  3.374925e-02 ]  GeV^0
StdDevMatrixElemValue       = ( 8.200854e-03                 )  GeV^0
MeanWeight                  = ( 4.515827e-01 +- 0.000000e+00 )
[Min,Max]Weight             = [ 4.515827e-01 ,  4.515827e-01 ]
StdDevWeight                = ( 0.000000e+00                 )
***********************************************************************

time ./gcheck.exe -p 2048 256 12
***********************************************************************
NumBlocksPerGrid            = 2048
NumThreadsPerBlock          = 256
NumIterations               = 12
-----------------------------------------------------------------------
FP precision                = DOUBLE (nan=0)
Complex type                = THRUST::COMPLEX
RanNumb memory layout       = AOSOA[4]
Momenta memory layout       = AOSOA[4]
Wavefunction GPU memory     = LOCAL
Random number generation    = CURAND DEVICE (CUDA code)
MatrixElements compiler     = nvcc 11.0.221
-----------------------------------------------------------------------
NumberOfEntries             = 12
TotalTime[Rnd+Rmb+ME] (123) = ( 1.044441e-01                 )  sec
TotalTime[Rambo+ME]    (23) = ( 9.709213e-02                 )  sec
TotalTime[RndNumGen]    (1) = ( 7.351930e-03                 )  sec
TotalTime[Rambo]        (2) = ( 8.758798e-02                 )  sec
TotalTime[MatrixElems]  (3) = ( 9.504147e-03                 )  sec
MeanTimeInMatrixElems       = ( 7.920122e-04                 )  sec
[Min,Max]TimeInMatrixElems  = [ 7.825940e-04 ,  8.001750e-04 ]  sec
-----------------------------------------------------------------------
TotalEventsComputed         = 6291456
EvtsPerSec[Rnd+Rmb+ME](123) = ( 6.023757e+07                 )  sec^-1
EvtsPerSec[Rmb+ME]     (23) = ( 6.479882e+07                 )  sec^-1
EvtsPerSec[MatrixElems] (3) = ( 6.619696e+08                 )  sec^-1
***********************************************************************
NumMatrixElements(notNan)   = 6291456
MeanMatrixElemValue         = ( 1.372152e-02 +- 3.269516e-06 )  GeV^0
[Min,Max]MatrixElemValue    = [ 6.071581e-03 ,  3.374925e-02 ]  GeV^0
StdDevMatrixElemValue       = ( 8.200854e-03                 )  GeV^0
MeanWeight                  = ( 4.515827e-01 +- 0.000000e+00 )
[Min,Max]Weight             = [ 4.515827e-01 ,  4.515827e-01 ]
StdDevWeight                = ( 0.000000e+00                 )
***********************************************************************

epoch2/cuda/ee_mumu/SubProcesses/P1_Sigma_sm_epem_mupmum/CPPProcess.cc

@@ -229,6 +229,28 @@ bool * isGoodHel)  // output: isGoodHel[ncomb] - device array
 
 //--------------------------------------------------------------------------
 
+  // Retrieve the compiler that was used to build this module
+  const std::string CPPProcess::getCompiler()
+  {
+    std::stringstream out;
+#ifdef __CUDACC__
+#if defined __CUDACC_VER_MAJOR__ && defined __CUDACC_VER_MINOR__ && defined __CUDACC_VER_BUILD__
+    out << "nvcc " << __CUDACC_VER_MAJOR__ << "." << __CUDACC_VER_MINOR__ << "." << __CUDACC_VER_BUILD__;
+#else
+    out << "nvcc UNKNOWN";
+#endif
+#else
+#if defined __GNUC__ && defined __GNUC_MINOR__ && defined __GNUC_PATCHLEVEL__
+    out << "gcc (GCC) " << __GNUC__ << "." << __GNUC_MINOR__ << "." << __GNUC_PATCHLEVEL__;
+#else
+    out << "gcc UNKNOWKN";
+#endif
+#endif
+    return out.str();
+  }
+
+  //--------------------------------------------------------------------------
+
 #ifdef __CUDACC__
 void sigmaKin_setGoodHel(const bool * isGoodHel)  // input: isGoodHel[ncomb] - host array
 {

epoch2/cuda/ee_mumu/SubProcesses/P1_Sigma_sm_epem_mupmum/CPPProcess.h

@@ -87,6 +87,9 @@ class CPPProcess
     static const int nexternal = mgOnGpu::npar; 
     // static const int nprocesses = 1;
 
+    // Retrieve the compiler that was used to build this module
+    static const std::string getCompiler();
+
   private:
     int m_numiterations; 
     // gpu variables

epoch2/cuda/ee_mumu/SubProcesses/P1_Sigma_sm_epem_mupmum/check.cc

@@ -645,7 +645,7 @@ int main(int argc, char **argv)
 #endif
               << "OMP threads / `nproc --all` = " << omp_get_max_threads() << " / " << nprocall // includes a newline
 #endif
-      //<< "MatrixElements compiler     = " << process.getCompiler() << std::endl
+              << "MatrixElements compiler     = " << process.getCompiler() << std::endl
               << "-----------------------------------------------------------------------" << std::endl
               << "NumberOfEntries             = " << niter << std::endl
               << std::scientific // fixed format: affects all floats (default precision: 6)