Slightly different AVX512F, a bit better 2.06E6 (remove -mprefer-vect…

…or-width=512)

./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[8]
Momenta memory layout      = AOSOA[8]
Internal loops fptype_sv   = VECTOR[8] (AVX512F)
Random number generation   = CURAND (C++ code)
-----------------------------------------------------------------------
NumberOfEntries            = 1
TotalTime[Rnd+Rmb+ME] (123)= ( 3.753826e-01                 )  sec
TotalTime[Rambo+ME]    (23)= ( 3.477140e-01                 )  sec
TotalTime[RndNumGen]    (1)= ( 2.766860e-02                 )  sec
TotalTime[Rambo]        (2)= ( 9.360017e-02                 )  sec
TotalTime[MatrixElems]  (3)= ( 2.541139e-01                 )  sec
MeanTimeInMatrixElems      = ( 2.541139e-01                 )  sec
[Min,Max]TimeInMatrixElems = [ 2.541139e-01 ,  2.541139e-01 ]  sec
-----------------------------------------------------------------------
TotalEventsComputed        = 524288
EvtsPerSec[Rnd+Rmb+ME](123)= ( 1.396676e+06                 )  sec^-1
EvtsPerSec[Rmb+ME]     (23)= ( 1.507814e+06                 )  sec^-1
EvtsPerSec[MatrixElems] (3)= ( 2.063201e+06                 )  sec^-1
***********************************************************************

epoch1/cuda/ee_mumu/SubProcesses/Makefile

@@ -7,7 +7,8 @@ CXXFLAGS = $(OPTFLAGS) -std=c++11 $(INCFLAGS) $(USE_NVTX) -Wall -Wshadow -Wextra
 ###CXXFLAGS+= -mavx2 # DEFAULT!
 ###CXXFLAGS+= -march=core-avx2 # DEFAULT!
 ###CXXFLAGS+= -mavx512f -mavx512cd -mprefer-vector-width=512 # see https://stackoverflow.com/a/52543573
-CXXFLAGS+= -march=native -mprefer-vector-width=512 # see https://stackoverflow.com/a/52543573
+###CXXFLAGS+= -march=native -mprefer-vector-width=512 # see https://stackoverflow.com/a/52543573
+CXXFLAGS+= -march=native
 LIBFLAGS = -L$(LIBDIR) -l$(MODELLIB)
 CXX     ?= g++
 

epoch1/cuda/ee_mumu/src/Makefile

@@ -4,7 +4,8 @@ CXXFLAGS = $(OPTFLAGS) -std=c++11 $(INCFLAGS) $(USE_NVTX) -Wall -Wshadow -Wextra
 ###CXXFLAGS+= -march=core-avx2 # DEFAULT!
 ###CXXFLAGS+= -mavx2 # DEFAULT!
 ###CXXFLAGS+= -mavx512f -mavx512cd -mprefer-vector-width=512 # see https://stackoverflow.com/a/52543573
-CXXFLAGS+= -march=native -mprefer-vector-width=512 # see https://stackoverflow.com/a/52543573
+###CXXFLAGS+= -march=native -mprefer-vector-width=512 # see https://stackoverflow.com/a/52543573
+CXXFLAGS+= -march=native
 LIBDIR   = ../lib
 LIBFLAGS = -L$(LIBDIR) -l$(MODELLIB)
 CXX     ?= g++