[prof] in gg_tt.mad dsample.f, add time profilers also in sample_put_…

…points

./build.none_d_inl0_hrd0/madevent_cpp < /tmp/avalassi/input_ggtt_x1_cudacpp
 [COUNTERS] PROGRAM TOTAL          :    0.7442s
 [COUNTERS] Fortran Overhead ( 0 ) :    0.2437s
 [COUNTERS] CudaCpp MEs      ( 2 ) :    0.0871s for    16384 events => throughput is 5.32E-06 events/s
 [COUNTERS] CudaCpp HEL      ( 3 ) :    0.0008s
 [COUNTERS] Fortran X2F      ( 4 ) :    0.0162s for    16399 events => throughput is 9.86E-07 events/s
 [COUNTERS] Fortran PDF      ( 5 ) :    0.1335s for    98304 events => throughput is 1.36E-06 events/s
 [COUNTERS] Fortran I/O      ( 6 ) :    0.2629s for    16399 events => throughput is 1.60E-05 events/s

./build.none_d_inl0_hrd0/madevent_cpp < /tmp/avalassi/input_ggtt_x10_cudacpp
 [COUNTERS] PROGRAM TOTAL          :    1.9099s
 [COUNTERS] Fortran Overhead ( 0 ) :    0.3233s
 [COUNTERS] CudaCpp MEs      ( 2 ) :    0.5203s for    98304 events => throughput is 5.29E-06 events/s
 [COUNTERS] CudaCpp HEL      ( 3 ) :    0.0007s
 [COUNTERS] Fortran X2F      ( 4 ) :    0.0956s for    98371 events => throughput is 9.71E-07 events/s
 [COUNTERS] Fortran PDF      ( 5 ) :    0.7980s for   589824 events => throughput is 1.35E-06 events/s
 [COUNTERS] Fortran I/O      ( 6 ) :    0.1719s for    98371 events => throughput is 1.75E-06 events/s

epochX/cudacpp/gg_tt.mad/Source/dsample.f

@@ -1755,10 +1755,19 @@ subroutine sample_put_point(wgt, point, iteration,ipole, allow_update)
       data fprb/maxfprb*1d0/
       data jpnt,jplace /1,1/
 
+      LOGICAL FIRST
+      SAVE FIRST
+      DATA FIRST/.TRUE./
 c-----
 c  Begin Code
 c-----
 
+      IF ( FIRST ) THEN
+        CALL COUNTERS_REGISTER_COUNTER( 6, 'Fortran I/O'//char(0) ) ! null-terminated C-string (maybe not needed but it does not harm)
+        FIRST=.FALSE.
+      ENDIF
+      CALL COUNTERS_START_COUNTER( 6, 1 ) ! FortranI/O=6
+
       if (first_time) then
          first_time = .false.
          twgt_it = 0d0
@@ -2288,6 +2297,7 @@ subroutine sample_put_point(wgt, point, iteration,ipole, allow_update)
                      call store_events(-1d0, .True.)
                   endif
                   cur_it = itm+2
+                  CALL COUNTERS_STOP_COUNTER( 6 ) ! FortranI/O=6
                   return
                endif
             endif                  
@@ -2354,6 +2364,7 @@ subroutine sample_put_point(wgt, point, iteration,ipole, allow_update)
 c 129              close(22)
                   tsigma = tsigma*sqrt(max(0d0,chi2)) !This gives the 68% confidence cross section
                   cur_it = itm+20
+                  CALL COUNTERS_STOP_COUNTER( 6 ) ! FortranI/O=6
                   return
                endif
             endif                     
@@ -2395,6 +2406,7 @@ subroutine sample_put_point(wgt, point, iteration,ipole, allow_update)
          endif
       else
       endif
+      CALL COUNTERS_STOP_COUNTER( 6 ) ! FortranI/O=6
       end
 
       subroutine none_pass(max_events)