Add printout SCALAR/AVX2/AVX512F. Test again SCALAR, ME 5.4E5

./check.exe -p 16384 32 1
***********************************************************************
NumBlocksPerGrid           = 16384
NumThreadsPerBlock         = 32
NumIterations              = 1
-----------------------------------------------------------------------
FP precision               = DOUBLE (nan=0)
Complex type               = STD::COMPLEX
RanNumb memory layout      = AOSOA[1] == AOS
Momenta memory layout      = AOSOA[1] == AOS
Internal loops fptype_sv   = SCALAR (no SIMD)
Random number generation   = CURAND (C++ code)
-----------------------------------------------------------------------
NumberOfEntries            = 1
TotalTime[Rnd+Rmb+ME] (123)= ( 1.098961e+00                 )  sec
TotalTime[Rambo+ME]    (23)= ( 1.070591e+00                 )  sec
TotalTime[RndNumGen]    (1)= ( 2.837009e-02                 )  sec
TotalTime[Rambo]        (2)= ( 9.763392e-02                 )  sec
TotalTime[MatrixElems]  (3)= ( 9.729566e-01                 )  sec
MeanTimeInMatrixElems      = ( 9.729566e-01                 )  sec
[Min,Max]TimeInMatrixElems = [ 9.729566e-01 ,  9.729566e-01 ]  sec
-----------------------------------------------------------------------
TotalEventsComputed        = 524288
EvtsPerSec[Rnd+Rmb+ME](123)= ( 4.770762e+05                 )  sec^-1
EvtsPerSec[Rmb+ME]     (23)= ( 4.897185e+05                 )  sec^-1
EvtsPerSec[MatrixElems] (3)= ( 5.388606e+05                 )  sec^-1
***********************************************************************
NumMatrixElements(notNan)  = 524288
MeanMatrixElemValue        = ( 1.372323e-02 +- 1.131684e-05 )  GeV^0
[Min,Max]MatrixElemValue   = [ 6.071582e-03 ,  3.374925e-02 ]  GeV^0
StdDevMatrixElemValue      = ( 8.194264e-03                 )  GeV^0
MeanWeight                 = ( 4.515827e-01 +- 0.000000e+00 )
[Min,Max]Weight            = [ 4.515827e-01 ,  4.515827e-01 ]
StdDevWeight               = ( 0.000000e+00                 )
***********************************************************************

epoch1/cuda/ee_mumu/SubProcesses/Makefile

@@ -5,7 +5,7 @@ MODELLIB = model_sm
 OPTFLAGS = -O3
 CXXFLAGS = $(OPTFLAGS) -std=c++11 $(INCFLAGS) $(USE_NVTX) -Wall -Wshadow -Wextra $(MGONGPU_CONFIG)
 ###CXXFLAGS+= -mavx2 # DEFAULT!
-CXXFLAGS+= -march=core-avx2 # DEFAULT!
+###CXXFLAGS+= -march=core-avx2 # DEFAULT!
 ###CXXFLAGS+= -mavx512f -mavx512cd -mprefer-vector-width=512 # see https://stackoverflow.com/a/52543573
 LIBFLAGS = -L$(LIBDIR) -l$(MODELLIB)
 CXX     ?= g++

epoch1/cuda/ee_mumu/SubProcesses/P1_Sigma_sm_epem_mupmum/check.cc

@@ -11,6 +11,7 @@
 
 #include "mgOnGpuConfig.h"
 #include "mgOnGpuTypes.h"
+#include "mgOnGpuVectors.h"
 
 #ifdef __CUDACC__
 #include "grambo.cu"
@@ -600,6 +601,14 @@ int main(int argc, char **argv)
               << ( neppM == 1 ? " == AOS" : "" ) << std::endl
 #ifdef __CUDACC__
               << "Wavefunction GPU memory    = LOCAL" << std::endl
+#else
+#if defined __AVX512F__
+              << "Internal loops fptype_sv   = VECTOR[" << neppV << "] (AVX512F)" << std:: endl
+#elif defined __AVX2__
+              << "Internal loops fptype_sv   = VECTOR[" << neppV << "] (AVX2)" << std:: endl
+#else
+              << "Internal loops fptype_sv   = SCALAR (no SIMD)" << std:: endl
+#endif
 #endif
 #ifdef __CUDACC__
 #if defined MGONGPU_COMMONRAND_ONHOST

epoch1/cuda/ee_mumu/src/Makefile

@@ -1,8 +1,8 @@
 INCFLAGS = -I.
 OPTFLAGS = -O3
 CXXFLAGS = $(OPTFLAGS) -std=c++11 $(INCFLAGS) $(USE_NVTX) -Wall -Wshadow -Wextra $(MGONGPU_CONFIG)
+###CXXFLAGS+= -march=core-avx2 # DEFAULT!
 ###CXXFLAGS+= -mavx2 # DEFAULT!
-CXXFLAGS+= -march=core-avx2 # DEFAULT!
 ###CXXFLAGS+= -mavx512f -mavx512cd -mprefer-vector-width=512 # see https://stackoverflow.com/a/52543573
 LIBDIR   = ../lib
 LIBFLAGS = -L$(LIBDIR) -l$(MODELLIB)